From 8256169c9384a5b644c1671f6df7e42acbc482b0 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Fri, 18 Jun 2021 15:01:40 +0100 Subject: [PATCH 01/31] Bump versions to 3.3dev --- CHANGELOG.md | 6 ++++++ nextflow.config | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 3ec15becf..b8912fba6 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,6 +3,12 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). +## [Unpublished Version / DEV] + +### Enhancements & fixes + +### Parameters + ## [[3.2](https://github.com/nf-core/rnaseq/releases/tag/3.2)] - 2021-06-18 ### Enhancements & fixes diff --git a/nextflow.config b/nextflow.config index 31288750e..e8179d03e 100644 --- a/nextflow.config +++ b/nextflow.config @@ -220,7 +220,7 @@ manifest { description = 'Nextflow RNA-Seq analysis pipeline, part of the nf-core community.' mainScript = 'main.nf' nextflowVersion = '!>=21.04.0' - version = '3.2' + version = '3.3dev' } // Function to ensure that resource requirements don't go beyond From 0677fee5511d7a969191da977a1e4e887c876a8d Mon Sep 17 00:00:00 2001 From: kevinmenden Date: Tue, 13 Jul 2021 10:57:58 +0200 Subject: [PATCH 02/31] Template update for nf-core/tools version 2.0 --- .editorconfig | 24 + .github/CONTRIBUTING.md | 2 +- .github/ISSUE_TEMPLATE/bug_report.md | 5 +- .github/PULL_REQUEST_TEMPLATE.md | 3 +- .github/workflows/awsfulltest.yml | 52 +- .github/workflows/awstest.yml | 50 +- .github/workflows/ci.yml | 19 +- .github/workflows/linting.yml | 21 +- .github/workflows/push_dockerhub_dev.yml | 28 - .github/workflows/push_dockerhub_release.yml | 29 - .gitignore | 1 - .github/markdownlint.yml => .markdownlint.yml | 2 + CHANGELOG.md | 2 +- CITATIONS.md | 32 + Dockerfile | 13 - README.md | 71 +- assets/samplesheet.csv | 3 + assets/schema_input.json | 39 + assets/sendmail_template.txt | 36 +- bin/check_samplesheet.py | 146 +++ bin/markdown_to_html.py | 91 -- bin/scrape_software_versions.py | 44 +- conf/base.config | 94 +- conf/igenomes.config | 843 +++++++++--------- conf/modules.config | 32 + conf/test.config | 47 +- conf/test_full.config | 38 +- docs/README.md | 4 +- docs/images/mqc_fastqc_adapter.png | Bin 0 -> 23458 bytes docs/images/mqc_fastqc_counts.png | Bin 0 -> 33918 bytes docs/images/mqc_fastqc_quality.png | Bin 0 -> 55769 bytes docs/output.md | 63 +- docs/usage.md | 214 ++++- environment.yml | 15 - lib/Headers.groovy | 43 - lib/NfcoreSchema.groovy | 528 +++++------ lib/NfcoreTemplate.groovy | 266 ++++++ lib/Utils.groovy | 47 + lib/WorkflowMain.groovy | 94 ++ lib/WorkflowRnaseq.groovy | 59 ++ main.nf | 405 +-------- modules.json | 14 + modules/local/functions.nf | 68 ++ modules/local/get_software_versions.nf | 33 + modules/local/samplesheet_check.nf | 31 + modules/nf-core/modules/fastqc/functions.nf | 68 ++ modules/nf-core/modules/fastqc/main.nf | 47 + modules/nf-core/modules/fastqc/meta.yml | 51 ++ modules/nf-core/modules/multiqc/functions.nf | 68 ++ modules/nf-core/modules/multiqc/main.nf | 35 + modules/nf-core/modules/multiqc/meta.yml | 39 + nextflow.config | 300 ++++--- nextflow_schema.json | 255 +++--- subworkflows/local/input_check.nf | 42 + workflows/rnaseq.nf | 141 +++ 55 files changed, 2812 insertions(+), 1885 deletions(-) create mode 100644 .editorconfig delete mode 100644 .github/workflows/push_dockerhub_dev.yml delete mode 100644 .github/workflows/push_dockerhub_release.yml rename .github/markdownlint.yml => .markdownlint.yml (90%) create mode 100644 CITATIONS.md delete mode 100644 Dockerfile create mode 100644 assets/samplesheet.csv create mode 100644 assets/schema_input.json create mode 100755 bin/check_samplesheet.py delete mode 100755 bin/markdown_to_html.py create mode 100644 conf/modules.config create mode 100755 docs/images/mqc_fastqc_adapter.png create mode 100755 docs/images/mqc_fastqc_counts.png create mode 100755 docs/images/mqc_fastqc_quality.png delete mode 100644 environment.yml delete mode 100644 lib/Headers.groovy mode change 100644 => 100755 lib/NfcoreSchema.groovy create mode 100755 lib/NfcoreTemplate.groovy create mode 100755 lib/Utils.groovy create mode 100755 lib/WorkflowMain.groovy create mode 100755 lib/WorkflowRnaseq.groovy create mode 100644 modules.json create mode 100644 modules/local/functions.nf create mode 100644 modules/local/get_software_versions.nf create mode 100644 modules/local/samplesheet_check.nf create mode 100644 modules/nf-core/modules/fastqc/functions.nf create mode 100644 modules/nf-core/modules/fastqc/main.nf create mode 100644 modules/nf-core/modules/fastqc/meta.yml create mode 100644 modules/nf-core/modules/multiqc/functions.nf create mode 100644 modules/nf-core/modules/multiqc/main.nf create mode 100644 modules/nf-core/modules/multiqc/meta.yml create mode 100644 subworkflows/local/input_check.nf create mode 100644 workflows/rnaseq.nf diff --git a/.editorconfig b/.editorconfig new file mode 100644 index 000000000..afb20bb1e --- /dev/null +++ b/.editorconfig @@ -0,0 +1,24 @@ +root = true + +[*] +charset = utf-8 +end_of_line = lf +insert_final_newline = true +trim_trailing_whitespace = true +indent_size = 4 +indent_style = space + +[*.{yml,yaml}] +indent_size = 2 + +# These files are edited and tested upstream in nf-core/modules +[/modules/nf-core/**] +charset = unset +end_of_line = unset +insert_final_newline = unset +trim_trailing_whitespace = unset +indent_style = unset +indent_size = unset + +[/assets/email*] +indent_size = unset diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md index 853c22202..f17299425 100644 --- a/.github/CONTRIBUTING.md +++ b/.github/CONTRIBUTING.md @@ -74,7 +74,7 @@ If you wish to contribute a new step, please use the following coding standards: 7. Add sanity checks for all relevant parameters. 8. Add any new software to the `scrape_software_versions.py` script in `bin/` and the version command to the `scrape_software_versions` process in `main.nf`. 9. Do local tests that the new code works properly and as expected. -10. Add a new test command in `.github/workflow/ci.yaml`. +10. Add a new test command in `.github/workflow/ci.yml`. 11. If applicable add a [MultiQC](https://https://multiqc.info/) module. 12. Update MultiQC config `assets/multiqc_config.yaml` so relevant suffixes, name clean up, General Statistics Table column order, and module figures are in the right order. 13. Optional: Add any descriptions of MultiQC report sections and output files to `docs/output.md`. diff --git a/.github/ISSUE_TEMPLATE/bug_report.md b/.github/ISSUE_TEMPLATE/bug_report.md index 264add6cf..d2c0af458 100644 --- a/.github/ISSUE_TEMPLATE/bug_report.md +++ b/.github/ISSUE_TEMPLATE/bug_report.md @@ -18,7 +18,7 @@ Please delete this text and anything that's not relevant from the template below I have checked the following places for your error: - [ ] [nf-core website: troubleshooting](https://nf-co.re/usage/troubleshooting) -- [ ] [nf-core/rnaseq pipeline documentation](https://nf-co.re/nf-core/rnaseq/usage) +- [ ] [nf-core/rnaseq pipeline documentation](https://nf-co.re/rnaseq/usage) ## Description of the bug @@ -51,13 +51,12 @@ Have you provided the following extra information/files: ## Nextflow Installation -- Version: +- Version: ## Container engine - Engine: - version: -- Image tag: ## Additional context diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index 818c22a3c..31ed7da27 100644 --- a/.github/PULL_REQUEST_TEMPLATE.md +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -16,8 +16,7 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/rnas - [ ] This comment contains a description of changes (with reason). - [ ] If you've fixed a bug or added code that should be tested, add tests! - - [ ] If you've added a new tool - add to the software_versions process and a regex to `scrape_software_versions.py` - - [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](nf-core/rnaseq/tree/master/.github/CONTRIBUTING.md) + - [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/rnaseq/tree/master/.github/CONTRIBUTING.md) - [ ] If necessary, also make a PR on the nf-core/rnaseq _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository. - [ ] Make sure your code lints (`nf-core lint .`). - [ ] Ensure the test suite passes (`nextflow run . -profile test,docker`). diff --git a/.github/workflows/awsfulltest.yml b/.github/workflows/awsfulltest.yml index 149b636ef..8d64b1e97 100644 --- a/.github/workflows/awsfulltest.yml +++ b/.github/workflows/awsfulltest.yml @@ -1,46 +1,34 @@ name: nf-core AWS full size tests # This workflow is triggered on published releases. -# It can be additionally triggered manually with GitHub actions workflow dispatch. +# It can be additionally triggered manually with GitHub actions workflow dispatch button. # It runs the -profile 'test_full' on AWS batch on: - workflow_run: - workflows: ["nf-core Docker push (release)"] - types: [completed] + release: + types: [published] workflow_dispatch: - - -env: - AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }} - AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }} - TOWER_ACCESS_TOKEN: ${{ secrets.AWS_TOWER_TOKEN }} - AWS_JOB_DEFINITION: ${{ secrets.AWS_JOB_DEFINITION }} - AWS_JOB_QUEUE: ${{ secrets.AWS_JOB_QUEUE }} - AWS_S3_BUCKET: ${{ secrets.AWS_S3_BUCKET }} - - jobs: - run-awstest: + run-tower: name: Run AWS full tests if: github.repository == 'nf-core/rnaseq' runs-on: ubuntu-latest steps: - - name: Setup Miniconda - uses: conda-incubator/setup-miniconda@v2 - with: - auto-update-conda: true - python-version: 3.7 - - name: Install awscli - run: conda install -c conda-forge awscli - - name: Start AWS batch job + - name: Launch workflow via tower + uses: nf-core/tower-action@master # TODO nf-core: You can customise AWS full pipeline tests as required # Add full size test data (but still relatively small datasets for few samples) # on the `test_full.config` test runs with only one set of parameters - # Then specify `-profile test_full` instead of `-profile test` on the AWS batch command - run: | - aws batch submit-job \ - --region eu-west-1 \ - --job-name nf-core-rnaseq \ - --job-queue $AWS_JOB_QUEUE \ - --job-definition $AWS_JOB_DEFINITION \ - --container-overrides '{"command": ["nf-core/rnaseq", "-r '"${GITHUB_SHA}"' -profile test --outdir s3://'"${AWS_S3_BUCKET}"'/rnaseq/results-'"${GITHUB_SHA}"' -w s3://'"${AWS_S3_BUCKET}"'/rnaseq/work-'"${GITHUB_SHA}"' -with-tower"], "environment": [{"name": "TOWER_ACCESS_TOKEN", "value": "'"$TOWER_ACCESS_TOKEN"'"}]}' + + with: + workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} + bearer_token: ${{ secrets.TOWER_BEARER_TOKEN }} + compute_env: ${{ secrets.TOWER_COMPUTE_ENV }} + pipeline: ${{ github.repository }} + revision: ${{ github.sha }} + workdir: s3://${{ secrets.AWS_S3_BUCKET }}/work/rnaseq/work-${{ github.sha }} + parameters: | + { + "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/rnaseq/results-${{ github.sha }}" + } + profiles: '[ "test_full", "aws_tower" ]' + diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml index 303a63737..12ac9ab93 100644 --- a/.github/workflows/awstest.yml +++ b/.github/workflows/awstest.yml @@ -1,42 +1,28 @@ name: nf-core AWS test -# This workflow is triggered on push to the master branch. -# It can be additionally triggered manually with GitHub actions workflow dispatch. -# It runs the -profile 'test' on AWS batch. +# This workflow can be triggered manually with the GitHub actions workflow dispatch button. +# It runs the -profile 'test' on AWS batch on: workflow_dispatch: - - -env: - AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }} - AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }} - TOWER_ACCESS_TOKEN: ${{ secrets.AWS_TOWER_TOKEN }} - AWS_JOB_DEFINITION: ${{ secrets.AWS_JOB_DEFINITION }} - AWS_JOB_QUEUE: ${{ secrets.AWS_JOB_QUEUE }} - AWS_S3_BUCKET: ${{ secrets.AWS_S3_BUCKET }} - - jobs: - run-awstest: + run-tower: name: Run AWS tests if: github.repository == 'nf-core/rnaseq' runs-on: ubuntu-latest steps: - - name: Setup Miniconda - uses: conda-incubator/setup-miniconda@v2 + - name: Launch workflow via tower + uses: nf-core/tower-action@master + with: - auto-update-conda: true - python-version: 3.7 - - name: Install awscli - run: conda install -c conda-forge awscli - - name: Start AWS batch job - # TODO nf-core: You can customise CI pipeline run tests as required - # For example: adding multiple test runs with different parameters - # Remember that you can parallelise this by using strategy.matrix - run: | - aws batch submit-job \ - --region eu-west-1 \ - --job-name nf-core-rnaseq \ - --job-queue $AWS_JOB_QUEUE \ - --job-definition $AWS_JOB_DEFINITION \ - --container-overrides '{"command": ["nf-core/rnaseq", "-r '"${GITHUB_SHA}"' -profile test --outdir s3://'"${AWS_S3_BUCKET}"'/rnaseq/results-'"${GITHUB_SHA}"' -w s3://'"${AWS_S3_BUCKET}"'/rnaseq/work-'"${GITHUB_SHA}"' -with-tower"], "environment": [{"name": "TOWER_ACCESS_TOKEN", "value": "'"$TOWER_ACCESS_TOKEN"'"}]}' + workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} + bearer_token: ${{ secrets.TOWER_BEARER_TOKEN }} + compute_env: ${{ secrets.TOWER_COMPUTE_ENV }} + pipeline: ${{ github.repository }} + revision: ${{ github.sha }} + workdir: s3://${{ secrets.AWS_S3_BUCKET }}/work/rnaseq/work-${{ github.sha }} + parameters: | + { + "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/rnaseq/results-${{ github.sha }}" + } + profiles: '[ "test", "aws_tower" ]' + diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 504e2ffb5..eff6bd638 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -23,28 +23,11 @@ jobs: strategy: matrix: # Nextflow versions: check pipeline minimum and current latest - nxf_ver: ['20.04.0', ''] + nxf_ver: ['21.04.0', ''] steps: - name: Check out pipeline code uses: actions/checkout@v2 - - name: Check if Dockerfile or Conda environment changed - uses: technote-space/get-diff-action@v4 - with: - FILES: | - Dockerfile - environment.yml - - - name: Build new docker image - if: env.MATCHED_FILES - run: docker build --no-cache . -t nfcore/rnaseq:dev - - - name: Pull docker image - if: ${{ !env.MATCHED_FILES }} - run: | - docker pull nfcore/rnaseq:dev - docker tag nfcore/rnaseq:dev nfcore/rnaseq:dev - - name: Install Nextflow env: CAPSULE_LOG: none diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index fcde400ce..13b4fc818 100644 --- a/.github/workflows/linting.yml +++ b/.github/workflows/linting.yml @@ -18,7 +18,7 @@ jobs: - name: Install markdownlint run: npm install -g markdownlint-cli - name: Run Markdownlint - run: markdownlint ${GITHUB_WORKSPACE} -c ${GITHUB_WORKSPACE}/.github/markdownlint.yml + run: markdownlint . # If the above check failed, post a comment on the PR explaining the failure - name: Post PR comment @@ -35,8 +35,8 @@ jobs: * On Mac: `brew install markdownlint-cli` * Everything else: [Install `npm`](https://www.npmjs.com/get-npm) then [install `markdownlint-cli`](https://www.npmjs.com/package/markdownlint-cli) (`npm install -g markdownlint-cli`) * Fix the markdown errors - * Automatically: `markdownlint . --config .github/markdownlint.yml --fix` - * Manually resolve anything left from `markdownlint . --config .github/markdownlint.yml` + * Automatically: `markdownlint . --fix` + * Manually resolve anything left from `markdownlint .` Once you push these changes the test should pass, and you can hide this comment :+1: @@ -46,6 +46,20 @@ jobs: repo-token: ${{ secrets.GITHUB_TOKEN }} allow-repeats: false + EditorConfig: + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v2 + + - uses: actions/setup-node@v1 + with: + node-version: "10" + + - name: Install editorconfig-checker + run: npm install -g editorconfig-checker + + - name: Run ECLint check + run: editorconfig-checker -exclude README.md $(git ls-files | grep -v test) YAML: runs-on: ubuntu-latest @@ -84,7 +98,6 @@ jobs: repo-token: ${{ secrets.GITHUB_TOKEN }} allow-repeats: false - nf-core: runs-on: ubuntu-latest steps: diff --git a/.github/workflows/push_dockerhub_dev.yml b/.github/workflows/push_dockerhub_dev.yml deleted file mode 100644 index 27bef18e5..000000000 --- a/.github/workflows/push_dockerhub_dev.yml +++ /dev/null @@ -1,28 +0,0 @@ -name: nf-core Docker push (dev) -# This builds the docker image and pushes it to DockerHub -# Runs on nf-core repo releases and push event to 'dev' branch (PR merges) -on: - push: - branches: - - dev - -jobs: - push_dockerhub: - name: Push new Docker image to Docker Hub (dev) - runs-on: ubuntu-latest - # Only run for the nf-core repo, for releases and merged PRs - if: ${{ github.repository == 'nf-core/rnaseq' }} - env: - DOCKERHUB_USERNAME: ${{ secrets.DOCKERHUB_USERNAME }} - DOCKERHUB_PASS: ${{ secrets.DOCKERHUB_PASS }} - steps: - - name: Check out pipeline code - uses: actions/checkout@v2 - - - name: Build new docker image - run: docker build --no-cache . -t nfcore/rnaseq:dev - - - name: Push Docker image to DockerHub (dev) - run: | - echo "$DOCKERHUB_PASS" | docker login -u "$DOCKERHUB_USERNAME" --password-stdin - docker push nfcore/rnaseq:dev diff --git a/.github/workflows/push_dockerhub_release.yml b/.github/workflows/push_dockerhub_release.yml deleted file mode 100644 index 8774c080d..000000000 --- a/.github/workflows/push_dockerhub_release.yml +++ /dev/null @@ -1,29 +0,0 @@ -name: nf-core Docker push (release) -# This builds the docker image and pushes it to DockerHub -# Runs on nf-core repo releases and push event to 'dev' branch (PR merges) -on: - release: - types: [published] - -jobs: - push_dockerhub: - name: Push new Docker image to Docker Hub (release) - runs-on: ubuntu-latest - # Only run for the nf-core repo, for releases and merged PRs - if: ${{ github.repository == 'nf-core/rnaseq' }} - env: - DOCKERHUB_USERNAME: ${{ secrets.DOCKERHUB_USERNAME }} - DOCKERHUB_PASS: ${{ secrets.DOCKERHUB_PASS }} - steps: - - name: Check out pipeline code - uses: actions/checkout@v2 - - - name: Build new docker image - run: docker build --no-cache . -t nfcore/rnaseq:latest - - - name: Push Docker image to DockerHub (release) - run: | - echo "$DOCKERHUB_PASS" | docker login -u "$DOCKERHUB_USERNAME" --password-stdin - docker push nfcore/rnaseq:latest - docker tag nfcore/rnaseq:latest nfcore/rnaseq:${{ github.event.release.tag_name }} - docker push nfcore/rnaseq:${{ github.event.release.tag_name }} diff --git a/.gitignore b/.gitignore index aa4bb5b37..5124c9ac7 100644 --- a/.gitignore +++ b/.gitignore @@ -3,7 +3,6 @@ work/ data/ results/ .DS_Store -tests/ testing/ testing* *.pyc diff --git a/.github/markdownlint.yml b/.markdownlint.yml similarity index 90% rename from .github/markdownlint.yml rename to .markdownlint.yml index 8d7eb53b0..9e605fcfa 100644 --- a/.github/markdownlint.yml +++ b/.markdownlint.yml @@ -1,6 +1,8 @@ # Markdownlint configuration file default: true line-length: false +ul-indent: + indent: 4 no-duplicate-header: siblings_only: true no-inline-html: diff --git a/CHANGELOG.md b/CHANGELOG.md index dfe18a71d..44b32fe48 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,7 +3,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). -## v3.1 - [date] +## v3.3dev - [date] Initial release of nf-core/rnaseq, created with the [nf-core](https://nf-co.re/) template. diff --git a/CITATIONS.md b/CITATIONS.md new file mode 100644 index 000000000..df81a131d --- /dev/null +++ b/CITATIONS.md @@ -0,0 +1,32 @@ +# nf-core/rnaseq: Citations + +## [nf-core](https://pubmed.ncbi.nlm.nih.gov/32055031/) + +> Ewels PA, Peltzer A, Fillinger S, Patel H, Alneberg J, Wilm A, Garcia MU, Di Tommaso P, Nahnsen S. The nf-core framework for community-curated bioinformatics pipelines. Nat Biotechnol. 2020 Mar;38(3):276-278. doi: 10.1038/s41587-020-0439-x. PubMed PMID: 32055031. + +## [Nextflow](https://pubmed.ncbi.nlm.nih.gov/28398311/) + +> Di Tommaso P, Chatzou M, Floden EW, Barja PP, Palumbo E, Notredame C. Nextflow enables reproducible computational workflows. Nat Biotechnol. 2017 Apr 11;35(4):316-319. doi: 10.1038/nbt.3820. PubMed PMID: 28398311. + +## Pipeline tools + +* [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/) + +* [MultiQC](https://www.ncbi.nlm.nih.gov/pubmed/27312411/) + > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924. + +## Software packaging/containerisation tools + +* [Anaconda](https://anaconda.com) + > Anaconda Software Distribution. Computer software. Vers. 2-2.4.0. Anaconda, Nov. 2016. Web. + +* [Bioconda](https://pubmed.ncbi.nlm.nih.gov/29967506/) + > Grüning B, Dale R, Sjödin A, Chapman BA, Rowe J, Tomkins-Tinch CH, Valieris R, Köster J; Bioconda Team. Bioconda: sustainable and comprehensive software distribution for the life sciences. Nat Methods. 2018 Jul;15(7):475-476. doi: 10.1038/s41592-018-0046-7. PubMed PMID: 29967506. + +* [BioContainers](https://pubmed.ncbi.nlm.nih.gov/28379341/) + > da Veiga Leprevost F, Grüning B, Aflitos SA, Röst HL, Uszkoreit J, Barsnes H, Vaudel M, Moreno P, Gatto L, Weber J, Bai M, Jimenez RC, Sachsenberg T, Pfeuffer J, Alvarez RV, Griss J, Nesvizhskii AI, Perez-Riverol Y. BioContainers: an open-source and community-driven framework for software standardization. Bioinformatics. 2017 Aug 15;33(16):2580-2582. doi: 10.1093/bioinformatics/btx192. PubMed PMID: 28379341; PubMed Central PMCID: PMC5870671. + +* [Docker](https://dl.acm.org/doi/10.5555/2600239.2600241) + +* [Singularity](https://pubmed.ncbi.nlm.nih.gov/28494014/) + > Kurtzer GM, Sochat V, Bauer MW. Singularity: Scientific containers for mobility of compute. PLoS One. 2017 May 11;12(5):e0177459. doi: 10.1371/journal.pone.0177459. eCollection 2017. PubMed PMID: 28494014; PubMed Central PMCID: PMC5426675. diff --git a/Dockerfile b/Dockerfile deleted file mode 100644 index 08b4ab74d..000000000 --- a/Dockerfile +++ /dev/null @@ -1,13 +0,0 @@ -FROM nfcore/base:1.14 -LABEL authors="Phil Ewels, Rickard Hammarén" \ - description="Docker image containing all software requirements for the nf-core/rnaseq pipeline" - -# Install the conda environment -COPY environment.yml / -RUN conda env create --quiet -f /environment.yml && conda clean -a - -# Add conda installation dir to PATH (instead of doing 'conda activate') -ENV PATH /opt/conda/envs/nf-core-rnaseq-3.1/bin:$PATH - -# Dump the details of the installed packages to a file for posterity -RUN conda env export --name nf-core-rnaseq-3.1 > nf-core-rnaseq-3.1.yml diff --git a/README.md b/README.md index 652c073f8..330a70165 100644 --- a/README.md +++ b/README.md @@ -1,67 +1,69 @@ # ![nf-core/rnaseq](docs/images/nf-core-rnaseq_logo.png) -**Nextflow RNA-Seq analysis pipeline, part of the nf-core community.**. +[![GitHub Actions CI Status](https://github.com/nf-core/rnaseq/workflows/nf-core%20CI/badge.svg)](https://github.com/nf-core/rnaseq/actions?query=workflow%3A%22nf-core+CI%22) +[![GitHub Actions Linting Status](https://github.com/nf-core/rnaseq/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/rnaseq/actions?query=workflow%3A%22nf-core+linting%22) +[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/rnaseq/results) +[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX) -[![GitHub Actions CI Status](https://github.com/nf-core/rnaseq/workflows/nf-core%20CI/badge.svg)](https://github.com/nf-core/rnaseq/actions) -[![GitHub Actions Linting Status](https://github.com/nf-core/rnaseq/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/rnaseq/actions) -[![Nextflow](https://img.shields.io/badge/nextflow-%E2%89%A520.04.0-brightgreen.svg)](https://www.nextflow.io/) +[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A521.04.0-23aa62.svg?labelColor=000000)](https://www.nextflow.io/) +[![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/) +[![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?labelColor=000000&logo=docker)](https://www.docker.com/) +[![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/) -[![install with bioconda](https://img.shields.io/badge/install%20with-bioconda-brightgreen.svg)](https://bioconda.github.io/) -[![Docker](https://img.shields.io/docker/automated/nfcore/rnaseq.svg)](https://hub.docker.com/r/nfcore/rnaseq) -[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23rnaseq-4A154B?logo=slack)](https://nfcore.slack.com/channels/rnaseq) +[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23rnaseq-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/rnaseq) +[![Follow on Twitter](http://img.shields.io/badge/twitter-%40nf__core-1DA1F2?labelColor=000000&logo=twitter)](https://twitter.com/nf_core) +[![Watch on YouTube](http://img.shields.io/badge/youtube-nf--core-FF0000?labelColor=000000&logo=youtube)](https://www.youtube.com/c/nf-core) ## Introduction -**nf-core/rnaseq** is a bioinformatics best-practise analysis pipeline for +**nf-core/rnaseq** is a bioinformatics best-practice analysis pipeline for Nextflow RNA-Seq analysis pipeline, part of the nf-core community.. -The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. It comes with docker containers making installation trivial and results highly reproducible. +The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. It uses Docker/Singularity containers making installation trivial and results highly reproducible. The [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html) implementation of this pipeline uses one container per process which makes it much easier to maintain and update software dependencies. Where possible, these processes have been submitted to and installed from [nf-core/modules](https://github.com/nf-core/modules) in order to make them available to all nf-core pipelines, and to everyone within the Nextflow community! + + +On release, automated continuous integration tests run the pipeline on a full-sized dataset on the AWS cloud infrastructure. This ensures that the pipeline runs on AWS, has sensible resource allocation defaults set to run on real-world datasets, and permits the persistent storage of results to benchmark between pipeline releases and other analysis sources. The results obtained from the full-sized test can be viewed on the [nf-core website](https://nf-co.re/rnaseq/results). + +## Pipeline summary + + + +1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)) +2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/)) ## Quick Start -1. Install [`nextflow`](https://nf-co.re/usage/installation) (`>=20.04.0`) +1. Install [`Nextflow`](https://nf-co.re/usage/installation) (`>=21.04.0`) 2. Install any of [`Docker`](https://docs.docker.com/engine/installation/), [`Singularity`](https://www.sylabs.io/guides/3.0/user-guide/), [`Podman`](https://podman.io/), [`Shifter`](https://nersc.gitlab.io/development/shifter/how-to-use/) or [`Charliecloud`](https://hpc.github.io/charliecloud/) for full pipeline reproducibility _(please only use [`Conda`](https://conda.io/miniconda.html) as a last resort; see [docs](https://nf-co.re/usage/configuration#basic-configuration-profiles))_ 3. Download the pipeline and test it on a minimal dataset with a single command: - ```bash + ```console nextflow run nf-core/rnaseq -profile test, ``` - > Please check [nf-core/configs](https://github.com/nf-core/configs#documentation) to see if a custom config file to run nf-core pipelines already exists for your Institute. If so, you can simply use `-profile ` in your command. This will enable either `docker` or `singularity` and set the appropriate execution settings for your local compute environment. + > * Please check [nf-core/configs](https://github.com/nf-core/configs#documentation) to see if a custom config file to run nf-core pipelines already exists for your Institute. If so, you can simply use `-profile ` in your command. This will enable either `docker` or `singularity` and set the appropriate execution settings for your local compute environment. + > * If you are using `singularity` then the pipeline will auto-detect this and attempt to download the Singularity images directly as opposed to performing a conversion from Docker images. If you are persistently observing issues downloading Singularity images directly due to timeout or network issues then please use the `--singularity_pull_docker_container` parameter to pull and convert the Docker image instead. Alternatively, it is highly recommended to use the [`nf-core download`](https://nf-co.re/tools/#downloading-pipelines-for-offline-use) command to pre-download all of the required containers before running the pipeline and to set the [`NXF_SINGULARITY_CACHEDIR` or `singularity.cacheDir`](https://www.nextflow.io/docs/latest/singularity.html?#singularity-docker-hub) Nextflow options to be able to store and re-use the images from a central location for future pipeline runs. + > * If you are using `conda`, it is highly recommended to use the [`NXF_CONDA_CACHEDIR` or `conda.cacheDir`](https://www.nextflow.io/docs/latest/conda.html) settings to store the environments in a central location for future pipeline runs. 4. Start running your own analysis! - ```bash - nextflow run nf-core/rnaseq -profile --input '*_R{1,2}.fastq.gz' --genome GRCh37 + ```console + nextflow run nf-core/rnaseq -profile --input samplesheet.csv --genome GRCh37 ``` -See [usage docs](https://nf-co.re/rnaseq/usage) for all of the available options when running the pipeline. - -## Pipeline Summary - -By default, the pipeline currently performs the following: - - - -* Sequencing quality control (`FastQC`) -* Overall pipeline run summaries (`MultiQC`) - ## Documentation -The nf-core/rnaseq pipeline comes with documentation about the pipeline: [usage](https://nf-co.re/rnaseq/usage) and [output](https://nf-co.re/rnaseq/output). - - +The nf-core/rnaseq pipeline comes with documentation about the pipeline [usage](https://nf-co.re/rnaseq/usage), [parameters](https://nf-co.re/rnaseq/parameters) and [output](https://nf-co.re/rnaseq/output). ## Credits nf-core/rnaseq was originally written by Phil Ewels, Rickard Hammarén. -We thank the following people for their extensive assistance in the development -of this pipeline: +We thank the following people for their extensive assistance in the development of this pipeline: @@ -73,9 +75,12 @@ For further information or help, don't hesitate to get in touch on the [Slack `# ## Citations - + + +An extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file. + You can cite the `nf-core` publication as follows: > **The nf-core framework for community-curated bioinformatics pipelines.** @@ -83,7 +88,3 @@ You can cite the `nf-core` publication as follows: > Philip Ewels, Alexander Peltzer, Sven Fillinger, Harshil Patel, Johannes Alneberg, Andreas Wilm, Maxime Ulysse Garcia, Paolo Di Tommaso & Sven Nahnsen. > > _Nat Biotechnol._ 2020 Feb 13. doi: [10.1038/s41587-020-0439-x](https://dx.doi.org/10.1038/s41587-020-0439-x). - -In addition, references of tools and data used in this pipeline are as follows: - - diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv new file mode 100644 index 000000000..5f653ab7b --- /dev/null +++ b/assets/samplesheet.csv @@ -0,0 +1,3 @@ +sample,fastq_1,fastq_2 +SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz +SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz, diff --git a/assets/schema_input.json b/assets/schema_input.json new file mode 100644 index 000000000..da0d4e1f6 --- /dev/null +++ b/assets/schema_input.json @@ -0,0 +1,39 @@ +{ + "$schema": "http://json-schema.org/draft-07/schema", + "$id": "https://raw.githubusercontent.com/nf-core/rnaseq/master/assets/schema_input.json", + "title": "nf-core/rnaseq pipeline - params.input schema", + "description": "Schema for the file provided with params.input", + "type": "array", + "items": { + "type": "object", + "properties": { + "sample": { + "type": "string", + "pattern": "^\\S+$", + "errorMessage": "Sample name must be provided and cannot contain spaces" + }, + "fastq_1": { + "type": "string", + "pattern": "^\\S+\\.f(ast)?q\\.gz$", + "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'" + }, + "fastq_2": { + "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'", + "anyOf": [ + { + "type": "string", + "pattern": "^\\S+\\.f(ast)?q\\.gz$" + }, + { + "type": "string", + "maxLength": 0 + } + ] + } + }, + "required": [ + "sample", + "fastq_1" + ] + } +} diff --git a/assets/sendmail_template.txt b/assets/sendmail_template.txt index 41387bfd5..df93faab7 100644 --- a/assets/sendmail_template.txt +++ b/assets/sendmail_template.txt @@ -15,15 +15,15 @@ Content-ID: Content-Disposition: inline; filename="nf-core-rnaseq_logo.png" <% out << new File("$projectDir/assets/nf-core-rnaseq_logo.png"). - bytes. - encodeBase64(). - toString(). - tokenize( '\n' )*. - toList()*. - collate( 76 )*. - collect { it.join() }. - flatten(). - join( '\n' ) %> + bytes. + encodeBase64(). + toString(). + tokenize( '\n' )*. + toList()*. + collate( 76 )*. + collect { it.join() }. + flatten(). + join( '\n' ) %> <% if (mqcFile){ @@ -37,15 +37,15 @@ Content-ID: Content-Disposition: attachment; filename=\"${mqcFileObj.getName()}\" ${mqcFileObj. - bytes. - encodeBase64(). - toString(). - tokenize( '\n' )*. - toList()*. - collate( 76 )*. - collect { it.join() }. - flatten(). - join( '\n' )} + bytes. + encodeBase64(). + toString(). + tokenize( '\n' )*. + toList()*. + collate( 76 )*. + collect { it.join() }. + flatten(). + join( '\n' )} """ }} %> diff --git a/bin/check_samplesheet.py b/bin/check_samplesheet.py new file mode 100755 index 000000000..51705c60a --- /dev/null +++ b/bin/check_samplesheet.py @@ -0,0 +1,146 @@ +#!/usr/bin/env python + +# TODO nf-core: Update the script to check the samplesheet +# This script is based on the example at: https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv + +import os +import sys +import errno +import argparse + + +def parse_args(args=None): + Description = "Reformat nf-core/rnaseq samplesheet file and check its contents." + Epilog = "Example usage: python check_samplesheet.py " + + parser = argparse.ArgumentParser(description=Description, epilog=Epilog) + parser.add_argument("FILE_IN", help="Input samplesheet file.") + parser.add_argument("FILE_OUT", help="Output file.") + return parser.parse_args(args) + + +def make_dir(path): + if len(path) > 0: + try: + os.makedirs(path) + except OSError as exception: + if exception.errno != errno.EEXIST: + raise exception + + +def print_error(error, context="Line", context_str=""): + error_str = "ERROR: Please check samplesheet -> {}".format(error) + if context != "" and context_str != "": + error_str = "ERROR: Please check samplesheet -> {}\n{}: '{}'".format( + error, context.strip(), context_str.strip() + ) + print(error_str) + sys.exit(1) + + +# TODO nf-core: Update the check_samplesheet function +def check_samplesheet(file_in, file_out): + """ + This function checks that the samplesheet follows the following structure: + + sample,fastq_1,fastq_2 + SAMPLE_PE,SAMPLE_PE_RUN1_1.fastq.gz,SAMPLE_PE_RUN1_2.fastq.gz + SAMPLE_PE,SAMPLE_PE_RUN2_1.fastq.gz,SAMPLE_PE_RUN2_2.fastq.gz + SAMPLE_SE,SAMPLE_SE_RUN1_1.fastq.gz, + + For an example see: + https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv + """ + + sample_mapping_dict = {} + with open(file_in, "r") as fin: + + ## Check header + MIN_COLS = 2 + # TODO nf-core: Update the column names for the input samplesheet + HEADER = ["sample", "fastq_1", "fastq_2"] + header = [x.strip('"') for x in fin.readline().strip().split(",")] + if header[: len(HEADER)] != HEADER: + print("ERROR: Please check samplesheet header -> {} != {}".format(",".join(header), ",".join(HEADER))) + sys.exit(1) + + ## Check sample entries + for line in fin: + lspl = [x.strip().strip('"') for x in line.strip().split(",")] + + # Check valid number of columns per row + if len(lspl) < len(HEADER): + print_error( + "Invalid number of columns (minimum = {})!".format(len(HEADER)), + "Line", + line, + ) + num_cols = len([x for x in lspl if x]) + if num_cols < MIN_COLS: + print_error( + "Invalid number of populated columns (minimum = {})!".format(MIN_COLS), + "Line", + line, + ) + + ## Check sample name entries + sample, fastq_1, fastq_2 = lspl[: len(HEADER)] + sample = sample.replace(" ", "_") + if not sample: + print_error("Sample entry has not been specified!", "Line", line) + + ## Check FastQ file extension + for fastq in [fastq_1, fastq_2]: + if fastq: + if fastq.find(" ") != -1: + print_error("FastQ file contains spaces!", "Line", line) + if not fastq.endswith(".fastq.gz") and not fastq.endswith(".fq.gz"): + print_error( + "FastQ file does not have extension '.fastq.gz' or '.fq.gz'!", + "Line", + line, + ) + + ## Auto-detect paired-end/single-end + sample_info = [] ## [single_end, fastq_1, fastq_2] + if sample and fastq_1 and fastq_2: ## Paired-end short reads + sample_info = ["0", fastq_1, fastq_2] + elif sample and fastq_1 and not fastq_2: ## Single-end short reads + sample_info = ["1", fastq_1, fastq_2] + else: + print_error("Invalid combination of columns provided!", "Line", line) + + ## Create sample mapping dictionary = { sample: [ single_end, fastq_1, fastq_2 ] } + if sample not in sample_mapping_dict: + sample_mapping_dict[sample] = [sample_info] + else: + if sample_info in sample_mapping_dict[sample]: + print_error("Samplesheet contains duplicate rows!", "Line", line) + else: + sample_mapping_dict[sample].append(sample_info) + + ## Write validated samplesheet with appropriate columns + if len(sample_mapping_dict) > 0: + out_dir = os.path.dirname(file_out) + make_dir(out_dir) + with open(file_out, "w") as fout: + fout.write(",".join(["sample", "single_end", "fastq_1", "fastq_2"]) + "\n") + for sample in sorted(sample_mapping_dict.keys()): + + ## Check that multiple runs of the same sample are of the same datatype + if not all(x[0] == sample_mapping_dict[sample][0][0] for x in sample_mapping_dict[sample]): + print_error("Multiple runs of a sample must be of the same datatype!", "Sample: {}".format(sample)) + + for idx, val in enumerate(sample_mapping_dict[sample]): + fout.write(",".join(["{}_T{}".format(sample, idx + 1)] + val) + "\n") + else: + print_error("No entries to process!", "Samplesheet: {}".format(file_in)) + + +def main(args=None): + args = parse_args(args) + check_samplesheet(args.FILE_IN, args.FILE_OUT) + + +if __name__ == "__main__": + sys.exit(main()) diff --git a/bin/markdown_to_html.py b/bin/markdown_to_html.py deleted file mode 100755 index a26d1ff5e..000000000 --- a/bin/markdown_to_html.py +++ /dev/null @@ -1,91 +0,0 @@ -#!/usr/bin/env python -from __future__ import print_function -import argparse -import markdown -import os -import sys -import io - - -def convert_markdown(in_fn): - input_md = io.open(in_fn, mode="r", encoding="utf-8").read() - html = markdown.markdown( - "[TOC]\n" + input_md, - extensions=["pymdownx.extra", "pymdownx.b64", "pymdownx.highlight", "pymdownx.emoji", "pymdownx.tilde", "toc"], - extension_configs={ - "pymdownx.b64": {"base_path": os.path.dirname(in_fn)}, - "pymdownx.highlight": {"noclasses": True}, - "toc": {"title": "Table of Contents"}, - }, - ) - return html - - -def wrap_html(contents): - header = """ - - - - - -
- """ - footer = """ -
- - - """ - return header + contents + footer - - -def parse_args(args=None): - parser = argparse.ArgumentParser() - parser.add_argument("mdfile", type=argparse.FileType("r"), nargs="?", help="File to convert. Defaults to stdin.") - parser.add_argument( - "-o", "--out", type=argparse.FileType("w"), default=sys.stdout, help="Output file name. Defaults to stdout." - ) - return parser.parse_args(args) - - -def main(args=None): - args = parse_args(args) - converted_md = convert_markdown(args.mdfile.name) - html = wrap_html(converted_md) - args.out.write(html) - - -if __name__ == "__main__": - sys.exit(main()) diff --git a/bin/scrape_software_versions.py b/bin/scrape_software_versions.py index f0a86e207..518ee4220 100755 --- a/bin/scrape_software_versions.py +++ b/bin/scrape_software_versions.py @@ -1,36 +1,18 @@ #!/usr/bin/env python from __future__ import print_function -from collections import OrderedDict -import re +import os -# TODO nf-core: Add additional regexes for new tools in process get_software_versions -regexes = { - "nf-core/rnaseq": ["v_pipeline.txt", r"(\S+)"], - "Nextflow": ["v_nextflow.txt", r"(\S+)"], - "FastQC": ["v_fastqc.txt", r"FastQC v(\S+)"], - "MultiQC": ["v_multiqc.txt", r"multiqc, version (\S+)"], -} -results = OrderedDict() -results["nf-core/rnaseq"] = 'N/A' -results["Nextflow"] = 'N/A' -results["FastQC"] = 'N/A' -results["MultiQC"] = 'N/A' +results = {} +version_files = [x for x in os.listdir(".") if x.endswith(".version.txt")] +for version_file in version_files: -# Search each file using its regex -for k, v in regexes.items(): - try: - with open(v[0]) as x: - versions = x.read() - match = re.search(v[1], versions) - if match: - results[k] = "v{}".format(match.group(1)) - except IOError: - results[k] = False + software = version_file.replace(".version.txt", "") + if software == "pipeline": + software = "nf-core/rnaseq" -# Remove software set to false in results -for k in list(results): - if not results[k]: - del results[k] + with open(version_file) as fin: + version = fin.read().strip() + results[software] = version # Dump to YAML print( @@ -44,11 +26,11 @@
""" ) -for k, v in results.items(): +for k, v in sorted(results.items()): print("
{}
{}
".format(k, v)) print("
") # Write out regexes as csv file: -with open("software_versions.csv", "w") as f: - for k, v in results.items(): +with open("software_versions.tsv", "w") as f: + for k, v in sorted(results.items()): f.write("{}\t{}\n".format(k, v)) diff --git a/conf/base.config b/conf/base.config index 7fffc8326..2f132c0e4 100644 --- a/conf/base.config +++ b/conf/base.config @@ -1,51 +1,57 @@ /* - * ------------------------------------------------- - * nf-core/rnaseq Nextflow base config file - * ------------------------------------------------- - * A 'blank slate' config file, appropriate for general - * use on most high performace compute environments. - * Assumes that all software is installed and available - * on the PATH. Runs in `local` mode - all jobs will be - * run on the logged in environment. - */ +======================================================================================== + nf-core/rnaseq Nextflow base config file +======================================================================================== + A 'blank slate' config file, appropriate for general use on most high performance + compute environments. Assumes that all software is installed and available on + the PATH. Runs in `local` mode - all jobs will be run on the logged in environment. +---------------------------------------------------------------------------------------- +*/ process { - // TODO nf-core: Check the defaults for all processes - cpus = { check_max( 1 * task.attempt, 'cpus' ) } - memory = { check_max( 7.GB * task.attempt, 'memory' ) } - time = { check_max( 4.h * task.attempt, 'time' ) } + // TODO nf-core: Check the defaults for all processes + cpus = { check_max( 1 * task.attempt, 'cpus' ) } + memory = { check_max( 6.GB * task.attempt, 'memory' ) } + time = { check_max( 4.h * task.attempt, 'time' ) } - errorStrategy = { task.exitStatus in [143,137,104,134,139] ? 'retry' : 'finish' } - maxRetries = 1 - maxErrors = '-1' - - // Process-specific resource requirements - // NOTE - Only one of the labels below are used in the fastqc process in the main script. - // If possible, it would be nice to keep the same label naming convention when - // adding in your processes. - // TODO nf-core: Customise requirements for specific processes. - // See https://www.nextflow.io/docs/latest/config.html#config-process-selectors - withLabel:process_low { - cpus = { check_max( 2 * task.attempt, 'cpus' ) } - memory = { check_max( 14.GB * task.attempt, 'memory' ) } - time = { check_max( 6.h * task.attempt, 'time' ) } - } - withLabel:process_medium { - cpus = { check_max( 6 * task.attempt, 'cpus' ) } - memory = { check_max( 42.GB * task.attempt, 'memory' ) } - time = { check_max( 8.h * task.attempt, 'time' ) } - } - withLabel:process_high { - cpus = { check_max( 12 * task.attempt, 'cpus' ) } - memory = { check_max( 84.GB * task.attempt, 'memory' ) } - time = { check_max( 10.h * task.attempt, 'time' ) } - } - withLabel:process_long { - time = { check_max( 20.h * task.attempt, 'time' ) } - } - withName:get_software_versions { - cache = false - } + errorStrategy = { task.exitStatus in [143,137,104,134,139] ? 'retry' : 'finish' } + maxRetries = 1 + maxErrors = '-1' + // Process-specific resource requirements + // NOTE - Please try and re-use the labels below as much as possible. + // These labels are used and recognised by default in DSL2 files hosted on nf-core/modules. + // If possible, it would be nice to keep the same label naming convention when + // adding in your local modules too. + // TODO nf-core: Customise requirements for specific processes. + // See https://www.nextflow.io/docs/latest/config.html#config-process-selectors + withLabel:process_low { + cpus = { check_max( 2 * task.attempt, 'cpus' ) } + memory = { check_max( 12.GB * task.attempt, 'memory' ) } + time = { check_max( 4.h * task.attempt, 'time' ) } + } + withLabel:process_medium { + cpus = { check_max( 6 * task.attempt, 'cpus' ) } + memory = { check_max( 36.GB * task.attempt, 'memory' ) } + time = { check_max( 8.h * task.attempt, 'time' ) } + } + withLabel:process_high { + cpus = { check_max( 12 * task.attempt, 'cpus' ) } + memory = { check_max( 72.GB * task.attempt, 'memory' ) } + time = { check_max( 16.h * task.attempt, 'time' ) } + } + withLabel:process_long { + time = { check_max( 20.h * task.attempt, 'time' ) } + } + withLabel:process_high_memory { + memory = { check_max( 200.GB * task.attempt, 'memory' ) } + } + withLabel:error_ignore { + errorStrategy = 'ignore' + } + withLabel:error_retry { + errorStrategy = 'retry' + maxRetries = 2 + } } diff --git a/conf/igenomes.config b/conf/igenomes.config index 31b7ee613..855948def 100644 --- a/conf/igenomes.config +++ b/conf/igenomes.config @@ -1,421 +1,432 @@ /* - * ------------------------------------------------- - * Nextflow config file for iGenomes paths - * ------------------------------------------------- - * Defines reference genomes, using iGenome paths - * Can be used by any config that customises the base - * path using $params.igenomes_base / --igenomes_base - */ +======================================================================================== + Nextflow config file for iGenomes paths +======================================================================================== + Defines reference genomes using iGenome paths. + Can be used by any config that customises the base path using: + $params.igenomes_base / --igenomes_base +---------------------------------------------------------------------------------------- +*/ params { - // illumina iGenomes reference file paths - genomes { - 'GRCh37' { - fasta = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/README.txt" - mito_name = "MT" - macs_gsize = "2.7e9" - blacklist = "${projectDir}/assets/blacklists/GRCh37-blacklist.bed" + // illumina iGenomes reference file paths + genomes { + 'GRCh37' { + fasta = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/README.txt" + mito_name = "MT" + macs_gsize = "2.7e9" + blacklist = "${projectDir}/assets/blacklists/GRCh37-blacklist.bed" + } + 'GRCh38' { + fasta = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.bed" + mito_name = "chrM" + macs_gsize = "2.7e9" + blacklist = "${projectDir}/assets/blacklists/hg38-blacklist.bed" + } + 'GRCm38' { + fasta = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/README.txt" + mito_name = "MT" + macs_gsize = "1.87e9" + blacklist = "${projectDir}/assets/blacklists/GRCm38-blacklist.bed" + } + 'TAIR10' { + fasta = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/README.txt" + mito_name = "Mt" + } + 'EB2' { + fasta = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/README.txt" + } + 'UMD3.1' { + fasta = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/README.txt" + mito_name = "MT" + } + 'WBcel235' { + fasta = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.bed" + mito_name = "MtDNA" + macs_gsize = "9e7" + } + 'CanFam3.1' { + fasta = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/README.txt" + mito_name = "MT" + } + 'GRCz10' { + fasta = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.bed" + mito_name = "MT" + } + 'BDGP6' { + fasta = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.bed" + mito_name = "M" + macs_gsize = "1.2e8" + } + 'EquCab2' { + fasta = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/README.txt" + mito_name = "MT" + } + 'EB1' { + fasta = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/README.txt" + } + 'Galgal4' { + fasta = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Annotation/Genes/genes.bed" + mito_name = "MT" + } + 'Gm01' { + fasta = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/README.txt" + } + 'Mmul_1' { + fasta = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/README.txt" + mito_name = "MT" + } + 'IRGSP-1.0' { + fasta = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Annotation/Genes/genes.bed" + mito_name = "Mt" + } + 'CHIMP2.1.4' { + fasta = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/README.txt" + mito_name = "MT" + } + 'Rnor_5.0' { + fasta = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Annotation/Genes/genes.bed" + mito_name = "MT" + } + 'Rnor_6.0' { + fasta = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Annotation/Genes/genes.bed" + mito_name = "MT" + } + 'R64-1-1' { + fasta = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Annotation/Genes/genes.bed" + mito_name = "MT" + macs_gsize = "1.2e7" + } + 'EF2' { + fasta = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/README.txt" + mito_name = "MT" + macs_gsize = "1.21e7" + } + 'Sbi1' { + fasta = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/README.txt" + } + 'Sscrofa10.2' { + fasta = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/README.txt" + mito_name = "MT" + } + 'AGPv3' { + fasta = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.bed" + mito_name = "Mt" + } + 'hg38' { + fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.bed" + mito_name = "chrM" + macs_gsize = "2.7e9" + blacklist = "${projectDir}/assets/blacklists/hg38-blacklist.bed" + } + 'hg19' { + fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/README.txt" + mito_name = "chrM" + macs_gsize = "2.7e9" + blacklist = "${projectDir}/assets/blacklists/hg19-blacklist.bed" + } + 'mm10' { + fasta = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/README.txt" + mito_name = "chrM" + macs_gsize = "1.87e9" + blacklist = "${projectDir}/assets/blacklists/mm10-blacklist.bed" + } + 'bosTau8' { + fasta = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Annotation/Genes/genes.bed" + mito_name = "chrM" + } + 'ce10' { + fasta = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/README.txt" + mito_name = "chrM" + macs_gsize = "9e7" + } + 'canFam3' { + fasta = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/README.txt" + mito_name = "chrM" + } + 'danRer10' { + fasta = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Annotation/Genes/genes.bed" + mito_name = "chrM" + macs_gsize = "1.37e9" + } + 'dm6' { + fasta = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Annotation/Genes/genes.bed" + mito_name = "chrM" + macs_gsize = "1.2e8" + } + 'equCab2' { + fasta = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/README.txt" + mito_name = "chrM" + } + 'galGal4' { + fasta = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/README.txt" + mito_name = "chrM" + } + 'panTro4' { + fasta = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/README.txt" + mito_name = "chrM" + } + 'rn6' { + fasta = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Annotation/Genes/genes.bed" + mito_name = "chrM" + } + 'sacCer3' { + fasta = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/BismarkIndex/" + readme = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Annotation/README.txt" + mito_name = "chrM" + macs_gsize = "1.2e7" + } + 'susScr3' { + fasta = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/BWAIndex/genome.fa" + bowtie2 = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/Bowtie2Index/" + star = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/STARIndex/" + bismark = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/BismarkIndex/" + gtf = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/Genes/genes.gtf" + bed12 = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/Genes/genes.bed" + readme = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/README.txt" + mito_name = "chrM" + } } - 'GRCh38' { - fasta = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.bed" - mito_name = "chrM" - macs_gsize = "2.7e9" - blacklist = "${projectDir}/assets/blacklists/hg38-blacklist.bed" - } - 'GRCm38' { - fasta = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/README.txt" - mito_name = "MT" - macs_gsize = "1.87e9" - blacklist = "${projectDir}/assets/blacklists/GRCm38-blacklist.bed" - } - 'TAIR10' { - fasta = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/README.txt" - mito_name = "Mt" - } - 'EB2' { - fasta = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/README.txt" - } - 'UMD3.1' { - fasta = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/README.txt" - mito_name = "MT" - } - 'WBcel235' { - fasta = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.bed" - mito_name = "MtDNA" - macs_gsize = "9e7" - } - 'CanFam3.1' { - fasta = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/README.txt" - mito_name = "MT" - } - 'GRCz10' { - fasta = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.bed" - mito_name = "MT" - } - 'BDGP6' { - fasta = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.bed" - mito_name = "M" - macs_gsize = "1.2e8" - } - 'EquCab2' { - fasta = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/README.txt" - mito_name = "MT" - } - 'EB1' { - fasta = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/README.txt" - } - 'Galgal4' { - fasta = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Annotation/Genes/genes.bed" - mito_name = "MT" - } - 'Gm01' { - fasta = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/README.txt" - } - 'Mmul_1' { - fasta = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/README.txt" - mito_name = "MT" - } - 'IRGSP-1.0' { - fasta = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Annotation/Genes/genes.bed" - mito_name = "Mt" - } - 'CHIMP2.1.4' { - fasta = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/README.txt" - mito_name = "MT" - } - 'Rnor_6.0' { - fasta = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Annotation/Genes/genes.bed" - mito_name = "MT" - } - 'R64-1-1' { - fasta = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Annotation/Genes/genes.bed" - mito_name = "MT" - macs_gsize = "1.2e7" - } - 'EF2' { - fasta = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/README.txt" - mito_name = "MT" - macs_gsize = "1.21e7" - } - 'Sbi1' { - fasta = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/README.txt" - } - 'Sscrofa10.2' { - fasta = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/README.txt" - mito_name = "MT" - } - 'AGPv3' { - fasta = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.bed" - mito_name = "Mt" - } - 'hg38' { - fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.bed" - mito_name = "chrM" - macs_gsize = "2.7e9" - blacklist = "${projectDir}/assets/blacklists/hg38-blacklist.bed" - } - 'hg19' { - fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/README.txt" - mito_name = "chrM" - macs_gsize = "2.7e9" - blacklist = "${projectDir}/assets/blacklists/hg19-blacklist.bed" - } - 'mm10' { - fasta = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/README.txt" - mito_name = "chrM" - macs_gsize = "1.87e9" - blacklist = "${projectDir}/assets/blacklists/mm10-blacklist.bed" - } - 'bosTau8' { - fasta = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Annotation/Genes/genes.bed" - mito_name = "chrM" - } - 'ce10' { - fasta = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/README.txt" - mito_name = "chrM" - macs_gsize = "9e7" - } - 'canFam3' { - fasta = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/README.txt" - mito_name = "chrM" - } - 'danRer10' { - fasta = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Annotation/Genes/genes.bed" - mito_name = "chrM" - macs_gsize = "1.37e9" - } - 'dm6' { - fasta = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Annotation/Genes/genes.bed" - mito_name = "chrM" - macs_gsize = "1.2e8" - } - 'equCab2' { - fasta = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/README.txt" - mito_name = "chrM" - } - 'galGal4' { - fasta = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/README.txt" - mito_name = "chrM" - } - 'panTro4' { - fasta = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/README.txt" - mito_name = "chrM" - } - 'rn6' { - fasta = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Annotation/Genes/genes.bed" - mito_name = "chrM" - } - 'sacCer3' { - fasta = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/BismarkIndex/" - readme = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Annotation/README.txt" - mito_name = "chrM" - macs_gsize = "1.2e7" - } - 'susScr3' { - fasta = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/BWAIndex/genome.fa" - bowtie2 = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/README.txt" - mito_name = "chrM" - } - } } diff --git a/conf/modules.config b/conf/modules.config new file mode 100644 index 000000000..0b1bfdec2 --- /dev/null +++ b/conf/modules.config @@ -0,0 +1,32 @@ +/* +======================================================================================== + Config file for defining DSL2 per module options +======================================================================================== + Available keys to override module options: + args = Additional arguments appended to command in module. + args2 = Second set of arguments appended to command in module (multi-tool modules). + args3 = Third set of arguments appended to command in module (multi-tool modules). + publish_dir = Directory to publish results. + publish_by_meta = Groovy list of keys available in meta map to append as directories to "publish_dir" path + If publish_by_meta = true - Value of ${meta['id']} is appended as a directory to "publish_dir" path + If publish_by_meta = ['id', 'custompath'] - If "id" is in meta map and "custompath" isn't then "${meta['id']}/custompath/" + is appended as a directory to "publish_dir" path + If publish_by_meta = false / null - No directories are appended to "publish_dir" path + publish_files = Groovy map where key = "file_ext" and value = "directory" to publish results for that file extension + The value of "directory" is appended to the standard "publish_dir" path as defined above. + If publish_files = null (unspecified) - All files are published. + If publish_files = false - No files are published. + suffix = File name suffix for output files. +---------------------------------------------------------------------------------------- +*/ + +params { + modules { + 'fastqc' { + args = "--quiet" + } + 'multiqc' { + args = "" + } + } +} diff --git a/conf/test.config b/conf/test.config index 1eebf468d..3307f2530 100644 --- a/conf/test.config +++ b/conf/test.config @@ -1,28 +1,29 @@ /* - * ------------------------------------------------- - * Nextflow config file for running tests - * ------------------------------------------------- - * Defines bundled input files and everything required - * to run a fast and simple test. Use as follows: - * nextflow run nf-core/rnaseq -profile test, - */ +======================================================================================== + Nextflow config file for running minimal tests +======================================================================================== + Defines input files and everything required to run a fast and simple pipeline test. + + Use as follows: + nextflow run nf-core/rnaseq -profile test, + +---------------------------------------------------------------------------------------- +*/ params { - config_profile_name = 'Test profile' - config_profile_description = 'Minimal test dataset to check pipeline function' - // Limit resources so that this can run on GitHub Actions - max_cpus = 2 - max_memory = 6.GB - max_time = 48.h + config_profile_name = 'Test profile' + config_profile_description = 'Minimal test dataset to check pipeline function' + + // Limit resources so that this can run on GitHub Actions + max_cpus = 2 + max_memory = 6.GB + max_time = 6.h + + // Input data + // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets + // TODO nf-core: Give any required params for the test so that command line flags are not needed + input = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv' - // Input data - // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets - // TODO nf-core: Give any required params for the test so that command line flags are not needed - single_end = false - input_paths = [ - ['Testdata', ['https://github.com/nf-core/test-datasets/raw/exoseq/testdata/Testdata_R1.tiny.fastq.gz', 'https://github.com/nf-core/test-datasets/raw/exoseq/testdata/Testdata_R2.tiny.fastq.gz']], - ['SRR389222', ['https://github.com/nf-core/test-datasets/raw/methylseq/testdata/SRR389222_sub1.fastq.gz', 'https://github.com/nf-core/test-datasets/raw/methylseq/testdata/SRR389222_sub2.fastq.gz']] - ] - // Ignore `--input` as otherwise the parameter validation will throw an error - schema_ignore_params = 'genomes,input_paths,input' + // Genome references + genome = 'R64-1-1' } diff --git a/conf/test_full.config b/conf/test_full.config index 0a94f6e07..49a3d0d09 100644 --- a/conf/test_full.config +++ b/conf/test_full.config @@ -1,24 +1,24 @@ /* - * ------------------------------------------------- - * Nextflow config file for running full-size tests - * ------------------------------------------------- - * Defines bundled input files and everything required - * to run a full size pipeline test. Use as follows: - * nextflow run nf-core/rnaseq -profile test_full, - */ +======================================================================================== + Nextflow config file for running full-size tests +======================================================================================== + Defines input files and everything required to run a full size pipeline test. + + Use as follows: + nextflow run nf-core/rnaseq -profile test_full, + +---------------------------------------------------------------------------------------- +*/ params { - config_profile_name = 'Full test profile' - config_profile_description = 'Full test dataset to check pipeline function' + config_profile_name = 'Full test profile' + config_profile_description = 'Full test dataset to check pipeline function' + + // Input data for full size test + // TODO nf-core: Specify the paths to your full test data ( on nf-core/test-datasets or directly in repositories, e.g. SRA) + // TODO nf-core: Give any required params for the test so that command line flags are not needed + input = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_full_illumina_amplicon.csv' - // Input data for full size test - // TODO nf-core: Specify the paths to your full test data ( on nf-core/test-datasets or directly in repositories, e.g. SRA) - // TODO nf-core: Give any required params for the test so that command line flags are not needed - single_end = false - input_paths = [ - ['Testdata', ['https://github.com/nf-core/test-datasets/raw/exoseq/testdata/Testdata_R1.tiny.fastq.gz', 'https://github.com/nf-core/test-datasets/raw/exoseq/testdata/Testdata_R2.tiny.fastq.gz']], - ['SRR389222', ['https://github.com/nf-core/test-datasets/raw/methylseq/testdata/SRR389222_sub1.fastq.gz', 'https://github.com/nf-core/test-datasets/raw/methylseq/testdata/SRR389222_sub2.fastq.gz']] - ] - // Ignore `--input` as otherwise the parameter validation will throw an error - schema_ignore_params = 'genomes,input_paths,input' + // Genome references + genome = 'R64-1-1' } diff --git a/docs/README.md b/docs/README.md index 3775cdd28..052f60f03 100644 --- a/docs/README.md +++ b/docs/README.md @@ -3,8 +3,8 @@ The nf-core/rnaseq documentation is split into the following pages: * [Usage](usage.md) - * An overview of how the pipeline works, how to run it and a description of all of the different command-line flags. + * An overview of how the pipeline works, how to run it and a description of all of the different command-line flags. * [Output](output.md) - * An overview of the different results produced by the pipeline and how to interpret them. + * An overview of the different results produced by the pipeline and how to interpret them. You can find a lot more documentation about installing, configuring and running nf-core pipelines on the website: [https://nf-co.re](https://nf-co.re) diff --git a/docs/images/mqc_fastqc_adapter.png b/docs/images/mqc_fastqc_adapter.png new file mode 100755 index 0000000000000000000000000000000000000000..361d0e47acfb424dea1f326590d1eb2f6dfa26b5 GIT binary patch literal 23458 zcmeFZ2UJtryD!S#x<#o93es(Ww4k)maRbte0-+a?-g^xY-3myTE`8G_KvA54)F1tn})nJ5u%TA4Y;^!^{48eL_}p#q-Umo0M|F1 z74+PQh^X8N|9_jcWbq~ zzn+tZC9B75nKdz=gQ8wo9GJ$P{D~3knlI_`-PRhCw34f1oYDLr^;oEbgxa#A^J%*2 z>FfDE*(~JzKFs$t_oeLz))qDU?s}%Q?7b~3Y;lUi^Oy-2@3g?joA4Wkgb6-2=ih*jub)~7yZ`T=L=Z`B`{1jhkB-iSjea94&Eo9A zxN59pv1p_}RO1>EC^q}Z2)ZI;b7JV_x4lMr=Bker2+EK;8~!;JO7re*@ZkDmoV878S*N^yX(F@U1yqt?Is3nnV>7}#(5pk`V3C) zWhB8;CwWIwsVIjH+`<9=YA(j&3DgQdFOOGU~*`36wNC&QDv8> zr?h2PQgnHkp&t^S)q^K!68h~`$PjZW&-Wns;Zlw$M2sc z1xR!u{m|Kih*|Hht#M@eOMM#8O*={^6b9k5B5^eBsrnhVHD7XZ5BWO&F?q(>Y=QFl z`f>yQ9NCoxZCH-1F{#mz_j{QeyY~4h*VeyYZ#S@Z(Pnb7G=ud!RW)5svqM*&GI_za zzn;8LkOTT?``1Ygt6w!2;5arK*o5k15cdIJnMg)IQhF_zVK%!ma$z&jL zZt>Q{!PqKl^`Qw?nJUOEm@@qX(y(TwSJ~dqW&M@7-N4Wk_wC4izx(xJMrmNjsl$XR zCyK&INt}7@FzNAbbg-nW)sJ>3->I1+2~YdlPsaS}^X-H0GR_CEsw`PGjpq`uX}8VP zJ)HC34>D(z{KR9;E&z=@?@q_|I{NPOj~g>w!$gR?Tlu~F+L$Mk%}xQEm+{&T(5zkH zacVy0k3w!T9r*p2sgX@V;^+PfUYUrEde07XSV=KSDbkIZU!j!Rk3MQV=h-!y@kWVB zdYkmu^fiU~pp#ixe4hBEMx7^LdHa z_L*14aVIHtrsR)SO?=&kQS&JR#^AVvln=P=bUXEIy$QB&!s34znCV@y(C%j9V=}SU zoYLHn+-Lalm0$-=QQ}a(+2dR*{DPF+)J4y!ukiA_T%dF zVKEk;c?LWheG#A5{A20}CKjMw5G%2}cT5@Oce=wqdobHC70=kY7}dxt3diH9(Zcwr zCabx8yObHQ@#e_wjl%wp8s_!Wvxe5f-Duin@obgt>qOcqN$$@{X^C_rEDh3fmM;|X z$zu4;D`{YRbaJ?o!KkazII&|th9v5MG2Mao$ytOHtW+wo;XJJdtLuGjg;d020qT++ zpD}e&o?SeKSqR`}4`OdkWNC7K)Wltn zbwBrWGM;bBGm8uP_RiqfwvDD1f+uRX>b=nTH9Y%vpg{ka0e*E>%<+3!G3#s*-1D>q zHg~1@BT52a*L>mVcP>6y*0iX8@!3tDFJLE+sRlnU(cl``hF`0Q>e4i6P8|wKmqIqI zoY+a0V*Bib0`F9nG#sR(8$^!IWLR)cE8@7XZTN%L-ucJ{9yijy)w5Pom%XG7V<^PX z$Z$U82w0qgcGmld-O6*e)?pm$g@!6`Pps5SPKccjDf(|vX9zcLs7t!7cyyckZI#R* z#lj(HqfVeqyZ+Va{)>65sAb3IQ%a{9W^_F!5!;w=XD}ZUHFH$8=Xjw+VE)s$q(nt> zE2^aDYki5`e73RQ=DxaBNZ6CK?XKCv@V}=y(g?YHnFaHfXnl}Lo;36@?471W;&#Se z>pE*@M{Y?CevLG8il9#HXG#W3>;o$1``EYBY5i<;JlBqj2M8Y2!+6bPj1(S_bOksY z<34UQE;=Z>KiL``pYd}5fpOOT)GJQnXfNiAc5wgJ>F|$Eqw&D*Vmz+#mM0oFD^`-^ zB~SXe{T+5hd$gnKd7Afo9cy&Lii@syPDFDK)^V{iWEAEO@?xzx1bd`ta z;$(vG+=i3~9|D=GX%f~<>eOVjy~-yRAhLf2dR8V<@M_`C^ev(yOTg{uf=L3uyDb-w z&)l7KXS_HTo87BxI}fXF{ge&5p&IHk9M1}eNAwqw)`eZSOPFhqjS70{hyE@C{oSN$ zam*`-UH3RF-RWEP`^Su1q#n_J{AncekkV4m7YITf%QHBo60h@pk4N4O}hhf%rxuIZGiQpprVMal%h7?8+cY#L>pYnx6v!EnuIgInW` z)w!NuTp;fz9md^}*x@K9+`^2LO*bZp1^?BG#iS@(4i%AB6YP023T8Eb?M5K7ElSpe z9-wA22Mm}VwDkmECLd*}a=7bCf(}@SHs6UBe)Xvk(+hQ^^unj5JBeo$=><{4PBI%P z4_9XQ=XnE``;1Daa6f`~rGwNj9{YXY)eIw3G90Ip+QEWg0%?g=i$UHuQ?Qc0OR0!w zv?BvlQa!QMyI*IP!0>goBt$xo2^hlD&wRp?$=}}#?q~Yw z{**_|5&yL*Epz|4V#SJjg-lNaIx_{sCL3R=_VH&_;oOn5J2P=h!0enu-i%FAZ- zw`Hm*u6N*}&A7pAqr>-?%0(lveb{r8>hpDmex?Yo*8!-%1?YV0R~VEPBFp>)ba=mv+2(#>WEy0yxHZX=Cr2 zKmew%=^>HsD3BtRR*#H!@!TTGcI&fHrVh)P&|X;>)OHML+uWDn(dlsDjXa;5uBM$r zdt!r~ig?5iGbx!GpH+kdG8k0%;~)Q#0L6wFROJ}^Z%DvO3x#yNk13^&ccd&l)BP9h zD5cU-qZg-rV3Sg&?)`x}cI3`zw#zq{-eN4pNf(+?QuOG4oZ7zMGSVqOUe>`u=GfKM z{xPCciJFw9%Pk+uDSoormR&c=fS#hGOk=RGUtizBOoY^8P(>!Si|I9i=1ZCQbcc)5 zgE6UED;+b$4u&#dhZjdXwO3tpG0QaQwXrLOx5YP#TOaS@FP!h|G!z!Pbv?hTp0eQL zoUsiv4d@*Ck#ID9-ua|zPbQepcC4a>>9-bJApd()Wg%}hj#%A4pO-q{jIJ$f-SL7- zo&=keG_jhq$Ty4e|J^l6j6TQ=W)|~&Ei6gRn<{*^cFG*tS19#kHpMD7Y;wb~!3_%X zS_-3NQoGiWCX!M-Id;Nsg7oSi4VJ=Hi{bYNfjnmTq?IyK@@&_uacfb&8h@DIe70-Q zZ^KaT(4UX*vf7@A7CY;P!IVGIuXPRIe^&71Z1EyHO5&^=jUUKHF+h&m!4!dOA+!Ed zfA#uQ&p6vD7|O8(?5`bf8^gK)6p`>+$c*yG?Sw29;OD+tp}kDD9augDAEXWbSVoie zpHF1Wj8lWfIZ}mx%(2XREqF9!{fNd&iurAaoQDMCSNo!vRHE8wH%QLLZf9u;ADqnxOaAD#VE%Yg z?Gb?EmGbY}a0|vSZPlF3z6;Kf669Bf%h zlSGiY-}E4LFurm_CJN)(*l?=uX);o&R&qLuzENz?9I%S&YQ2>rVhx#c!hbvWLL!CI zA8mXM$zjnnJ#Me@-99}hjxCE!w8|9w{SBlj%Miq#dvS5GHP!DxO$sDx^4PF^#`;A! zb=bZ1pyj{R#9h$r7svB$QlJqeF1cp*ubT12UZ!deKFG%1N<@S2x&2UtqsVz zn=gF&$D4i3x7&vdoa#^cS?bQuP69OpspVPxm*%@DSWf!NG`o`y^R~o1Hvta;#!r%i zvEB~Jsi~sJ7Y35P!bf?OQin->fAk+TpU$Ow1st|l9|i2rrOneBP3&aDyoUj3K{a7! zOYpnJyYD#nr4GNJ;@$ce2dSN=eS7f-VptzM(|Ek^ze)mPVrpAEgrFs3mL>f(ZwriH zCZ65HdO0|W@2<+v9t?J=-4U9>bvM@@Ew4uVZy@c^Ovw9`k|$!+CTAn(u#4kC7TVTB zXuy#d+GC@RIMaPyp|Y2jS%RJkktCracCaLqfs^i^XFqK#3z+d}n02*VDF&My)vp)lNzWx<< zGB7hEAH?7_joYR?>+&+JIas*%Oiux%kr*X*B=8N8Ulowx0MkRK?pR)K1F_m8>dSe54 z)48k>#|F!OV#yOs7xQNQ@1iun5pl;py{tx+o044?r{W2O{f}3r{#QS#4bf(|f9R3y#6*0YY) z5Ey{M`dj)yHl)B{sdmvti^b0IE5xFx%jJM&5w69;`PGy0vGk2ztSW|5H3~zhXO?mn z+4mo>;Y7=4&gC}HifyMO`#70u3H6;0|| z!l=0lP|zVF`bfxm{%i98943^7y4Iz};Z9F$oY3iUI*FIsYa=o=nS^d`;3?*wDxi&| z=?oqs6uDcd1e_e5z7M5q(+I^PilSRE(T6%z<=U8%sq63V!wELY9Rj%#Y@2Y+TEJ8(f_Kh0ih?l6E6~wDl3~?-5%7>d{ zKs0XHUeORoi5+U#M{kE!Ae%|)^dabh1DsJI9N~LVXp*8$XlOfc6J+Cc?}SM zsc3N~L7hzcpXn2>b(_YN=J*C0N}$f_NINTiV!~L}nA{wn^XfBogd5hu!G?*THg^mF zFJm@9m{X~X3t5{7 z#lWIO++R8;BTByGl7U;fz|JBB^*4R|bLvm18x;DF*U`=kyxbH2nD*RIH5AWfJ4^5o z&Nr;*|NreNKo$fUI5}~n#Xcbjr0T-7MV;wZXA(QPt^`x;=ZK)5^`AFgQM?7ry_(Tm z0|EhWs&cYJW?|uvc3af(tfuyDf$28~R=HOa#}3Edru##Wwm0a$Vnk=_8+eQ; zfyq+GVt0Twr^QS*HtI+&&>_<%-Gq-!{iQr-3LYn-6bqW0VW)>%iat!2IP)Jd+LgnS zgI+jJ-I9HMJ8Z*$2FjwK1T0RpF%U`&x)S{3HqRJ z5^;r?VoA(k7*aP@tzB`O5Y26jv#x54xNH;E`KzzLxC)FEnQ<}IR#w*>9sq|zFzZq< zdM1%ynXvcLfZ{Xm=l(Op?=XGV8`BwRiQ%@@A-GnjD+y3K zN2Pm011b!s`3368%P&MapW-PDulXKfpeyRXNjN`lKKgC%CplwE#GrRw#0FE#Q4>R+ z23B4CmO%uy8Y@;F$hCHU6+oJ}_cKgm|4Amr{$`38ue-?+GX1T!hd$w@x=z{w30Z*W za@$MLl^=f#*oR+8(&a&`E@Bj{{1O;DPjj$g9U7~{m*?^Tj}Rrc^wc=(SycXVT?bW{ zUus*6{74fo{nOh@zQyv0g{)t}Qekl*>KXQYCI9m2jqge|&Ntj{V?gLs*_GkeODYhf zW39Q1L1~vk+#E^S!nCyO&z9Wh}2=K}`9#{=`j&)^}8=U|lz}DqgAteVsos){s zDhK`>&pK%cVuhO7tPu7@Y4|yXAdHs!(uKDuLL@i$Okc6Gs;2456Br??ZNZiONAe!~ zvY5w1(C)E9fRmpWgWU2Su0u6~9{@wIm<-lha;uuEN>&C^FJ#^|oopkg``l#i0&{OX z%rI6Q>l^9J++K19D;HrFU#V9o0M`MBTT#-(q&A{|n-`T~CgAFET=$E_&pIQTPE;J#&nrwf2N^I*d zH)ev~7d=Sy8<@syK<`PFvNtyfa#8^JceG^ua^o%!fl6R&j--jGkz8wS`EgfEZouOD zr97H059Dj(#$*$-!UQLvb92wS40!wJc!4K~lq-K2h2rXunCs?SjQERnvv9Fs?tF;y zWUTcQ&PtDMbsUY6_&np`UGMS0ZZIhnDh~p{`Bryj7XS~*R}%z6 zUO^hJn$_-CW(;$)hHu0ej1BNqv^o%*D2gR6zUvCZyw)ddNB6JE$;okhf7PEEz|dRN z$sP&o`MU(L_I8mDW33;)3!U*;HRm$zVV%%zaDn^*Qj~RdWdFNb;^fRhnF&{oeY-tv zq$p~pZw)Ls$EWKsEZubtx_9bpdCfsjdy*<8_Io8VtCIC+8kk@Qxdti>xnu}nRYJ-y zp8$3YP7u;u+YlPQ2`o_>S?mpXvd0-x!Z3=}>ceWDg*e)+#wQLE)Uwhneo z;*y`VfoY<#lwT^k4BP(ytfI;M`FoYsedi}L{1V|Ho}ciBs=`@vtgnieHdpWz%Vyy$ zlnn?k0KJWOnlJD9>6y64*X=G{lyl&%pV8Uo&>tXw%1za!6*YYVB$jR$Y0XhB#1mVx zvjd8N4X~{Dd&28RVEkCw9TLN9*Ng!?9F88l2Bl)w%7!97mtx5(Qx%1u6h+$OGa4#qGGGI{Pj4d)5yg8F4O2sfu61u0uM}?$_nH8=0St?`ogZ@1LAr@*uC4Z9(|dIQ z?OH<_%?PD56K*Kty@PQT;W#)tazY~|I7-aq)tQ($$#Q?{gEbJwJK3mnk)|l>XgmJQ z_POHzee+4NEWu0i0zUFmLTF(zvD3B%sp1_F7 z<|O7{-oZ2>t9k~zX0MDQ(4&(YZ#~baV{$ah?o_K1p$Ad`PAvgtuhW(xO{@bMjNb>Y z-k>lsDx?xX;x5*9RSpJe~BwLtb79%{p~+JTs5HZ&#({u>j3kAOLx*Y zW{7^+`OD%vhcxVW39F$jZ;I@H`3X?>Wwt@269f1o{V4-t-|dX4x7L3j zUHltoa@jqToWvn&=0CF%6%D0h50m^)qaXkRMC&Owv8iG~$}1PBgld3nBE#Rg(5)8n zga7!2@yjoBBoF_e3M$ongy7N1L_hT@!LUaCXX6QLZFKcq1r;;Z$sca}zfwaCji7PcbfW7H9p`7Eh$-j*7-=%{5f&}TidFWiMr=NYvc}Q@gh_z)<;^d&F zd@za3ugvK(BbprUX|)`Rk0&+6)#sm5S8a7;dzrqn*f)iXpvW$BVu6u)bR+ywtGne@B61Om=Q)yvb`45S}|LKt&5@)wSOfk;LhZ^UofjlQz0h zm)>a9f&40n$;-ndr=xntY3nOFGmA5POfiIsfgTzT*Cl zU{P;It;qo}n}IeEA1&?GRONCJp3=_!ce2$kKRZonNV+tS_uFPWzeS zhqSPws(Jp?TsgNT7yGtphSz=h2-}y#HTWNE#@LHFs^pseT#RfN*P8yLUm`jG1N5s* zfU25qv2akmjD=Q`s4SJxi@i`xIOCdT5B%W6wj1Fz8)Kuv*iB`}b^(em~z zz4~VcUB9M5@W}s3-SOWXu+*?)Al7p)Bw?jh8_#s)>lYp{{b%_vCY00=iC@I3$FcpY zYuOjg948l-C~}cDxL!%j&X1(H6ZC7U5?oVLQ<)zh*qg)k6HdNPB;PQcbVRXucl7>@ zE`Ga=^8RPrIRE!3E#e-v8MTy%%a1yk_k{s|V-=5ML7(Mg#S@LA3;rEyjF&X1w*^R&VJ>2%B@{=W9BD)oa@0!_Gl{G8Oe+Vki1QQWd~<<~Et zEV_YlJ=t8VXv>#L|FKXIJ)GZ1(d6xUoSPZVFOzMhM$6tgyhWq=@}=HzWm&b4o8R}L zQd7<0PV(LqaHYNNcXtTN4rc2ov$)VeRm&}XS-vamGB^G4tspa#HrPa5#22^pb?s&W zS%!p!fba6R+WLMjkeUo!qpKob}#cMpU4(`C+U6R8i>qlJ&Hbh52enW<`FmyjlhwlfIlxyu$Pg z3uS-Qau7K~%A$hBFocIe2<$LBIbEI!uddh9(JX=++R9aM|DO2#5*qKh#Zq^~O40f6 z0#s@~v{DPy=4^A}ieKe(Idu22Ex4~>p=#u?w_Lx>bHE@Z4Dh%iKrDJj2IJ+qNDIxj&WPRXRSaNz$JyFkpFK#gLAB6G;4KKql{+5w z{2yWKln-fjDCc()q_W&mmIx?JvpXPb{)hR&ok40*!M7lC!&?b|=efwVb@r0;FeD2( z*x!h~5OA8DEVr>6PS6o_oYt+7HY+d${lh@ruB?hP=`vq;@uLNGIb%@~*X54+`NY0- z35nZLFQArwtL~;t?sb(T6k;wi@v0FFLV}%b1@;p|R%u%8ROV= zRWO3*fG33>>}We#nQ5Vk3gY2ODY5fL+-E@ zvWG%=(;1n3UEEjqSDn9V_C*FMSXjR{uYKa`>$>D#@FacqRX4qmy{)y4&Gf)@V_BVr zvNEa@r<%e5HW?jhEb!SY6v|~N%22Y0992I>~ud8In`Lf`QStH3E)x@G=`2&AraN&V){PF%a=v)Pu{I zuQ7a;TZAlAgDiVUO+`B+z-8%M0kCiylcazP7I(w|^h*D4Sn6R#-jd7ZMN@iJo=6v2GyL zo;~Df{e7CCta*U4B1pD0lfi=EwI3CTf2}#(`mwSD-u-%XLU(&V?BTG?P-Fx}R5*E5 zcvSdpxqh`s3e`yRJ6%Efp|NYd2}SjJ)h@$9391YRLSU!qq4E=W9yx#}_KqRcG)(~r z!+&i&OckDJQ2El}fI8mdeCHPcJ2=byp-dT&ZFDzLuqc{lvh)^vKB2 zL}g}~j~QUN0Fo{!0BTTKwrDjx#j6KVb>MsCz=!G& z0?uz!q)+3>Q|KAM0zy>+^zjMt4}XE)t2HIfc*Tmi?$;KdI7B#Aw9_O-Zg>98L}4}% zna0Es9syWr5+f5RGVqawtNUt}*r|Zy#6ay+mEGaSGMmMOW%88u6mXzDD_wlGT6!zy zpLOrO442P{0J&IYJjqwrVrEF87ZDTT<9iz5xv)C#pUTTj+d73+z7GI`Ehx*q&zxS(F>^b?4*udLeSbU~XBKKi_PI+| z`R!s3tpv7gX^R3~Cce0vX(P9@UCS)XwG6mNX_eM`6X(`UW>OMp*nTlrcUU?`gCzDr zKR0P?yj9z#ME0=e!>GupM|%&t{Qcx)sN)wVzW*5E>yxt5g6NEc!GR+F(!Nysd6n&^ zN?K|Q@t>y$%H^ z1}}eMB%-GY`CK5%Pj}AkUNRem1zBUE6y}0KA;6;dZu&VyB`KCwPfdQ5Xri>Osl*$@qxi zNUlL!r3OOxC4C`xXPqL4Ec)b`ajpfaw12E4xMZ6=Yyb-WN0LL2RUzLj zAKS$6X%>ekm|3yQ$#-`3N8ah|B+0f4bxDc4nfJcHZ{dlBeXYRL5bY2afSAF|vcc%G!HPxGS8==1)_U|T zNvWWGt}f~OGmCtqW8>q3f@5Go0Rce)p>g@dgop$3UUF3))$Wn6gRX7M3GQ}?tC)i6 z5#2fg?U#)GsvTF-;w zY-Nw9hPGMC9F9(W5F-PUEmiuS(F06nlcE{I)}b=%A7_~A6cEH$BClS~DB|X6Z*IT2 zIpOX|#S?qiLR2Osk#^=DtNG&ym+&FR*Kv8P<@ep!ZLZtJSjcEO2t@V!3dE-*!yhNO z<`xWq;JT2z{)iLD9MQ;&^p<*B%Gv z9;zH_>TGtlGO@9MT_xDkFS4=QaZA)){{?|_B)8Hw-q)H3IPzKPiHM2|2?0GNX^+EI zRf5>q`4yE?GgaPuK8|(quyuVfv-aF(wlXs_w}4}Na=7tnIA2P*pcwxEhcBp%Q-6rI3Rc0j@jnbz>h=|(@M6C7U>fx%lJG+#q2Q4af?@H7>c`6Fw&JpwfW1WFvJ!J#H z%4DH$Nww@r6h6K-1K$M;1QOi8g)GMGRywKGssy2=E7s%k;ESt|W)#O-pRtb)vf8-D zxR2gI3De!E>)xMZTl>m(C!Tx|_c}u7mC!FmY~hT4&*t)mO76L0VQ$Zm)=+l7>+9FH zfQZjFC%h{enbPhuNz~lx(beZsjm#JG@8B$iw_cTSX-?0fRc}lkFJafCcF=wqJsUd8 zMn~$&N!wK2xp3mXuom2=TlzBdg~W^u`*x0IxUuITUpwpCCpIqO47DsRfB}i?8mn+k zO?VOK*oa)bFN6F7oN04eyGiZR6q#;01`nk`g-ro<5USFo8#dEMz{N z)FLtwpl>inBl;{0syyqD<@D`l$#Jfl)EJHXIv_2TJFdCbB1tJq2^~2}iq9XvxA^o{ zn0YLREmF;vJ(gM2^u>gGlpZOM>hd=@e@%v3L4CC$gdajz11>;t>9B37u4gN+c2EaN z7N{PzCO`Ov_B8QVS#5&Tgk_TYRF@xdXvUjab#=&lP?prpL~g4|3*W;OC@JF8+0RZoP6YS5=9t%X5j<@=9s zJZx5j1kEdx-027b#7vEm4TRT9soiaOv=y$Y#MT=^nhP%|fDdU^7Ez#Ft2I{)2fQ7` zW7SkW?%wkBWnL)w_~|{}hkUWMk@uEt@uS1%?(3-dK@CnX)?b$25^pIgnsh^HS!eiB z?gK|C)llrf;ga;b^r9EOF`p3yYRe*y*MIBz1Bd-qR8TlBdJn2ur@`?phF`DfaY8;D zCwmvCvRQoWVlI$tetKk}o?MNTX9H3!Y@C`PXWV>S%$VZ{%|p4jHr#UH_Ryyow;{{;KtygLxrG7(#ca)wTYK z-Y0sN6h;=V$f!GPone8y(zPnL+1N>PyLSs(y=`1y*FQ1lR8e`3s=cW#m$+c=3)Tb3 zN7!8_R~a%Ek8tTvTN6~|O}BoxmiKrt8Mkh0)vSD{hV=%yVvnL*%!|m2!23pSnTfsT zwQ-^GnI8{pLlWXKtGU!5h-Pk2LFIGB{oj=);~!Nlji{=PmP~Mqtb8I%bKzXfV~y`v zhZpp~H7qb%5D%?Sa5$&Vmvl)54qk6v;W{B~UlL4_ z81zf;L5bb3SJPuc^~%Ua_>tB)$VLK>FZvy&b%*eB+g)qdbU(k_R*eJS(gX< zJxL0apH$ji6sKDr)n`3{aNlN^Qwkhtd8DRdnV96&?L&8b5Co{7; zvmmb;3CdwVs8W1GMY~|zn1^&RO1t0hBt(ULtGJTf^IAMxRpD7HU;6{ij?XXdjHv`a zw9!c(a5cYpR_vk~eKYL+k6gM+5023LHvMEY_p}y=4k&Q!!C<*zC^2Ia3C3Ji zL1sbM+*p_j602gKXP|mF$s?~%_vnUv zj52~Vd_MWnLq+!(*+*-Lw~%K)_w>^_onjFhcBsl-1z4eAVzf$ZoD9yB+;Sysedi;%NXg8B1{e-#F_eG|zvUc4YC2OlIpARjmdsP@u05 zr*U3jsq00uHQh{r5KWSeeT?KjD!)FjzCJInzFM??L^jL9NcW`?Lr-^4X;Bzlu&Q?y z02M)ULBT=3$s#1Y9wAzg8-+0n||g$cI`eH$?LAzF9rpS6h3c^3UB*o~o`&^2bx~YDhrzULrno%G+^r zq3*RFmK+#R^m@8?svWLq){v0z;Az zxet5`c$dkiO>9f|6fbU>MAIx-Kjc(r4SckyK$1&9Ug3)mVCA8Y1>GV0bcjayWKU?1 z;d6`Ui1G&YLMmdtb&4SB(ffffFqD_1Okq%F3-y=7Xr$+V_G^RS{QgC zXKOBBq9L5K2Qnz3y##l~^f-q^dVo0JTO6ysmtjFF?tQ4=Mh9FhB)1vUcK2(Quo8ja4+LSJ)Y<8ba zuA}O{%Nltg%FD9=r+$Zri;I)XEgq8j;?A9Ap0;b5j5DIM+@eRt2of>UaXBan>ZY7* zVXIJgT25e+vU`n3vm9;wD-XX>S5Izts;k7?q0ifUbXFZ ztu890yFSO?daUUr!gp4FD4cm`X`a_ImZ)oY+O^`2sgS=Z-sfHvxbI807yFk_pf??D z)@elHpxFmUW>0G7ey-bx)DpdGO}*NS(z-#}PYqNxLg1@YN}fvhUtBLqKc+GUT;OW% zO_B<`R#rcqET`udx*1pLFro0I)_p#G&G^C(J)_;ph87-;WP@^*-yrWnJiD`bUJP4q znYR1%sd_A6GDQ|qpc%2A)KEGs;Y;857S{2jmRaCehP?GUgH%@%HTz-B?uYLBrVgP} zH@h;%V${F6+&AJkBG1T_xqmSr-oU0c++uF-EFD zir8XIv!Ke#t=O)W|8PyRa?ZUc=)2$4uI5;dauysN?Iuy7nk&-rwtj_ zbqWwtQli>QcMkpbLD<<#ef^2AtKAu7XV^+t%ng>C+4%Wb9$F58#E^h`#n9f!Ps zj#E`k*Ev&FK`3R|?l*-YBQmL)w`1e~thLbiWK69X#vg3g_b_#aGcF(hyvqEk72SD; zu~^e}9oE2m94b1C2NhicobMMlg}U1!FA|mJle8de9Xe&=-H(MvA(68kA0+z|@_;-# z&(b*W+h^U$FizY_L_j1L?db`Rywq|kJ8nKA;QjfTaq4P?Nw-t8PTt*s02E}f>sbOX zogFNsq@})oI`S|>iHp=g?5*Ri>{ zfB@dk5v}dqihux<=+%{)tOw&-*p;K#;k0?3?5LDv#-^~Bshk-i29xz)oSMVH0{UfE_@k=$Td6mLADmA5HCS>H;8Elg7$zuRGQ_PzI@ zO7f{m&I)ngat~(Q!A^05yQ_P6@m+rB1*YFo4Y=~o+^59v4+%;&=jKhGbUydp4sH`1 zy;I`gK$wj(W`yp3Yj2)F9^2eqVW8uZJUv^BWHR7|G0X^Vuta6p*nh6WK_UPW?g|4H zCB73}#_XrDiYLG?L;{a;A`xflU$&e61X|e>FFS;FXT~~Nej^;8D;T+(JOGZ)-YCl! zDic2c`~DhIAgQ(OXEkNRICxKJ<<&$(86$}P>l1x?yCEt=imFk`Pe$TW&4$L37fnx4(%*=smL>0uH114m_}1+sdfuU!A0Zqzr@~p)h_Rae)3fnObHlP6C?me#TrO zCzi%;E6iC);zLiV*o22GEXIF{NL2tM-wS{K&aCtKGNF+iOQ+JaXYw|H4%FRB?7R&T z1KbAY2p!11zb8icU0Q6TPkZCL#ztpG;uZYw`xg!FyJfa%ZgI;OhQyI`fsLCle_S+t z4uqjjj%#Gy0#Ipt92R{W{euP*jXIOxh~qaUFM9L1FgE=XM~3_=Bba|6C*-;_c4HdFiehcxh0 z3i5W02=DV{(OsRR{NTp{O}%1D0O?=QOrHWG;?)^(Uyagt?*2oVuw0Pnoh8{=0EzL^H|PjFP(dF&|L7WETT0GcVgY_ zx1oq}^k1#{aimB=*)HzvnsDIHm*|-4-oMfmwO_ThrZR-9o)Q(i2K8OOn)fj<5|I>i zrMN-NYx$b70)BeTtJLb1l@(5>DzdL{44E$Db`c|6v{j8rk`njaT(d`!Q+zvdV+~uc zwOi(`abOznKOr4><!y3?&Pn`#_&3l#Gef?)=p3_f^Ui;vfzaAOR#H0C- zC_m1^677NRcZrEQlhb%^AG}2eIicl$V9+BoV;Y&B{w1=n5~3`>l3tCJ_iei91O5sJ zlfRNrKdWsWxAWWhrxQmbuci*ftO7n7Oc}WO%lj>uVaUiDKPF^(#js~|dl-WEB(b%;R&%wBZo4s*Feg>11~T!zk!KqRO#H>GQupBCvQnt=r+5tC~|_jcwZextGmQ=bxnE*pJAI!;`6FR9y=}o5@Ho683hnm=2#mq1!K9 z;~t#M?%xqQa&ju$A*O`A5Y;)3bM=^-yRtSfb`+m*&?NHD1^&k_^1V`zUUp zBQjO}+aSl}wx4UqTg2FEd)wQlHv^*CRVd!3FhGRo(ku4))jpO12ugP&rZjKiwWfRW zYw>!=HK|cBWxk2w*r^o8&xo`u5~q#7C$1%JvzI7GnjkBxN}y~)MsK5FzthqT)I+i9 zLQUJe#tLyOp$}IIr$A@HkBqga9H3%Ak12)kQ{#!2%+*+9#70XhbyV%2UkvY~D0|mM zOicCza3cpNf8-DDqMQ{MkW2mhk21pBOx#yO@k>+nz1ZeIc+LzQXaBES&Mc^@EREx+ zqiBmVE)B9tyJ8C(1%!qWVxu&JY>L`J5QAF>)IcL^2uZMMRMdci4TdEsixgYJCJ-=e z(Lp2&ix5o$VGm(RSON)Tn;Yzh>4%xBd6>6bx9&ano^!tXf8ROv|DAg`e-7-iRZ8cm z=ml-2W49d)ss}v#)i{V&<{UK+J~DWlkr^ixT(|EP4_lGEv+7l6mX7 z`rnoA>yKLGlLdp#ymRS3uTeX~bc`pDe>eR8u{uRKGM^xch?2hX5Bxxz6(kXw^chB# z#7h9KbJ}H`x6PI{mOk`b>sfNpaaH^>y|DfmqK}?)K;U6OD{UDN0WtzaUnVZ#(spqZ zVUr8UHtKKJjt*vN1d8xgpq!jad2C3(uDSb@6AQqAzw;SdN2f_9m=Y%6(PT^t2e zg=!ibR|V#v11NDo)>*m?5o>hTQnM~G5obZpgu!tGj(YQzF70x0uAV}pwc8nXX9bNO zbd)kXD!8@U4%A|o<87&s*`|`dnky@hr;;ZAo2~Bu2g7qn%3zfDbCVL7wu5 zo6Tn~<`BAK((ct9AG1D;F6BcA^^r>vEU%LrOxsOA%-~5M z#X&|sFPm7+R$g01eYw6pxAtP}a&bw{TPi%16;?Qf0?g2_F$#<3}XnXEmOcm0X z!{Mfdfq*I2fU-a1TZs929@5Rg{4M{z@?9Cko|M^ReIRLnw|jnGRaL}G1ibFOa|A7s z+co|6Dsuoxs)B@lW!!Fy@jnb5RF(!^gPXPin?1IG|04fYi3yRqp(DWls)4f1ZERc>4-}4==@QsXQg#VCX`Pjnxeb({{Mj4zJ&j-1gzqTJ&ZexJiN=qXShYkaMiouM$* zihdgSA>BBh>UG8sz{fP)%#B>6)ZZ=Zve3ylD#}%J_s_FUjp|p?zS5nme$D^s9D%?1 zd2a%1f&hF>jr5)w_Qg&=>>L|+n_ZGJ{}HuB-aWy6I|{a6W`Hnb;cfm6{HJ~AA5ZV+ zO^P4X_D8eT5KMzCi0L0n3XE^`Xqp2~J~>=whP^9u!!3KaNy^5JOLz)Qwu7R8tf2ks zjisRN+T82EvVNsTX1X}xJ+r&E1Ana8Qpn2QD&fVB#c4QXwtxn8H8-fA^k_PfU1K3X z>IqazcZf<=_}R)j8P@aQ7;I*x%o;+#m133p4|1XdRsx)DWgq8qRCq~o16CxrvV~U` z$2#Ub_snsmq87&UH8fBu1S$k8W-@S#nO1mvLoQ#oa#qzo1j5WsbiT7n#x9E6xctup zJJ%*Op$=MhR$JZqbv_dwGf|=jmqw4H=Qe2mw@dI%LXLx+E_G`7=_yvYv(qNF3xrZR3f^9WzweTrZ7WqEQ>&+*-xiy?FBw3-ZWJN4Th}bQmbtp<+ZqlYjQPJ zzNJfa4MuhJC8X&CS?MdFHTA9?=isQw$nkr*(2+Po!G*E?U$K}~)F4_CUzSe8@O3kZ^Er5IyP;Rw( z35J!UL`-m9!A;qPy7nr*dZ@-uSCrN8P)B_V9{n(?zi#F`+gKxs#*j zIH*Icy{ipTSyFy2@?sB~?5qc-cE2IAHt=n!gOV&jwpC}hxH_Kx% ztE2W0xmBmGr@cJg0cyO-?r1X(kr9xzu3+5V>1YzBtuK6Ra+RToix@7>2?<#qlBORE zbPI%~d_ybB0wTJa@)1vVt^ENOxF^N8TUJ5l82Ua|j9w5GM!ns$6;8y2MsryfV`-qN zEznw|%v2>{C)I{qY-dkz`?}Fkw&fQ zBN#PretyOeaJs1{;WawCpt=$SI;XBPp7InnGa1cDG>a+B>Gj%*6DIE9rWl)H8{q`X zVd*sdD=SM1z|Vy6zDVL-OqDUa_)7$Y%8SwTNc$fK$`(EpOnd?|qD%^KF$$pzZLs>; zv5g|58uwUn(Y{xXl&jn#G4$KyOX%KD$tr1&*MWVUnx;mKg3#9O_l|8-Q|n3o{>>eu z!`5^oYumbF>)9rC1!*L0!jnc)RWy#I)ou2c_^7-jK29i+|GW6{gJ3&?o*?PGQU4@` z$7-B=gU6FGBh1l6I?5Y{G*rvYh!1zuM?w70^DH5@`^PXicUM2_WGwV*Cy$rqr&KUs z;}joZDc2XLy+|3^isfRqI4kTS5mliCSf3Z_X+6tS(ggtRztKx~?*aru3zmUEkLmby!sE-ZloZO_Y`t>6Y$Ly1P@lk?ycSK)R&6OFD*7$sq=57)m6D?#^$`jN9!w z$Ftw}yzlq@^{wmjQf8PnYd!0E?%(f@$3O)+@w>P1Z=s-|+?A9NQ9?mM?L$Gi>i)-7 z;FZH#{oBA_R~(hZpP`gM2$z8$uA4oTeTsro7IypWIV$k;%@-1yjwmP?PVhfhrcFuQ zP*C1rN{T#HanoBrM|UIK_dfItqc6S?i^K#wb=ab?`wf!gEn-xkev5WY+aryTcai40c^)|>K>E+ec<8oTH!6Jvz?Pot=)BPAz*Z5>N7QUnkVti;^*btsSu9JUB@m~FS*n@cgXc6=9G3|4JYC@2aKBbRSEYonlO za7Xp=p9IuQxwVwM&PZnCJ#%x~OjH`hZAy4prD3VfDMm6~t%mQtl1`0vY z*HSSM%jBKyrWm|{+j6?LEI}Y3GvqKEDtH)kdJrmQRpWguolR0j=(SSeI_c4Jel05F zE(*$y81yR2r!Hccg3dmurS^Q(HErm&J9Lcb19agHm=hjsYU3Xc8JP81a5~KKILPL7JFyC z^*y&LQk#x%OoY^&&%X9NV8Xxp!e{Yo1&Fv(yp%lKzl_l9%%8x6n5Y`}aGHU!@%d=C z%jwtMQ?X)wPTTQXsI6($fxrBiWKUnp@$!V6r|EpIV72dz`))g5bBFxBNjs7q0h_?| z+eB8$4^{il7xeGQr?`&Hv+-V>O$Tf^Z*KOwdfAV%mO|c1H&BWl2sj+taB>rPpM2Ks zBTjfYnw03!%t6XgR&N&9DCQ*5^#-(%(Jz$S5s>P!v_TB(teM{aHrGek#kJFI=zD-| zcF#h8!oH(eZMS`5FU^Vlw!V6P zQzEMlGS7gS9xjcGDfav+vr-4~BAJaDGUC(`T{j2v{X^#xw?pNF?_27&6{QB-d@81T z-jvQ!gz*74P}1rns(}HmjXUJydQr5B-n6IgyBo%&<#RShWtQss{dV*2*RaN!muBb} zZBwb|QQl@PVS=EU>8^+Z)QZ_ATzx_hx8TNFo3PrwHnftOgs4nG#~VdD!^6)nyJlbO z60GZ^q1Vss__}XBJROZK>0Z}AUiyRIlw@c7XzjF`2{syyG6|e@>Q88&&ncr@ zyL*nFhnc(7S6a{Y@q4H*1@~P-uU$@Y??fFAT^^bIgMnpt^lYt6P)Fa+jKb4p zZ?a(y9I-9h^0XbT>Ehd`CI8bVkHh_97f{nGrvBL(!@$zC_yMt0=!XydN3CR@_mZc# zzSR&{_SqO)=z+GUr^3#2Z|8}7`RJTNUqcfKh?g2YU$bK6U3AHNE#Iz@u-ounY9?{0 z-hv)})tBIH+I?|E1_`mA!fP^WBqy3Y4a;XR(;wR(FXiVP^nw}5Q*d-Ej6L8FeIGK` z%;B=&-IU%>;#5Q2qwWxVl-YB)%VX;np!}q(Hrr5%~#e840K*K^J zXcHTx3)+WF6rWzaCOLOne!#;jc)rSiKz3TfJ8HH{jDli7`g34i??`x8>?ZHGakeMr ztT#S{d9E&*&kEl+Jr9sDc9uJ{rKTST%iDCs3SLZK9zkHq@v^LBWkl&IM4ozkJwiOb zFJ@BFr3c!#LQ)h73OTLoo<_E(o`IQKgW`QBL8B`n1TD=mdM|4BpF!RqRe0{f z!}sj9;oIzeC<8$;nc#j@&rR`xcC?El2&4SX+3Fm*)tPOw4vf0Cqe0)YKCS5&Gt~@r zw0Ch`M8b9}Ac`y5Jh^pQ;}Om0p;gUQhyK-E=%sI<`?H{G4fJCE8Bg0~Yw`eyyzlZ$ z0{*b26E)cV%nm-^VM5cm%T8daTZY4zIv?Z-=4^S0c1e}bT|tl0Q2xF!2)*JqxoqPu zzwg1BW^PPsEACOnTf)3YM2VZz=W7+7O@!6*ZcbkFflHf{n<}Jb=R0k%wKvp8K{95! z$pt;c_|DCr`-q29D}0Jo1$0`sIRo}!YjT$oixKNbi+kz)J?`?l;~g>YNifUW=0DG- zYBrDfcnL$m0;t6Onbp&hY^G8DV;IwC;Q3l8RRB%qZ4@Cjcp0VdUOW2yl8X4`m3NTNM5AZhNpzK~ z&uW>?=+MOHR+1U}-QJq1&EjV(W>ck82ABBmrymA;NF&-Rd0H%aM(Q(##X91M6JK1h zncX~}GIHf%?%Gl(hQdac_|HqCK*lo7_1hODTyeKpJCZ``dDdph+Zf*EjY@iNgKfUEl!h{(dmX0U zNbz!;kR{sBr3x_OwFRwzHcMjq+Qd^|;_NSb_QkcJeIirtLHIsFi9?W?mw5}-ntn@w zp8ke;z?rkP`_|2xrp?dKrxG{l6MPoj=vB_NSmHOjeCA(FV=LXNeov;i7%CAVc28G9 z@mmb6hyFD8B|rL1Rd%Mk%g!+s02W^9s-9O+^623Mj%Ds*tiBicI(O9ew4&MLXpmsU z^r71~MeXK;ldWsM2Wu6V=byFJqzATP#3zt}Dvptv`red+?eANkC&_Tz^}X6lIz4QT z=4|gqkA#pk4_}<`Z8htj)rv+ko*pr928n7rCSsBi*6(HW;cM+m29P2} z!v`B^9BA)Z01N_^hi#`)S9UH|+jgs0bD&Dk5vERZb3*!ZH>T|x0ZVYP*VcijfX(_@ zUGo`;5LO${U%N>I@>!{7n%wXrt*M;e83%!iq%TYl2Q6T%O|_HmG6MnCTs1}_o}a12 zmX_+frrnPAIVWAZxGn5czTuRDpLn{lWgd>$xrCl&94NcW4WeSC4<8m=z>K0w~a56+P1wDksK7nRmdn4Ee zq=bJC5eDh$Rl;@wG!s7z9W8A>EKEHl7uX-2KHbtCX+rmz6ZCCyq+AJ}JL=rJ9XaG> zc0_4LFR^}Nqu(@GPlJ{U<%~RiBSj!!U+O(`X~9)oy?SiFzO8#ni7%Pq)>~AwwRPmE ze_7!j-)1dPzAo*;;{0NBCUkzAQ$uN$Dg)j2qs!sZXqAq8_glj4a-dQO+U3WY9(o@K zpZe4dRjqQ`o(k4zxSoPv&Q{9ykqo5Z$7Yp)1U;p{WA(VZs*`H@nl$cjcABq(>)V z4s?5N_!w`pHsiSp$B%E%>iSm8TTbt6;YQAcua^$WT|6m2^lZuSvvmlU-t|Yju5Ca5Cb>mVJixq34`PMiwUGtt}AZ4}nLGr6Kod{&6Y zL23K+JOusXTZFb&$KkZ^W+s%0(kz*mg_oJfTo7q5DSX1X@*xE5(7!Q*j*vk2PPuCYwgK zvyhqQUV+>`k?(d+J}#z)d*3Qfo3=a9DO}4r_BxH4XV_0)Gl?0IWpq%Yub)OOVcJzs z@5FQn_}c7jruw>Kr>!mumWzMqYjm9{gbh+4*yAQFA z`s72sHv3!!_uuPgnCw$EZFA~3wt-&mR~@(I9$pBYf-i)lQkcnfn=dui!fKp`f=qMf zGFt>Mv~3KG=W#P_DMC)VM_j%4>g6vMd$p@|Mu$n8G62@#JE88MO+eyvu>Dd0q4p}r z*_wDCKkHd0uK2x1i}li`xrDIGkxl>2S{v!n?{=e@WS*C+Df7D1Zgah99)mCAHRME+#PX!(3lN1tyq=wT z4A#BN&r~(!hl?8D-(8q?pbPBoHJJs7`@|k~muzS?`<%BY3SNMFYl-# zSpNE*;$dCwjgys>^i6)kf_KLvz&kOo>VZ$g4^g2h;ERF7FZdOpHo%Xx4-x>mh95zJ z|G&Qk*S3oEGcz-Fb#*srb?`S+5oBUZl{ ztFc@4{$KCIbmON+V<1@XIkP&EV_d%Z0;RhHk5Kd@szVHg4sn+t6ke?YtZ=e*eNt@7uFX{LH`VP z^yuQ?DeNfC5hYr{6eFhO_!#y4>pYskSNdV*DC%HvK6rS&(8|h66ttI=%Cy&vI|72Om90UCr7>1mT5s8(#7L*CZeotBrN>eyyZ1y+y3kbcz4m? z-vfEW9v<~|b#Ecyu9c+N*w~Yk;0f+g-I}NLF)?J~p&BI4_yh!^1j|KeVf%`?#l^Cf zv(LTd?p?oHTwI)S7k&r8o%W^hPxSYbLb=HYu?J!Y7IGNu8gRMHF{b0PPqda(o9krR zfCnMf6Qi!TJs-u~PfeG_a3P`Xb)Ooz&ok_V>L=2FGr426Yed6D4eK>rI!RThXoL4Z zf2^+%$BEOJta5P6g<@7tw5Ju^!y9>3s}{sORA`w4DiS%(2m&pAJtZrv1$}_V7~jip zOlV{Z8)9#aa}htS_B@PZG!k5PB|W?gp&jRqcTImZWJBXR1eZCp-`6w51l2PLP|JP? zM$46ErF!W+LZau+=Gv}Q_oJR`^%63KCl{3lVv+O3mipCrU+{*qhztYzH!4Ls@KlV9 zp08Tsu#;Of1_r<4-;nw|U0ANUrWLkt`PuyYD>oUUo_8iJG~f_f*>(A;6&+44G*3=T zbFcz(rmCcU8N}ho36_>(W3DtVOQVP$Bs#|Z* zzeLHps63DlHS0g@i0LH|%|vN`Za4Nohl=1@0dJZp$=57}*hGUn2NtW5n!(AZ*Vktm zgb#drNEu4r#HCy(|6t@_DQD^g*UbT-8!9iDXT%o1zFtNZxGX%fxzTzQd37vPC2Qk_ zLtZd{996+m**lZV_Ps!9M#nrmp<4kB0ZJL(mKp;pt304=i3{bIYumgICnbo}q3k%= zLnN_OI8Z6hEj$$h`9sW&(#zf|)4A$uDQX)jgtU_L@|SfKiabuqpk*}sBu(z^6IGS& zVGu<$C;=?*AyPZ`c)55`TYzyxjnXG3D*#(2~YjfQBB=%Uc-N3od4ttKbpexVfi(dnjDP% zP)qx|aoO*D;_YcU(mOdDB9Dz$&}67?NX@m<*)uSEN{rrkFB&Lw@4G-`4dPsWuNcfI zBg&^zY{;aN#>#Us4ou&w3Nr6q^XFxvA=R`H4b%#FA1tlnsitVzCpKBH6?-hTqo#US zQmfRH!n0Ebx<;b*87&`E?4wSGru(E;y7_a1h~btRvq^RYgfcZD<`*=R~q$@dq?Wh%Bt%nbs1AI*a|w7 zm4RUOm;mts1-ZOP?fOaDIt19VbY`!y%b%Z7U9MYY0PibYEos;ZqDp-qD5jY%RU%k0 zf0A~;2pBOERR`qNsA0f|6F7vJ;leEZz{33b5<`tt32|_%Q`uU$a6!E)&g$#u&Sqis zjAgY}3tMtkROU4yPgRMY6rtJ|V;SYC56ie}1|EoFyY{CaiW}OyGFQ=o36(tAJ@tw6 ztvs04Ll0~YH<)zWeFiq4Z4e~I?>kj@U+>ZbVPZ^wLel_o!6A8pQE#O`*m*xGm2yt|-dK zogz9zqRwH56>=3Xpz*o*i)8CNc^iH>-a=8&G;LookL4Cin=-g;U{(gya0yHQBN*#V z-+9Djl$3?2p?)jnMYMI&ZTFvgu1Ol6gztlRnVYgu4ydv7d6NiN4Eq)WX+7u-$D5hG zzejcxt`LNOA>B-m&f|^isE63nL>{UhSZ^hY8QNd z%9wY=@rL0}Gm4O^7DVQ;35b6}ESjs#M4n=;_g0~g;S$;%PlI=3#T5TN(1vIx?RG|& ze?9D=$d!>9Kz$#HT;vNmrq7>$K4ItKfesHZloYtZd!?*Cneqz4G95ori}yN13AMYs zw@=c+oYS`n+4=%iskM8R1uwzArwQi34YnZPTKkws->Nji~nkb z-JKxW#*N=)Wo1kCrt}!YlB73}wlQU8L+;+ai|AZCw&yw$6A}pUS40VjfesufM~jO% zJXCarj#^q;E2~VlFdf&a8)YhLd6BDOKe4HUJCHUYvD(XAw|k|Uvh3E)k+~7JUI;{P zbwQ};*;OQkIPt1B?M0N7QYl{P~Z32{(ltt)fva$`&O@I;js25et z^u|d}?fNZ&B|_gU27y1YynqVGMFqIb!0}1ymy(7o9!I`}yT|?LvRaAB@yV_=Xo%l4 zc?lGXp&^M;o&Jqo$9=ST3k1{%9j8m#E;|&?kFc>5r;=f58-FfQ9GaYLD5&n?feBtL zqZQx9J?999Xtt42MeV`4%QxS zvSxn6oF~cKdM|UzA~2LWuf6@t$S}R7#DE7TE~@8b%&SIqlZvq_;??0-{jI3mA9y}I z=r&f0BuGqvrgGJCXGuOdyt*1G`gG9nz;-B{QxrMhhcmV+MZ?;@M`Fm{VbG+f?v6~q zn|1Z3w}^WEF8(a3T?nOX;hQhz#`u9l?S!oJvOxp}ol}Vpn3zN12FD^2R@LN#~aAA#Z%DCzEEK4h?B5E47AWNEtgHd_*&qz=gnKjQADb(QFEGm z=k_MMV*S*9_G1JV*GIwaek=EA`_b5Fq8BLfUVB69jYkY&0#7~Ny2Beu93_J3W-B$N zeR`OMwW!P{pnPjYKU$V>TTNAmijMm<|E2)R3pki=YaH0gq}I-}1f1N+deP}gO##jI zr;x2Gsn8DMs(8O+7&a3z=t_b2I)M>89E!MRKTF4dtw7I%e^Y_L8MHScesK~fXOvdL z`=2Ozb0TD9L-K^B?@HSb5*`W#=Sp!`IlRVIIznnIDh(#t4B%IkuaXtBaMNNuZPnMb z>gxG@b3a8e0FAuo#Ut0rE=Zo?x_hqjEly%-I#sJMF)*P+#$m_aMjrpI_IxdZd-zaW zGc`q9xfmU*O%H4Pguzr9TjZp60LB_Y5@O>;=?#C+5|j%@{;B>rwE^`fWpT_*B#5rR za!?D|4jL=|Re#)ZjA4XA0c+?@7 zrL9%1YoxjaPml%ZLv8RuCq9{T0U2^&Cu3QoB*ty~svl6uS&zTQ^{lWSmUmzUI0I`G zH4RXH$_lev+b9b73#qHj$ZT~Py1gje3k&?oi$@zH`Hd-UTq2oFK&+{qbykpzK|3{Q zB@Ob#(f>ppxZ7+8%_td4ch)l=2>hNm9J8jV&3Mf@_XB6hV@W+xIl8U?E~wpsh}$8n zv9YnNOtCV;7EmmztE&-O1T#B3_8-@^w6zfs-W)|GpTh51otY_I=_rvyH~gVG`u0F< z5TcwEJhbSh5Q2VxE%X^!-=$wG7rrN50kSc`k*4*V2KYBG*~?`NETlx4Ygux6eYqg` zZ1q&@Lt=9A?dxj8(VB*NzL$mj&g>cX{XG!KjjJyc5`ulwSSp|J@`?jgA~CVBShvbj zwHQeqI61YowaxZJ5kEa|d_Fwf&pobc2|I(9Is;!59O8&^{H>A~UK5h8)H~E#bO(%7 z71>&06own{+sY2Et*uq+-D{;K2P(=U3|8D{W;Ie&CeR$DD&e}f)DI{*i;Jd6fydDB z%gKw8zgWun$ukL#+w$k;=Hx&pCRSJS z7UIDkZ9wVOYpidSA>oeuv^__akbqBsk1v9##B&{Cob2qJY(v2ud_Vyj931TJWdLfV z8mzLia%fcD09lwTb%t!V#iwvcqA9n5(vvA=yYON#_RlsZ534sy@DzM`j+{*Rz-0R1 zh@or!v&7~_A{)eyk$}!zc1e*j9Dh(HxYmnS2 zQ?TOqoZ+2SHlA=}foXlWR3%eEZScKDL5yHfaK5hOVmP#L{B%b`chJ+qwbBmc>buNx z5aoj#$vGD3UQxcaCugdTD8y0-6G)(9oV+V>Vq(T`rTEv1l(+=1Nbhl&{ZmF_ z%pZ4@l_tyRMfXl^JQIk1AraetCnEB?X9k#F@@By6NbZfeRO*SSr;(G6pvUn6js2L2 z^_XXkn#*wVj$e^_4L8NQJTu76fiJj8u*7?Eza&)LEAw_IN0vR2%Af*hI`-BQ|-sIu32GbNaWR!8W# z(^e18lCO$alRw7TJbpcCPsf`XR0T_xqnUK0FIFk$$ER@Y44ftz1ZBF6J;!ZUZFwp@ z(J1m+D_5$d%9X#Gt9MzRlGFW3fC!h!5R#C@(EP6}mRH|`b?R-&TlvSRtcdGQ%fJ$- z77Y{wt#4CZm_4n=d~o`o6fe-5t_%@MG$sGvHWgjoZV{Y1uvitC!9`TPX-tCpIJbYN{& zxKz6lvqs8lQ4!_EZDx-XA6ap^ml(rgL;Jc(kdfQOFf#U54)Wom=4)zbeDnzk4RvvL zt}CQXQC{QlHdUIAu^XhvpC!YsqTDz;d*x%k6LNSJt=G{In^tspzRzdJ*H;%VP!+W2 z3SeJ+!Oh4h(-99Pw6L?Yv$n>v$x2K~DJd?tv9iLnag&jiMZNlRWJC>t-JA2^D6_tl z^`)iz>x7ZZQtUYl3$H4(U%_jW---y-;b!>%f=Yd@j~%v=HN?g!>L|8INKQ_EDfE-U zTy#c|0Tm^`un@B_d}FCUlYxPux3?EboLXB&00%-D(@sMZC_hD`^MHm2@FpZ)DN>B0 zy*2O#ILvPW)}*Z`DP{MP+uZ{KUF%tE0P!Qnmil%U1D)yfryl#om;!>Ojprp}Sco^G z(E-hDa0FxNVqY$m#H3NzJGU&Q8A*;7-Z)~!Fdim}3@WwEVjj%=p?7=W%jBB1?xT+d z{%o|EfKjuaB;@TKqC%!dI<+=wU2O8B{yuk>OCIKQlH)+QFad+y&V_2*wkfE|b9Nh( zIsi!=7R}H_Z5O+^I7$Sv22GIho?vb+DH zJP6)BFnqZ)?mN;%hrh7QnpziCncZrC1I~ef=N9u9yERF!25LrxL^Gonyj(03v50h! zf6BQRZ>TD_7`|e=Dz)BfdMD`i@YBr|oxKkrXYyE=ImB6nu=Cc+7##W_O-*@^wcHgl zyh8zrqkyU-qNd>OTIX~KexxXJWvF19VwhyV5iVyloo5Y2`YfM!Xti09UN5ic1$l+Z3$%;>iTx!rb0 zULiG>g|rJ?byj@y33+{3zf&#nGG-MrT*_i!F-RHBhZoo~KrJ$1Fx)-ir~nwgo`;!Q z5#l#@-E`3!h0yS9#HP$_e=X8n7AOD zg^kMw-{3pMo77am+Wy6SH4i&4Ec+>N*E3`X)7JSQh2N(!li3Q8L7+hgnp615{MiP1 zHL#zx)Qz*UvlrqQ^*o>>=-xLOOMNQW@6ri!2U(>p{lEdJYE2fz89qVi=EyTW+zU zR>$w{Baxi7K>9eBVOu2xOPZchP5(Y%8FtSqTu}~p_zH-&_uevjA=h7;PW12BY}Z1$ z3l1wF?C*aG=tNwKU-@U53^uu#$-KwQWqZm**gXO*5mDp!s}S!hm`G^jC}${&26Y&A z_W>GtDdpRtXAuAEh<9nPTS#+Au|aKc?KJhK;k?*@>r38`E5!g7H=s_gf1!Je#&~j3 zOCF!FqT*+-^NAWr$pMFg?LXM~1wm%;ewq~j9)%^Y70p-%n;4^|>?G0#pRMzcn~ujW zgn#Z)O`Pjx?%}kjJez`mz-~P6W*y8iqwE>rd|!PjWMx%oPB!(A-t-S85)L|kufnUN zX#lTU-5mP2`&=??rI#I6tCMcAHTtXptNIP9#dBMiYR3B-s=|gJ0wLS8E^=v2O=1NP z3d3z(Y^z7g3)Cv%Yvm(PE@Xv(hl&6h7+6lKS1oko?0W^--mdWW6H)WHtH zqena(0y+4QqT_Fuhe=z5r={)Lm_;gy(N1O6c-`*q#sT~Rprp}TXfE>^1em^ z@ZuQlS6JF)dAM=;7+>@Ycc9k`C=mi=fXog2_$^WE;;~`&_aKY#(XAu|Xwm?$@w?cH zm$F1GZ3Rg^q{CAqG0?zXJQ-a)X?EYk{`1B2-dbgwZ|ro1btIzv72A5W9xd!w8ZM zfhDYjv{3U57gDQR|Ea2K<~(``s9Q9%^9nyc?F9UmQ?L?UiFu7iBVR^?jZDx%KL67) z7BHU5@JoZrG$|wlNb7nMMg2>m#c34GARf!YKrU1i{VaxHn*O}UZAR0W=nr38(wB(1 z9z1#d2jUWs$ZWu3@Fx5_!(%&UKzzGH^&0WmP&BUoS%X{e>AXL>LZ&&;mVVFSN6!+j z+xz9qt9>gcr^>>@Ze7*wB*PjD`@r&suA0Xok`clMS`CBPy?sne0hH){>kQiOs&4f*+X>FIii<^3Tg z#n#p~9Z?~(v$LC0AmEHIJh1vzj(6FQXOlz(xYptM9uhOZlAr6?`IlCEr28dcIP-LL zoSmITkcp2JX)3FC4AO#tvaFS=pO~14^dtfUZ?3jzDl13*(1|Fu_5WB-Dk_5fNgm*C z`OhSc{f(t^W=9XmC2W3~+p1!B*M$&itpNT@caWw=xSsdwo4!6PyXIAEczzW)gt$p< zG?{G}UT)}b?j0+ROprydSpH=&Pbk$-)-&W@l`SRVWl~f9h%f1Ywq1+;vUp+sl}Ug3 zer@=L6*88L-G$C)SZ5PNA?(>uDW4Sy55SRPauXINCgw z3`mG1^w{^1$_CZqYQ!y-QC!7s^u07KtHO_Ei$S)$ewJTkGKzjtNVH8{`|HW!_|kkP zGM;kBZ61iOfcYBcKOr?s1!ka+X6?9Rk(~5Sqv2M!+~4;Gu{09!42cvM_mIiWdJcom z^cPng;}I7u6i;_qnXMhIWiJY9TUmIpU}L0IDZhR*C`J-)7GBRhR(n-;yWs<=YA9eS6R?za z39lg~N7|b|+lL44!Q4Zf23!wi^!6@35dUJ5KDGfvxPvQn-9+Qa$$UOZ#5&pMy%sR@ z8vz_o@Q_MbaT~7`ag78RA%Z6-KI*9J zdk=3+U5c^=8UKe`GftW@f}3YNvZ-rD7S&s_+VIdQ{P@+*{Efr;^Q9kE($d;@CPI1F z5IYiQE$A!2z6&iS@8G68detTm4m4N}qdG%oYo_(s1s>zaEd2276sQm@1fUc3>FG@+ zp%5_8aoDd6<@@{J04O?7hxl7(h_0&*ru08l*k70f*yrzxrEusY4Frs56ICC;4QHC^LBg3uSO9cY?v)Fk{Rve4!L zIh|cfrhD932NcF)3`VmyM#wcjS$_T%A)Qm*fi4piK zNG%{dRY^vB&qq}ox7X-PXfGaT_BTq3h=O@zLPlyHW;iPKEFtw9g}ec2Z85`x%CuH% zAf+M{GB!YYy{_!t_@<6wH;-;7o`+UkeG539QTjzk_nVy*Zsbx4S8xD?=TQpfRe~PE zzzl0wx`MrYQdS(rfCk4`-^4gk1*g47muU8QIs zbl)W83cI?bw!0NMAzS5@zP71;k+-;YFc(o4^rd`yu`to0Yl%Z%892f4{75|UZgeM- z5q9d+jMxBjilqc(mGD_)mbHpQTt!vk`pVRCte>R9+7=~oH*5(x10G5-+mv-`51ZFy zbqtu@sdJKLO%89%wpLSO4I5ag0Q}R0e34y(;YhJS9&su=B#NQ}&R$!FwfZ`c7~J>+ z*C=l^KhH35S!yU{J<6cwRfbaDeegE1vQB(?TXq_e%VT&k5}EpsyeT}Odqv(#e}WNSLsXX|#4qM^5(OCX zv0;GRx4ym}5)zUT;sp3DRaI3sHZ~b|!+=b)(4((VC@maT&XW1uch<%$h=_r=(pqJ+(64TIjLi_UZ7fNiR_W; z>c*i^oPpsDQ99}sQO8zVF_p3r;=PjUJVH&c3 ztXlM}{=d>lkVy9ckz)RtX2_IcL_DD1Bsczw{lOr8pb13v^D7sEmPg8^B zu+-4tv2m-LI*y{CzP@3S%2lo5;T=xI+Dl7%fwUo){=}==4{E7Lha~3I@Lc`PV7F6lk0Dch*+& zLTjd`-XfCK71T6fA~P5v@ zwe}q)3=_{C|8D*ox=44fnHIz_`t7I(Sp-j)TCQfe%Z!yhoXf$Q%pzBcNqXOcDoVBZ zfwVX(j`Lb)cauBf8`Bb^^`I;m6}hMsrq|pbUbAeC-^kXGO!RcfD>FW6O^Vr6Pt_TL8bS*QSUbok1spKPn97(M zu`f@B3AS`5iDa>)>{qi0zbb3KCl1a-u z`W2{TSOklXmq1zlJ*FNo0<}+Bu?=G|CXauD>a#7X=oMW%Zydm|;bIMpEH~lg<}$N~ zIJ(K+@b=Y-l<94J8hRU#0@*Nj$^H`^eGf!YB@#WOiD%|*6!CvCV*YN4{NI2+9Ygpk zN;3?vR$(2$Awhbdm7+>PzrT=s?3)zTiIzJB*IeiB ze1%82N*XPlz0-g!_pAL{cG-%Gia`(VpRwo~fz)EnikyxsA zfiE#JTHH&z>;n%vj+nw=>s)sb6B8cTz^?fCsPSavW@_r_w9n}Hd*nVRKZj>XX=$o? zdU-dqs79Rn7f@8F$#$x9)|Nv}&=YjgE21}yIuB(p{Exzf_k;k z@|I*~`Sei{ovr|#!+zqSYAj%HWj*tCCQW4eSsW5ep2sepN89 zc8}AB`%lfQ>t%j^X0sQ<67;*}&_UEJ4pquW@K$8wp&|Jbn*XwjvQ=u@fIxMX0T3=Q zwgAG>8k3rv$Y^%RdudRn_r#PgB7eXW92q%j?*f^<(;uE?pfNQb#plPIS8(n7muwf~ zendM75555+qcUQ{i%>S8aiV5Ao~g=A;qWiY>Jd6ftV?&k*J}Tg-z_rq7?7zdg^Pk+ zs4(vfN~u_vXv};##Y{{TPQbEf`p5`25(ffo3M)7n1#I31$r=c3RmmQZ(SDyk{o$d~ zE zP~2h+p&5sT(E2>ry&!a>$>>*!(IN$rQTDZIeyxP8SZysRVW(Iab} zWu98km0)kVV2Txmyb1|rpl!vdTJ6TaW?3RtxicccWo~{gB^Z<$cqWVpfnW2W4emEW z(B;&;w(r1>5|^BgND2qcJs(%`AK?5+{+~Nfr3Gu&@nM(!4KL|W@AScWH;PI)@5WK1#JpZVwXm|XGO!w}s#Fnb+wUDa8fC;f$y3QckY`UL7=2`i?%yvE*DGCSWCqz=|Hr_5R5yxxG)E9x0Ig zF$Bn#KVz|_g@8-;r+=3Y_;*1F--_39QAW0x7J&!rC7|lSY!(qx4WyW@^3$aId#e3^ z&!qdEevXj!H->BEj?Nkm4nP0|LzI8P*~sZpjIC3PoD$^vSO}o4%kD0Y1i9Eu#5=MZ zV)IevQmWUK0=Wh3^;4=N?9$uGQ8B~ZK-ge^-$@SGRnr_FA5~RV$f&1zxLPvtD7Nc9 zGF!k!r3epuwK(2oYGkETOXtzS;mY>re+*v>Lg3oD(3xN)1S9AOkl99p%J25PDANqv zF#oTZdhLsRBF$gh-vS)?|A2*}kdQZ_^cg^QY-L~zqk9xC5FtCoV9AUvd$GdupbAjr zDA(_=W=sLQ>Nx)->DIRQER58zWRQLa2o(rW9rPj>`f%3& z3~7zmB?z9(D{!SU^B^8Z8cVbeG^4{AJalq{RXl@w0yA6T83JsCqqnmQBdBeUAaoCUQCy4(yz%qwVj~CIj|`+;wBz z2&LRXuaWDz!XMKH>_r6j3MR-88QK@jYw->mfidcCdNhMF&oXcvC7f9aGJcqrGXH%5 z?mg6j9Ndh_;wwBu5{oV+fLMr57l?r<_+tf(I>rt0i2KQtV!wU+_DE@ee}72{qw8=Ge2VrekHh((m8dC;yac0QM;ZTR;%GrGWi}$&nE;n6Zho9I#i~$S4!x zsvvi=Sn<~Z0>Xd2Veda>?q*see=&DJx`Wr9pB@=X?VIVdRi=k?Mu;tYlmaLHVSEQ; zHKJs8$XykPsqkCU{!3@5NTCkjDuIOvrj~VmFNta49ZpFDwd1X*vJdLUDorE`Tb7#E z(h)gGsMd7BMSVAQ?Pzm-l?UC+EH05gMv)+g!?lv0-o}O4$$;)_zz#tJ6NJneO;#|k zcV|I|Vw5k9DheyOY33$9Mh_`_20)v=C3&+19$1cH^-^67btEHpCk9sJ-lXw_$W%O3XhRC$M_ZTzqZTW1rMQrh;#tCrYJsL`$&n$ zV4xJnZ7Q*9ES8HLx@R$8Wikv7DY?15J5Q3iSH+tqInTZtJxF(@Hj)Vf_SH$wzPQkY zM_dg*Fh*Yy2&9J(r@+O%%eHY z{fdsKWLh=Vfau|*|J=&_@HZh0A!rggMZJi1)D#fHxR<{&l99~e@sAxG$|s7wMSWi| z9tkE~EN9v75A&HX>u6%YcL(y_KQ@JhI03PIKF~5#=u9;Mdjb&2 zi+Mx%rZ4$^ZUMO@uKuwxgo8W0o;-TlSj@aXgMlE)8II+=K4)&q%8tUqjR+KA=I5W9 zoP34=2Vjq{H-B;zJPl~NXbfnLh%9|aPtW^(?vMCCT;2vigC~KJ7yJ+G-D9s~ zHhJvs>WP?|3OInj0&IYB>cw6c5LEa5nqr}8Wb>!asOlgcr%h2)cJ3`M$J}5NfeJ!4 z!v7|;#uMad=D5uRtAbso<_Ni)t^R&<7%=$2rJF&L^7A#@#+%ALHXB)iF0SDJly{zC zO{H7kcg9g%ac%cTYalgN&8m;+>7;sRAQzKcsL! z9pdSp-)^vD46y^}ZSo8jw7~|G+H&sxaLztL2KDbbZ0?mi)ClgWC9UwIH- z17CgkS`JW8#g)EVwxU^5+l4f*{DI-wYZ4s7KrOL2cH>;^Xnc(=#Kr}~2eBT{{rL|d z+T{I0lC7_u7L1*@nrq^;#*J{QMywSe;GdeohQ!z2&9Usb4zV2je%+=8FuN-Wo4osyaw zOG%I|3KuP~O(nBoAZKvJ6A99jOgB+t0cj4+Lo|*^>p>a>K0)hdeQ;2Wa;}St#?YC# zjqH^IvcbLR39D`;M=8&11eM|>vtMMy>F8U)yuzWf&YxuZ`#?v2-hm>X!;}?Q@tB8` z!fOmsT#}Re+TGXCMhEnH$C*(=;_j?TzK#I@Ha!F&iI-)cfvO?E8!?-H!PX~Qs5H>v`6bfxFdo14N~kp_>vNA47z9PSn7%X5y^mcq};(@5$Yu`t-EWoV}Nke?`&98vC<*d=66R>Ot`8# z&|CP-8zazRrzcgs{y+q9pK1zgX=wp%_ij|<3-f&wm;7*oWDp6(W09gQ^?%W3)zQ`@ zzb#zM(6}c2hLvGwM~6Y$Vc`5p7&xHw=!*Y~s(2_abuNrPxCD|&3ZLl?0n1h_W93W6 zFEtnb*4Fnm5r3wf;R3RsCNFa5`GaNrx3MNj=_*sq%2s7biEbNm29*0`N+J z?>wQ`W|IhmA&~T7V>k%FP@5# zIm6X<<~=8J)gLm7G<$|s_klLm>pVM&mt!%X>V{ z8OkVf2)fqC1ux?`7>>0(P8yDl9eONSW-J802x>U_D7SKUVN8OdWk4J=8-pFp!QLzd zQ%7n6R@!8d(e^m}AW)q8#|XNO65@Hx-2Y3)5!FR3g(cfI~Sf_55# z2s+Q)#^7fO;5k~N$-(_(>659=$+0#FiLsZUhdqwx`I<~ zHJ^Q!4_~#&g-4JXVg8$PBEVpu$lIAT^{I`@OmXtS5TUWE%kBwo!4fhe^S4{{(awhkNpg=`Jfxt7In5W3@)d7Pu!C9DL?p53ulWm`KA<$hwy zq|f8_?1?44Zy54Vm(HE2uSTB_I+peknNFArf~kp+JZ9*00w|{PTT3>oo<;tUdKP;E zy3bp;%Lhlg%MoWZ%*s8ohb!q*bw_O%fZ<+mo_x_QS2Ig97-(r{b~x1dX;w(Ahb3P@ zhB;Alm@+MXF1aLp@Qm?jd?)fPdg$v)W)C_WnY`pBO^y}|gCZsZQvLGB&i0}7jVtQ4 zJF#^&B;?E?-DxY9y?KP`1a+kHKbQ(h?p5%cI-ETT&0w^qwUaaj4qjZ2f1|$t&3}D0 z=~Qp!^=;k*bN=5r0H|vh{?%{)sc*Hc?H`6{zFYe$%gej})i-mCY?U-p=O-g_;x;c1 z`5Tfk0{;XE5c;eAZ%apj{E;*OJV&qN{r!zUqns`1R*`?yMtRU__9FUccfm@=5%t>o z?GxnE^u3F+rkLTd{Cg(8CbL<;l{g`}i)|vBn-57K zgG0xIe}6tAb`OVR+#5H$A-{lbmRKc1&N^fc4GkH!=M5*buiqLGE^I;Tj{?kcbTdyxjot~Y4)i{T@hjy<+1ZtZ6PrYMk#S__K>z!*sk7$GKuvkx z?Djz=T;wW-XPZA})EM)jR{O|pP}9628^AQ~KT|3*P(rZ--w8P$(%*a3&ZNbbSHVA= zSSGuu62hoS|SV#5o~d8Ie%3Kn`pAEv$wGmycK$6 ze2tBqH2Gep-~V1)3x<$uYp13^YwHA1TXQJD*?-6^4+O%+rmG?xOed7*-k1l0A%y=; zo+&mm`J)$+vXlK+AJ>@J-q3;xcxli~dtfOboSmlY92GpecZHh?CF9sl(lAfhRNWWM zS%{$~_s|hk3?4am*~o(9T@QU=P`KarDm_!i*_LDL%FD<{HfKPzgzMUSJ74=1`@zxV z$zvx=tug__=U0JRc+R9+5pkQ|S1`rD&hp@UF6ZZePd%IOY?4w>Go}>l*@NnwtOf?l zNfmKVC=2@BGUqJ4=s;c|>1}a3!>md^EtYnIogbdvoH@It#ZV)P(E0qw*=GJP)G$AF zNo#UDhNK1p>`?3tho8JH$#>;i7FThZyp{;Wn8=TSgW-^4?RQ#+;u0n4ORbwuGN?V& zW*`w|wo(VHzF8mtAtkMN&W-w^n(tU5k-g#!ov#Xj2@Cn>({ds{Y)Z@PWUO1W*0RWrMHS< znBh&n?wo%r=RcECC0y5m1D&HcJ|^j#>#_g;G++H4`2p&|1&=PJPlJSdw(L1z3E~^1 zeF2=%`h77B`~ZyTCXt=x*T*ByS<{=XHUM5n7UgQL)Z)5`>Yjm-b_L13+3FNOZ{DL` zN~Q*m$Ayp(+}AlOWUh8LBO~K{aslYufSv+iH+}-SC^;|1)(1xG0n+WW|Ji(Gz9$%e zKS#nT0^CdknSN%p)XG8T=afjZ8w<3PWlG=~KQOWyC_OpwKK>PIY5DNrYbq-WF88}D z=%5>{>1wlm&Gt2LAjGU0B^}<~|2DW|_Mct+|NU>}{s0=fkxOzeVt898QykPk8WzyC zN)(a`?^2$3WL45|84$tLP3Fx&)eG4o=bgqD%<~KP!{u4iFP#)~J`LgE7=y)&f*=9#d);a7Q8)-D$BoJ^VS zw)A8ajO299nwOo#LNTv>@nxfy+|-&&Y|Juq+c=H=RaWNdxL^ExT-==3J-$u%NR<0|q1J2|-=;+~ zZvV89e1rUh!wxsG3>03jkj!n}M;a9p+h!V#*OkUI-{2e1C3qKF))`H`pwXSmRZI8m zN!63M$~>)KK?NJ27VWY*W zQ)DezvXGXox+lf_XG3Y=;j-Q;AX9Fpc3lBjt^GyOe9CK!=1*F6+I%S)mnNLzBgdiW z5wRFv3J(0jCurDdnG4<#Se5veK#DPYDG#lEbGMmv-sbX81BaIQ6tv<-UF~T@P{n4x zdqIkQA zOodNJUK(13$SPhA9L3h7bd3rL{ z1}>QfUr6?f$HV>3vIIu>u_zfUYk3sixQ{=dyjyP)*-<>Rl-WpN;Dk@-#=pbd%1u;3 zI}77;buE^c4VC9g#%G%EG`Ky6xkT|SFxAOSJyz1}vVNK+j@;#k@1UGcsw;Np7(&b#e*M}=eAT-#<-voHLR(k94qFB!M`88NHLy&+9NzwOjvB}Dc^j3w*(SZ! z$>r%KIZ-I3PZ}Bm!Q#}d$##p4_|J~8xGT$(l(aiTeGJQ`=l@vfn_jb#F&cHx#281d zTV%aw&vzZvj?=#Pz9;X6=dy%dptg@S3bVx_!D5ioU43vZt5prXDPW-JTi^nY1 zduhn)cB})E7hrmc9eMY`%JodPjoov$CC*+P+7*}y&>@`DE7s{&`FQyYe25|qj*sh9 z`FJE?gKs#H-I-fS?fs&SLeXwLh5ls;$cD%L*3U**Whf>~YD1+`W=9V*;xM(IzwO*e z5MUNS69f8NQ{#1e#Q3Xh6%5qWu9#MPj#Ad)f=maFvUlyYhEMJz?Iq`e5U>r05PT={ zY;$ziZ&6YieT26!PTJ8DTg}E9DJf`ZDi)aZ|ImzJ-&8H8OCe&{N{F(&_|`l68AV9K z`~xF-A~F}$=&>=4Ma;DphRLhaC{9z&_a8s{jIhivFePR;dFWJ_8IM9Zz|%DwRQ82> zCe+sOMnYGIms+(lz9Zl|Sa;r}br;K=ZJ0JD-|iR3+2yX$xlGI`GTSN8mrKM~RL|3X zG_wFXTFzjlE>t6VXMfQK`6U;3x__y~qE~{gTXQ!hR#rM?njmwN_Z2jIP4C2BjheDf zalH&D&klP1KAXgJF~~+CJg&m&o}=_;*qPijdrEQ7hcGCywgBAV$TK6Sw>h7P=gNk% z#D$2sT8pYK`jcq*lw`tuvb?1HFJMKX*X<@bK2UUBR@ee3AC=bTM_FA2tCz0^D~h8n zsy7B*rI`Q5Y|MjxWxFU%rvEqlmp#5&#T3nOLuCGlU_i;MYLE!O`|@%;cLx>55t=*F z+@g(5+4YKAzx8%8V?-)@s_?{a?dL(3TLtE+C1+^cG50=E0P$`2?F%HXIh1-29v^_q zj9;xJ(r~x;A_M8}__gSs*rOSlQn#wL2)l6EuZJJqaCQs}m^$LnQyPn6@6YLprz!j< za9!FrVMslV2|VmfHJ*7mA}bAvQj!Ffw$~> z+aXTVb@q9_-aO<6ux|$DeWb~l;!U;xqWp%Qmg{M48sE^Bb!>@J1j0( znVzA#l=qu0x16mf!IOJL2%$BYL0u9h^BQ-RcTXNbY{Pokw}^jmrd{%i+D;ioXf6as zeF*`8h>S;x7i0qNZ0&Y*sA!Z2-$70HnrdRKelU?9)CqTQaP-o)kaPj?`n$1??|{_* zOkn+g^jmK&{duW1DX6-u<$$m5@lp(vzdVKw=p6S*o}D;aAgjr-;;Zedm*W?oavRyS zkxd4}w%V0#mO$C&k|hZk>BpO`iZ^Preg+8VGqsXjpc#<!dv!hWLF=PxZdsvP zxxdjp(oJ3Btv>~>HJNW8_X1;AW_8enh_2;GL)Qg_}dl$aoik?y6oCZzkgwBS*tGN zWq+e*&En@~`5T(W>VhE4hw~R=61r!`UueU#prxGCMG;es6dM89yOkjb&yJZH7VozX zVLHwAe~4XeGZPTi^}Wh17IOhOGCjMjKw)u&4C%B{QR?7qyNcjq6a!|;a;*%xrrnoE z1R+Y;N?E#XR^d2E!kOh_OiW#%WJ2jY=zV-3Pk?Y)SxRfFw#Qd8OgD#7X&simU$O}k ztavikwkFOkJb}D(UL+LR{l9Tfa<9Xskn%CEpK<|yb z%cMqs@~)iOIKvItCbOF!ze=7RLYtlAbcCqF6C_>QTRWvKC+4o)xaId{{bn_ZG!=^P zQXiZ4>vslir3*HSg}h)<98;`<#-iudnoVrEV}&l}KBd$H)By4W%;gCtY2xILTO{(G z9V!@4%}`SUgPL-~&e%&+$%f&=yG0(qIrl{3NbXKur)g?Kp-3=zf>Z9a=H_d(DS zW{09il11yfqvVbxD5jM)p55zRGO=cs@-E$WRZAkyq?Qj)jt)IJ23P}UGJhzH4yw0n zFTkb~RtJjie>}l_V9)#iXa|Ts%no$j^;Rcysx-s_n7VHaF)|0PPY_l2Cx4I&vp#G{p!F-iaeM|p}i^0f+VJ;eAR^MA{7~hUf+n)w> zh%sR>=|pTNdh`MV6sAw#d=>!&pErXCTY{uBricm=D+SU5939lkdQBS;liLVrnqB$~ zzKbZf-|0#iTIkJ|ml#9Ku;9lgs3Jh!{H34?MzMCMmKb@AaslO7un~1lx=N72_QfSF-e(t>6VS4+W?n1q(M(FE1yW)@S&9g@Z(#V-pv60ZT`MAxOH1}X9w(ma~ltK zkz#Rj)1Mh_edt51gJ#ui4Qe}LO7xfO^nbb8e|5bktt7}8veHbS7PmFrPDwMYzg#oD z{Lwx7k}B9bM2~mY!bil`bjC!SAJR1_Dk+ZHH)|V*jx}sXbcqXgjzbeuA6Y9<>z#z+ z7MqccdbWm3uQA?w{w!jxr?2)TC@k+@Q$y0t3O?O=FdV#OyJ8_AAnBj9XV8gf_yQd@ z%R_=3DvPA=X_y+F`_&ig=$vy}g}w=g!@oUhZ<;9NF6$rY)g8RbvX5A=)2Uuc{bJ)| z3R4)pNbC2EX-CC2v$4V$QHj`DHBOdY4wP0&XB&K^m@Lrevl@k5ZUhYnzRMnI_(uU_ z@tD_)%qc|;D#R?BLMOi&*m64}_$~f?P?)!mPk2_=r-6aW%F3{tgnpmdy~IoCj9N^lB3VLA*FFw0(l*lnVV+3&PuyJ2b3Y6J5D3U-^fXYjp#seSEaJ3C4sJw-vVrNw4Te&sQ3yZO^Uu;)9 zAkoki_0WebPq)Mm zw+dv!g$ix$!6Ns)bY*BcT7ZM_{lF+b{i`78Eb8@*2I$7x&9J_L``(FQCsZ~pt=&-8 zG3lSxqc|&->?wL5IhbRcDU0iflJtJaQj!lH%($2=@U{waSqxXb4(*mqoC)0Kv$IT_ zH42b{pfk^m2oIPrpCCrr%~aU;QZ;NEUyZo=Q;d*}OY7w|xnBguX2i_6SF^j4cVcUC zv0Jt5!Qceh(W-p@r{;o=&uqS_n}>nW4lJtR_ALgm8xVgJ41(Ks+NeR zFZ%UML6MR>1F+!~eh~zeOWoDxRGOcFEhzbap?;!mA_I)N(-f*5Wa#spDGU z3Fh>CdOyuNEHay*mGr@ibE_<_HH|RnnIE%xeQVGbp`_E%d85PA&_le>1J6Q4qFrlO z!Jy`liFaRU{Z2CxW_RXVTxvObOq4^VXYFw!B#RgsBjQ~TIFn&jR?QX;zqz@Wl1F1YlWBeEWsWBJj=nNkCOvK(k4cYPWYD_ot+aYV;7X+7 zI7P6x_gGy+_g3`nI=j7Lw=`%1U8VKSmuoph_9!QjQ8bFKc-wOX<~lSTM5Q+9W4wZ7mwpdC{~$5n#h%3)AK*U6)o} zdv&9DlP<~!DQE7Cq`u!{4>sRzV+;O50eO70dc@yf?>A4@&M&v|J)0Wz{s=8dMZ5Sli6wZCTqbg1 z?BgTW7>b_5IMlM(w#gCOTmjKko*bhE9Ko4htrr(dK@$AH!&{6=he+0th5;bg-KOZ98*t1i7d(5%nP=ag3FOAMZl+T8U$4nc->{a?L;C>flNRi zplitg`cJtJq_-!%{+56LU%uB5P9$3L+j40a9^aH9M%4`By43^kv@=3>r~GEIdz;(n zz;r8t0AeUIenpCf&ek_ zno^0AIi3)fg&{*e~y@EJqFwi!ipU__DEJ#qQ-16{S z|DA|a*G?q5O0iV7i(~(D6kl4E{cEYy_BBE@==cV8lj#gjFUXbf@>n=b zEJMbnZqy}v!6f+6%(8<2Y$UwDAFi~=Q&>wt8FfXri$1iOoABPdws zqp4Fuq@c@$;J8b5){re~y#^Ji-qxefjCD`a#-j2dMgkCus)7Z(^5Cq6TAati zYguGLr0DXY_ihR{LPF?m(?y&>3v5>+k&z4QeFnt0fC_ghUBafT%Md?QuNKo zai}G~GY-WHamRcpCBiEB4Trm4q!Nr~*^ zn{_>80{RM3`+JWeo5c%fb2krHP5;I@y)#h8>^)rSvV5H%^C7XhAmhoBj5M!dO?hl$ zBhL6Wfz5breR5*QV5vhDWmnw!$bGnYcIl3ZV_e{T-vLP3{=%$yj=& z!hNZ)8~fzwbtamRjIC`6b?s-EeiS)RguQhYmDf~jz_070-W;*v0~f)4uGx0kp^UC( zaV1p7ZL9Avn-3J>yfU*yk<412vaUdwZ9eQmInrKOwXeEw=uU<1nQMO#CX6;7sFxUt z)8iQE_Z#0y9AJzaDR?kku5*h$-zv*Ogs2TwOZ{9C6Ukjz7SmxEw^}zuoBQPlZl9PuT?ut@#>I4jtKjOCkMqHdziOPd>sSE(3jidh}P9 z&>ODr9aGYG!0lOlqs;yTgX-HLYii(20Dr>&;*%fYezh literal 0 HcmV?d00001 diff --git a/docs/images/mqc_fastqc_quality.png b/docs/images/mqc_fastqc_quality.png new file mode 100755 index 0000000000000000000000000000000000000000..a4b89bf56ab2ba88cab87841916eb680a816deae GIT binary patch literal 55769 zcmeFZRal$t)-Fn+z*nS{Vx>rm6qiDAOL2F1cMtAuDNvx0;#Q!zyE_zjcbDMqmSlzR zn{)pEI@tSUUwdu2)&Y>bJb7fuJ?=5a1EER^lGqq;F_4guu%)HMRFIHRN0E?_z5hZ+ zJaJ}X&O!Wm=At4gf>b&}x`%l4+)`Lx7zwEYjQMDcig^FRNlM!V3F)=#)7P^V3xFpQ z(!7JTn6R3s!6EcTteK|QPPjx@DDOv5T2*CXB}Z%z@|SP-DsObzPh`FaVcdV&m0)j; zcZ>LN@}*RhsyUw6to^1IV&KrBgSL*D84<+V=b92tLUGmkCzrla{Dr!*h^X~IGAQjM zyD9lfz=>mTe@ql{QdCq_QdAt=(BA&2YBUsY=dfzD{{p(Xxaz)h;YCF8?Ul%1e}5}@ zO@0yZuh)nND%kn8|Na%lH#NLM=KqYOnC|MbCw}whr}=*yP7H-Y`-r9qwQ2rq9Dz|0 zBdN65Kl4A$DgS>m=QkV7|7=EzGh^Yu&HaDh$NCi3wnS$c$@$FVUp#HFss7?l0LJ~{ z!`SL7tNPPP=8^Kq8)3(i@(qbit!IaRj$Duu3h(VXaI4Sdu3~_@H&ak|A1shtFJP;$ z&Ff|ziaT$FS{aiU@Te#m;Cp!+I*IbJ@XxAqIeeeH<$>FQ&-YdyTH@a_&X?%>7*prF zp2!e%;=M(CLssc(k6U1h(+Z6N7fk4b1$pU zx+k}@k}uu*?&UWT+g}Y#gV?3_XQkIe!hs%Suq9Q))|Tlh`Wr-J#)v6)bNt9IQZ-?zd%Hw*=ZrCzD^f-D3r^0KBi$+ip$`A6Mk<3rtrZFNxAf zKk90T99Gb#t7ndaGJ(*jcpaOR-2zFV|0MH`0H4>cX|8kH-A>yB@PzO5QPgAAeG<9~ z(7IdVikhJ^RFhx&6*~Cd*30U>;FKs>ES%nYuI$%8RM=1({ChUX}X7!Wu zAA=&In$O5ezi+pM8LtJ8`oW`oa28+E!&*f>9{W97;k4XXkIS^H4+UAGvZx7D{UOIK zH$}ZEkpj2NC%)GxA>My-R{)`xdTyO1fcg{J)!T^@lJhkw=vrQzj&$^Qa(I7Cu2xl- zg5af(2k=sEQGeBmBNF1c9B_MFCIG7eR|`T^)>Jws({-d$>S9rNoIs$o1qKW1U(s7gPai5(qrX(&Um zwy;AI@AZ}{%d9#&PBP>zwc8=%jgWWGH2jQp`DWYPw4k^T`^Nvelzg_m4tOygvshAx zSic)*_56B2$iwR{sdtKA-$NW8Cffewvz4#abf1JwCg*y2X*Lu~6edkmydt&um&!Yh;0Fgz!I z8S zXW#cIlDgIR7Kgd*mV>IL1+VdR*KujmVe6Bnrwi2`nyj5h(N`umHB#h26X zt}BBFa)TAfq5C^R?mPC5nk4!GljuO$+PG#|*B4a_2>^!?m-qb{I`I10^!40&Ah?Xo z5pt;rAZdrM_}>Q86li@(J8)D#f?(9Br`@U}FA1>Jx%%}~}bmH|q8K|Y!jaNAu?dYM~6 zRZJc^eBV;Y!Mnx?kn&2<<#2q|Pp)+P>ZBPmqA2KkX?Et2s&9LqBzZimIWVsmGYatA zRXt~RY=fjB;A5x~rSrZ2e#S!_7>vCGqC{9lj*|V8LTb}g!H@mpp{+Rn_v>x&(6H+J z7}nKf@B4Ld%Z-a7|M0=og<;D>XSx@Y&lV$4Ekin}o2SXK^<>^M{r+%K-I&?XE$nJSn(xJK4qrH|bnqfPU>4jm=e=x!oc#?Jke&g(g- zUucQtw<$SVY?d~P}!t-c2Lo8mx6d`@70 zvP5TBSUX%%C7-WOwciMN4WbKqP5B%ow3f{Z-jx6kgNKYV|^tpbL^<*qZ-A^30n?FBY*Hn_q~jp%0Mg-<>UCF!!;rL{!Y{b z*3Cv>f1?;licgf`G`bG-zLl-3R|wc#Q538g0z$S#C86oCbHSjNy?ANChiOIVH2rMI zG5nGlT3Axtm$CYA3AoOV^jpuMy|ROZ?T(T^1UI_*!$t2I@DM>^@!2%tQ*2Px;zGGh z02fo5-BK-N3cz|cST76mXYkO_egPK}#MwY7cUixalk{5k7n=LGIBj3hTJKhyeXzl~ zGo3fkBcT7$3Q6oSx65M@pbZ+YC;(b=HY>1%!!mZp6Fqznq0rpI#0pXZU|dVnIlk9-%u>~`h}VhYjz zmPod{6t5ndj-zKD=!WOo(!>9dq!*2ld8_8dca!LG1x9m|yPCUXkoxbbV)V`B^QlP* z2QLUMxOI2m3%(x6c>7K);Oa-%C(!K#N~N9Ef%3qRq9J)~x4KpV>itdW?%7A43LDIa z8X^^jrZk!ojDyDSMXww70zLApJntoe%=xcBD#D>RDy64nfaU_M6Z)d7V4v3O7+UfM zI23&xL2-PqOi$oj<6nQBorePGYWBHH+x}3PF;m>1({p~`Te}(*tYP8JcKw|ZaIa3W z5|KeaW+a1}*~V9jOh9(L$~YKYYcNd}*`l$FOU6yA(HR-(cSZ&9*~&v1R}oErionDF zkmE|SIb~(H=VJ$DZ4b&-CQ)fO@a_a4)*zSnmv493+6k&S(%z0p_QJ>psX^O_V9lhrb>BAr9 z#!w93wGILaXkvaRP39@H;n)|GB8ih{1e-l>kB{FBn1qGHL%+#NzbvY3$Xf&5Ir5z2 zPG9!I*3-qPiSN%$8O#PHBV)1VD}P1)O~7Dhj2?72@pBcduzphsN8H)`k=p3Wh%;_$ zOeXLMp7o@Qaw@rwstN}`?{)X08s5C`DQlRw*eDrX7{@P}7d8#NUz6uvKJSkcQF?Ne z6pViyWiT|=e=Doa?LjcWpUG)555Bnx)chgcgWJ97&2EQZf!xal z)p2nI02nbGF^RF>u>$hlk&33=WQ-^JoI>Si0u8 zV07Zbz#>r^qAXD{lBu!00RKml^p=Cv64=~UMF`M+kogAK za9tvbFb_5Czmu~*!Wcf7X4}nlOhFn>z@2UYs5e8zXiDYQ=Ox))S3>&zy2o(u2h5!JvYvSsLq$lAJ%%c;J%Lb@e5mEkCW z?eZ|Dux0i&Si?wGLD+e^#G`KKbCx{u6gsr?6jUM?pE*3wAGiPuHc1MIvY4|WVosn|)%172v_ zuJ9qyLTdW=-$|n#8!G@V$$7Z3oifYzxs!m`vv;S}RV*&e|L#YrvkJalcR(jP&|ivp zdX?VXKmoSP&tSH<4&P*Xc=vJz77}8-1B8!d0cW#BxWLd8o=iJfUfU`0+(QVsx$4{8 zM%dD+!cq1`U^-K(q~!|)T~eLAZia5FB+I+)`mCM=ATeKEa>FyeeU0P0N(2$?H5_a% z1c?1K;t}s!d86fx%Dsml&FIN>)%>u!tJSay-_BD*KV3b8rOY0MRDF}8&W3rMO8Cvd zq4No{`UQOiAyeW&=;8TZg&{D6<%2^Z z!|qE6iY8+BPguq9y#O>n~H+h-giBAsF%%~f&;2z zHSJ9+elB|j$&@GebI=dtreMMQ&ghri{%!G?7SS%=%2G0KqHH#RkD(za3ny=Hi$(=p zLGvS3B|d!WGOoC}J8#If=~Y0uQMxBB0Dao47Ri8W79ysyRyY66Fcmx+Tm-DB zhy25cx=95+#qc?ToUlOnSSf2{HM2o=*VzYQSjU+-RrVoQq-g{FF4Zg zE~D2d*8doXY~?Q)$%+d%R^R5T*Ja|j(efj$qMbfNU$|`D4f(?#^kdi{t)k*vJRUdL zlxcwb4m#}66CTp`2n9CPSQhv#x;!Mn5l~6yO6GGaT9+UCvj-#Cg^PfUgy(9?6bFXL zpNb`ZMW&HB#=RloUUl{4T*WAYN0#{>9S=giO>#Fy+5dV^K*r~FnE~_`y9;cG`R|Z< zoOm=C`0i!|j9q)!?A~%82Uz7BM!4{L-9s2&lDz;lp6G%f*Hh2|EjuF*ZTdWkb~fij z6_P^E5528|&KH1y9o-vpP$5xCn_I}+iK{MC;6&BY+8Fs=m!-n;b%SD?b{UHjMD=vl z=|HehRp36=l!l{Nb=j)%E)c-p>$yu+7f<0NCv?~F0Cqtaf)`7bVV&u>BhZse9N&i(A3$x{)K4e9C)`q;|M{`52%Ol-Fg#F@RhIVC{{nI!7gqddBASWD!btp-(BBw zy3b`l5s_nR2<)6q^Y+vd*eWbZ{zSIO{;S}l*pU8|lJn$|PvBuKUqx7+=-R09e`&ej zfx{|HP3Z%AGj5jsR!`dCO19@yQ~>yvW;*!(X7#4zWHpB}1(BEfJf?t!{10!5-z-JJ zQX-eGqE>l9_7%!}cZXT{YORv&H@6?!P^VBI%uu6V6=U2bfK z-nUhXzIRgAtSRD^1sRqBr@J>`*yP8cp7G0o-9a4q`1%ZFqkHR25(W(nc!>F8Rev?+ z2p#E#0X>$-*t{U__3WWm|LRC(^ku5R)_I#q+`)twhDXu$zH2tK)}SV;F#zE0@2 zg?0JR?v@D90Hrb{11&%10Dztc$r&o2>~^QX>Hg!vk;( z#!o$oW+d2aJ3E!HTRLmi#ku04&fiTkl>~TQ=DSMO6nU&V@0^f&T|`G#xX*^A`Jd~q zJ}%Ne)$q(Ccl0IwAN0|Wt_{zb<)PfG{R#-xbxpIXTB^TSg|zin6u zSh5q{v1O+fzBxjo@#?QW1SARF$04v2_)CFv*=aWK_yOuc#x(QJ=Ett;&FUqs;sfxq zCIB|&O^N=5HrZJJV02Sr(xjsQLk19jeTIiI@V|PQ~{$B-zwT*x3pGviT$60%8 zCF!>divF-$D){m87X$&aRcy6G_WdbycC+L(o9?%>1B5-W24q|AHU&J)RiTV0+o^D# zT@WW6EHpXfOd)pp&5q{s?`;3C`S)0Y*FJT?+vbC9;6s04-B?QK(}F_(bAgv9`a9z3 z6M28iWc~@r|2+7AU-9?vZT>GSHUD2*%^6Xwe{?i5`rX!MSZEWDhZAtQj+cwo7%6a? zSLc=zv`#AoZy(3i_dRGaga;nDKI!IPS|BN(j!XSr`)E`qYOKB0Wf*X2oba7V#{I5) zk=%1laIo%)G5j-l9>dPfyf>2it=GmbYZG{h1;(^o*K*Rh-V5gQHTu_th|#qnsfD#z z@N=S0eaEKKL8ivW8}}v!0nvu1qUJx#E)FXw=}JTjohk=?^dIb7E2n>IU)7z^yXKN5>F_agCUG}=!;#J&CZeBX*c`T6-#zh=YC zndemokzv74zo3(!G~OKC6xP?%!8h!~ZNg_vh8nM8JRn4`F)hCQXDep(R~_D}48xI{ zy4B6+;dRhGlsf5MLde2Kp_-kt&0xj4>3R zhquhEz2pj?@1^q#2>W9fj)Lo|e>Qu;f1NoyY^u>Q{MwRUOwH>_4=8z=h;cgr9=^=* z?xGoVzo&BQKig6XySlGE%#IRELH|3M`R8%$1||7_>z7ob{BH;Pi(>l!kOxD5aw~vz80WD^z{{}CSKKBaMsdz*X zg6)>mlPEl1p-B3iKpQu{PzB-uPdhWO{u5Cs7TY70bf2c^q^bito#+l%nrww;wH*q9 z9^AY$9%^s&xgT$p@9X{}TC>IZXEuYUIBot@Zd+L=dt8Ib>xM9s`UCq}w*sdfH-c>$0J>4`lZ*J!KJWf!Y{KJ18 zO*eu+eRMMb1qB7s`&Lme!UCS%p^vnj9Q2HvZ-t@@!T%j}87W(a>}+UdXigJcB$4Fw!o$e+tk>*3^i~SJOF4C(3^hQo`+k zUHc7b-*l>D~O}$@DWtwNsB+WB=I-1wY3B z)aL(26^f6bcMLQ!gU#$v8OoT`dO;}%ZkQ@+oL)F*{Gtk~zA0_h*@O(Wo!zyFkK)04I`B2uMsXC_I zU!z7c!RhYhJk8D~`gE!0=iP>pQ1&?a zB!)_?vR+2ekCH#{3X(;%F)T=$KuNw;e-z^P__rCKy7~zHo4Nd6PA>hsiCK;Rkg$~!x* z1oZ}mhF_&o*#{n_Gl6O4`E5MaZ`8*?L(y-2KH65;x&P}1M}c~Nt(r)Z&EUbuGWgb` zq7h*-WJ2sQ%Gao%mg#yU&%gCFZGLyHw3wSiqxS1=ra7 zhfVM<(E_q=xL(ERoMH|F6v6KtK8Lk~#`=qi2h8)gZN zpyUxJ+PA&F!GFW~&t>#~6y)_7(HpW8GA#0Jj)JnO8cp|o$d$>=w7`eLBf~3W4w@?I z3W{(h>8dd`6ru&FGa6{(H&J8WF#<6i9@Pa!~XE?j?N_|er(s~ zoQnPL+2qvYPfp!VWX_=|XJ`LT_K`)B)Hpg6`5Jj1h*XuWGaakV^^5GAL8 z1<+W`_)7+Y9;rgWz7UMAb3^H0$qF~P}9YX$|(l68N)eOTs+-Qe#c_pox#H>9Hd=PVCb?037 zc_zYv+uwJQsXssy&e|r6osX(3gtZO%F+;}1ED_{DN(OKVGEW(OEgOHy`z;Y7edqUg zys_WA|GWh3p==edvj;U(>@0s)K za$RXeodzH`gT9(d)4eY`^}kKtGx+twpn!(!VK&>E+`yXpuh(v|Wpi(xTH=d7h;v5M zR!OVLI0!YPL@|EdV)~92GWb13R$pt`GEOT?Qb3x8FL#*Qs?^3PjDp30bwiH;|K&TnmI{XS_VTuIA^Xnk) zsnw>~BEwGBj$xwjGp_8r=GxpTbLY>4v$JC!E~~?Hz8N?^Ndu^6cq%-o7f>+JKkXTPIu#nTp1%Bf8oJEn+~#k zN$lGfo=h(}gTm<=NmRx#HWubhurWa9!z_j0mirhQKozcX)o-MCKS+U+)JmbYr=O&@ zqxm_+j`#c2m5$2FzBZCB1j*|si#Xvy3^!Fg04#vUxMh?he_JB87X1Pu^@Js}Al%lvRC}tTS?07wM`*eC|2fyacbu0nu1^PZ>k4AuS6p2pa8h}3!lXb z7r_gjW1#8@siJi4P7|_X)OLVfrXKQ1D=O4MjItz#=B=8o?40SD-1vq-P6EOgSr>U~Z9S?C>u(HvJCbLw4qC ztop8mY8GXcZ~_~n((s%NJy11JVUEbad`sQH;>i#eZ%GutbswFi`1%Pt)KH$zcr%DNDbV>DfG#DbOi8HOuFJpN&gT2;Iw>eOv}O#o z4R?4w{O&%K5Vb8@eB}{yeS>?T6RABQWkJM`{;QZIfGnGhyGq@IV*-6knvpw|-p9>L z8_Al3s`00QS`2aOB3S!KJ6PoClJHk*^e<9Ad|2h$i@?&-W7MU;?%kal^yz-r<+G^1 z3ePEaFu4kt4B8S>_b4Tog*3~bz8YIp2aKD9eM`&~kMoKBWiRy9>3*ex{3JikcJ}Fb z%F|>X-1Il#2ykyN?PknmKS5VQ>R)oG6|@i!HKt@e_*{`e6InENts%!y^}F{k;`8W< zOrqN3znhy>Y9D=`Y^b~%VAL%YTfa)04G_FL@T75=u?EDHHkKYcahGyN8oqe$#fkN- zL8ZX;gEHG~1>0NUj1-Y$rY3Fo=O%*5W=W@_?&iwRXu`HWXo{>Xyp@Hhxe!iZ?z&aD z4#nffwZ_Qzzrns#X;7I)Zjo{zoMhLa+xqy$Lg_DE<4d}V4`)a2&!Cd8UrIb`$7hQ~ z=rk3pL_>uShe-#nDQLLow4nimpL(^LXX95){J{Vs+#}lAx7hhMZKMAmM z@F@}Uj3|<`r$;{V-DHE@vA-qpGrh)EZ5nLHWL(KsXXqLi6M2tSeldQ*-*^A#+2(TN zh$e0D&p8p<0o2}CZ?Hhg*9_EEM8poNPOG1Aa2MN4ah2O+F;TTtw>uGr!H)Gh>J2rH zXFLlZh85r9yE4=+UxGnHePi3;6^A7(&UUa7E_@yVU?4Y_-Fl<@d%Quv-C`T%DQ|3``&(L^MPUn-q&sCZ zIsW1CvgOQcUB>3?@6N76^$4n~f@AH|@$r9Ikk}0E6n$%+>4bIhw}NC?o0k^zHGQCq zxp%a2gBW2V&eD+hK-KcNgv_rD{9j9$3M3nTudV&qOyVhqdTQ*bNTlgAZR#YREPi=I zfkqQU1+uZ!r~ zapTZw$fVK7r9vJg-B@Ml62+w5DO-4xdbOHw%~CT+&0R2hKK6+*aN;}#xCcXC8`-rj z#;6lm-Bt>#;*zI)V_WakvCNkFRBe|M;i6nIt8_Sqf)GD$y4Ebet;_EQ-h36+-}Hwi z*G}Fgdp~G<3==(#xp-|EIBy&Mupf-xtXVY1eM0f9a^eqffibJ*| zFeh(6S1byR5ldEw}h82UX3!s5W0g3eUd%q+f2x+?Q9?AJ$OF(NzRM^O0ul)+F&srRw4rpP9NNM zC+6g5Exi}AgJU;t`_6WH(mrCoZ3b*c%ri})d9Ihd2^NoS7gwNk za5jd{cQ*6X&O$wBl|Mpu%G zfG|V3AiCEMp;(0hIdu;xI$DRF-Q+5CzoEklgGPL8%wa`qXo-C(ae{e2;oprIn(;Y@Rg$=FML#BVB8#k+Rsl+tItuyeq~L*%@f2v&d2@{8TD zM4U=vKs?;y0D1T4AlMAjt@pZ4y~b5b@2%c%N=e{S-}#nshr*)&pdIT`hWpYx&!zQe zjQd!}?*!y1TmKrsOhSFkV0&vQpSUeJ3^??Yn_vhJE!C@OqdrT8p(8U?oK zh4%j8J@{vmM&n5g*a{t_Z9=H#&%@^O?8k?dY_{BgDp+AGs7eel>=}gdqYj%0RVi$( zsT+LAc6Q%axVf$PzQhzC+57B3hfK@;tUU~41cfVo{!Kj}NUffe)J3ZeQ!*z(w z>Yf&dPaI1$fq6}(4-q#NuR(Tjuk+8QT?>!Z%}?WO-j#B?w@`gzPQ`$y$X_?XzFGTR zq4hP-)!S%(Z9A9kK-iSIk7=8q-+i=TuFWi-ym*_>eUoPt=U@$W&Du0xolIbxFcuds z4|Sb9PnETL$71WkID^fx}bZ->Qs>AzZ!# z)c%0bGRnt2(({R^w`7S zQ7`JPVihS~JElzLcg&Jdd}{iZFO;O*+4PfZg117qLHd0iCL@#g)Gf`g%DXKUr@=Yy zaQwqceMb;fi5;K|T|B z`ANT$P7xM#`E`EtzTje-z>i*~rOcq&w0y=+5+UNB=7_ZR+xavh$!gMiy9+D2V)I5) zXmTO4S339dDqho((|)vpY7L~`^o1fNL?K(C>SAW7+0tP}5O6WnD~RdrArPuwYBrFn z0t9YDTYbmUanM0m#&K`|H1tT-76<{b^1V|*ZWLDqsJ;U0k+kIi?txp3rqAApczcKB zo-dSweIHV#%4W#2=aTn${B1Sv+UK<<0kN}qKR$ZB4bCuBx0k6_9x~vVoKV+ z&(}WQ=Jfd5nXXxN3SCvQlpXd}JoI-|b2eC!WgJd}PGeu$0!A_7d^#zIInYxi2_?*Ae@&^G z$PDnH`PPs*7BM*M79tWQTA8;<+CjnjahNS z)TAw}dr@;mwFV9luiSC7%1XKG3xtoE5sB2~ygqfPHmK?D`3S&-UbuAZDCpu%&f(5$ zZ=tm6>C+h!4NRlD7~_9!xK|Rw7kh7$EdN8&O|Q*;*ZCaD z4jJd=S~Xv{DiBm!zi9n!b0}i$`%OoeZgb9z_M07f<{%w$=I`(F7_&6GM`$zITB8MB8N6Ln8`vU|&v^H% zzlI7CK3Iehb#r8caRv?DU*F)1A3F@2*T^{A{zQd`>S=|uUQsZ&KA$%6(}JuU$Osz{88r^rp+Wi2e{`0T9QV1?p4 za~L#5T~1-Vhe|5^Tiu~ICc2J`73V*Tefm#B~4=bveHUwyMjMBL|;cX%8)=8 zoFo#i&)!T+)w-21=sR3;km9s1*flcnP%RDC*F=Tm+O94aEg_pD%leF8vta2*Az+P5 zADCIRacf?WQ5yN&B7R1q%5=w5DPM1NI*8FkNSjOkOD-biO1n=>Yb5tgEnr6RP3U8p z5Y3K}dS=;@c)-P$KCeSaK>{xIyvtA`@hFg}FUHmS*FTS48)2aw_y`Ge$ znPdOp^4YsOOpB;eHiXpO*`L}sIyT{J3b~>{{`Hm*>q&-6fwqLN*}Hm*SJZr0npYDr z?=PMOu;BO2GP-?w@jR;0&XjsqFWugHNL(Ya_7gUH7>j4_c5%P9E#H1=OZjV-#{l0u_)~I>-0fUVyiYkdf9XWUa zM1Xd3e6i;hJ1jx+30m4J7u2Est`0T%J8*(f$K%%KjgCZsHvMO3bvqCnPh3H|?xQma z4rSbdWu=z(`9a-Vy*y?Xf&ekh=h1@{dte9L4d-_~uQ60YMb*`Oc8Afv+%Yp?VF6=U zBVxaZSM8}7nHB{T5Ec5;B(df4+%q?_-G3OE5S=3EkUl8VV4L_ckv;LF(c9jrKJ0u# zcUAY~BU|YBk+VVlfiscRFj_~_Mj8R6yWmfL^BTYEytrmUr|}&luY{yq2gBhj`^c5Z z^S(cSkrU0?2?&(}>)0c{^rSVWrQMSY%$yc?UR!hrcSNmq+0&B!svJ0?5C~GA8}c>6 zj3N{*t4OCfKpu_^evK+tV7fprL3p;sL9(|iBI7Pia)v6MwpCc}&x=Mz?g403Xl<e;viOll%5G z0F13z2bFa2Hzg%Djq*8s(f={4DAR z_VYbC*mT3k8^YwXI%jshm2GBx>{5ieUdx1_gq9OvdT$5b@dmgLq=((RU{ZK6<-f+T zm}DK>i(S6*_7hf2xOTX|1-7HO4%Lop@E&^79{! z@9zg?%&B$Nbb{u$4&`iUl7ECne{W^Zt*<`qAxIkdiPu5@9OKNSobC�)v~C(0C)c zgd3@mu<_@wnt>uVJydQ~oz|jKOy0;^`Z?+o2D0^+hp!@j_=nH5zG^AYBuV|wimv<8 zJ-BGiO^XI}T+0%OK+mPa+&L+!)PYa5H}wL${$XzJBCc;XV=Co{g^!)F^tz?jpNo4b zH_VuCMYaCaZVyd48bC?#x#Q0K4CK%<=X&Zv)V@IQ!g5ZVK?zTp+C(vj*rq zre0*ZTR%sn9`4BUqa`iQwuwP$!iTu9y z*^Aa8nvPt{NV`}cy5l$vTGknczicBgdPa#+$B~_lxB0^l39bW-wL`u?WXo>LbCrxs zHO}TPn@o1wSYvVPGZi62B3}9ADk9<9rEQFD-?ViCJHyk~ulRlQ*z07+ zmqT0+dAd*&o$#ah@3U!@BqPvJ}Ns=MjBuIqf9PCEedGznEA@4tG^@#xdHP z5}hhW*p9vTm8p^F2zoA2iJy%YoUT99TiNM^!6xPDkXY%@^R6F7n4GGx+4V!RemOu` z=Bso5M|O}5LA6BSOdLB#UmR7s1}UL!yoSsl_4aP{66T2X(LM*|9)bk2fjUQG@;XV5 za7g2iD)Klhxr?NUp}g%l7S(du@pSRzjsod24a*3J?<_x#8}8QdV|kf7grum zMHRS^M;MRa{Q64RKHpz0W`#~YUyQ#oG(l?D10Z|E)=~C)c9e1bRQzl_KE8L*d#S4H zGq*7)2eRPeh6YhjH3bvBj1tQl|SyY`C6lvas01T(9PNZJK6 zP3wxPDqmT-KbA4>ntJkBD=r{uh>P2dKe_5iem*i@&Qi7(JIJESfjBKGU&VlMgWXOZ z+grrgAg-ko&vt-qp3qk_{Jyj{S5C8tp_aWI-lcFeqdCorB>t+{;r}X*a{YZ_D7jsx@3ZLF5~Y0 zEmA^FHl-=O@oYTk=b{3)f#6wrVMR^aAFkWt`K!X;*hkOEJ}h?qih1@jUzl5Auc6L~ zxmKdYX`}A(wIiw@Nvhre3EN-J<9T?KI85Pa#lXhN0pxf~!g)YyRJC$%aOPVO z1|N}Vm(EBijEx+5zwlamO7S~iGl_`D(3_AYNv=Tp-B zLfLb!LWW&-P|dCrm$Sp?uU4-Z9Z(L)Y`Z^8vKv;BwSQutkP{9P7Ks==4@J%CYWj*9 zM}5&B_xX$_jmo8fH#TZaygRjP#vD;JIFLu_3CL=zp!gk|koyVmeEXBMat*taN>zb& zg&Kq-YKy~J*#7QCz^h^O!Y`}mn!;bvx)sw2>M`%V$C^-PmWPOs%LdR>R9a zjk<;fPnjUHaeQF}hq2MN56#UAxS3c@3Q9#gOvfR69IJ)f)#IIsnP!H1MzFJ+M~v3H zm2atRwZuz(u=p#QW$W$iOXDKnfSyYt`5~>Wm|Mz|({I|E$#NdL=fer>#3u1y5dSj4 zhbTlcNm<$ZXDm5+&{w;^Vnmq)aShdk!HJ)q1*3!J?c7eue z4Ayl-cd=DH3Kr87G6hlUw+4yt%YStriba0x#%6h8yWB{-wpg`bEXk>vAuT`8CMCZ= z-ET)=GS~U_weHAuj!N8$QxriRCC_$2*OZ)z1s7+y0Y=tKL9QtIwdQO;E))*V`;X)q z!yVh(pIlUb7qE?K#Tiudee6%#>#9!n7viM7$pyuCMEsl%le^k_Q@40@a~s%d)S`(E zEoa4Rt!`>1A*l{oFdqaZ%8$Gp!HH!0fyIoqj-0fBJZJCd=cuTUbI%~>YWI-?Xf_iU z;p(r4yd|!ntJP(HtQYRCvJmF3CM-fcN?4UOu~xNlO#K4l9UutOL;i*TcD40HZNfNZ z48=KpV`9#O&p~l1lqXnxeu_{R(_Fy18x?Do2vyIpfsMNi==h3*DeaW9KFeGKVIEUk zFA=1Sbsa>aOw&?cN(-LAsQGLQI*QKv_J(QxZW9@`w79A$t3iTm_8RU}= zPk1~jn1_ubHVP*Y=ty%DSKZCk_LL+S4BZt3ps?hcWV7U@v&+g|tce!uuT zoaf$auXWTi2^OKA6T^5VDK+&=LRZ zh}nwN4f|Wi2H;M29qxDsS1;ds?$L2%vs&=*`}(}x?fu@t5*h?7mkz7o7{o ziz|$({9mgQP|Q^QNr%LsNmqXDY%h(Z4D5=5G#s8mXc;bGXjqNhviHGjue>Uo%4SRF z*bqwj7Nod}m)P&L4UmIEG5T06`^F6ydHyGsz7w|bSdf}FmmV{OAIoAn zvSLZ+%SiQOM*3+%Bp+W1Lg$l}=r{Uk#**4isDECH=%jX5K&c!$Byp5BG?w8J;=YkIeXoqkj znKUFjOl-m^nECRn!;La!Lg$gJIgh_m;Fm}zxFr*;hzA!C9k~v(P>w8rpF(hXh1ovr zzA%Rm`6u4?vDUSNLT~;c9KJVF;WP;$)M+Y!vNGWDe8gda@!UuX;bF}B<-Nf*2T4sj z3>#r!`)cWpK08bL@-hHE@LQROyQGIdK{mv!k;3mAV~Y*& zSx9%5c6=H`R2c<5TZom~S)T3I8*R!KE9Z zGy!Hum?_Ifj#-ah^FhR$lt)QpLd z4Z=r(dZzP@l^;2su|VZMmnmOEH~2N&6&pO_5y1FY{2%~AEy}vnB0qX?;I+BeKcB&f z|5-n=5l=bT!BIq+;RyxX6beD)7x>UAtobc61SA?P_ozwGiB-Aj_c@!Lx0)r0&$Q*; z7-Q3p>Q8fJ@t8ETi=ab%YjAt}qA~>G@Vs;N-`I%rADs}msjm0>eWY*01Gn@It7Gr) zvfk|JHY~V9eI(H5^?}anqY4?%?)Xku8F<& z>_)a|3WD-J7>6{IyHJ7Ny`sr%kPEeFA5=8sz8I;*LW|uf$ijVCB$3K8y`x{FJORg-`CT zC}*oRScJZ^5!az4e_~k*L8Kie5o|%0U=n+}6MSoXJV^q{avZhx_N7Rh6~0qzf$Y&r zdu6)*)REIY#^T(0%7wuvlqQEMvE;#rG+58^o-`ukh`jLP##HQy1~6-E4c@rB3Pqh8 zDUnBX7mjDFaBO-{#bn&eWY$}&K#}-hW>rwhHS7<%)64c=7yoZj1-pKq1+iGlPBJuV zKWWI?fcdcbKl5WJrm2fffh~(~uvkVjp*vVr(~|$L=|8=URvWRpUf6Lsh5vzbQvm?> zx`zl(i*xr!4lxhdG3~Y`Q1gGiOqdro9<4s_DQ8>s)cb318F(RE9jSx=U_oa)!&<@6 zW>xI-V$Y4~$-l&cpIC)?eD<+JdcA$LeW$*9XCE(FnjzJSg_7=*jN^W1@WeUBcjDH4 zDPL7o!srDPfz9aXRG;qPXHjo@CM^=WfXt`E4qzoma*pJ40+uSL4biBj23qPqe)@#A-O+O882J9sS zx^ICqC-ENXg873a)hiL?Yz@}dc-2eO3P(wUqi2Mlig-`}Xn^2<>c-!c)nYA2ANpSM zuX$`hTok?gLtX^Ds38~f)saMV)hGjY49J#-6JXcd)fmPuT>MU&!;gXb^H(>&Zpei{ zD6$?;nhRf>Cl)J|l?%H+@7`H_THjT#q2NZFv}4$jI?{y^AFw)t(<3NOQOC{@uK$`a zoPZm>!1K=HBz(h-CC8)qCeFF)q=Y?4W0+Y>aYM_;Ck3GXj6bx#QiT@aGiN1BTVkl{ z$_soMv^o*z|IS*ibD=5ke1x4mH+90p^=6jL+vCqdmy>bpw>AThce8)=@3y`C^n)S` z2As*5mQq-ZofZMgl3aFv4EY~!kc=DVgPk4%_|XB9(t z&pkSvEgC-Fd2cJ<#I~D^+)wy<2|Dc}KteTsyumg~<4T`RTwO73uT1x6b7?Nz2m-zv zqyOe#?uynui^nat&s)saS#K051fD3HM8_dfRsv_4@!qD$rGwLBE5@Z2j9$ta(Iy%Q zyI?(ek&`*!o}zI)2_mMe+s^6{Ncvh8eAY-1@6{vYFcn>k8*Sfm zy$cr$g*55TbyE3$Y-}MsJmS0A>(>=$`3LA|Pq1!y36T*z%Y;3sBPxQ9<3LzLbMRC2 z^lI6cc)`I^f-xhbbhyc!6GZwVIRv`9)wSdf+(mLG-yGJyMG40l%UHu-3#%X;qlpQ4 zI#_zNF=lp0{;4(>6BbnpqPK82Py0fT!H1JSM(`6+d>88_BgyPd;`e|gGv!)&v8f|h zKFe}=GlJEsk%FxPR7!jXRBNR>!wcL`rav1Gca&M6@ZFqE% z`4Mh^%VfTB>88(OnS}XjA%!~1TgzdO3p7|7|926;mpc4??7wq26+B<|^nJ2fDzywu zFo?l1EdtXHOpk5ff@z1DS-<$rG(ZFiXuFs|}Y34Kpxiz9w9v)SYh`Qlsa!LK_OFPk$W_-wQcU; zqnMAG5Q$Prs$WQkS8`znPLX==kuQ7CiAW{Rl1k9zUL&)gL2Ky%RI6%ljx`3Lym78HOG_r#NWZ`h;UmT; z8Q;NB(OjT-ypxw`C{7rz=Ah6?Ilf*d)0!r@p+-^-rj8xi z_6SQ&${Rp@207;QK;#<376gviKcGm_O;|y6$pBqF&Tj(sX+L)PBhju%zN5&)Py{q84S1 z!u8GCK6^gp(|xu;h?PPKnUh7Lmhp+RzfjWm!UtOhw9(KveIW^uIn_ z_4XfElclN`*ZUd3r=6|g_*_mCYn{^noi)emliSaY^fz<49-|%;zdlvkVbJWlK+ewK zY*{HA(P$@!lXVkSTpg#-w&~WQVm=nA@QV~tjbwOd-7zb2C?(IOw{6?D(sBB$ncUFf zOE(5xIKJ9Pt&il#NG9BsH`1^QjnQt{9LJsje&!xuc&TL(@ zAuXdsJ#S?ulhXa4ohB~W21ju2HEmn9;Ale><}Dj~ZAt1pw2jd+HpPP}W)J-w1RDseHl7A;l`H-f zBR?QsBau>#e*U!E>9Dp@ArRa{F&#eiGa?C9X0D*u+HD^SnppyBly#h5H*jF%%7=!sw59c9vD zehhfcSO<-^K!2XtS}}-6ld)lbeq<@ttMA$#^BVn6O>T$3LxpcObE-NtEn)SH3DAgsjf%Hy@L@o z>)9|}Njhf6u=~m;LtCH0meC4`1j`X@*Usz5Oj(WAi)jVKP9?vMg6!#`W_aJeyzA9E z8Et=&jhAK;rplBlx~kENNni)V)@4o#6iK~r3DI>TTeDky--t|0k4HK@%pgO9xQ%UD zyh!gX7B7xtM3{)5K!6}U%CGpooZ#bwfJBA8TNJ|w2h=#+HMy)2qAkKu)x~cv^MTR5 zgRFZprT~ARVEa$0VJl_teYh6S_m})2e(B2S7D%gA2}!UY_BEL%&Tpl&tiC2nrB;xd z>BKo49MIQG#xbHH@XVM6HDxXHxI_x8HLWh^aO2<0Q|I4KOH9SCksvdzy{{R;Q_qkt zt6QqxbuiwIc%>4LsbH_z77CuZ(N3Eh{Hjl*tq**sjUxsbL00hB%O`K$_t@x|s{n4T zNd=a$$ae5z7;Rcbu!eQO`0qOBG$j8>tyuBKRunfzdwqI*M)DkXw4BTY9#k;h5lpSc zQ`n|Bngm4zP!!TzK$%?Z-G;AmCHO7HG zJ4a(MJnx8jrjb>P`5nQ+l}d5)GCk*Icu;gi*^oOINvafMb|ZIakvKmN9Bc9!zuX@| z8c!6fcJBtgI}cj%Z*hu}cIGcMT*eEDaRt3viG8Pz`YPlFCsx%E3 ze|0qp+oBM@_a-zIsY9^~(nq26QCP#uvzBLITT-Fz1pxTVGcnL9>X6Hfuvh0pCi`ERa%Md2+UxG~gfM-;9Wc)ekf>K{tXe9Mtf!(RFbeqz0o?=Tkh6Nvrj3gQ`mk*o^N zm!-*o=#C|``9cYa3e9*JN%R@qkelPrEPd#e)szjS?u45l-g~tSiv;RefFk~@$ll69Yelw0B?`5LzC;tmCJSyx_+HqT%Gc-2 zhqa7V;q8X$f6QtH%hylOT@X$Mzo#h71A{SUK$?cZ-d!_6boCTtWx6T|zRb+Ik5lZx zC5dG%G$-g=G*YM6F_`aAlH>GIDIqE;_y7oJh498JT}+&LXR4d;+c`H(r3h&!=?z9x z4Q9TKSxmY$n+qmpaZ(L5^RA7HmY@KNAqINP#5>dVozR%cDNn*ch4az#C??EvxggEz zsSOE4zWxw3&F#htFngbgdsT{RM~3V7uK!%; zSN!T%2CcRzG~5cBOfItKldRJy+p^9QA@i?}dZ znE+cDmfM=j?ciR(FH$XL?toJf-0P#?``x(7+V%+5_T&Q}4ryu>>On>|O2>w&hEpt* z5)Q%Yc&uncx(~56ht=CiOPu^_jEY%zk8Kpx8pu5Vbwy1^yuRo6Z{#hTke{V6p)&Tv=g`ZHv@IDp| z9-YRIOoK7?Vhu_H48|kcl8_9){<@Y7i_RF`qbV6-7s>n$_Pk7Q+O8Ny@3HclM47Ac z6zq|t>*>*jzQ1Q3l^j2@k0ZK+I`N0qp{^YV!oBYzZE5 zSvR>;F(^9oMiSA@_%a>wFdl#lN12STlFn`{Qmaf}rDn#9RS6j!Q3~}X zj=UMxLXAIWT*~kt-mDJCc)Cpz=ibFBQnyK#3pFG)Am4l|0PbQn#eT`Vij|AEU5G%h z$?8@IdZ=eNwR^{eh9<;Pjkqg_&CZ`Hvor z^fGvd$l6WXOdtBDp6J#m__((+#YK7r9MVZZf^jwc^VldYv>MnCwxEHmjCA-@!jTj?aPs5l^liizJ(^&FE1FpZ{Ym2#`r~ z3$WnCaEA?+aPxO%`B{1|`gSd*Ka{eb%NZ?ZKVE^@Xr40xBKY^cL=YK*9#^7FK>)h( zQSI76fgkV{B@bpHxC!faVCy9_0+fD8)Zyl>Oz5wZTeI&x21V>$btPM->8wm90k^yf zdoyGD<+a&Jz#pF3h!1alyPUX(tHDr~S87UyD+l>$24NU?oQO9D4|DnM<<{P-5v z0EfE~)@KAjemmaKTCM0`k3tG8krF!R2_~LbrBR2%teCVPh=veVmQB9mWCw` zRBgo9P5Zjdo9INN96~`85TLimeAWEwn27-7gW?#U5e%o(cE$*1-b}L?*H}@0i!8#D z>Uo|PP&r6F`v|C&?si$#j^150fj%x~5ONvfry{1>s%V^z?BIVI6%;awoqIAAE+1r% zr%okZN!tCI+p9joS~>M{6SzZ;3?!2Dhs9X!)6EG?W`;1=K2r-_=(Wi~M!Bb|OgmT_ z`2VC)SopD@PttM9_!%^JN0ir>nt%q^UFnwBe^6%XTT+3YDSb?Ycreb%B%%D&Nya3+ z2w8xJsD7FRj?pAvgW`tTb`Y4^yWJDg1&-?3wn>%6BsC2_CNkshL&e|3s0g6 zCp}stZhun&7%~}K)l7`s*HIU=ZT@Ig^~ciyxVAo{|#log(TGcqhFz2n>YD}PfA{!SqL*%27i3L zVt~5xwo(|dpyWNbTT%Xq90l-OjX0{cQ19gm4a+43;MeNTZ=^*pQErF466HVSl3n+B>}KhjI4M{vNuAyFoXS1WABDQ=ro#C9LHsinW@c$u zat7*s0VfDf|5M;;M0)rQl0tU8yk)AY$&F5i9w5cuIvS^~N4`8Er&8j=LloSD zIB@a!n7j^ZL*-A|ES~z_uESM3XAG>{e-s_b5@Y`0H<8?2V(vtNLcG>P#L70QDc=)3S59YTUZanCyxMgJ9IkJd@Js*GAR@QbFvEkyRt*ihX00jFbI`A{T@Hi7a>$ z9dv>9Zj5Nb)QrZRk2L02K06WlI?fU!y<7-R6wIRSDQm0??g)lKHj%zN!@_9%(a0V@-q0Y8JIgQw0k zW7KL3JY)7Dk5n5?r)jU5j0mN7vF}HdGu<)aLXMCHNd@t)OBd>dOcSQhVqu3=2eTsJ zgNs889adQocnYQEJQ%-no23VQ4pIz4bPKzPwc4-DLBR#uam?%N00hJ1njr|mOjTE{ zuR*ca{PW6n35vM9iK!*t8#DOOToBZaHj4?8k)~387a3NBLhj#R<;uK?z!bpJAS{wMPPYv6QFvJ; z1pm(5kCd0#WeWoFpwEhy?MR{TpwFJvXUtWgmeSGOP~>%i;$uC8L4s7CRaGSMz)fV7 zUH@X6>SJwD$y@wy2ft<@D9oe0{#fa=1O4+V;?Bu0XBj9@M&lTPmY1jKr%$u)t-%0H z3-xW%={G`|GW$M+@#1R2?cK`Es+e7a%3W&Y1={ajI{pp38a*BZf*cLMk@lcca%YXg zlb1((z53>tdl)5ewLO~{@W(aPGbV;*m_@yq z!qTY3JAN1dwSq6%J#P}Te0+5klVk5cW$!ppnl4pN5rBxnk}NjD;mr^O8WxI(tuyk`0_N-ZINriG=?|u0V*1~khV8VY1|dGfHsb!! z+(Ui-?Et=|dkl0Y1P6cph=LaS8TfA9T!yz?PpqW;y^36HLg)!o#r+qiEHMP~Vi977 z$7(}MP96Xy$AJ4j@)5S$ z2snd)MC1dM)y=FAI%aa~((I9!l;V~J2~%)Ps1pnWdtN_h)#4y1#Z|)Fy9R6MzFoTe zsG`5SF9Og>19#F$6A!2U5?$CmJUloKIWH2K!Pd!8Gl`-1B`tWbEj% zwiRkjD6ZDTM|sd?csJIOZSX&P3A_*kqq5%5i_x!yzuk!p2uJdXg!FMp@@_6aB7IoK zTfZ~n1_C0XsCgX-MJnqGCJnx&_GY%K+A@wwo}wu?zoJ5#%SCTshjddm*NlVOA60_o!t^8= zI0W__5IW`8Nk&UmI_i37>*#cFxlw+_lofMOq0LpPidbt%JRf+;51US0iZ2wkzhXBU z{sXo$ZRM!4y-fB)6GIa>mYK;(pHg%hKn`sr{vXS;Aw-_P)O1OwGV)Fmp4(3wz9Z;JL^LazLgBqs3c>31Ete zkvJ1G`mg2RFVoXBnbHFFXWG}DO5nA2ddz$^Q8rNcLw=sroH}ESu(vXg%7D4dr20c9 zVNbh2>kz^V5OkSK&mtMk#;7y~;;>bHPfBU~h1=K)Dez%9_oT_M9oq@hXPaCI-KAEa zu{h^qo^D~8_;yJU*(bQ2%Oy5pYPXS<8wW+^w*v_EnVFo=7Mxz0CO69%AvIkDua;ml zz0U!d&tone{&(zC2X!Ary4j(iv_c8}woL+hqX_34lAb%E5GR|RK3+PiU)tc&EO!lKt<)6Q?q{01?$TSpi z38`d+Wo9~JQFS7;L2m6=S4)!eGXEzn&)k-^*? zd1y`4oT}4%G%!z%}xCXHc>M$mhmTVAT336kckoBel%Bj z)&g8&jvAf@O!Xhv1y`%@vuHDzBU2eIKJHE-d^ihaG#+dinEZ??qTvKcSlIFl81&S% zoHEM=3Op{yn%GAlOe-^MQu7mA{UvC{^itXKzvVGn(In#i#7D#%-g`5-t%^txqr;ss zRa0U@3P+4G!CJk))@m4Yv!C;=t6-d2%gT=&k-LlU|HZLBjegiyu>*aHJ!<&T@twR$ z^k4HAr3$u8`D~&vUEwT~q%_-kU^k{QgYV^l6xU@aP~?)2R7Ni$;PRB>bq>wO4x z2Q47emNCk?Js?qGe-5jolGaEsMPNIPaN$dtXL$dp|N+K@#;;e$!}L;e9} z9|)HU8%z}N04-t!fy*cV-| z&}2yI^chFepYwSOh4h{7N6VIfD{fU8et0cv8q!pPWz}4dDhN9|6I4wEbU6S->l0aK z?`%!J%XqGI<%f9I^uH^v<41c29XWsR#SV7|oO?9xCy>;&NqxDJX*3)v0PF5mQe}Es z@{;McY=s=QsWN-j8l0i~VYxwu_RW_Ls(MO$M{F8D_^*6~WTdgNv!&mSpEEAgV7HKY zTz%Wg9D9(mFuZm&NL&x$k&5rqgW!Yx@a3u(zOIv;Ue;XgsP!R%QYvY);a(757zH9- zc4Ud;32BE97bj;-a`!?>KVi0llNL>XV{9ku{Qmt2^8w^JR*d2BdNFU}#jr1+?>tXidnE0BuK=S-> z=h>P=fbRnz5T;}T#2o|*n;igrz#sHq*Bq9%ys)H0F?pyPCv1_YM@pkxZGk0jT@WbQ z5KDokY=z2KTuDMU4aqZi^4=l86&mO^S~CWqFJ#i%2anIL^fydaUH znXJV@%IYSNofgsOQP}Cg&4d09K3VJd-5y#GZ}o0}XOvHnK&sdphlZ&~#{|6}+ePr)l?$_|NKwLRKN(BdZ3 zo#DJ@U=>sU752Y!1jPp&lbVL#t1ET51sA7t1e0$u;%X|Ct*=X&mew+NwOB)Prz=`#`&@WnIu3xwe)a~C4 zL3v7x3@n3V8V#$U@_G!`_`vmnCMluP{oO7rK%lLl3x8yU+u<%d=vI7RcD(rIYmub< zT~sKdn`Pe^#RKp{qrZlIH+Iz?rGH+&5V9Psbt{^s~I1Ml@4D2Us9a; zf4SJtwo@OBo~(qNojBF^%Gy!d?!UHHei#89mXzm%#QE2`WDj{{{~$+0LOqi*%6P%0 z%3*@i?u*OGyVk3B*A@ywsLuGBl2XYGDBy!kJtwQF*UaS`^K4pW=iof1FET}khs3Pk z`NJ&y!b>98;h~${_Too$)x{x$R6!8lWcpKg1iM0@TPL@5L~j{1C5nuVnU4R5xHDw3 zqy^a<2LKeQ&$;g-_YXS^u5A2l7-&=BGi7NvGn(RPbh&U4IM@v9x)hMm*~+kBFCBdP zu4W6LX$?j_MX-4Jo@9aOZxENUak7i;55J?NPMBy`KM7T5ki?o8-nY?+u$qaWER8=g zX0`0P5AGVR99*~Hw`{`*p!!-^knJK}Mz1=QZU%3}(R)yvgcrj?|fbhq#uk$67 zMp4}MhtDq#SrBar_6ynA{zL$l`8iMX#AmJRP2+R3}^5MRaqpmbj8GW4!Z$hLkza1`zr z@k1u&zx9zVlB`!`#B2Lg5tCAMDrTA+UfcW6Nk5kMr}E;uAB)ID3+Z}V$xKiXWLCGu zb&@@Pb=!WfDCLy2e{fUTg0SW%7c@zmHGmJkn5=1dILIl&6ZLKPV0MRz{m^T^tnU0UCMJ`aMmWMX6AQLqmL;?q?P zsbsx@f@LdX-&7D>Q*qjpw6tK(m1T$qYAVZXr#d;VCrG*3N1uYBJ$*>h8d-xGYpn=o zUXj?>QLCMN@Z(K7T^8!Pfq%bg=|gHJDV*VtQ|Rre}=?E(~;cSh>N0a!&!`UV$bA_ zrNERQ=kmQr#)YKfW1eZN?^ZaROvEf+Yg$8b;+I~$(Pc$u*9{X-G#3IEkEt*`$QSVIog6J# zA`y-Qp5M6VpbaKYFu}LMRK3jUvBOu0mF2z1`>m?1rp5!TB?KT<)b`${2^}{Z=Kap0 z{@V3UP2Cu&xngy8UO?MRAL3Ui;OO2=NV3gbgfYwkP86@NxCxSNd?D*Z;Zxl1p2TPq zrfV*YYx>zPG-*J6HTk{i<}%v5b&p^5)+`-ncA=7+ncNZE0?ZkE3V~-}!vX1E{LVMpgh3KmU##d}~-$~?0L z!|)PA9W6o#giPgsU|Bd3WY?@A&mz2kBdC8gH59E4D;y?C1g*@8X)44>)LvUB+KSRrZn=Pa@>glXfFN%iKv9F#NG)hABKjwmrQf`7$ zE^WH##}=w5_T5xu{lMbWSxb-&^K6pkh!Q&d0xdri^MFOgdH#*LE+|n)iWM|pweW{VTV9CFXr9w? zT@lQL5&`5YX#i=(c#8(v!80ed^u*m4}!_GKMeCmXy@wwvgds+K#6l{NU|Do5{(O1B!Z{bv(e>!|OAEauS zFeCzQ!T5<^)IA>Yesp68z2Lp{xE_t0@12s0l`&0uW2#aSd@}jt+iIPR$@|wAI{##s zO~&Eqz$0ku7AcgPbRy%=czUPh9_h?#Y7j1-_uwi+$vayFT~X+LPFx#MV3UgN7xq*W zdRE@0<>|@hX2qG>alJKa2Lf$fQ{-%T4DfS`J5Uf9P!LYt8I`KK-+Y^67+c?upqH?A zbu+jCX>IsTy&Mr$c#Z{Qw{IN)7_C$@ll$C^JjFaM4UaBV3d+sjB%0sMUs6dF*N}-xms`V{CaT%m*h#p@O z>BQbq6`f=qyyS0ry8-B=tf6jBpPis4XrLe+l{eb)ECZnKA49`I8v$CsCnT;z#CU*a z3rJ6pN9ZOU#7HD0wcJsit~-$nq-<+5xq1!z^C_`6szx(sQ!bfJfwoLDM^!hV!6YSJ z+0L#W|7eCMNd}#2)Rrn)R4P|t<_mHSDlSf8mDcyxcR%pilbomaJVaG_erwu*dH6n; zqfkc$7&t{y139)h%fUV|pyCnKR07)+)&mzNl~E!yFB_feQ(|~4lV8CVewB`IK~pJV z&M*5ev^{b(giYFsq`_n9ZtN>{C@9!j#P?p^RxU&>uHm3yb=kO%=F>&qmOf-m(WdU_ z|GyTDdlZ_dFE9Y<2rhwQ#LPA(L4NcFlH`}C(gvI9b*L6E0yhqi4ydqdDEI}QbYJ#w z6s3BOr4oJ1EEBU=s*~`r&>xDG?ao@fK z-5cUhSAgf=s%@m1wL)&1?g>1;v`GxC45skT;j)yN7-vDMotdI z3OSDKnsivlGMbhGKdZ2B)r5|NC4od58dXW%bW&>Fm^=Eey|!iZb?s;alW-ume{ME6 z^-@gBV6DY|joezuIF0uoWhvV7FGr*jd;7XXF#8r@)E{3E0EdqiKw}A+tfszOT1xAM zI@Yp=1WjEk8mu1Q_};EU1QG6i8p@7^)KpTH<|>_KzF@VKS?)}5?*^>Muh{Dbomv}C zZ)MM%Wl3xss_PQ69Hptk8=e64H@5$<)w6K{ka$v-q*jkReP%Hpze^vX@;;S^oiF#p zP^ZC<|BZbn$a_rk_ND!%!^nzsbP&HxMfr4&>`&zRfbmN4n7}mH0brX_P`(N#XNl#< zmlf3~Eab19m+!$p{M;v`C0hYbGa_hx+LXnSpxzr-XRM%bQN=*EL!~-s>=JoHgqoiD zmVUtXU2Q0#koE<;u(ea_d7+7=)KNo`nZe3H+js%Zapby%dzMdg8Q?dPc>0LC=XW%$ zA&94IY=F+HD-W#y=xdOp2alN6y9Fl0=p-sQ1-ZEslOzb)HC zFhk+y8%GUGuIY{$8=Ly=tk*N+t09D{jR&g)Q+MN9*#U%VFjBCoYKH{i_rn4lrfa>o z|Ip`>IH&N+O+v3&tywmNYXlqo#0uK=MYXTRWm&c7fih5AWF1K^{7`h}&tQ%WMSXlH zROqnOkl9@Ep_(hq0c+Lm%78cqD5!7Hhd0}Sm(MfNEQPfILeGVu3nP>A1{j(9C!*9% ze%Y-f92R*nz*5!ps^FtUL*f%R2QFQZ?qg>85EhKo2PkKZ?fG5MUQ(OS#3l1T7ru+F zj{*hHy1JjQSmy((?D|kgxB4pGy3VpoV$y(Rb%Ou@QQXk+LK+jk1>2b~=1%HZh4Dy`vziB=x^Yls~C#>020lv-;?LpQ~-2kH;EQQ~}+TdG)vi3@3};f$5i3CQ3^ zYuR*OoV=rykE7K;8F2*>kUmk|ppqG+Wg5r&D9;dTq!bzT=#>%e^-IZIqXezVLBrT& z@UWkNe@2~93z#=99oN6=eT_z!x91M{2FA`8&61U;EHu_+{`Z+zQ}A4Ix8FtM{{Ptf z%BU*4w@*+36#)eWk$R*XrKLqWr8}j&J5&UuyG!Xt>KwYeI}aeufkSuCMxXyXGi%M4 zS!>pOdOykWu6^(O>iAtNOJpgMtw<0u=ihwTrl^KTyoGbW!|`F5VD^;|{;*Ck`6BwK z;R!>C7GoQZuIm}L!o>aW6XTd5)NV}ssjS7%Bne6|c$O3=(!|DcO2obc5h<%vtQa7IKA^Y(eaz^nI_J}jXD6Qbc0+zw*m zGAIlpF_r2+duF^JU?lZXDB#CXv2-iSNV9zV=2n^iF}4MD^%w0|x+=}D5%*+(Z+p)n zGcHG)kIj}gk@-va5Iz_UmCi7B(sM-TG9gZ}QMBu+aG7*L>S^TK`ae}ldtf4`t3`*4 zS+Go=c!Y$kP>Ok=f!pk;I~OzWHnjn_M&IKy?9^)CuV?9YyHgdXu4(;7Bd5 zQBNYajdS@nDLd2>L`LZ_uqL%P^s?e#6x`!(UOu7E#8ZB2dT(B!9;#i)q>$wuuwA^h z1As!TH~iTQ%?dE+i+}q5Ts+rXiQ4Zbt;Os7rw1K@bJs%jRGxR}QP$xyB(hl|UGzI{ z_&}Bl{<|`5m=#psfJY=E?{IQ)LLo3%Td_LJuKal7>!>LA_aF(-0WAGk`b#2n8oQuR zBXSrK%_V)B-RXe|Lo6jl_-`$PR(VcOtlCKd8NuQV~m%VsU#5A;sxAif^%f2W!v zV6na%<#KXl>0(A?!t>d|Xs6GdrDS?=5%hQbgnWqO&}rE3oN3R2{281Vn#d2EoVz@B zFNsQTDcvkO^}5C)G@p3%M-UpQ=)qV!vgOej0_~u zxVm?()qPlQu+IR^jSYtx)EOOxcHyV4N>Mx8W1m86nCC2Aq}jL3u;Zzt0>tq%$*_Zg z&GV8S1T?JU?YpbxzgXO#7f|@|2zNjV06!N&KF*F8sq|(Fg7m&tlTDpz=v;hi6_F}?!{@{|?Ly{}xL_P%Q^5Mf!3Uv<6(a-(z0BoMwi+9SaqTkg#>?mqAtcx z7Vh2pH*2+T)_C~?zp_=^DTZ1|e#lm#W1_Vlgs`z7dTFc5)y!=)yBXI-q93sE$jN)W zci(K*?77VK`%s(xh#R+Q~3K z_SwGZ*lrDT=#Mw+#TV5Lh&{A|&l%X$hAv(%Jbc;)oh`WA`CHg`HO0zn^yJ?xXia%> zY$BfiLyFS#=9dCN5Pa)_=e%*kN9L;KaGTbp9fi%{(1NmOTlM$WOpd2na~su$2FzP8YrqpiD@lmitMf1)uah)UIlDowLgx;4CIVWA`=~L--eODx>>w0 zq42Eoza~BAJ$%bJ8Q@=ev~=X5hW6KsUuq+grCk-ylG{ChyStG|2W^?vp5IkS1!|R| zJSPJ+XDyG$!`L6Bm17Q=bH6bt)CN0vhdsU=$w}W%*ORs^itINANY8Cb2CVGrJspQ` zb)d7%O^4T_1pw(B^m`ENeE5N!-7XZc0m)L83yNq5Ii!L#^uAxITrXC#pbdEI`eu*v z#E0BJaTx@Uo~e9t8hIOS_`46)_Yv|b{mzas8ou{kUhRy)ro0!yLl7r4i6TRolRV}n zz-b$y`%$$Iokcs&O|=MfK(P&vM=x10xL%c2mnubaFlTN1%ctRr)FX*W-I!^U`wo+i zI-^egAkap=9LUdqa}}h(l>NB8Yf;Z7cl&ARwr@Ayo=ud*FQ^{V<~}t`@2c&7K7)kz zyBVdYim}v8y6~A}!9RB7>w@1h#(aCtmq=hdK;2j1FUGnr_YR@HWSDx=ZKq)<6Hr6Q_OlXKN8P8$@+TzJM)aIEAUWv3 zRqdt7&kapo0e$O~MVW5fCL9lD+K$`%mK__~j;r%g3SKioa1-)p~6CIl7WCx&<1X52k`&E#vUN_LjxZ=#tYs}e7C}f@Xbwd?wN6I)TQcH2O z@5phbWfo`MPTKAqrfOkfq9=v|)5=zU=+cfCgud1f%5fmbfuHk`W((P-W)v1iwI)-# zTTw^evY{)a)4mqLo2YoA7YM3Gxm#068=i-tQ=<$RvO;o68E$ctQBJ1Sa@yiRVIdk} zL=b9xV0Un+?$XP$2Q1o(0S4>|1Npxj?(l%Ge|wek#Dct)dyLE%#oYoGJE@PoZ|C<; z@)J&;GVmBE7WbN<@i=`{Eg{7Dbq{hzio)Y-6WX=!z)WCDZV)D?Ctnk;_MI}L>ZwtX zq3*g$rM9E=EZfxURP~agWyVx(C)$<#uvSu-H&`7L~=IWbY`erWU!GmxK~32z&7iUb+4*)M{62<(fbyUL}X z;gLm}Me|4C>eTss;;XQP>xoXUeV5lBizj>0%{g1R)I0IYWtBK63}X;0EhH7hLQ8V% z&Om<@Nl(RSGmZ4NM3d2HhT)ech{7#I(Uv79d#if5Ql5nb4U;ciMlm(CS+y)@o4N&_ z{#9|!`p$5O@O?)9JeGu3iqbtzYq7Wpi&>&;f(%-8*3}2kD_Px)daZ;a znk{{2M~%;IcIhlz@B$u?f|ir$Ee}Uwu6A6X!*;bG+>FQSp%Jg5dz~>OjdfER!Hgc2 zT^048Zs#3gx&VRG(F35LS%gfHvX}iqLC+*XDfZHS&(dK__!}bD{u5%5pkn z7n#LZcQwzs7b~;B)y6MFzNeECGlF>$ce|L_o+43@7eQsrt6(qxD|?McH8|!+ zi~&PUPFv{vaG(@l1+Ui{n-B=zCyWgUsRQv~->GuKGC1xZjYvO^bI=im)K{aT(C@qA z#}k2~RC=rwBn4zh)Cy?h$VQQ>9B05SnMGgDWEh*k-}&|hnc&GufLcy76!=D+pO()y zOV6e(>{dC4K*$4dzk9CM>Y`JxWx|WBFFz^D&<{W;$)#;>9HC)^Y0^bktoQ4W>w!j6(8#7d2(>HFoYbWxPa;=9VaWbohWgh0wIqJUyA;R;LdJ;Q%B>TbjyysI8lR36tBt z*F(=XO&(Q%$)4OFQXseJpCeeXN$>+qW61gL^>!B8eBL!fr#{c7gZUD!vgLgBYtI!S zXjja|Ll6cT2_qA}pijQTowea`BG`{%3k?X@5@b$NY`xD?3ST+0FjMxUZ$JJg8^G?S zw~Ia13HUvWu(o;x88d}GgT)xtGEhbJ3XN_Og2@`3`$~T3kNiRX{E+Q^ne~<{-`lqr z{HS=iS}K7}2@P4>3@Yq8rqv9HtLpvr)HJtwVkF;*rWtefVj9t?7M#iwaZ`?h@=sv4 zwfFU}Ei5Trm~;xVn}N$)fwy;pv`aaXfTUMiW{s*NVx5xmAPT3tJHUh9NSUd%+&HY# zxTMlL&3Kp3e3wt5wzgX|WBPF24sXDiDOohs$f4-v{q{2Yiuo^+g*TFgl8lZVV-vqJ z7Tfl^6QX?fo4Z#GSaGz9l`X#EdP{n1-QLt(U$$Iw`J@aC(U!xf4@(c%m)9e7zU!zC z4}7VdAlTeSKR)(VGCPJQzMyDAKe6#Rvp^scd|8b3jk6U-jeLDjbz0~5vRKWi&9lSw=8yHd5Ypk-r=N=*>&*L`*@5vnFxto1Bx7H98)pfdGR2n=eWjXGX?eq@pEG%q4pLag@G(l6N7amC4vea^al|i&J zo8DR}R@#f7i!z1mpj9l$6W7y3u_#7*Ctk;1O@MHwe38G#PD zXK4WD6J!+7$M8do`F=p4;H%MORtoN>AL4I6m)cIUrudR*Z*#v^Lk%)SC<6O8lf z=qF5psNO-g+DoF4qNl#1s1Lt+F2)K-O6F$0n}TiVFnd0FZQuw7DND&}`x&?2VW+be zzom_~X4GoV_&^Em=ntJ`SqcO3YRfQCKr@#(V3pLi*Rls#8-&yhpP@}JOnGZ{I=Vbv zd}nWmSOJEUkv$!{Z0u}J-TA?XZU4QlmL)iRbc%RTHQM_$e?g0-YfP9o(q!~+csQI$ zK)aoBALEJpAlRWN8Ja5%5zs;@9Z@%L=!8y9IRmRQ-hL{9+*0rKv)e7a!eJVPt$%h8 zvxlwXPV%n=toc+k6kgGB)4uzZ16)oi(Els1D|9?|dNg+I;Kvyr2u66}yDMNz{W9!-8T&0< z9`tLV5LKyQC`jb%NvOiU<7S9Zx%z-+2|nS_vTw@MU-zVdrvN5Yxqn*2m`yO0H5hc< zo?Mjk8+8TMg;C2?Dz5B1Aqd_vuUx41yZq#^ROedQSyiDr%6|oXUUOqQldf`eBe+=* z1TPO#@lWWV%VIh;asl>;g0>-AZY#M92GUD^P`#CM{+3l=v?B??h9y~ zMbgEK3L|ktg{6D<(H}cSKkutKzK<>;y{_P=omYFkncFbMmzW3essXsRB-@|bErFiYvPPVZ!)vc1PQ;Jo_0&@kl0D?z9*FXtQcPj ztMzyy*Xeb2Z>yFNa}rRlp@L4rW1|zNHFNrboj@s2ULkLv-tte{ciH$CTWz48mk9vt z>3;gh*>45~RB=G?or>l4@9C)bya_rZli4?X!4%^{8G0Xra}r?vb}LqHx4`-lEfi1u z*B0crsH33Mi*5^f(#Zkxv0M=zRWJ)NKuSM`p!~TuZ)JF-ZpEN_Mx$H@R^oUJwq&PF zXqpF@7wo>n&Vy0BRkahDEeT^h_1*B*3BF1nqd!9mt0btk=9%&sqL0g78^dK&I$Un0 z)}&%VO>sHP=(L831;_M%{%hVcQo`WDr-<*=OcL+ER{NuA&u}OEo}J0LFz=b4z>`&#jB*MLq2J&h!&9@o{VO zwYu({G*vbgPE=Qxu5zJ}!VmFiJOnOx$?15~i*MoiUoSoRKq;xb{iFVkFColaGzrqN z@>(D)dGes>A7c6{*LM4&*F#VDg(nJR*}x2?IR?4DvV@+1ON zfuGxXg4k8DO-p573F@$PwK^6%qc6$Ol*>RS%d^KeDH`{ncFrpoa#ww_LfVm-dbo)! zN}KX_*Qg-eJhvCZzLrP|Y|~@X&Xq*6>Jb)Mo#-kBQwo)OzFd&Ne^R?l_YJ8F!jZ!` z7u8U~7G8(S~@urM;F z7b4B;``hMIlP^ua4Uc16d>O9n8Jv5w0y1}`4c~8jHO&SJHBd24L8k6Hn4Rr{AV|=S3HYCloaak< z`wC}VdCjdWA7_6SXq0pqgE?Y@A$+F?N4>(LU#-ufDpwli9}@v=&6tBABSl$mx6eSm zYym_5K>|URD$7U9KPr9aJq8;WH-ac_UusZI!9EqfaS+c$7YR^V5$QyFWeg$jR{B*H z4a?hwrRGJqS|j>0NanjXQn4K*Pu6f{_|1i_xjrH?!!ws9Lj9w`_=A z@pXIADP9D)JMFL(*+HgIoweJ3Hw*{pgB4)VKkK zdwNC9X6lE|b^zGsSGab(>>#KT*`tn^kqRQ~OSE#1W7Bc^u#Qo{gLZI!WnNyALdg9t z=FQ>IVr*mnYCcH#iPx>m$foh}*%2;;9_(sg*SPIRPiq)yx{(?5Y%xorkii72G zv$3bKYY4;r{q~+Yw0drlXJiJaPo;(TrJ7Pe-(pJ?vLR0#;$v0IykGro{+7<-2}dv8m)YC4 zsesa{czQQjDu9Ldmh99J%9}1_5ulTe#mTnV;5*2{f=w9Wn*A+_xGPUfk`r4GB;`aEQkpd)ZSj8EYN`#wd6z05IlD;7Z|)jhM^WA ztus>Vv$o>r%7U#>)(htR(8rRRcRmV^{mk*()>Zd;3{J*--*OC~DdMH*YW91nUu$@P zY3I@%DnXG!TGKa7Q{{)wyDpS`Z@6vP-JITVZ3N>4f7*HIjIf4zi!W0YT*=5h%tP6G zevw9YYww^pMsHrTRb!24C}pXeA&L8W{u3Av1j!`P!q8dIANx%jT=QRzea8yLL-H7O zg)YnEQE+IX6Mv1Rr)9RV=|VQvMQ)BwUXCSh{`?g`#N!jE`E{jFp(jq8Z$-5dcG%X>nL1+YPd`8n>(p}-c@!<}9T(=L#1zT=fIv`13~G>80;F0BH6%20Ep=KO z0GZ3ZQBrTNe&fA}fKA)muLqLW{dQM!iR-v7NV5DEzKtTAdi(B*e^7KV$q>Wpkf7E| zb50UPwrE`>jhn@}gT7YNGlI_}pRK~_pY0h14X1m5V~>LQq1Za8oiPYIDa-f;sd#Y zcDUVzqhptwmjsumY>2I*T{fjxgzSjoa(m+-%2-VIR*7s=SYwXYpqp_z#WxF#s#Rd< zcmwlq{S(??Ak?uDAm$*K*I~PSOeW-Zb-SpbcjKMsE~&Ebf96|>O94G0T`GR?Co%9X zoT16tY0BM7k%kE`yzlA7YUZW8;uPL99k*HO?e?$6l$-oT9@^m_*(*^F_^g*M=v=>eI2o^n9%Pr5?lmlmp>E{s5Nj~x!};_dDqpH0koFDG0kXL zOWPnD#(!R|Bc>!zdfifZ0}bhnRv_su>9P?TJUn@xx&A&>MiT@u~uqLW{da5j3+G9YU>3JeCn1OS>p0UCopmL8 z3)Va5{Yq;o;M3uCTO0t}RY&%wMoh~Sh?-)n+8XMApiyATWal=`dP8w(gb=MsFVnoT zyPj>(f0(eoiiNac<1>?3RvTWUwe8gK{6LVn$3CVkXcye|KCU}O{9@BW9FhXOr@k92 z$DPX>kV3QT=cdV|v-k;`e6-VCJzeysOfh3f5$LtUOm+$KsZ4Lu_Fgr*(a(bkX&MW& z3X`J>3-`@I8^j(6nA*G)9+5S!viDxTQ!GibBAY}ZA^OYq_C2zqW>#B`MNA`9hJs>6 zU#L0`aR$>~az_kgNyiXVAFZ8m=*&88qt1<*S&_>P2MZ-82E|DJjZ|l5+vKpI>~DZ=Kxi@a-b-h5%ME5J4XTS`&6 zZoq&RFO}Z-dwWjt-9z>F7N3>6E$oEZazGU>9TTV+`7({1d45!fbtSnpsc-`1EC1JqGzR>|7byEk!PP2vt36DJ<{bj?GRJu-Ds4qfdx1-m^^NoE`-XN2CT6~CW{)68e>}wpg-DpXx=y;3)#Prr zT?F!FlC3wq&qTT@3`8Rb*LA=^E4-!hi~CT z-&zk1$K0(dGS9I03{T=eGr=1MEJS;SNgMh)qtDWPFfIo|U5w&fjHgyMTYI*0Nyn<)KQ&tm=LitCT53i%K7fgfu<3Wf@sP2)f1t* zMJYz^w2-9yd&E#<*)YPk4EL-j=I2 zp{YK3I)Bny-&{u7csL1VgBG)wR{T;j>y`KvU}i=5tm*Iwk>8Vs|k+7eXO0ndvY&uPPR?yvQV4#3s%v-inRcYoC_suE5G3pt*+;hn$H zUP&!JAzC@W8O-vFiXzLSiHW3@U7<~Gdgub%`9&4qzrIwxBv2PSJ4#?u0{uE{apj@^ zwyKYp7pg^U6s;-fMC;QXaLcvNuN{V!VA$VW)3C7H&`%$o-Qa4SnWgNZG4^B#^g0ut zjn39cPK=@ctIinZ5ArI+us~YqRc}Z!Az|An>^FQ%xd;7#SBo)ivT$l~WqmCManNy& zX!1q)K2z9gBHGiqbT7K^UU)55pY62%CMtnMS~}=~&pi<2&`+t-D*n-#X1^L0nkQw! zb=}{k;epXO=~*xa0J<2L;R#e!Vf_5JeritDJ6o3mvOmV@qkm+B$RL*Y(Z+oG&ktt0 z!_{P!Yjgjmtqh!X+v1vsVJO?@%x~+zt_O8)!%dXRBz58{{hr&O1_%#~T7aO2s(yX8a?l*)v6m#lqT zDX6HNHn|CZ(<7;KDvZ5H5jTh#YJi3sGuS)bd?jf66en(W8*X(PcwqNqP^(eFCnh*6 zTPHBZ-E|Qrpidq*m@tD~HB2F8`%H3BJbFCsI-{NhaRA*g6YSdgN)|x-^{*HH5P+?C zXp^t?t{mAd&k{X0TNMs_H#56kT>DZ#d#!^qWye=gyiIiR@haS)Jc=Ys#TFSR^5OQGeh)Gwp3p0MdYBY7OnJZB0jKGQeSC zNcN<0+8LknO^1iTe#OM*nFr4bb`@uxjKvZm|JCkK%VZ7$6i>!k;5rTAu5d?%tWw6g zt=b*h-Jd>Ijf09>^zqdp15Zd-73lirKx>XCbE{klcSS4ZxEBN8*+EP7Xz5`_o~eRT z)AET}A0FWCGV}k10K~FZJ_Q_g$1yj0=ygBu&-E{Ra{O+|K_d|j^yd7TjDFJYZ+ZGBG0$k9r!7sDI7{D8-G?mk-p+JcU(&G z!QapOtm(dwXu}N}8*Y{FzXUM-rn)=fsJwB2=TzUyXh3n%mz(fN+kMD+E(Qn=vw@_b zXUSDXb-Ch|af_yA;SXyiT;Uchm29$HX|4?HE?iDGljz24%o1`JV+~l9myD4}yx+nd z3^ zuvtE%$N_pOfkL z=U^?Ts`-NT6!z?2f>=qXit4W0OMHwt*u>A-_zk#3%QUpP9B zBT#hpp_x_2jrPJ%Ivy?Vj&@(IL-Bd{tf1qKqMf7lFrp{%Jwb`WtE+t|Ig?=_Ia$M_v!=(6YVI{W z?lmyvMz!}3U(ZU12zQTf2GZc!o@_f~#$m^Qs6{*?l}_b&u{r5$SpyXz%DuVOtz1u%iCx0XpHy*s>u=Yz`Y6ztlGP zP#8gf893Kf%1AwWn}P%>vHCu zf@Snh=Wv6Gv{AYLHTxA6XNW|G2x z!x&&kMEPoT@6`rN#ph?aBoag)jEutJ!t;w(!SOHfcwJSjB!YlIEXNbE`;bA0>S0?w zmkKe;k~(&RCoiGD&g>b>y(^pHzu03^`gwVRM(iSMDcq&>pS!aOSh?_U^TZM)bYX_9 z`gI(lzb)6N*|GVE!V2F$a&T6yCrUlRE!W2jPl_MF2r(QCGZ@6m2$wA;Z}@KiG||L5 z%-EXa@g2MvZ5HJiZdOs%&h-UJylPb|zsK({o#+u7W(qbx|D=>b9xu$p;Wal;s)DK1 zi;ir~>SVR`rtMQ8_t*}^^4_Er)l$#wv?)5-up0B+2|^fO+AEt1Xy?qV<@T1X=w{zz z!G|K`@y($20XwMgiMTG{06`lW;-NzRlTDCNpm0 zYznetu>CM{(X4iP63P%pvt??2qFrEsXCB6xzDvohwz_BMMV@mMw+LGa&U5})TF}quF=FDk_9~}1H!*++63B)oqR6uKBMi^jtx;&0q5a!%L z)9^DTb;1vsL&x<&$PVTpN%3d5SJEldB#gCP80E0I$Lq3$t1l%fxT~ZboJi5zGZUeG|2~}-vVCAX*hvN3qS~h zMehJS4r3iR-s>y6={U6H#IM{Nr`onn?#G4`FVHx@ib%H?`4M6CT8L&(tUjK*zC9s^ zwL9Uwu6>!$@Z$YnKjs^P`2g;4vWiSmTX*Efw`#Mx=T;xLd#G(+eVQ)`dwpR`U1scG zw(e)=^Qjr@s>FmuLGt0WG$?y~_#a_58QE>5?L~HYMVAn#ql2w9xm=2gi0BT6MQ|yI zgEfP3OaJw>a0~Xs9(?euGxeL>h57pS4#)LVWd6DhtC?7aX_j;;joJpwIz}gf5`+;> z#v?nL4Iu}1VYv+PFA(Z(l)#gp+mdqM$bJZa{2}YQfjOR&ju{}8v_6cVtk+#RUx zmRN|<8#@_jD9!>gkYu-1!;2iXH^TJ)AW=cFD%=0_=v)A4&~UBK=7x*KzTxWD`<96@ zli-t<++b7ad?)edwFZ{6HJd224P7Ke6VDVK38^B%b87=}>u!J2pT-!Vm7eR~$y?8V z_`9Z)I2dn48VUM2G>0K(#3V10vBUt*Bdqq1B{I_I-u_AB1y?5c_CW{t@nBqE1gzfD ze0LeE^VaQRSDFJER#(hs3AZY~kAy@&IX8Z}cb~xfP{r!fd1034;B=DrxTtuRo#V7G zjn95x7Axhl{`TbD`-%yV^44PK+RUCCsZ@zrT#+WE;bNsttbk0i&TFH)(9t3QK6?)d zNyT_)V}E)wO!J~!<5-qYl7r1*!PR|ccJ+n`PWd^hz4F8oPJJdnfu!98X-05cRc5OB&^lXja+EC#W7c^H>wi%$U2Lz zfGaZBsW6t2p|r&a2}u_N4sUdBExCckdLM^Duadl9F;zUS>PtI6TDm>oufDzF=f9jA z@xAtDc0O{6KFUF>@+~x*i6rP!>Rm{)AZS)g@z^hr*Z}WrE^!Je+VbAd>%U!sT3{Z%lE!-mbJ#Mc^u55O4I@4XN(QPDEuWK0M`aec5DA4mo z$*M35&fy{omtLyG4rY@Rd1iWTd^X4$DG^)I$k@xZ<;yjFBoCC78yy1+T7-n_86kmYk+H5-72Z}ir-B<=&(2iZeqiNL;rD)B-+blaxpsISMKVzDcrX(p0r{mq0s9yb;o}a5Mf_L1wG4rdzcyi#FUt{Vlsj=)l?Y4FH=DHDf zP;%Ryy+Eve8zg(|wY;U}3^|T$WaW0Qb28ne!t1%c)P$e%U#2WvUOAt7?(5wCZn?c^ zEVr&>xgDN9GD6~jZHAIx>~%KYQmv<+abt;!YI~hWiF#iL6n8IqyPcOe8{baru2Ftr zk9>%PRF-Gno4w<{v*T%_I|pqjy;)EDetXP!AmDskKL=fy7@yO+UGiY%U#K&@zVba+ zFkTBKPP^`Hjl*nkg8x23M4YbipHT-|ms@E~W{31AA!`;$g^-(tQm9YFQSjG6Iin?2 z%38!ok&sj~HjmF0NCs78+0aP(mG}$257cVR^NOVjYMtk2N7Jsh<`cFWwhEY%krK-| z?mJkPacaxZtujhUMZfz)LTco^nxWoroJr3)yz3w%;pxR8TeZ8rr-(iZHaB0UrnsK} z(D`plC4O()8zIZ$h(-^!voco&S#RvxOkN$xeCiHTm+H(&VidL3Amg3Xg}sX0TXnfR zlYFtaGcA)lR-z>?MH~_NjcK2M5gj(e90RG4y-K$Hvjz%^*3fxtUnY{iG_}_r(-o!b zUv5Gcu2+j^ttB~-p^?EMHJD*0AQAx&!@c%%qqMl{<;rs$aM?NQ-0&|r z^yG-|#-`>TOoEvs(quYV2xGbcO!o$ok1^^S(=JtMFYI!>*s-4A7L=b%9A{sC*66Ox zW|-@DL_$J}h0j!!o-U$I+_pp|-3*r#q+PPfq1(jt0Sp>z@JdL(?s)=kM?&I)qbhbY zsEo$oI^O;M%tof*sgWPG(8yy3o`h7DP;`+jB)4`^su^%c&`3>>na817dn>v%55O;* zAk{hAYTt;`T*c(VtOD>qNF4RQ$pRvWKg2k=Qsl1y34~D5uTSj#CsNe0LX)^6~hn zT=`cFp75@pEvn27)RKMTcgrvQhs+-PZZ)uUZe}|)=6`VEXYMy5$dAzdJCNd7sGqZC3$#y8`^$&>> zX274XAfxfY6wHQgOk7}rA^PRHOC4YzKlQ+8#C-z5)t@nYy<%Y5naWm{vZZHI>g3Qe z>k5bTdXt?40?j11`ipsUI5Rj;AW0fJXTJ`)9Epjk9Eqt6hm27MEw93+gbKb&7P|dV zO`fTbhiJmtCw09VE}GH)y=XpY9lCHkUfTUiLPL3@BC?H6q4pHlKQT)qQbTx>2tw|u zftiT>3Ou0d>ntkj1*%m({tw9**xttKvX9+|R-f^M8zU{)=1NeEviRM%`i$A*vJjiu z+cOg2_t=t1H9u;(-OfHWy}2|XqVfGy`d@BaI z{-KzM;&=KC>1kvI3i#(A@;_$@h~4oV(&z9yMnXb*E&hk71tTGMzrK>RQ)@v5_Dg`ufZviPSX%1&>B?v&`<+Pgu47RqDZjZR`I_<_;2tLBUS2mlH#ZK3hD8pBMcE7? zE{0~O^GhGg!Gvj6^}u3o3-OWINo~ovJ7G6tQL~=Py<5wqr8Yeys}YI+g8;c#tgeXb zUFwko4WGSlKzfNpy*97Qo4+@=pKTIYXcDL?D^sp1^Vtl{k`}7^?@>F3bN>xf-KNc6W!Fa|*OeI{8D1d27rki`TN*e*RIUS}^Wt z>*C43`W0|&crRQ2;N$}5fnJSZtY*Hmv*>YZ@rpOi^jnSH&?Ez`Nsk&Cqqc2qsEq7n z9W}3cU6SF1Ca)LM)`4HFv`n%^;A|FMpj!&tG!93%W<9r6V%3+f#Et-k-DAJlx8=uG z;>9QCP1%malZ{T+e>qcmG*+aJxzgR*Hdn1C3s^hClLQcP$w;BT}X=w$Mm+Z%xTLvOmRww&?h!p7Y38yLZ8p60diT$X}+62y(V7n-P9fWSb zuNGAtMPY1Y1hqh@?Y4Et4>rUHmAvAxK4SaF-e`R*&4b!1nD?5w#xnY)1J3l`h3sIPwc+dzEWS7j zpCpA>hxfXjg9Mfc7U}J{vYc{iRlRkB0q2_D+u4_$JU)TN%|?PV*9Qh0T#pb?;_6x| zxR(%w@ZAY~Erj>_l+(5>%k2Wzw;o5_a2x8t`|VE7WmL9^*`5iRvdYn)h6SkKkrTb@ zC{e<}2X`uYajZXf%>awV6L8@F&K42Oc64^kl584>&(<+&kxEXSUNrR=A8%F2h*)Ya zL@^?(bWS35g%-Qj6W?;W9c>hA)g~r^ryx}+7dZ&e2>K~vJrBAp*cbG=GyWQ?OYyo`5ss3_VGD*ZV_mbtXwQTA6Jy zd#YnjpXy=ivEqzLKi5xNKz!y^ARGx%H3^Q-h8J#r*$?pTP@Q1iFOJy1Ki*-d!D8z} zu`XPAJvPKjY+b+6y*{us z4ptt$GOq2iidT{HUNXtFdy@^SK&SQgV*;W;ra`rP7vG99sA=_2eL5c|o@(-t1)X9{%$!Bf5wnAB<&)?;)41Iew<|Ie(j}@j>7L}M2>34Yp7#VrO%BV9;4+se zC*-d>V?i1`S5fWcR+T1?QslWOHougZmSvWeD5_m)mJlXd-A=>|o{Em=1!5f%&^0(| z)={ecFlCkmi#Rr5=-FmuEfI(v0*~W;Be!E+Ut*dVDye-ak;j?f!D0SDZ;<^^LV8pW zNIV_Hl>lG9Qk2mMEB?sC_8C6sNTYm0GtC}y6;_`h@2RC4v)A(F4 zPW?Se;W38>;0=uSn}ZFL!x9Y#?Zd&wNyU#L1Qh%gP}dQu;N!TUB1yM0-5Q6D+5Qe1 z%yrtV6VBi#-%DO*@MgdtJ}mnQoGZ@C+ISC+g4j;cppHxfp$uJHNAFU6VvEU%g|G~`=rPM9as(*y&Vi++ENO&a$J#4ne8d41GsHj$DnvW2UN78N5gd-+ue zbL^3Y^v#JpEUIKDP3&eT-Ly=1aaXUjl&EtFRZJc1tN2K1u2#mnoRw%@>9Ag-)=0^! z+W~N>65{9(14=pB8giZ^)5VrmWE_IW0=A3Gbs^c^#Vt`j+iVVz|Ijzq+H9vi(@cX{ ztCpS}yyeiexEf={&oHFP*s$ULJ^k^Kl!tq)<`fd@4%-P50%>_(L#KNl-HA0 z+K)U(%AGBC1tD&nBE}b)okXFDO{ao;`FI4k%v$`*My6GlKFvp~?*_?E$7T9yZvnei zcFPwG+Q@TzzTKup;19^gjeZf9?8zV1OQhs}<(rEu>1m#b8PvGM82ipddp2j($s}<= za&t*%5sNl4yZqID&r&dZ$kIRPlY!uZM4V!V=RAOXBMDv+Yi_)pKZBX}SJpVxY z2tL|0A5|)uTqY3>Bc7`?SFy)&P|RXYjE>b*-u)r>HuHR;{w-!%X?srG^VwQI(?l6{kK>ZP3$Q+O^AzCBPCPjUZzLBo znE2u`)HHD*UmCZw7kyzQ*6Z02Ys%P(mD4$gf%NFJ?q2O$1WJiaC|+;>p852;j61iM zlkLT-Iy~^NZ~IxfM*pu*@c-Gp70?~OpVh5i_Hmkni;GXq(xT2RW~4!)<{?s{G;p;4 z(a1*&%#e&O=6BDP?&wtCztL$ptpP$Y?~5R#R;`oo;>|&B6AIGAoeLlS-nTR$yHrq- zM$7&*90iEg<);`iBO50B0<#gZ2#hRw+Ht=|j%Znx649H4#TEw|k0%e1VAOZd>3!Vl zejvB4`bl%()kofs#Vby?7+ermibluP_O1SSq|Y)@z{58e{e&3&N|C}p(@DbMq^m|q zr%1!*rF=@oA!+@~gIsRp-0*#=noE}H&nt;7RJvpCJmu{C^EuyDA`RTMlO;U@Sx&xz zB_9Y0YaN3V^==&$s(GSm0g;w_s6MDwlHhxk?rGzv~s}vT<7f6k#!$Pyr zN@9W*!bAxCi3kc~J7>dQ@tYjR?~|?3WkJ4E0WUGX)4>Y)bLE|{YM=t*$mzMfrltuFev!U8<`6GHijVw!)&De8So2^o7;`?4a>x1fhe|5@$d?j?;mO z+|(~{x8RSL$wDewZ$|2DD|z_bSftW43ntQgQ7Mp-%)bGeR>fi5vKWcaGcgsPA1L{*R_Z=pk5kU7ucPZ%>U!a{-r#U1D<447=)Na`FF~eFg%5S|*TatjGp@5B*BEU9R7%jwSX9z3V@IDVlbo(R76 zyC787atv<4HhaNH#YoC#_sodKJtXshyG4=NeQ2+5mHYH~UDdSa4Z9qn+1fMHggBux z&!4p0^5;KyG1kpj&u)SggqX~p7pBOBDZofDcI!9gq%0%HjHdhgeLiIj3mxXJnw08W zeb7V9`oF48Y?RqTrdz!pH?q`4(q-7ppWNCH%McCQnW-$OeuVUSO9kY~IDfG!Re#<5 zqMw1f_kuLVU@~AaAi^BW9qDtZSr**|AixJoFX?vpAervHm3h&^3`oB^?tJNcz5Fb( zn6@>Cn9<%fd{|L>w+|9iyYPe@eGpX#*UuC99Objq6NG-bPg zb=>|e%QL1(JTo?C4}-(3v|N*s*83bU`NuDj+Q%o^?< zncUo8ASQ_u0kymrgVYxoJ!9Xz6Bb^9t(SE8pJudq-Hr zd)39HpZH#qG+Nt}d7HqNeHeVO*svOZ!MDRQf`*9}zVD7tC4b-5 z_TrzMiiB-$uVoOX!cH@)n``I2ZW?b5=6-(|9`WZqJ#nxc%e9NBQvOavW;pF$ILz&U=hg#^G!(p`jrmEV7o+YyB(~ zLIp*<)@QL+jLhLYI0}u5p*yCiKFkxmIFcbL?0e#|y;&1%AxpAe8?sQp`nY6#PUF&O zpiPwjYNxy5l0+@>M3d!Dv=?^d^nBza8NQGGL5%1B*hcZV`7b0aukwwq0Er}f<#pt=s&-;&I!&RFpNhjn=13e}f^lf1lE%(44X zb1U%a%egOgr+NQsTe5Cd!kcfqC)X)0x9fUW|Ky_Er=lN^XUfL!o>g79(p~@AV&=?R~j!`T6hP`EI3K;1p0={86)cK~BzX=kN3X zf8?K(wPoXyS8o@W$5vFox|;I$(pzi0s`OQXOUiElVXy!Acx4*r?Z$TYbN>GWtNM@K zJIlPYRkyg-+HUWTOwXxzj%?fcDqiMhz>ljx949-=-i-Kh_1KBUKX&esw4a``^RJ>* zXwhtT%ei{n#FzEH|C;yZ>+$!u_x#*+`=L8{b9SH^9&27u3G_Gxqxe`L2UJtdxghk z&-wzDFvLvW{chK5u3{n6GSKKy!P&C6w^IFpbD0bcp^A{{2lcLh_DXj@ybtYvc^;(2 M)78&qol`;+0Fu7JivR!s literal 0 HcmV?d00001 diff --git a/docs/output.md b/docs/output.md index 930f94bc2..527d10dce 100644 --- a/docs/output.md +++ b/docs/output.md @@ -10,50 +10,59 @@ The directories listed below will be created in the results directory after the ## Pipeline overview -The pipeline is built using [Nextflow](https://www.nextflow.io/) -and processes data using the following steps: +The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes data using the following steps: -* [FastQC](#fastqc) - Read quality control -* [MultiQC](#multiqc) - Aggregate report describing results from the whole pipeline +* [FastQC](#fastqc) - Raw read QC +* [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline * [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution -## FastQC +### FastQC -[FastQC](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/) gives general quality metrics about your sequenced reads. It provides information about the quality score distribution across your reads, per base sequence content (%A/T/G/C), adapter contamination and overrepresented sequences. +
+Output files -For further reading and documentation see the [FastQC help pages](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/). +* `fastqc/` + * `*_fastqc.html`: FastQC report containing quality metrics. + * `*_fastqc.zip`: Zip archive containing the FastQC report, tab-delimited data file and plot images. -**Output files:** +
-* `fastqc/` - * `*_fastqc.html`: FastQC report containing quality metrics for your untrimmed raw fastq files. -* `fastqc/zips/` - * `*_fastqc.zip`: Zip archive containing the FastQC report, tab-delimited data file and plot images. +[FastQC](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/) gives general quality metrics about your sequenced reads. It provides information about the quality score distribution across your reads, per base sequence content (%A/T/G/C), adapter contamination and overrepresented sequences. For further reading and documentation see the [FastQC help pages](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/). -> **NB:** The FastQC plots displayed in the MultiQC report shows _untrimmed_ reads. They may contain adapter sequence and potentially regions with low quality. +![MultiQC - FastQC sequence counts plot](images/mqc_fastqc_counts.png) -## MultiQC +![MultiQC - FastQC mean quality scores plot](images/mqc_fastqc_quality.png) -[MultiQC](http://multiqc.info) is a visualization tool that generates a single HTML report summarizing all samples in your project. Most of the pipeline QC results are visualised in the report and further statistics are available in the report data directory. +![MultiQC - FastQC adapter content plot](images/mqc_fastqc_adapter.png) -The pipeline has special steps which also allow the software versions to be reported in the MultiQC output for future traceability. +> **NB:** The FastQC plots displayed in the MultiQC report shows _untrimmed_ reads. They may contain adapter sequence and potentially regions with low quality. -For more information about how to use MultiQC reports, see [https://multiqc.info](https://multiqc.info). +### MultiQC -**Output files:** +
+Output files * `multiqc/` - * `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser. - * `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline. - * `multiqc_plots/`: directory containing static images from the report in various formats. + * `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser. + * `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline. + * `multiqc_plots/`: directory containing static images from the report in various formats. -## Pipeline information +
-[Nextflow](https://www.nextflow.io/docs/latest/tracing.html) provides excellent functionality for generating various reports relevant to the running and execution of the pipeline. This will allow you to troubleshoot errors with the running of the pipeline, and also provide you with other information such as launch commands, run times and resource usage. +[MultiQC](http://multiqc.info) is a visualization tool that generates a single HTML report summarising all samples in your project. Most of the pipeline QC results are visualised in the report and further statistics are available in the report data directory. -**Output files:** +Results generated by MultiQC collate pipeline QC from supported tools e.g. FastQC. The pipeline has special steps which also allow the software versions to be reported in the MultiQC output for future traceability. For more information about how to use MultiQC reports, see . + +### Pipeline information + +
+Output files * `pipeline_info/` - * Reports generated by Nextflow: `execution_report.html`, `execution_timeline.html`, `execution_trace.txt` and `pipeline_dag.dot`/`pipeline_dag.svg`. - * Reports generated by the pipeline: `pipeline_report.html`, `pipeline_report.txt` and `software_versions.csv`. - * Documentation for interpretation of results in HTML format: `results_description.html`. + * Reports generated by Nextflow: `execution_report.html`, `execution_timeline.html`, `execution_trace.txt` and `pipeline_dag.dot`/`pipeline_dag.svg`. + * Reports generated by the pipeline: `pipeline_report.html`, `pipeline_report.txt` and `software_versions.tsv`. + * Reformatted samplesheet files used as input to the pipeline: `samplesheet.valid.csv`. + +
+ +[Nextflow](https://www.nextflow.io/docs/latest/tracing.html) provides excellent functionality for generating various reports relevant to the running and execution of the pipeline. This will allow you to troubleshoot errors with the running of the pipeline, and also provide you with other information such as launch commands, run times and resource usage. diff --git a/docs/usage.md b/docs/usage.md index 1bf8e8ddc..8a6fdd7f2 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -8,19 +8,63 @@ +## Samplesheet input + +You will need to create a samplesheet with information about the samples you would like to analyse before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row as shown in the examples below. + +```console +--input '[path to samplesheet file]' +``` + +### Multiple runs of the same sample + +The `sample` identifiers have to be the same when you have re-sequenced the same sample more than once e.g. to increase sequencing depth. The pipeline will concatenate the raw reads before performing any downstream analysis. Below is an example for the same sample sequenced across 3 lanes: + +```console +sample,fastq_1,fastq_2 +CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz +CONTROL_REP1,AEG588A1_S1_L003_R1_001.fastq.gz,AEG588A1_S1_L003_R2_001.fastq.gz +CONTROL_REP1,AEG588A1_S1_L004_R1_001.fastq.gz,AEG588A1_S1_L004_R2_001.fastq.gz +``` + +### Full samplesheet + +The pipeline will auto-detect whether a sample is single- or paired-end using the information provided in the samplesheet. The samplesheet can have as many columns as you desire, however, there is a strict requirement for the first 3 columns to match those defined in the table below. + +A final samplesheet file consisting of both single- and paired-end data may look something like the one below. This is for 6 samples, where `TREATMENT_REP3` has been sequenced twice. + +```console +sample,fastq_1,fastq_2 +CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz +CONTROL_REP2,AEG588A2_S2_L002_R1_001.fastq.gz,AEG588A2_S2_L002_R2_001.fastq.gz +CONTROL_REP3,AEG588A3_S3_L002_R1_001.fastq.gz,AEG588A3_S3_L002_R2_001.fastq.gz +TREATMENT_REP1,AEG588A4_S4_L003_R1_001.fastq.gz, +TREATMENT_REP2,AEG588A5_S5_L003_R1_001.fastq.gz, +TREATMENT_REP3,AEG588A6_S6_L003_R1_001.fastq.gz, +TREATMENT_REP3,AEG588A6_S6_L004_R1_001.fastq.gz, +``` + +| Column | Description | +|----------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| `sample` | Custom sample name. This entry will be identical for multiple sequencing libraries/runs from the same sample. Spaces in sample names are automatically converted to underscores (`_`). | +| `fastq_1` | Full path to FastQ file for Illumina short reads 1. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz". | +| `fastq_2` | Full path to FastQ file for Illumina short reads 2. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz". | + +An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline. + ## Running the pipeline The typical command for running the pipeline is as follows: -```bash -nextflow run nf-core/rnaseq --input '*_R{1,2}.fastq.gz' -profile docker +```console +nextflow run nf-core/rnaseq --input samplesheet.csv --genome GRCh37 -profile docker ``` This will launch the pipeline with the `docker` configuration profile. See below for more information about profiles. Note that the pipeline will create the following files in your working directory: -```bash +```console work # Directory containing the nextflow working files results # Finished results (configurable, see below) .nextflow_log # Log file from Nextflow @@ -31,13 +75,13 @@ results # Finished results (configurable, see below) When you run the above command, Nextflow automatically pulls the pipeline code from GitHub and stores it as a cached version. When running the pipeline after this, it will always use the cached version if available - even if the pipeline has been updated since. To make sure that you're running the latest version of the pipeline, make sure that you regularly update the cached version of the pipeline: -```bash +```console nextflow pull nf-core/rnaseq ``` ### Reproducibility -It's a good idea to specify a pipeline version when running the pipeline on your data. This ensures that a specific version of the pipeline code and software are used when you run your pipeline. If you keep using the same tag, you'll be running the same version of the pipeline, even if there have been changes to the code since. +It is a good idea to specify a pipeline version when running the pipeline on your data. This ensures that a specific version of the pipeline code and software are used when you run your pipeline. If you keep using the same tag, you'll be running the same version of the pipeline, even if there have been changes to the code since. First, go to the [nf-core/rnaseq releases page](https://github.com/nf-core/rnaseq/releases) and find the latest version number - numeric only (eg. `1.3.1`). Then specify this when running the pipeline with `-r` (one hyphen) - eg. `-r 1.3.1`. @@ -51,7 +95,7 @@ This version number will be logged in reports when you run the pipeline, so that Use this parameter to choose a configuration profile. Profiles can give configuration presets for different compute environments. -Several generic profiles are bundled with the pipeline which instruct the pipeline to use software packaged using different methods (Docker, Singularity, Podman, Shifter, Charliecloud, Conda) - see below. +Several generic profiles are bundled with the pipeline which instruct the pipeline to use software packaged using different methods (Docker, Singularity, Podman, Shifter, Charliecloud, Conda) - see below. When using Biocontainers, most of these software packaging methods pull Docker containers from quay.io e.g [FastQC](https://quay.io/repository/biocontainers/fastqc) except for Singularity which directly downloads Singularity images via https hosted by the [Galaxy project](https://depot.galaxyproject.org/singularity/) and Conda which downloads and installs software locally from [Bioconda](https://bioconda.github.io/). > We highly recommend the use of Docker or Singularity containers for full pipeline reproducibility, however when this is not possible, Conda is also supported. @@ -63,27 +107,20 @@ They are loaded in sequence, so later profiles can overwrite earlier profiles. If `-profile` is not specified, the pipeline will run locally and expect all software to be installed and available on the `PATH`. This is _not_ recommended. * `docker` - * A generic configuration profile to be used with [Docker](https://docker.com/) - * Pulls software from Docker Hub: [`nfcore/rnaseq`](https://hub.docker.com/r/nfcore/rnaseq/) + * A generic configuration profile to be used with [Docker](https://docker.com/) * `singularity` - * A generic configuration profile to be used with [Singularity](https://sylabs.io/docs/) - * Pulls software from Docker Hub: [`nfcore/rnaseq`](https://hub.docker.com/r/nfcore/rnaseq/) + * A generic configuration profile to be used with [Singularity](https://sylabs.io/docs/) * `podman` - * A generic configuration profile to be used with [Podman](https://podman.io/) - * Pulls software from Docker Hub: [`nfcore/rnaseq`](https://hub.docker.com/r/nfcore/rnaseq/) + * A generic configuration profile to be used with [Podman](https://podman.io/) * `shifter` - * A generic configuration profile to be used with [Shifter](https://nersc.gitlab.io/development/shifter/how-to-use/) - * Pulls software from Docker Hub: [`nfcore/rnaseq`](https://hub.docker.com/r/nfcore/rnaseq/) + * A generic configuration profile to be used with [Shifter](https://nersc.gitlab.io/development/shifter/how-to-use/) * `charliecloud` - * A generic configuration profile to be used with [Charliecloud](https://hpc.github.io/charliecloud/) - * Pulls software from Docker Hub: [`nfcore/rnaseq`](https://hub.docker.com/r/nfcore/rnaseq/) + * A generic configuration profile to be used with [Charliecloud](https://hpc.github.io/charliecloud/) * `conda` - * Please only use Conda as a last resort i.e. when it's not possible to run the pipeline with Docker, Singularity, Podman, Shifter or Charliecloud. - * A generic configuration profile to be used with [Conda](https://conda.io/docs/) - * Pulls most software from [Bioconda](https://bioconda.github.io/) + * A generic configuration profile to be used with [Conda](https://conda.io/docs/). Please only use Conda as a last resort i.e. when it's not possible to run the pipeline with Docker, Singularity, Podman, Shifter or Charliecloud. * `test` - * A profile with a complete configuration for automated testing - * Includes links to test data so needs no other parameters + * A profile with a complete configuration for automated testing + * Includes links to test data so needs no other parameters ### `-resume` @@ -95,29 +132,140 @@ You can also supply a run name to resume a specific run: `-resume [run-name]`. U Specify the path to a specific config file (this is a core Nextflow command). See the [nf-core website documentation](https://nf-co.re/usage/configuration) for more information. -#### Custom resource requests +## Custom configuration + +### Resource requests + +Whilst the default requirements set within the pipeline will hopefully work for most people and with most input data, you may find that you want to customise the compute resources that the pipeline requests. Each step in the pipeline has a default set of requirements for number of CPUs, memory and time. For most of the steps in the pipeline, if the job exits with any of the error codes specified [here](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/conf/base.config#L18) it will automatically be resubmitted with higher requests (2 x original, then 3 x original). If it still fails after the third attempt then the pipeline execution is stopped. + +For example, if the nf-core/rnaseq pipeline is failing after multiple re-submissions of the `STAR_ALIGN` process due to an exit code of `137` this would indicate that there is an out of memory issue: + +```console +[62/149eb0] NOTE: Process `RNASEQ:ALIGN_STAR:STAR_ALIGN (WT_REP1)` terminated with an error exit status (137) -- Execution is retried (1) +Error executing process > 'RNASEQ:ALIGN_STAR:STAR_ALIGN (WT_REP1)' + +Caused by: + Process `RNASEQ:ALIGN_STAR:STAR_ALIGN (WT_REP1)` terminated with an error exit status (137) -Each step in the pipeline has a default set of requirements for number of CPUs, memory and time. For most of the steps in the pipeline, if the job exits with an error code of `143` (exceeded requested resources) it will automatically resubmit with higher requests (2 x original, then 3 x original). If it still fails after three times then the pipeline is stopped. +Command executed: + STAR \ + --genomeDir star \ + --readFilesIn WT_REP1_trimmed.fq.gz \ + --runThreadN 2 \ + --outFileNamePrefix WT_REP1. \ + -Whilst these default requirements will hopefully work for most people with most data, you may find that you want to customise the compute resources that the pipeline requests. You can do this by creating a custom config file. For example, to give the workflow process `star` 32GB of memory, you could use the following config: +Command exit status: + 137 + +Command output: + (empty) + +Command error: + .command.sh: line 9: 30 Killed STAR --genomeDir star --readFilesIn WT_REP1_trimmed.fq.gz --runThreadN 2 --outFileNamePrefix WT_REP1. +Work dir: + /home/pipelinetest/work/9d/172ca5881234073e8d76f2a19c88fb + +Tip: you can replicate the issue by changing to the process work dir and entering the command `bash .command.run` +``` + +To bypass this error you would need to find exactly which resources are set by the `STAR_ALIGN` process. The quickest way is to search for `process STAR_ALIGN` in the [nf-core/rnaseq Github repo](https://github.com/nf-core/rnaseq/search?q=process+STAR_ALIGN). We have standardised the structure of Nextflow DSL2 pipelines such that all module files will be present in the `modules/` directory and so based on the search results the file we want is `modules/nf-core/software/star/align/main.nf`. If you click on the link to that file you will notice that there is a `label` directive at the top of the module that is set to [`label process_high`](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/modules/nf-core/software/star/align/main.nf#L9). The [Nextflow `label`](https://www.nextflow.io/docs/latest/process.html#label) directive allows us to organise workflow processes in separate groups which can be referenced in a configuration file to select and configure subset of processes having similar computing requirements. The default values for the `process_high` label are set in the pipeline's [`base.config`](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/conf/base.config#L33-L37) which in this case is defined as 72GB. Providing you haven't set any other standard nf-core parameters to __cap__ the [maximum resources](https://nf-co.re/usage/configuration#max-resources) used by the pipeline then we can try and bypass the `STAR_ALIGN` process failure by creating a custom config file that sets at least 72GB of memory, in this case increased to 100GB. The custom config below can then be provided to the pipeline via the [`-c`](#-c) parameter as highlighted in previous sections. ```nextflow process { - withName: star { - memory = 32.GB - } + withName: STAR_ALIGN { + memory = 100.GB + } } ``` -To find the exact name of a process you wish to modify the compute resources, check the live-status of a nextflow run displayed on your terminal or check the nextflow error for a line like so: `Error executing process > 'bwa'`. In this case the name to specify in the custom config file is `bwa`. +> **NB:** We specify just the process name i.e. `STAR_ALIGN` in the config file and not the full task name string that is printed to screen in the error message or on the terminal whilst the pipeline is running i.e. `RNASEQ:ALIGN_STAR:STAR_ALIGN`. You may get a warning suggesting that the process selector isn't recognised but you can ignore that if the process name has been specified correctly. This is something that needs to be fixed upstream in core Nextflow. + +### Tool-specific options + +For the ultimate flexibility, we have implemented and are using Nextflow DSL2 modules in a way where it is possible for both developers and users to change tool-specific command-line arguments (e.g. providing an additional command-line argument to the `STAR_ALIGN` process) as well as publishing options (e.g. saving files produced by the `STAR_ALIGN` process that aren't saved by default by the pipeline). In the majority of instances, as a user you won't have to change the default options set by the pipeline developer(s), however, there may be edge cases where creating a simple custom config file can improve the behaviour of the pipeline if for example it is failing due to a weird error that requires setting a tool-specific parameter to deal with smaller / larger genomes. + +The command-line arguments passed to STAR in the `STAR_ALIGN` module are a combination of: + +* Mandatory arguments or those that need to be evaluated within the scope of the module, as supplied in the [`script`](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/modules/nf-core/software/star/align/main.nf#L49-L55) section of the module file. + +* An [`options.args`](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/modules/nf-core/software/star/align/main.nf#L56) string of non-mandatory parameters that is set to be empty by default in the module but can be overwritten when including the module in the sub-workflow / workflow context via the `addParams` Nextflow option. + +The nf-core/rnaseq pipeline has a sub-workflow (see [terminology](https://github.com/nf-core/modules#terminology)) specifically to align reads with STAR and to sort, index and generate some basic stats on the resulting BAM files using SAMtools. At the top of this file we import the `STAR_ALIGN` module via the Nextflow [`include`](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/subworkflows/nf-core/align_star.nf#L10) keyword and by default the options passed to the module via the `addParams` option are set as an empty Groovy map [here](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/subworkflows/nf-core/align_star.nf#L5); this in turn means `options.args` will be set to empty by default in the module file too. This is an intentional design choice and allows us to implement well-written sub-workflows composed of a chain of tools that by default run with the bare minimum parameter set for any given tool in order to make it much easier to share across pipelines and to provide the flexibility for users and developers to customise any non-mandatory arguments. + +When including the sub-workflow above in the main pipeline workflow we use the same `include` statement, however, we now have the ability to overwrite options for each of the tools in the sub-workflow including the [`align_options`](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/workflows/rnaseq.nf#L225) variable that will be used specifically to overwrite the optional arguments passed to the `STAR_ALIGN` module. In this case, the options to be provided to `STAR_ALIGN` have been assigned sensible defaults by the developer(s) in the pipeline's [`modules.config`](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/conf/modules.config#L70-L74) and can be accessed and customised in the [workflow context](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/workflows/rnaseq.nf#L201-L204) too before eventually passing them to the sub-workflow as a Groovy map called `star_align_options`. These options will then be propagated from `workflow -> sub-workflow -> module`. + +As mentioned at the beginning of this section it may also be necessary for users to overwrite the options passed to modules to be able to customise specific aspects of the way in which a particular tool is executed by the pipeline. Given that all of the default module options are stored in the pipeline's `modules.config` as a [`params` variable](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/conf/modules.config#L24-L25) it is also possible to overwrite any of these options via a custom config file. + +Say for example we want to append an additional, non-mandatory parameter (i.e. `--outFilterMismatchNmax 16`) to the arguments passed to the `STAR_ALIGN` module. Firstly, we need to copy across the default `args` specified in the [`modules.config`](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/conf/modules.config#L71) and create a custom config file that is a composite of the default `args` as well as the additional options you would like to provide. This is very important because Nextflow will overwrite the default value of `args` that you provide via the custom config. + +As you will see in the example below, we have: + +* appended `--outFilterMismatchNmax 16` to the default `args` used by the module. +* changed the default `publish_dir` value to where the files will eventually be published in the main results directory. +* appended `'bam':''` to the default value of `publish_files` so that the BAM files generated by the process will also be saved in the top-level results directory for the module. Note: `'out':'log'` means any file/directory ending in `out` will now be saved in a separate directory called `my_star_directory/log/`. + +```nextflow +params { + modules { + 'star_align' { + args = "--quantMode TranscriptomeSAM --twopassMode Basic --outSAMtype BAM Unsorted --readFilesCommand zcat --runRNGseed 0 --outFilterMultimapNmax 20 --alignSJDBoverhangMin 1 --outSAMattributes NH HI AS NM MD --quantTranscriptomeBan Singleend --outFilterMismatchNmax 16" + publish_dir = "my_star_directory" + publish_files = ['out':'log', 'tab':'log', 'bam':''] + } + } +} +``` + +### Updating containers + +The [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html) implementation of this pipeline uses one container per process which makes it much easier to maintain and update software dependencies. If for some reason you need to use a different version of a particular tool with the pipeline then you just need to identify the `process` name and override the Nextflow `container` definition for that process using the `withName` declaration. For example, in the [nf-core/viralrecon](https://nf-co.re/viralrecon) pipeline a tool called [Pangolin](https://github.com/cov-lineages/pangolin) has been used during the COVID-19 pandemic to assign lineages to SARS-CoV-2 genome sequenced samples. Given that the lineage assignments change quite frequently it doesn't make sense to re-release the nf-core/viralrecon everytime a new version of Pangolin has been released. However, you can override the default container used by the pipeline by creating a custom config file and passing it as a command-line argument via `-c custom.config`. + +1. Check the default version used by the pipeline in the module file for [Pangolin](https://github.com/nf-core/viralrecon/blob/a85d5969f9025409e3618d6c280ef15ce417df65/modules/nf-core/software/pangolin/main.nf#L14-L19) +2. Find the latest version of the Biocontainer available on [Quay.io](https://quay.io/repository/biocontainers/pangolin?tag=latest&tab=tags) +3. Create the custom config accordingly: + + * For Docker: + + ```nextflow + process { + withName: PANGOLIN { + container = 'quay.io/biocontainers/pangolin:3.0.5--pyhdfd78af_0' + } + } + ``` + + * For Singularity: + + ```nextflow + process { + withName: PANGOLIN { + container = 'https://depot.galaxyproject.org/singularity/pangolin:3.0.5--pyhdfd78af_0' + } + } + ``` + + * For Conda: + + ```nextflow + process { + withName: PANGOLIN { + conda = 'bioconda::pangolin=3.0.5' + } + } + ``` + +> **NB:** If you wish to periodically update individual tool-specific results (e.g. Pangolin) generated by the pipeline then you must ensure to keep the `work/` directory otherwise the `-resume` ability of the pipeline will be compromised and it will restart from scratch. + +### nf-core/configs -See the main [Nextflow documentation](https://www.nextflow.io/docs/latest/config.html) for more information. +In most cases, you will only need to create a custom config as a one-off but if you and others within your organisation are likely to be running nf-core pipelines regularly and need to use the same settings regularly it may be a good idea to request that your custom config file is uploaded to the `nf-core/configs` git repository. Before you do this please can you test that the config file works with your pipeline of choice using the `-c` parameter. You can then create a pull request to the `nf-core/configs` repository with the addition of your config file, associated documentation file (see examples in [`nf-core/configs/docs`](https://github.com/nf-core/configs/tree/master/docs)), and amending [`nfcore_custom.config`](https://github.com/nf-core/configs/blob/master/nfcore_custom.config) to include your custom profile. -If you are likely to be running `nf-core` pipelines regularly it may be a good idea to request that your custom config file is uploaded to the `nf-core/configs` git repository. Before you do this please can you test that the config file works with your pipeline of choice using the `-c` parameter (see definition above). You can then create a pull request to the `nf-core/configs` repository with the addition of your config file, associated documentation file (see examples in [`nf-core/configs/docs`](https://github.com/nf-core/configs/tree/master/docs)), and amending [`nfcore_custom.config`](https://github.com/nf-core/configs/blob/master/nfcore_custom.config) to include your custom profile. +See the main [Nextflow documentation](https://www.nextflow.io/docs/latest/config.html) for more information about creating your own configuration files. If you have any questions or issues please send us a message on [Slack](https://nf-co.re/join/slack) on the [`#configs` channel](https://nfcore.slack.com/channels/configs). -### Running in the background +## Running in the background Nextflow handles job submissions and supervises the running jobs. The Nextflow process must run until the pipeline is finished. @@ -126,11 +274,11 @@ The Nextflow `-bg` flag launches Nextflow in the background, detached from your Alternatively, you can use `screen` / `tmux` or similar tool to create a detached session which you can log back into at a later time. Some HPC setups also allow you to run nextflow within a cluster job submitted your job scheduler (from where it submits more jobs). -#### Nextflow memory requirements +## Nextflow memory requirements In some cases, the Nextflow Java virtual machines can start to request a large amount of memory. We recommend adding the following line to your environment to limit this (typically in `~/.bashrc` or `~./bash_profile`): -```bash +```console NXF_OPTS='-Xms1g -Xmx4g' ``` diff --git a/environment.yml b/environment.yml deleted file mode 100644 index fb3f9f7f4..000000000 --- a/environment.yml +++ /dev/null @@ -1,15 +0,0 @@ -# You can use this file to create a conda environment for this pipeline: -# conda env create -f environment.yml -name: nf-core-rnaseq-3.1 -channels: - - conda-forge - - bioconda - - defaults -dependencies: - - conda-forge::python=3.7.3 - - conda-forge::markdown=3.1.1 - - conda-forge::pymdown-extensions=6.0 - - conda-forge::pygments=2.5.2 - # TODO nf-core: Add required software dependencies here - - bioconda::fastqc=0.11.8 - - bioconda::multiqc=1.7 diff --git a/lib/Headers.groovy b/lib/Headers.groovy deleted file mode 100644 index 15d1d3880..000000000 --- a/lib/Headers.groovy +++ /dev/null @@ -1,43 +0,0 @@ -/* - * This file holds several functions used to render the nf-core ANSI header. - */ - -class Headers { - - private static Map log_colours(Boolean monochrome_logs) { - Map colorcodes = [:] - colorcodes['reset'] = monochrome_logs ? '' : "\033[0m" - colorcodes['dim'] = monochrome_logs ? '' : "\033[2m" - colorcodes['black'] = monochrome_logs ? '' : "\033[0;30m" - colorcodes['green'] = monochrome_logs ? '' : "\033[0;32m" - colorcodes['yellow'] = monochrome_logs ? '' : "\033[0;33m" - colorcodes['yellow_bold'] = monochrome_logs ? '' : "\033[1;93m" - colorcodes['blue'] = monochrome_logs ? '' : "\033[0;34m" - colorcodes['purple'] = monochrome_logs ? '' : "\033[0;35m" - colorcodes['cyan'] = monochrome_logs ? '' : "\033[0;36m" - colorcodes['white'] = monochrome_logs ? '' : "\033[0;37m" - colorcodes['red'] = monochrome_logs ? '' : "\033[1;91m" - return colorcodes - } - - static String dashed_line(monochrome_logs) { - Map colors = log_colours(monochrome_logs) - return "-${colors.dim}----------------------------------------------------${colors.reset}-" - } - - static String nf_core(workflow, monochrome_logs) { - Map colors = log_colours(monochrome_logs) - String.format( - """\n - ${dashed_line(monochrome_logs)} - ${colors.green},--.${colors.black}/${colors.green},-.${colors.reset} - ${colors.blue} ___ __ __ __ ___ ${colors.green}/,-._.--~\'${colors.reset} - ${colors.blue} |\\ | |__ __ / ` / \\ |__) |__ ${colors.yellow}} {${colors.reset} - ${colors.blue} | \\| | \\__, \\__/ | \\ |___ ${colors.green}\\`-._,-`-,${colors.reset} - ${colors.green}`._,._,\'${colors.reset} - ${colors.purple} ${workflow.manifest.name} v${workflow.manifest.version}${colors.reset} - ${dashed_line(monochrome_logs)} - """.stripIndent() - ) - } -} diff --git a/lib/NfcoreSchema.groovy b/lib/NfcoreSchema.groovy old mode 100644 new mode 100755 index 52ee73043..8d6920dd6 --- a/lib/NfcoreSchema.groovy +++ b/lib/NfcoreSchema.groovy @@ -1,6 +1,6 @@ -/* - * This file holds several functions used to perform JSON parameter validation, help and summary rendering for the nf-core pipeline template. - */ +// +// This file holds several functions used to perform JSON parameter validation, help and summary rendering for the nf-core pipeline template. +// import org.everit.json.schema.Schema import org.everit.json.schema.loader.SchemaLoader @@ -13,16 +13,23 @@ import groovy.json.JsonBuilder class NfcoreSchema { - /* - * Function to loop over all parameters defined in schema and check - * whether the given paremeters adhere to the specificiations - */ + // + // Resolve Schema path relative to main workflow directory + // + public static String getSchemaPath(workflow, schema_filename='nextflow_schema.json') { + return "${workflow.projectDir}/${schema_filename}" + } + + // + // Function to loop over all parameters defined in schema and check + // whether the given parameters adhere to the specifications + // /* groovylint-disable-next-line UnusedPrivateMethodParameter */ - private static void validateParameters(params, jsonSchema, log) { + public static void validateParameters(workflow, params, log, schema_filename='nextflow_schema.json') { def has_error = false //=====================================================================// // Check for nextflow core params and unexpected params - def json = new File(jsonSchema).text + def json = new File(getSchemaPath(workflow, schema_filename=schema_filename)).text def Map schemaParams = (Map) new JsonSlurper().parseText(json).get('definitions') def nf_params = [ // Options for base `nextflow` command @@ -114,7 +121,8 @@ class NfcoreSchema { def params_ignore = params.schema_ignore_params.split(',') + 'schema_ignore_params' def expectedParamsLowerCase = expectedParams.collect{ it.replace("-", "").toLowerCase() } def specifiedParamLowerCase = specifiedParam.replace("-", "").toLowerCase() - if (!expectedParams.contains(specifiedParam) && !params_ignore.contains(specifiedParam) && !expectedParamsLowerCase.contains(specifiedParamLowerCase)) { + def isCamelCaseBug = (specifiedParam.contains("-") && !expectedParams.contains(specifiedParam) && expectedParamsLowerCase.contains(specifiedParamLowerCase)) + if (!expectedParams.contains(specifiedParam) && !params_ignore.contains(specifiedParam) && !isCamelCaseBug) { // Temporarily remove camelCase/camel-case params #1035 def unexpectedParamsLowerCase = unexpectedParams.collect{ it.replace("-", "").toLowerCase()} if (!unexpectedParamsLowerCase.contains(specifiedParamLowerCase)){ @@ -125,36 +133,36 @@ class NfcoreSchema { //=====================================================================// // Validate parameters against the schema - InputStream inputStream = new File(jsonSchema).newInputStream() - JSONObject rawSchema = new JSONObject(new JSONTokener(inputStream)) + InputStream input_stream = new File(getSchemaPath(workflow, schema_filename=schema_filename)).newInputStream() + JSONObject raw_schema = new JSONObject(new JSONTokener(input_stream)) // Remove anything that's in params.schema_ignore_params - rawSchema = removeIgnoredParams(rawSchema, params) + raw_schema = removeIgnoredParams(raw_schema, params) - Schema schema = SchemaLoader.load(rawSchema) + Schema schema = SchemaLoader.load(raw_schema) // Clean the parameters def cleanedParams = cleanParameters(params) // Convert to JSONObject def jsonParams = new JsonBuilder(cleanedParams) - JSONObject paramsJSON = new JSONObject(jsonParams.toString()) + JSONObject params_json = new JSONObject(jsonParams.toString()) // Validate try { - schema.validate(paramsJSON) + schema.validate(params_json) } catch (ValidationException e) { println '' log.error 'ERROR: Validation of pipeline parameters failed!' JSONObject exceptionJSON = e.toJSON() - printExceptions(exceptionJSON, paramsJSON, log) + printExceptions(exceptionJSON, params_json, log) println '' has_error = true } // Check for unexpected parameters if (unexpectedParams.size() > 0) { - Map colors = log_colours(params.monochrome_logs) + Map colors = NfcoreTemplate.logColours(params.monochrome_logs) println '' def warn_msg = 'Found unexpected parameters:' for (unexpectedParam in unexpectedParams) { @@ -170,266 +178,17 @@ class NfcoreSchema { } } - // Loop over nested exceptions and print the causingException - private static void printExceptions(exJSON, paramsJSON, log) { - def causingExceptions = exJSON['causingExceptions'] - if (causingExceptions.length() == 0) { - def m = exJSON['message'] =~ /required key \[([^\]]+)\] not found/ - // Missing required param - if (m.matches()) { - log.error "* Missing required parameter: --${m[0][1]}" - } - // Other base-level error - else if (exJSON['pointerToViolation'] == '#') { - log.error "* ${exJSON['message']}" - } - // Error with specific param - else { - def param = exJSON['pointerToViolation'] - ~/^#\// - def param_val = paramsJSON[param].toString() - log.error "* --${param}: ${exJSON['message']} (${param_val})" - } - } - for (ex in causingExceptions) { - printExceptions(ex, paramsJSON, log) - } - } - - // Remove an element from a JSONArray - private static JSONArray removeElement(jsonArray, element){ - def list = [] - int len = jsonArray.length() - for (int i=0;i - if(rawSchema.keySet().contains('definitions')){ - rawSchema.definitions.each { definition -> - for (key in definition.keySet()){ - if (definition[key].get("properties").keySet().contains(ignore_param)){ - // Remove the param to ignore - definition[key].get("properties").remove(ignore_param) - // If the param was required, change this - if (definition[key].has("required")) { - def cleaned_required = removeElement(definition[key].required, ignore_param) - definition[key].put("required", cleaned_required) - } - } - } - } - } - if(rawSchema.keySet().contains('properties') && rawSchema.get('properties').keySet().contains(ignore_param)) { - rawSchema.get("properties").remove(ignore_param) - } - if(rawSchema.keySet().contains('required') && rawSchema.required.contains(ignore_param)) { - def cleaned_required = removeElement(rawSchema.required, ignore_param) - rawSchema.put("required", cleaned_required) - } - } - return rawSchema - } - - private static Map cleanParameters(params) { - def new_params = params.getClass().newInstance(params) - for (p in params) { - // remove anything evaluating to false - if (!p['value']) { - new_params.remove(p.key) - } - // Cast MemoryUnit to String - if (p['value'].getClass() == nextflow.util.MemoryUnit) { - new_params.replace(p.key, p['value'].toString()) - } - // Cast Duration to String - if (p['value'].getClass() == nextflow.util.Duration) { - new_params.replace(p.key, p['value'].toString().replaceFirst(/d(?!\S)/, "day")) - } - // Cast LinkedHashMap to String - if (p['value'].getClass() == LinkedHashMap) { - new_params.replace(p.key, p['value'].toString()) - } - } - return new_params - } - - /* - * This method tries to read a JSON params file - */ - private static LinkedHashMap params_load(String json_schema) { - def params_map = new LinkedHashMap() - try { - params_map = params_read(json_schema) - } catch (Exception e) { - println "Could not read parameters settings from JSON. $e" - params_map = new LinkedHashMap() - } - return params_map - } - - private static Map log_colours(Boolean monochrome_logs) { - Map colorcodes = [:] - - // Reset / Meta - colorcodes['reset'] = monochrome_logs ? '' : "\033[0m" - colorcodes['bold'] = monochrome_logs ? '' : "\033[1m" - colorcodes['dim'] = monochrome_logs ? '' : "\033[2m" - colorcodes['underlined'] = monochrome_logs ? '' : "\033[4m" - colorcodes['blink'] = monochrome_logs ? '' : "\033[5m" - colorcodes['reverse'] = monochrome_logs ? '' : "\033[7m" - colorcodes['hidden'] = monochrome_logs ? '' : "\033[8m" - - // Regular Colors - colorcodes['black'] = monochrome_logs ? '' : "\033[0;30m" - colorcodes['red'] = monochrome_logs ? '' : "\033[0;31m" - colorcodes['green'] = monochrome_logs ? '' : "\033[0;32m" - colorcodes['yellow'] = monochrome_logs ? '' : "\033[0;33m" - colorcodes['blue'] = monochrome_logs ? '' : "\033[0;34m" - colorcodes['purple'] = monochrome_logs ? '' : "\033[0;35m" - colorcodes['cyan'] = monochrome_logs ? '' : "\033[0;36m" - colorcodes['white'] = monochrome_logs ? '' : "\033[0;37m" - - // Bold - colorcodes['bblack'] = monochrome_logs ? '' : "\033[1;30m" - colorcodes['bred'] = monochrome_logs ? '' : "\033[1;31m" - colorcodes['bgreen'] = monochrome_logs ? '' : "\033[1;32m" - colorcodes['byellow'] = monochrome_logs ? '' : "\033[1;33m" - colorcodes['bblue'] = monochrome_logs ? '' : "\033[1;34m" - colorcodes['bpurple'] = monochrome_logs ? '' : "\033[1;35m" - colorcodes['bcyan'] = monochrome_logs ? '' : "\033[1;36m" - colorcodes['bwhite'] = monochrome_logs ? '' : "\033[1;37m" - - // Underline - colorcodes['ublack'] = monochrome_logs ? '' : "\033[4;30m" - colorcodes['ured'] = monochrome_logs ? '' : "\033[4;31m" - colorcodes['ugreen'] = monochrome_logs ? '' : "\033[4;32m" - colorcodes['uyellow'] = monochrome_logs ? '' : "\033[4;33m" - colorcodes['ublue'] = monochrome_logs ? '' : "\033[4;34m" - colorcodes['upurple'] = monochrome_logs ? '' : "\033[4;35m" - colorcodes['ucyan'] = monochrome_logs ? '' : "\033[4;36m" - colorcodes['uwhite'] = monochrome_logs ? '' : "\033[4;37m" - - // High Intensity - colorcodes['iblack'] = monochrome_logs ? '' : "\033[0;90m" - colorcodes['ired'] = monochrome_logs ? '' : "\033[0;91m" - colorcodes['igreen'] = monochrome_logs ? '' : "\033[0;92m" - colorcodes['iyellow'] = monochrome_logs ? '' : "\033[0;93m" - colorcodes['iblue'] = monochrome_logs ? '' : "\033[0;94m" - colorcodes['ipurple'] = monochrome_logs ? '' : "\033[0;95m" - colorcodes['icyan'] = monochrome_logs ? '' : "\033[0;96m" - colorcodes['iwhite'] = monochrome_logs ? '' : "\033[0;97m" - - // Bold High Intensity - colorcodes['biblack'] = monochrome_logs ? '' : "\033[1;90m" - colorcodes['bired'] = monochrome_logs ? '' : "\033[1;91m" - colorcodes['bigreen'] = monochrome_logs ? '' : "\033[1;92m" - colorcodes['biyellow'] = monochrome_logs ? '' : "\033[1;93m" - colorcodes['biblue'] = monochrome_logs ? '' : "\033[1;94m" - colorcodes['bipurple'] = monochrome_logs ? '' : "\033[1;95m" - colorcodes['bicyan'] = monochrome_logs ? '' : "\033[1;96m" - colorcodes['biwhite'] = monochrome_logs ? '' : "\033[1;97m" - - return colorcodes - } - - static String dashed_line(monochrome_logs) { - Map colors = log_colours(monochrome_logs) - return "-${colors.dim}----------------------------------------------------${colors.reset}-" - } - - /* - Method to actually read in JSON file using Groovy. - Group (as Key), values are all parameters - - Parameter1 as Key, Description as Value - - Parameter2 as Key, Description as Value - .... - Group - - - */ - private static LinkedHashMap params_read(String json_schema) throws Exception { - def json = new File(json_schema).text - def Map schema_definitions = (Map) new JsonSlurper().parseText(json).get('definitions') - def Map schema_properties = (Map) new JsonSlurper().parseText(json).get('properties') - /* Tree looks like this in nf-core schema - * definitions <- this is what the first get('definitions') gets us - group 1 - title - description - properties - parameter 1 - type - description - parameter 2 - type - description - group 2 - title - description - properties - parameter 1 - type - description - * properties <- parameters can also be ungrouped, outside of definitions - parameter 1 - type - description - */ - - // Grouped params - def params_map = new LinkedHashMap() - schema_definitions.each { key, val -> - def Map group = schema_definitions."$key".properties // Gets the property object of the group - def title = schema_definitions."$key".title - def sub_params = new LinkedHashMap() - group.each { innerkey, value -> - sub_params.put(innerkey, value) - } - params_map.put(title, sub_params) - } - - // Ungrouped params - def ungrouped_params = new LinkedHashMap() - schema_properties.each { innerkey, value -> - ungrouped_params.put(innerkey, value) - } - params_map.put("Other parameters", ungrouped_params) - - return params_map - } - - /* - * Get maximum number of characters across all parameter names - */ - private static Integer params_max_chars(params_map) { - Integer max_chars = 0 - for (group in params_map.keySet()) { - def group_params = params_map.get(group) // This gets the parameters of that particular group - for (param in group_params.keySet()) { - if (param.size() > max_chars) { - max_chars = param.size() - } - } - } - return max_chars - } - - /* - * Beautify parameters for --help - */ - private static String params_help(workflow, params, json_schema, command) { - Map colors = log_colours(params.monochrome_logs) + // + // Beautify parameters for --help + // + public static String paramsHelp(workflow, params, command, schema_filename='nextflow_schema.json') { + Map colors = NfcoreTemplate.logColours(params.monochrome_logs) Integer num_hidden = 0 String output = '' output += 'Typical pipeline command:\n\n' output += " ${colors.cyan}${command}${colors.reset}\n\n" - Map params_map = params_load(json_schema) - Integer max_chars = params_max_chars(params_map) + 1 + Map params_map = paramsLoad(getSchemaPath(workflow, schema_filename=schema_filename)) + Integer max_chars = paramsMaxChars(params_map) + 1 Integer desc_indent = max_chars + 14 Integer dec_linewidth = 160 - desc_indent for (group in params_map.keySet()) { @@ -469,18 +228,17 @@ class NfcoreSchema { output += group_output } } - output += dashed_line(params.monochrome_logs) if (num_hidden > 0){ - output += colors.dim + "\n Hiding $num_hidden params, use --show_hidden_params to show.\n" + colors.reset - output += dashed_line(params.monochrome_logs) + output += colors.dim + "!! Hiding $num_hidden params, use --show_hidden_params to show them !!\n" + colors.reset } + output += NfcoreTemplate.dashedLine(params.monochrome_logs) return output } - /* - * Groovy Map summarising parameters/workflow options used by the pipeline - */ - private static LinkedHashMap params_summary_map(workflow, params, json_schema) { + // + // Groovy Map summarising parameters/workflow options used by the pipeline + // + public static LinkedHashMap paramsSummaryMap(workflow, params, schema_filename='nextflow_schema.json') { // Get a selection of core Nextflow workflow options def Map workflow_summary = [:] if (workflow.revision) { @@ -503,7 +261,7 @@ class NfcoreSchema { // Get pipeline parameters defined in JSON Schema def Map params_summary = [:] def blacklist = ['hostnames'] - def params_map = params_load(json_schema) + def params_map = paramsLoad(getSchemaPath(workflow, schema_filename=schema_filename)) for (group in params_map.keySet()) { def sub_params = new LinkedHashMap() def group_params = params_map.get(group) // This gets the parameters of that particular group @@ -546,14 +304,14 @@ class NfcoreSchema { return [ 'Core Nextflow options' : workflow_summary ] << params_summary } - /* - * Beautify parameters for summary and return as string - */ - private static String params_summary_log(workflow, params, json_schema) { - Map colors = log_colours(params.monochrome_logs) + // + // Beautify parameters for summary and return as string + // + public static String paramsSummaryLog(workflow, params) { + Map colors = NfcoreTemplate.logColours(params.monochrome_logs) String output = '' - def params_map = params_summary_map(workflow, params, json_schema) - def max_chars = params_max_chars(params_map) + def params_map = paramsSummaryMap(workflow, params) + def max_chars = paramsMaxChars(params_map) for (group in params_map.keySet()) { def group_params = params_map.get(group) // This gets the parameters of that particular group if (group_params) { @@ -564,10 +322,196 @@ class NfcoreSchema { output += '\n' } } - output += dashed_line(params.monochrome_logs) - output += colors.dim + "\n Only displaying parameters that differ from defaults.\n" + colors.reset - output += dashed_line(params.monochrome_logs) + output += "!! Only displaying parameters that differ from the pipeline defaults !!\n" + output += NfcoreTemplate.dashedLine(params.monochrome_logs) return output } + // + // Loop over nested exceptions and print the causingException + // + private static void printExceptions(ex_json, params_json, log) { + def causingExceptions = ex_json['causingExceptions'] + if (causingExceptions.length() == 0) { + def m = ex_json['message'] =~ /required key \[([^\]]+)\] not found/ + // Missing required param + if (m.matches()) { + log.error "* Missing required parameter: --${m[0][1]}" + } + // Other base-level error + else if (ex_json['pointerToViolation'] == '#') { + log.error "* ${ex_json['message']}" + } + // Error with specific param + else { + def param = ex_json['pointerToViolation'] - ~/^#\// + def param_val = params_json[param].toString() + log.error "* --${param}: ${ex_json['message']} (${param_val})" + } + } + for (ex in causingExceptions) { + printExceptions(ex, params_json, log) + } + } + + // + // Remove an element from a JSONArray + // + private static JSONArray removeElement(json_array, element) { + def list = [] + int len = json_array.length() + for (int i=0;i + if(raw_schema.keySet().contains('definitions')){ + raw_schema.definitions.each { definition -> + for (key in definition.keySet()){ + if (definition[key].get("properties").keySet().contains(ignore_param)){ + // Remove the param to ignore + definition[key].get("properties").remove(ignore_param) + // If the param was required, change this + if (definition[key].has("required")) { + def cleaned_required = removeElement(definition[key].required, ignore_param) + definition[key].put("required", cleaned_required) + } + } + } + } + } + if(raw_schema.keySet().contains('properties') && raw_schema.get('properties').keySet().contains(ignore_param)) { + raw_schema.get("properties").remove(ignore_param) + } + if(raw_schema.keySet().contains('required') && raw_schema.required.contains(ignore_param)) { + def cleaned_required = removeElement(raw_schema.required, ignore_param) + raw_schema.put("required", cleaned_required) + } + } + return raw_schema + } + + // + // Clean and check parameters relative to Nextflow native classes + // + private static Map cleanParameters(params) { + def new_params = params.getClass().newInstance(params) + for (p in params) { + // remove anything evaluating to false + if (!p['value']) { + new_params.remove(p.key) + } + // Cast MemoryUnit to String + if (p['value'].getClass() == nextflow.util.MemoryUnit) { + new_params.replace(p.key, p['value'].toString()) + } + // Cast Duration to String + if (p['value'].getClass() == nextflow.util.Duration) { + new_params.replace(p.key, p['value'].toString().replaceFirst(/d(?!\S)/, "day")) + } + // Cast LinkedHashMap to String + if (p['value'].getClass() == LinkedHashMap) { + new_params.replace(p.key, p['value'].toString()) + } + } + return new_params + } + + // + // This function tries to read a JSON params file + // + private static LinkedHashMap paramsLoad(String json_schema) { + def params_map = new LinkedHashMap() + try { + params_map = paramsRead(json_schema) + } catch (Exception e) { + println "Could not read parameters settings from JSON. $e" + params_map = new LinkedHashMap() + } + return params_map + } + + // + // Method to actually read in JSON file using Groovy. + // Group (as Key), values are all parameters + // - Parameter1 as Key, Description as Value + // - Parameter2 as Key, Description as Value + // .... + // Group + // - + private static LinkedHashMap paramsRead(String json_schema) throws Exception { + def json = new File(json_schema).text + def Map schema_definitions = (Map) new JsonSlurper().parseText(json).get('definitions') + def Map schema_properties = (Map) new JsonSlurper().parseText(json).get('properties') + /* Tree looks like this in nf-core schema + * definitions <- this is what the first get('definitions') gets us + group 1 + title + description + properties + parameter 1 + type + description + parameter 2 + type + description + group 2 + title + description + properties + parameter 1 + type + description + * properties <- parameters can also be ungrouped, outside of definitions + parameter 1 + type + description + */ + + // Grouped params + def params_map = new LinkedHashMap() + schema_definitions.each { key, val -> + def Map group = schema_definitions."$key".properties // Gets the property object of the group + def title = schema_definitions."$key".title + def sub_params = new LinkedHashMap() + group.each { innerkey, value -> + sub_params.put(innerkey, value) + } + params_map.put(title, sub_params) + } + + // Ungrouped params + def ungrouped_params = new LinkedHashMap() + schema_properties.each { innerkey, value -> + ungrouped_params.put(innerkey, value) + } + params_map.put("Other parameters", ungrouped_params) + + return params_map + } + + // + // Get maximum number of characters across all parameter names + // + private static Integer paramsMaxChars(params_map) { + Integer max_chars = 0 + for (group in params_map.keySet()) { + def group_params = params_map.get(group) // This gets the parameters of that particular group + for (param in group_params.keySet()) { + if (param.size() > max_chars) { + max_chars = param.size() + } + } + } + return max_chars + } } diff --git a/lib/NfcoreTemplate.groovy b/lib/NfcoreTemplate.groovy new file mode 100755 index 000000000..b6e689ec8 --- /dev/null +++ b/lib/NfcoreTemplate.groovy @@ -0,0 +1,266 @@ +// +// This file holds several functions used within the nf-core pipeline template. +// + +import org.yaml.snakeyaml.Yaml + +class NfcoreTemplate { + + // + // Check AWS Batch related parameters have been specified correctly + // + public static void awsBatch(workflow, params) { + if (workflow.profile.contains('awsbatch')) { + // Check params.awsqueue and params.awsregion have been set if running on AWSBatch + assert (params.awsqueue && params.awsregion) : "Specify correct --awsqueue and --awsregion parameters on AWSBatch!" + // Check outdir paths to be S3 buckets if running on AWSBatch + assert params.outdir.startsWith('s3:') : "Outdir not on S3 - specify S3 Bucket to run on AWSBatch!" + } + } + + // + // Check params.hostnames + // + public static void hostName(workflow, params, log) { + Map colors = logColours(params.monochrome_logs) + if (params.hostnames) { + def hostname = "hostname".execute().text.trim() + params.hostnames.each { prof, hnames -> + hnames.each { hname -> + if (hostname.contains(hname) && !workflow.profile.contains(prof)) { + log.info "=${colors.yellow}====================================================${colors.reset}=\n" + + "${colors.yellow}WARN: You are running with `-profile $workflow.profile`\n" + + " but your machine hostname is ${colors.white}'$hostname'${colors.reset}.\n" + + " ${colors.yellow_bold}Please use `-profile $prof${colors.reset}`\n" + + "=${colors.yellow}====================================================${colors.reset}=" + } + } + } + } + } + + // + // Construct and send completion email + // + public static void email(workflow, params, summary_params, projectDir, log, multiqc_report=[]) { + + // Set up the e-mail variables + def subject = "[$workflow.manifest.name] Successful: $workflow.runName" + if (!workflow.success) { + subject = "[$workflow.manifest.name] FAILED: $workflow.runName" + } + + def summary = [:] + for (group in summary_params.keySet()) { + summary << summary_params[group] + } + + def misc_fields = [:] + misc_fields['Date Started'] = workflow.start + misc_fields['Date Completed'] = workflow.complete + misc_fields['Pipeline script file path'] = workflow.scriptFile + misc_fields['Pipeline script hash ID'] = workflow.scriptId + if (workflow.repository) misc_fields['Pipeline repository Git URL'] = workflow.repository + if (workflow.commitId) misc_fields['Pipeline repository Git Commit'] = workflow.commitId + if (workflow.revision) misc_fields['Pipeline Git branch/tag'] = workflow.revision + misc_fields['Nextflow Version'] = workflow.nextflow.version + misc_fields['Nextflow Build'] = workflow.nextflow.build + misc_fields['Nextflow Compile Timestamp'] = workflow.nextflow.timestamp + + def email_fields = [:] + email_fields['version'] = workflow.manifest.version + email_fields['runName'] = workflow.runName + email_fields['success'] = workflow.success + email_fields['dateComplete'] = workflow.complete + email_fields['duration'] = workflow.duration + email_fields['exitStatus'] = workflow.exitStatus + email_fields['errorMessage'] = (workflow.errorMessage ?: 'None') + email_fields['errorReport'] = (workflow.errorReport ?: 'None') + email_fields['commandLine'] = workflow.commandLine + email_fields['projectDir'] = workflow.projectDir + email_fields['summary'] = summary << misc_fields + + // On success try attach the multiqc report + def mqc_report = null + try { + if (workflow.success) { + mqc_report = multiqc_report.getVal() + if (mqc_report.getClass() == ArrayList && mqc_report.size() >= 1) { + if (mqc_report.size() > 1) { + log.warn "[$workflow.manifest.name] Found multiple reports from process 'MULTIQC', will use only one" + } + mqc_report = mqc_report[0] + } + } + } catch (all) { + if (multiqc_report) { + log.warn "[$workflow.manifest.name] Could not attach MultiQC report to summary email" + } + } + + // Check if we are only sending emails on failure + def email_address = params.email + if (!params.email && params.email_on_fail && !workflow.success) { + email_address = params.email_on_fail + } + + // Render the TXT template + def engine = new groovy.text.GStringTemplateEngine() + def tf = new File("$projectDir/assets/email_template.txt") + def txt_template = engine.createTemplate(tf).make(email_fields) + def email_txt = txt_template.toString() + + // Render the HTML template + def hf = new File("$projectDir/assets/email_template.html") + def html_template = engine.createTemplate(hf).make(email_fields) + def email_html = html_template.toString() + + // Render the sendmail template + def max_multiqc_email_size = params.max_multiqc_email_size as nextflow.util.MemoryUnit + def smail_fields = [ email: email_address, subject: subject, email_txt: email_txt, email_html: email_html, projectDir: "$projectDir", mqcFile: mqc_report, mqcMaxSize: max_multiqc_email_size.toBytes() ] + def sf = new File("$projectDir/assets/sendmail_template.txt") + def sendmail_template = engine.createTemplate(sf).make(smail_fields) + def sendmail_html = sendmail_template.toString() + + // Send the HTML e-mail + Map colors = logColours(params.monochrome_logs) + if (email_address) { + try { + if (params.plaintext_email) { throw GroovyException('Send plaintext e-mail, not HTML') } + // Try to send HTML e-mail using sendmail + [ 'sendmail', '-t' ].execute() << sendmail_html + log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Sent summary e-mail to $email_address (sendmail)-" + } catch (all) { + // Catch failures and try with plaintext + def mail_cmd = [ 'mail', '-s', subject, '--content-type=text/html', email_address ] + if ( mqc_report.size() <= max_multiqc_email_size.toBytes() ) { + mail_cmd += [ '-A', mqc_report ] + } + mail_cmd.execute() << email_html + log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Sent summary e-mail to $email_address (mail)-" + } + } + + // Write summary e-mail HTML to a file + def output_d = new File("${params.outdir}/pipeline_info/") + if (!output_d.exists()) { + output_d.mkdirs() + } + def output_hf = new File(output_d, "pipeline_report.html") + output_hf.withWriter { w -> w << email_html } + def output_tf = new File(output_d, "pipeline_report.txt") + output_tf.withWriter { w -> w << email_txt } + } + + // + // Print pipeline summary on completion + // + public static void summary(workflow, params, log) { + Map colors = logColours(params.monochrome_logs) + if (workflow.success) { + if (workflow.stats.ignoredCount == 0) { + log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Pipeline completed successfully${colors.reset}-" + } else { + log.info "-${colors.purple}[$workflow.manifest.name]${colors.red} Pipeline completed successfully, but with errored process(es) ${colors.reset}-" + } + } else { + hostName(workflow, params, log) + log.info "-${colors.purple}[$workflow.manifest.name]${colors.red} Pipeline completed with errors${colors.reset}-" + } + } + + // + // ANSII Colours used for terminal logging + // + public static Map logColours(Boolean monochrome_logs) { + Map colorcodes = [:] + + // Reset / Meta + colorcodes['reset'] = monochrome_logs ? '' : "\033[0m" + colorcodes['bold'] = monochrome_logs ? '' : "\033[1m" + colorcodes['dim'] = monochrome_logs ? '' : "\033[2m" + colorcodes['underlined'] = monochrome_logs ? '' : "\033[4m" + colorcodes['blink'] = monochrome_logs ? '' : "\033[5m" + colorcodes['reverse'] = monochrome_logs ? '' : "\033[7m" + colorcodes['hidden'] = monochrome_logs ? '' : "\033[8m" + + // Regular Colors + colorcodes['black'] = monochrome_logs ? '' : "\033[0;30m" + colorcodes['red'] = monochrome_logs ? '' : "\033[0;31m" + colorcodes['green'] = monochrome_logs ? '' : "\033[0;32m" + colorcodes['yellow'] = monochrome_logs ? '' : "\033[0;33m" + colorcodes['blue'] = monochrome_logs ? '' : "\033[0;34m" + colorcodes['purple'] = monochrome_logs ? '' : "\033[0;35m" + colorcodes['cyan'] = monochrome_logs ? '' : "\033[0;36m" + colorcodes['white'] = monochrome_logs ? '' : "\033[0;37m" + + // Bold + colorcodes['bblack'] = monochrome_logs ? '' : "\033[1;30m" + colorcodes['bred'] = monochrome_logs ? '' : "\033[1;31m" + colorcodes['bgreen'] = monochrome_logs ? '' : "\033[1;32m" + colorcodes['byellow'] = monochrome_logs ? '' : "\033[1;33m" + colorcodes['bblue'] = monochrome_logs ? '' : "\033[1;34m" + colorcodes['bpurple'] = monochrome_logs ? '' : "\033[1;35m" + colorcodes['bcyan'] = monochrome_logs ? '' : "\033[1;36m" + colorcodes['bwhite'] = monochrome_logs ? '' : "\033[1;37m" + + // Underline + colorcodes['ublack'] = monochrome_logs ? '' : "\033[4;30m" + colorcodes['ured'] = monochrome_logs ? '' : "\033[4;31m" + colorcodes['ugreen'] = monochrome_logs ? '' : "\033[4;32m" + colorcodes['uyellow'] = monochrome_logs ? '' : "\033[4;33m" + colorcodes['ublue'] = monochrome_logs ? '' : "\033[4;34m" + colorcodes['upurple'] = monochrome_logs ? '' : "\033[4;35m" + colorcodes['ucyan'] = monochrome_logs ? '' : "\033[4;36m" + colorcodes['uwhite'] = monochrome_logs ? '' : "\033[4;37m" + + // High Intensity + colorcodes['iblack'] = monochrome_logs ? '' : "\033[0;90m" + colorcodes['ired'] = monochrome_logs ? '' : "\033[0;91m" + colorcodes['igreen'] = monochrome_logs ? '' : "\033[0;92m" + colorcodes['iyellow'] = monochrome_logs ? '' : "\033[0;93m" + colorcodes['iblue'] = monochrome_logs ? '' : "\033[0;94m" + colorcodes['ipurple'] = monochrome_logs ? '' : "\033[0;95m" + colorcodes['icyan'] = monochrome_logs ? '' : "\033[0;96m" + colorcodes['iwhite'] = monochrome_logs ? '' : "\033[0;97m" + + // Bold High Intensity + colorcodes['biblack'] = monochrome_logs ? '' : "\033[1;90m" + colorcodes['bired'] = monochrome_logs ? '' : "\033[1;91m" + colorcodes['bigreen'] = monochrome_logs ? '' : "\033[1;92m" + colorcodes['biyellow'] = monochrome_logs ? '' : "\033[1;93m" + colorcodes['biblue'] = monochrome_logs ? '' : "\033[1;94m" + colorcodes['bipurple'] = monochrome_logs ? '' : "\033[1;95m" + colorcodes['bicyan'] = monochrome_logs ? '' : "\033[1;96m" + colorcodes['biwhite'] = monochrome_logs ? '' : "\033[1;97m" + + return colorcodes + } + + // + // Does what is says on the tin + // + public static String dashedLine(monochrome_logs) { + Map colors = logColours(monochrome_logs) + return "-${colors.dim}----------------------------------------------------${colors.reset}-" + } + + // + // nf-core logo + // + public static String logo(workflow, monochrome_logs) { + Map colors = logColours(monochrome_logs) + String.format( + """\n + ${dashedLine(monochrome_logs)} + ${colors.green},--.${colors.black}/${colors.green},-.${colors.reset} + ${colors.blue} ___ __ __ __ ___ ${colors.green}/,-._.--~\'${colors.reset} + ${colors.blue} |\\ | |__ __ / ` / \\ |__) |__ ${colors.yellow}} {${colors.reset} + ${colors.blue} | \\| | \\__, \\__/ | \\ |___ ${colors.green}\\`-._,-`-,${colors.reset} + ${colors.green}`._,._,\'${colors.reset} + ${colors.purple} ${workflow.manifest.name} v${workflow.manifest.version}${colors.reset} + ${dashedLine(monochrome_logs)} + """.stripIndent() + ) + } +} diff --git a/lib/Utils.groovy b/lib/Utils.groovy new file mode 100755 index 000000000..18173e985 --- /dev/null +++ b/lib/Utils.groovy @@ -0,0 +1,47 @@ +// +// This file holds several Groovy functions that could be useful for any Nextflow pipeline +// + +import org.yaml.snakeyaml.Yaml + +class Utils { + + // + // When running with -profile conda, warn if channels have not been set-up appropriately + // + public static void checkCondaChannels(log) { + Yaml parser = new Yaml() + def channels = [] + try { + def config = parser.load("conda config --show channels".execute().text) + channels = config.channels + } catch(NullPointerException | IOException e) { + log.warn "Could not verify conda channel configuration." + return + } + + // Check that all channels are present + def required_channels = ['conda-forge', 'bioconda', 'defaults'] + def conda_check_failed = !required_channels.every { ch -> ch in channels } + + // Check that they are in the right order + conda_check_failed |= !(channels.indexOf('conda-forge') < channels.indexOf('bioconda')) + conda_check_failed |= !(channels.indexOf('bioconda') < channels.indexOf('defaults')) + + if (conda_check_failed) { + log.warn "=============================================================================\n" + + " There is a problem with your Conda configuration!\n\n" + + " You will need to set-up the conda-forge and bioconda channels correctly.\n" + + " Please refer to https://bioconda.github.io/user/install.html#set-up-channels\n" + + " NB: The order of the channels matters!\n" + + "===================================================================================" + } + } + + // + // Join module args with appropriate spacing + // + public static String joinModuleArgs(args_list) { + return ' ' + args_list.join(' ') + } +} diff --git a/lib/WorkflowMain.groovy b/lib/WorkflowMain.groovy new file mode 100755 index 000000000..d3bb4c57d --- /dev/null +++ b/lib/WorkflowMain.groovy @@ -0,0 +1,94 @@ +// +// This file holds several functions specific to the main.nf workflow in the nf-core/rnaseq pipeline +// + +class WorkflowMain { + + // + // Citation string for pipeline + // + public static String citation(workflow) { + return "If you use ${workflow.manifest.name} for your analysis please cite:\n\n" + + // TODO nf-core: Add Zenodo DOI for pipeline after first release + //"* The pipeline\n" + + //" https://doi.org/10.5281/zenodo.XXXXXXX\n\n" + + "* The nf-core framework\n" + + " https://doi.org/10.1038/s41587-020-0439-x\n\n" + + "* Software dependencies\n" + + " https://github.com/${workflow.manifest.name}/blob/master/CITATIONS.md" + } + + // + // Print help to screen if required + // + public static String help(workflow, params, log) { + def command = "nextflow run ${workflow.manifest.name} --input samplesheet.csv --genome GRCh37 -profile docker" + def help_string = '' + help_string += NfcoreTemplate.logo(workflow, params.monochrome_logs) + help_string += NfcoreSchema.paramsHelp(workflow, params, command) + help_string += '\n' + citation(workflow) + '\n' + help_string += NfcoreTemplate.dashedLine(params.monochrome_logs) + return help_string + } + + // + // Print parameter summary log to screen + // + public static String paramsSummaryLog(workflow, params, log) { + def summary_log = '' + summary_log += NfcoreTemplate.logo(workflow, params.monochrome_logs) + summary_log += NfcoreSchema.paramsSummaryLog(workflow, params) + summary_log += '\n' + citation(workflow) + '\n' + summary_log += NfcoreTemplate.dashedLine(params.monochrome_logs) + return summary_log + } + + // + // Validate parameters and print summary to screen + // + public static void initialise(workflow, params, log) { + // Print help to screen if required + if (params.help) { + log.info help(workflow, params, log) + System.exit(0) + } + + // Validate workflow parameters via the JSON schema + if (params.validate_params) { + NfcoreSchema.validateParameters(workflow, params, log) + } + + // Print parameter summary log to screen + log.info paramsSummaryLog(workflow, params, log) + + // Check that conda channels are set-up correctly + if (params.enable_conda) { + Utils.checkCondaChannels(log) + } + + // Check AWS batch settings + NfcoreTemplate.awsBatch(workflow, params) + + // Check the hostnames against configured profiles + NfcoreTemplate.hostName(workflow, params, log) + + // Check input has been provided + if (!params.input) { + log.error "Please provide an input samplesheet to the pipeline e.g. '--input samplesheet.csv'" + System.exit(1) + } + } + + // + // Get attribute from genome config file e.g. fasta + // + public static String getGenomeAttribute(params, attribute) { + def val = '' + if (params.genomes && params.genome && params.genomes.containsKey(params.genome)) { + if (params.genomes[ params.genome ].containsKey(attribute)) { + val = params.genomes[ params.genome ][ attribute ] + } + } + return val + } +} diff --git a/lib/WorkflowRnaseq.groovy b/lib/WorkflowRnaseq.groovy new file mode 100755 index 000000000..652860185 --- /dev/null +++ b/lib/WorkflowRnaseq.groovy @@ -0,0 +1,59 @@ +// +// This file holds several functions specific to the workflow/rnaseq.nf in the nf-core/rnaseq pipeline +// + +class WorkflowRnaseq { + + // + // Check and validate parameters + // + public static void initialise(params, log) { + genomeExistsError(params, log) + + if (!params.fasta) { + log.error "Genome fasta file not specified with e.g. '--fasta genome.fa' or via a detectable config file." + System.exit(1) + } + } + + // + // Get workflow summary for MultiQC + // + public static String paramsSummaryMultiqc(workflow, summary) { + String summary_section = '' + for (group in summary.keySet()) { + def group_params = summary.get(group) // This gets the parameters of that particular group + if (group_params) { + summary_section += "

$group

\n" + summary_section += " \n" + } + } + + String yaml_file_text = "id: '${workflow.manifest.name.replace('/','-')}-summary'\n" + yaml_file_text += "description: ' - this information is collected when the pipeline is started.'\n" + yaml_file_text += "section_name: '${workflow.manifest.name} Workflow Summary'\n" + yaml_file_text += "section_href: 'https://github.com/${workflow.manifest.name}'\n" + yaml_file_text += "plot_type: 'html'\n" + yaml_file_text += "data: |\n" + yaml_file_text += "${summary_section}" + return yaml_file_text + } + + // + // Exit pipeline if incorrect --genome key provided + // + private static void genomeExistsError(params, log) { + if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) { + log.error "=============================================================================\n" + + " Genome '${params.genome}' not found in any config files provided to the pipeline.\n" + + " Currently, the available genome keys are:\n" + + " ${params.genomes.keySet().join(", ")}\n" + + "===================================================================================" + System.exit(1) + } + } +} diff --git a/main.nf b/main.nf index f9f2c00b1..544835c93 100644 --- a/main.nf +++ b/main.nf @@ -1,390 +1,63 @@ #!/usr/bin/env nextflow /* ======================================================================================== - nf-core/rnaseq + nf-core/rnaseq ======================================================================================== - nf-core/rnaseq Analysis Pipeline. - #### Homepage / Documentation - https://github.com/nf-core/rnaseq + Github : https://github.com/nf-core/rnaseq + Website: https://nf-co.re/rnaseq + Slack : https://nfcore.slack.com/channels/rnaseq ---------------------------------------------------------------------------------------- */ -log.info Headers.nf_core(workflow, params.monochrome_logs) - -//////////////////////////////////////////////////// -/* -- PRINT HELP -- */ -////////////////////////////////////////////////////+ -def json_schema = "$projectDir/nextflow_schema.json" -if (params.help) { - def command = "nextflow run nf-core/rnaseq --input '*_R{1,2}.fastq.gz' -profile docker" - log.info NfcoreSchema.params_help(workflow, params, json_schema, command) - exit 0 -} - -//////////////////////////////////////////////////// -/* -- VALIDATE PARAMETERS -- */ -////////////////////////////////////////////////////+ -if (params.validate_params) { - NfcoreSchema.validateParameters(params, json_schema, log) -} - -//////////////////////////////////////////////////// -/* -- Collect configuration parameters -- */ -//////////////////////////////////////////////////// - -// Check if genome exists in the config file -if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) { - exit 1, "The provided genome '${params.genome}' is not available in the iGenomes file. Currently the available genomes are ${params.genomes.keySet().join(', ')}" -} - -// TODO nf-core: Add any reference files that are needed -// Configurable reference genomes -// -// NOTE - THIS IS NOT USED IN THIS PIPELINE, EXAMPLE ONLY -// If you want to use the channel below in a process, define the following: -// input: -// file fasta from ch_fasta -// -params.fasta = params.genome ? params.genomes[ params.genome ].fasta ?: false : false -if (params.fasta) { ch_fasta = file(params.fasta, checkIfExists: true) } - -// Check AWS batch settings -if (workflow.profile.contains('awsbatch')) { - // AWSBatch sanity checking - if (!params.awsqueue || !params.awsregion) exit 1, 'Specify correct --awsqueue and --awsregion parameters on AWSBatch!' - // Check outdir paths to be S3 buckets if running on AWSBatch - // related: https://github.com/nextflow-io/nextflow/issues/813 - if (!params.outdir.startsWith('s3:')) exit 1, 'Outdir not on S3 - specify S3 Bucket to run on AWSBatch!' - // Prevent trace files to be stored on S3 since S3 does not support rolling files. - if (params.tracedir.startsWith('s3:')) exit 1, 'Specify a local tracedir or run without trace! S3 cannot be used for tracefiles.' -} - -// Stage config files -ch_multiqc_config = file("$projectDir/assets/multiqc_config.yaml", checkIfExists: true) -ch_multiqc_custom_config = params.multiqc_config ? Channel.fromPath(params.multiqc_config, checkIfExists: true) : Channel.empty() -ch_output_docs = file("$projectDir/docs/output.md", checkIfExists: true) -ch_output_docs_images = file("$projectDir/docs/images/", checkIfExists: true) +nextflow.enable.dsl = 2 /* - * Create a channel for input read files - */ -if (params.input_paths) { - if (params.single_end) { - Channel - .from(params.input_paths) - .map { row -> [ row[0], [ file(row[1][0], checkIfExists: true) ] ] } - .ifEmpty { exit 1, 'params.input_paths was empty - no input files supplied' } - .into { ch_read_files_fastqc; ch_read_files_trimming } - } else { - Channel - .from(params.input_paths) - .map { row -> [ row[0], [ file(row[1][0], checkIfExists: true), file(row[1][1], checkIfExists: true) ] ] } - .ifEmpty { exit 1, 'params.input_paths was empty - no input files supplied' } - .into { ch_read_files_fastqc; ch_read_files_trimming } - } -} else { - Channel - .fromFilePairs(params.input, size: params.single_end ? 1 : 2) - .ifEmpty { exit 1, "Cannot find any reads matching: ${params.input}\nNB: Path needs to be enclosed in quotes!\nIf this is single-end data, please specify --single_end on the command line." } - .into { ch_read_files_fastqc; ch_read_files_trimming } -} - -//////////////////////////////////////////////////// -/* -- PRINT PARAMETER SUMMARY -- */ -//////////////////////////////////////////////////// -log.info NfcoreSchema.params_summary_log(workflow, params, json_schema) - -// Header log info -def summary = [:] -if (workflow.revision) summary['Pipeline Release'] = workflow.revision -summary['Run Name'] = workflow.runName -// TODO nf-core: Report custom parameters here -summary['Input'] = params.input -summary['Fasta Ref'] = params.fasta -summary['Data Type'] = params.single_end ? 'Single-End' : 'Paired-End' -summary['Max Resources'] = "$params.max_memory memory, $params.max_cpus cpus, $params.max_time time per job" -if (workflow.containerEngine) summary['Container'] = "$workflow.containerEngine - $workflow.container" -summary['Output dir'] = params.outdir -summary['Launch dir'] = workflow.launchDir -summary['Working dir'] = workflow.workDir -summary['Script dir'] = workflow.projectDir -summary['User'] = workflow.userName -if (workflow.profile.contains('awsbatch')) { - summary['AWS Region'] = params.awsregion - summary['AWS Queue'] = params.awsqueue - summary['AWS CLI'] = params.awscli -} -summary['Config Profile'] = workflow.profile -if (params.config_profile_description) summary['Config Profile Description'] = params.config_profile_description -if (params.config_profile_contact) summary['Config Profile Contact'] = params.config_profile_contact -if (params.config_profile_url) summary['Config Profile URL'] = params.config_profile_url -summary['Config Files'] = workflow.configFiles.join(', ') -if (params.email || params.email_on_fail) { - summary['E-mail Address'] = params.email - summary['E-mail on failure'] = params.email_on_fail - summary['MultiQC maxsize'] = params.max_multiqc_email_size -} - -// Check the hostnames against configured profiles -checkHostname() - -Channel.from(summary.collect{ [it.key, it.value] }) - .map { k,v -> "
$k
${v ?: 'N/A'}
" } - .reduce { a, b -> return [a, b].join("\n ") } - .map { x -> """ - id: 'nf-core-rnaseq-summary' - description: " - this information is collected when the pipeline is started." - section_name: 'nf-core/rnaseq Workflow Summary' - section_href: 'https://github.com/nf-core/rnaseq' - plot_type: 'html' - data: | -
- $x -
- """.stripIndent() } - .set { ch_workflow_summary } - -/* - * Parse software version numbers - */ -process get_software_versions { - publishDir "${params.outdir}/pipeline_info", mode: params.publish_dir_mode, - saveAs: { filename -> - if (filename.indexOf('.csv') > 0) filename - else null - } - - output: - file 'software_versions_mqc.yaml' into ch_software_versions_yaml - file 'software_versions.csv' +======================================================================================== + GENOME PARAMETER VALUES +======================================================================================== +*/ - script: - // TODO nf-core: Get all tools to print their version number here - """ - echo $workflow.manifest.version > v_pipeline.txt - echo $workflow.nextflow.version > v_nextflow.txt - fastqc --version > v_fastqc.txt - multiqc --version > v_multiqc.txt - scrape_software_versions.py &> software_versions_mqc.yaml - """ -} +params.fasta = WorkflowMain.getGenomeAttribute(params, 'fasta') /* - * STEP 1 - FastQC - */ -process fastqc { - tag "$name" - label 'process_medium' - publishDir "${params.outdir}/fastqc", mode: params.publish_dir_mode, - saveAs: { filename -> - filename.indexOf('.zip') > 0 ? "zips/$filename" : "$filename" - } - - input: - set val(name), file(reads) from ch_read_files_fastqc - - output: - file '*_fastqc.{zip,html}' into ch_fastqc_results +======================================================================================== + VALIDATE & PRINT PARAMETER SUMMARY +======================================================================================== +*/ - script: - """ - fastqc --quiet --threads $task.cpus $reads - """ -} +WorkflowMain.initialise(workflow, params, log) /* - * STEP 2 - MultiQC - */ -process multiqc { - publishDir "${params.outdir}/MultiQC", mode: params.publish_dir_mode - - input: - file (multiqc_config) from ch_multiqc_config - file (mqc_custom_config) from ch_multiqc_custom_config.collect().ifEmpty([]) - // TODO nf-core: Add in log files from your new processes for MultiQC to find! - file ('fastqc/*') from ch_fastqc_results.collect().ifEmpty([]) - file ('software_versions/*') from ch_software_versions_yaml.collect() - file workflow_summary from ch_workflow_summary.collectFile(name: "workflow_summary_mqc.yaml") +======================================================================================== + NAMED WORKFLOW FOR PIPELINE +======================================================================================== +*/ - output: - file "*multiqc_report.html" into ch_multiqc_report - file "*_data" - file "multiqc_plots" +include { RNASEQ } from './workflows/rnaseq' - script: - rtitle = '' - rfilename = '' - if (!(workflow.runName ==~ /[a-z]+_[a-z]+/)) { - rtitle = "--title \"${workflow.runName}\"" - rfilename = "--filename " + workflow.runName.replaceAll('\\W','_').replaceAll('_+','_') + "_multiqc_report" - } - custom_config_file = params.multiqc_config ? "--config $mqc_custom_config" : '' - // TODO nf-core: Specify which MultiQC modules to use with -m for a faster run time - """ - multiqc -f $rtitle $rfilename $custom_config_file . - """ +// +// WORKFLOW: Run main nf-core/rnaseq analysis pipeline +// +workflow NFCORE_RNASEQ { + RNASEQ () } /* - * STEP 3 - Output Description HTML - */ -process output_documentation { - publishDir "${params.outdir}/pipeline_info", mode: params.publish_dir_mode - - input: - file output_docs from ch_output_docs - file images from ch_output_docs_images - - output: - file 'results_description.html' +======================================================================================== + RUN ALL WORKFLOWS +======================================================================================== +*/ - script: - """ - markdown_to_html.py $output_docs -o results_description.html - """ +// +// WORKFLOW: Execute a single named workflow for the pipeline +// See: https://github.com/nf-core/rnaseq/issues/619 +// +workflow { + NFCORE_RNASEQ () } /* - * Completion e-mail notification - */ -workflow.onComplete { - - // Set up the e-mail variables - def subject = "[nf-core/rnaseq] Successful: $workflow.runName" - if (!workflow.success) { - subject = "[nf-core/rnaseq] FAILED: $workflow.runName" - } - def email_fields = [:] - email_fields['version'] = workflow.manifest.version - email_fields['runName'] = workflow.runName - email_fields['success'] = workflow.success - email_fields['dateComplete'] = workflow.complete - email_fields['duration'] = workflow.duration - email_fields['exitStatus'] = workflow.exitStatus - email_fields['errorMessage'] = (workflow.errorMessage ?: 'None') - email_fields['errorReport'] = (workflow.errorReport ?: 'None') - email_fields['commandLine'] = workflow.commandLine - email_fields['projectDir'] = workflow.projectDir - email_fields['summary'] = summary - email_fields['summary']['Date Started'] = workflow.start - email_fields['summary']['Date Completed'] = workflow.complete - email_fields['summary']['Pipeline script file path'] = workflow.scriptFile - email_fields['summary']['Pipeline script hash ID'] = workflow.scriptId - if (workflow.repository) email_fields['summary']['Pipeline repository Git URL'] = workflow.repository - if (workflow.commitId) email_fields['summary']['Pipeline repository Git Commit'] = workflow.commitId - if (workflow.revision) email_fields['summary']['Pipeline Git branch/tag'] = workflow.revision - email_fields['summary']['Nextflow Version'] = workflow.nextflow.version - email_fields['summary']['Nextflow Build'] = workflow.nextflow.build - email_fields['summary']['Nextflow Compile Timestamp'] = workflow.nextflow.timestamp - - // TODO nf-core: If not using MultiQC, strip out this code (including params.max_multiqc_email_size) - // On success try attach the multiqc report - def mqc_report = null - try { - if (workflow.success) { - mqc_report = ch_multiqc_report.getVal() - if (mqc_report.getClass() == ArrayList) { - log.warn "[nf-core/rnaseq] Found multiple reports from process 'multiqc', will use only one" - mqc_report = mqc_report[0] - } - } - } catch (all) { - log.warn "[nf-core/rnaseq] Could not attach MultiQC report to summary email" - } - - // Check if we are only sending emails on failure - email_address = params.email - if (!params.email && params.email_on_fail && !workflow.success) { - email_address = params.email_on_fail - } - - // Render the TXT template - def engine = new groovy.text.GStringTemplateEngine() - def tf = new File("$projectDir/assets/email_template.txt") - def txt_template = engine.createTemplate(tf).make(email_fields) - def email_txt = txt_template.toString() - - // Render the HTML template - def hf = new File("$projectDir/assets/email_template.html") - def html_template = engine.createTemplate(hf).make(email_fields) - def email_html = html_template.toString() - - // Render the sendmail template - def smail_fields = [ email: email_address, subject: subject, email_txt: email_txt, email_html: email_html, projectDir: "$projectDir", mqcFile: mqc_report, mqcMaxSize: params.max_multiqc_email_size.toBytes() ] - def sf = new File("$projectDir/assets/sendmail_template.txt") - def sendmail_template = engine.createTemplate(sf).make(smail_fields) - def sendmail_html = sendmail_template.toString() - - // Send the HTML e-mail - if (email_address) { - try { - if (params.plaintext_email) { throw GroovyException('Send plaintext e-mail, not HTML') } - // Try to send HTML e-mail using sendmail - [ 'sendmail', '-t' ].execute() << sendmail_html - log.info "[nf-core/rnaseq] Sent summary e-mail to $email_address (sendmail)" - } catch (all) { - // Catch failures and try with plaintext - def mail_cmd = [ 'mail', '-s', subject, '--content-type=text/html', email_address ] - if ( mqc_report.size() <= params.max_multiqc_email_size.toBytes() ) { - mail_cmd += [ '-A', mqc_report ] - } - mail_cmd.execute() << email_html - log.info "[nf-core/rnaseq] Sent summary e-mail to $email_address (mail)" - } - } - - // Write summary e-mail HTML to a file - def output_d = new File("${params.outdir}/pipeline_info/") - if (!output_d.exists()) { - output_d.mkdirs() - } - def output_hf = new File(output_d, "pipeline_report.html") - output_hf.withWriter { w -> w << email_html } - def output_tf = new File(output_d, "pipeline_report.txt") - output_tf.withWriter { w -> w << email_txt } - - c_green = params.monochrome_logs ? '' : "\033[0;32m"; - c_purple = params.monochrome_logs ? '' : "\033[0;35m"; - c_red = params.monochrome_logs ? '' : "\033[0;31m"; - c_reset = params.monochrome_logs ? '' : "\033[0m"; - - if (workflow.stats.ignoredCount > 0 && workflow.success) { - log.info "-${c_purple}Warning, pipeline completed, but with errored process(es) ${c_reset}-" - log.info "-${c_red}Number of ignored errored process(es) : ${workflow.stats.ignoredCount} ${c_reset}-" - log.info "-${c_green}Number of successfully ran process(es) : ${workflow.stats.succeedCount} ${c_reset}-" - } - - if (workflow.success) { - log.info "-${c_purple}[nf-core/rnaseq]${c_green} Pipeline completed successfully${c_reset}-" - } else { - checkHostname() - log.info "-${c_purple}[nf-core/rnaseq]${c_red} Pipeline completed with errors${c_reset}-" - } - -} - -workflow.onError { - // Print unexpected parameters - easiest is to just rerun validation - NfcoreSchema.validateParameters(params, json_schema, log) -} - -def checkHostname() { - def c_reset = params.monochrome_logs ? '' : "\033[0m" - def c_white = params.monochrome_logs ? '' : "\033[0;37m" - def c_red = params.monochrome_logs ? '' : "\033[1;91m" - def c_yellow_bold = params.monochrome_logs ? '' : "\033[1;93m" - if (params.hostnames) { - def hostname = 'hostname'.execute().text.trim() - params.hostnames.each { prof, hnames -> - hnames.each { hname -> - if (hostname.contains(hname) && !workflow.profile.contains(prof)) { - log.error "${c_red}====================================================${c_reset}\n" + - " ${c_red}WARNING!${c_reset} You are running with `-profile $workflow.profile`\n" + - " but your machine hostname is ${c_white}'$hostname'${c_reset}\n" + - " ${c_yellow_bold}It's highly recommended that you use `-profile $prof${c_reset}`\n" + - "${c_red}====================================================${c_reset}\n" - } - } - } - } -} +======================================================================================== + THE END +======================================================================================== +*/ diff --git a/modules.json b/modules.json new file mode 100644 index 000000000..e3139db6b --- /dev/null +++ b/modules.json @@ -0,0 +1,14 @@ +{ + "name": "nf-core/rnaseq", + "homePage": "https://github.com/nf-core/rnaseq", + "repos": { + "nf-core/modules": { + "fastqc": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "multiqc": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + } + } + } +} diff --git a/modules/local/functions.nf b/modules/local/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/local/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/local/get_software_versions.nf b/modules/local/get_software_versions.nf new file mode 100644 index 000000000..0b9a3453d --- /dev/null +++ b/modules/local/get_software_versions.nf @@ -0,0 +1,33 @@ +// Import generic module functions +include { saveFiles } from './functions' + +params.options = [:] + +process GET_SOFTWARE_VERSIONS { + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:'pipeline_info', meta:[:], publish_by_meta:[]) } + + conda (params.enable_conda ? "conda-forge::python=3.8.3" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/python:3.8.3" + } else { + container "quay.io/biocontainers/python:3.8.3" + } + + cache false + + input: + path versions + + output: + path "software_versions.tsv" , emit: tsv + path 'software_versions_mqc.yaml', emit: yaml + + script: // This script is bundled with the pipeline, in nf-core/rnaseq/bin/ + """ + echo $workflow.manifest.version > pipeline.version.txt + echo $workflow.nextflow.version > nextflow.version.txt + scrape_software_versions.py &> software_versions_mqc.yaml + """ +} diff --git a/modules/local/samplesheet_check.nf b/modules/local/samplesheet_check.nf new file mode 100644 index 000000000..595485f5e --- /dev/null +++ b/modules/local/samplesheet_check.nf @@ -0,0 +1,31 @@ +// Import generic module functions +include { saveFiles } from './functions' + +params.options = [:] + +process SAMPLESHEET_CHECK { + tag "$samplesheet" + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:'pipeline_info', meta:[:], publish_by_meta:[]) } + + conda (params.enable_conda ? "conda-forge::python=3.8.3" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/python:3.8.3" + } else { + container "quay.io/biocontainers/python:3.8.3" + } + + input: + path samplesheet + + output: + path '*.csv' + + script: // This script is bundled with the pipeline, in nf-core/rnaseq/bin/ + """ + check_samplesheet.py \\ + $samplesheet \\ + samplesheet.valid.csv + """ +} diff --git a/modules/nf-core/modules/fastqc/functions.nf b/modules/nf-core/modules/fastqc/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/fastqc/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/fastqc/main.nf b/modules/nf-core/modules/fastqc/main.nf new file mode 100644 index 000000000..39c327b26 --- /dev/null +++ b/modules/nf-core/modules/fastqc/main.nf @@ -0,0 +1,47 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process FASTQC { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::fastqc=0.11.9" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/fastqc:0.11.9--0" + } else { + container "quay.io/biocontainers/fastqc:0.11.9--0" + } + + input: + tuple val(meta), path(reads) + + output: + tuple val(meta), path("*.html"), emit: html + tuple val(meta), path("*.zip") , emit: zip + path "*.version.txt" , emit: version + + script: + // Add soft-links to original FastQs for consistent naming in pipeline + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + if (meta.single_end) { + """ + [ ! -f ${prefix}.fastq.gz ] && ln -s $reads ${prefix}.fastq.gz + fastqc $options.args --threads $task.cpus ${prefix}.fastq.gz + fastqc --version | sed -e "s/FastQC v//g" > ${software}.version.txt + """ + } else { + """ + [ ! -f ${prefix}_1.fastq.gz ] && ln -s ${reads[0]} ${prefix}_1.fastq.gz + [ ! -f ${prefix}_2.fastq.gz ] && ln -s ${reads[1]} ${prefix}_2.fastq.gz + fastqc $options.args --threads $task.cpus ${prefix}_1.fastq.gz ${prefix}_2.fastq.gz + fastqc --version | sed -e "s/FastQC v//g" > ${software}.version.txt + """ + } +} diff --git a/modules/nf-core/modules/fastqc/meta.yml b/modules/nf-core/modules/fastqc/meta.yml new file mode 100644 index 000000000..8eb9953dc --- /dev/null +++ b/modules/nf-core/modules/fastqc/meta.yml @@ -0,0 +1,51 @@ +name: fastqc +description: Run FastQC on sequenced reads +keywords: + - quality control + - qc + - adapters + - fastq +tools: + - fastqc: + description: | + FastQC gives general quality metrics about your reads. + It provides information about the quality score distribution + across your reads, the per base sequence content (%A/C/G/T). + You get information about adapter contamination and other + overrepresented sequences. + homepage: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/ + documentation: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/ +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - reads: + type: file + description: | + List of input FastQ files of size 1 and 2 for single-end and paired-end data, + respectively. +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - html: + type: file + description: FastQC report + pattern: "*_{fastqc.html}" + - zip: + type: file + description: FastQC report archive + pattern: "*_{fastqc.zip}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" + - "@grst" + - "@ewels" + - "@FelixKrueger" diff --git a/modules/nf-core/modules/multiqc/functions.nf b/modules/nf-core/modules/multiqc/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/multiqc/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/multiqc/main.nf b/modules/nf-core/modules/multiqc/main.nf new file mode 100644 index 000000000..da7808002 --- /dev/null +++ b/modules/nf-core/modules/multiqc/main.nf @@ -0,0 +1,35 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process MULTIQC { + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) } + + conda (params.enable_conda ? "bioconda::multiqc=1.10.1" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/multiqc:1.10.1--py_0" + } else { + container "quay.io/biocontainers/multiqc:1.10.1--py_0" + } + + input: + path multiqc_files + + output: + path "*multiqc_report.html", emit: report + path "*_data" , emit: data + path "*_plots" , optional:true, emit: plots + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + """ + multiqc -f $options.args . + multiqc --version | sed -e "s/multiqc, version //g" > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/multiqc/meta.yml b/modules/nf-core/modules/multiqc/meta.yml new file mode 100644 index 000000000..532a8bb1e --- /dev/null +++ b/modules/nf-core/modules/multiqc/meta.yml @@ -0,0 +1,39 @@ +name: MultiQC +description: Aggregate results from bioinformatics analyses across many samples into a single report +keywords: + - QC + - bioinformatics tools + - Beautiful stand-alone HTML report +tools: + - multiqc: + description: | + MultiQC searches a given directory for analysis logs and compiles a HTML report. + It's a general use tool, perfect for summarising the output from numerous bioinformatics tools. + homepage: https://multiqc.info/ + documentation: https://multiqc.info/docs/ +input: + - multiqc_files: + type: file + description: | + List of reports / files recognised by MultiQC, for example the html and zip output of FastQC +output: + - report: + type: file + description: MultiQC report file + pattern: "multiqc_report.html" + - data: + type: dir + description: MultiQC data dir + pattern: "multiqc_data" + - plots: + type: file + description: Plots created by MultiQC + pattern: "*_data" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@abhi18av" + - "@bunop" + - "@drpatelh" diff --git a/nextflow.config b/nextflow.config index b2f1b4e01..8f1ed9c5a 100644 --- a/nextflow.config +++ b/nextflow.config @@ -1,130 +1,136 @@ /* - * ------------------------------------------------- - * nf-core/rnaseq Nextflow config file - * ------------------------------------------------- - * Default config options for all environments. - */ +======================================================================================== + nf-core/rnaseq Nextflow config file +======================================================================================== + Default config options for all compute environments +---------------------------------------------------------------------------------------- +*/ // Global default params, used in configs params { - // Workflow flags - // TODO nf-core: Specify your pipeline's command line flags - genome = false - input = null - input_paths = null - single_end = false - outdir = './results' - publish_dir_mode = 'copy' - - // Boilerplate options - multiqc_config = false - email = false - email_on_fail = false - max_multiqc_email_size = 25.MB - plaintext_email = false - monochrome_logs = false - help = false - igenomes_base = 's3://ngi-igenomes/igenomes' - tracedir = "${params.outdir}/pipeline_info" - igenomes_ignore = false - custom_config_version = 'master' - custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}" - hostnames = false - config_profile_name = null - config_profile_description = false - config_profile_contact = false - config_profile_url = false - validate_params = true - show_hidden_params = false - schema_ignore_params = 'genomes,input_paths' - - // Defaults only, expecting to be overwritten - max_memory = 128.GB - max_cpus = 16 - max_time = 240.h + // TODO nf-core: Specify your pipeline's command line flags + // Input options + input = null -} + // References + genome = null + igenomes_base = 's3://ngi-igenomes/igenomes' + igenomes_ignore = false + + // MultiQC options + multiqc_config = null + multiqc_title = null + max_multiqc_email_size = '25.MB' + + // Boilerplate options + outdir = './results' + tracedir = "${params.outdir}/pipeline_info" + publish_dir_mode = 'copy' + email = null + email_on_fail = null + plaintext_email = false + monochrome_logs = false + help = false + validate_params = true + show_hidden_params = false + schema_ignore_params = 'genomes,modules' + enable_conda = false + singularity_pull_docker_container = false -// Container slug. Stable releases should specify release tag! -// Developmental code should specify :dev -process.container = 'nfcore/rnaseq:dev' + // Config options + custom_config_version = 'master' + custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}" + hostnames = [:] + config_profile_description = null + config_profile_contact = null + config_profile_url = null + config_profile_name = null + + // Max resource options + // Defaults only, expecting to be overwritten + max_memory = '128.GB' + max_cpus = 16 + max_time = '240.h' + +} // Load base.config by default for all pipelines includeConfig 'conf/base.config' +// Load modules.config for DSL2 module specific options +includeConfig 'conf/modules.config' + // Load nf-core custom profiles from different Institutions try { - includeConfig "${params.custom_config_base}/nfcore_custom.config" + includeConfig "${params.custom_config_base}/nfcore_custom.config" } catch (Exception e) { - System.err.println("WARNING: Could not load nf-core/config profiles: ${params.custom_config_base}/nfcore_custom.config") -} - -profiles { - conda { - docker.enabled = false - singularity.enabled = false - podman.enabled = false - shifter.enabled = false - charliecloud.enabled = false - process.conda = "$projectDir/environment.yml" - } - debug { process.beforeScript = 'echo $HOSTNAME' } - docker { - docker.enabled = true - singularity.enabled = false - podman.enabled = false - shifter.enabled = false - charliecloud.enabled = false - // Avoid this error: - // WARNING: Your kernel does not support swap limit capabilities or the cgroup is not mounted. Memory limited without swap. - // Testing this in nf-core after discussion here https://github.com/nf-core/tools/pull/351 - // once this is established and works well, nextflow might implement this behavior as new default. - docker.runOptions = '-u \$(id -u):\$(id -g)' - } - singularity { - docker.enabled = false - singularity.enabled = true - podman.enabled = false - shifter.enabled = false - charliecloud.enabled = false - singularity.autoMounts = true - } - podman { - singularity.enabled = false - docker.enabled = false - podman.enabled = true - shifter.enabled = false - charliecloud.enabled = false - } - shifter { - singularity.enabled = false - docker.enabled = false - podman.enabled = false - shifter.enabled = true - charliecloud.enabled = false - } - charliecloud { - singularity.enabled = false - docker.enabled = false - podman.enabled = false - shifter.enabled = false - charliecloud.enabled = true - } - test { includeConfig 'conf/test.config' } - test_full { includeConfig 'conf/test_full.config' } + System.err.println("WARNING: Could not load nf-core/config profiles: ${params.custom_config_base}/nfcore_custom.config") } // Load igenomes.config if required if (!params.igenomes_ignore) { - includeConfig 'conf/igenomes.config' + includeConfig 'conf/igenomes.config' +} else { + params.genomes = [:] +} + +profiles { + debug { process.beforeScript = 'echo $HOSTNAME' } + conda { + params.enable_conda = true + docker.enabled = false + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false + } + docker { + docker.enabled = true + docker.userEmulation = true + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false + } + singularity { + singularity.enabled = true + singularity.autoMounts = true + docker.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false + } + podman { + podman.enabled = true + docker.enabled = false + singularity.enabled = false + shifter.enabled = false + charliecloud.enabled = false + } + shifter { + shifter.enabled = true + docker.enabled = false + singularity.enabled = false + podman.enabled = false + charliecloud.enabled = false + } + charliecloud { + charliecloud.enabled = true + docker.enabled = false + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + } + test { includeConfig 'conf/test.config' } + test_full { includeConfig 'conf/test_full.config' } } // Export these variables to prevent local Python/R libraries from conflicting with those in the container env { - PYTHONNOUSERSITE = 1 - R_PROFILE_USER = "/.Rprofile" - R_ENVIRON_USER = "/.Renviron" + PYTHONNOUSERSITE = 1 + R_PROFILE_USER = "/.Rprofile" + R_ENVIRON_USER = "/.Renviron" } // Capture exit codes from upstream processes when piping @@ -132,61 +138,61 @@ process.shell = ['/bin/bash', '-euo', 'pipefail'] def trace_timestamp = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss') timeline { - enabled = true - file = "${params.tracedir}/execution_timeline_${trace_timestamp}.html" + enabled = true + file = "${params.tracedir}/execution_timeline_${trace_timestamp}.html" } report { - enabled = true - file = "${params.tracedir}/execution_report_${trace_timestamp}.html" + enabled = true + file = "${params.tracedir}/execution_report_${trace_timestamp}.html" } trace { - enabled = true - file = "${params.tracedir}/execution_trace_${trace_timestamp}.txt" + enabled = true + file = "${params.tracedir}/execution_trace_${trace_timestamp}.txt" } dag { - enabled = true - file = "${params.tracedir}/pipeline_dag_${trace_timestamp}.svg" + enabled = true + file = "${params.tracedir}/pipeline_dag_${trace_timestamp}.svg" } manifest { - name = 'nf-core/rnaseq' - author = 'Phil Ewels, Rickard Hammarén' - homePage = 'https://github.com/nf-core/rnaseq' - description = 'Nextflow RNA-Seq analysis pipeline, part of the nf-core community.' - mainScript = 'main.nf' - nextflowVersion = '>=20.04.0' - version = '3.1' + name = 'nf-core/rnaseq' + author = 'Phil Ewels, Rickard Hammarén' + homePage = 'https://github.com/nf-core/rnaseq' + description = 'Nextflow RNA-Seq analysis pipeline, part of the nf-core community.' + mainScript = 'main.nf' + nextflowVersion = '!>=21.04.0' + version = '3.3dev' } // Function to ensure that resource requirements don't go beyond // a maximum limit def check_max(obj, type) { - if (type == 'memory') { - try { - if (obj.compareTo(params.max_memory as nextflow.util.MemoryUnit) == 1) - return params.max_memory as nextflow.util.MemoryUnit - else - return obj - } catch (all) { - println " ### ERROR ### Max memory '${params.max_memory}' is not valid! Using default value: $obj" - return obj - } - } else if (type == 'time') { - try { - if (obj.compareTo(params.max_time as nextflow.util.Duration) == 1) - return params.max_time as nextflow.util.Duration - else - return obj - } catch (all) { - println " ### ERROR ### Max time '${params.max_time}' is not valid! Using default value: $obj" - return obj - } - } else if (type == 'cpus') { - try { - return Math.min( obj, params.max_cpus as int ) - } catch (all) { - println " ### ERROR ### Max cpus '${params.max_cpus}' is not valid! Using default value: $obj" - return obj + if (type == 'memory') { + try { + if (obj.compareTo(params.max_memory as nextflow.util.MemoryUnit) == 1) + return params.max_memory as nextflow.util.MemoryUnit + else + return obj + } catch (all) { + println " ### ERROR ### Max memory '${params.max_memory}' is not valid! Using default value: $obj" + return obj + } + } else if (type == 'time') { + try { + if (obj.compareTo(params.max_time as nextflow.util.Duration) == 1) + return params.max_time as nextflow.util.Duration + else + return obj + } catch (all) { + println " ### ERROR ### Max time '${params.max_time}' is not valid! Using default value: $obj" + return obj + } + } else if (type == 'cpus') { + try { + return Math.min( obj, params.max_cpus as int ) + } catch (all) { + println " ### ERROR ### Max cpus '${params.max_cpus}' is not valid! Using default value: $obj" + return obj + } } - } } diff --git a/nextflow_schema.json b/nextflow_schema.json index dce5cd53f..7e4c45fa5 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -16,19 +16,17 @@ "properties": { "input": { "type": "string", - "fa_icon": "fas fa-dna", - "description": "Input FastQ files.", - "help_text": "Use this to specify the location of your input FastQ files. For example:\n\n```bash\n--input 'path/to/data/sample_*_{1,2}.fastq'\n```\n\nPlease note the following requirements:\n\n1. The path must be enclosed in quotes\n2. The path must have at least one `*` wildcard character\n3. When using the pipeline with paired end data, the path must use `{1,2}` notation to specify read pairs.\n\nIf left unspecified, a default pattern is used: `data/*{1,2}.fastq.gz`" - }, - "single_end": { - "type": "boolean", - "description": "Specifies that the input is single-end reads.", - "fa_icon": "fas fa-align-center", - "help_text": "By default, the pipeline expects paired-end data. If you have single-end data, you need to specify `--single_end` on the command line when you launch the pipeline. A normal glob pattern, enclosed in quotation marks, can then be used for `--input`. For example:\n\n```bash\n--single_end --input '*.fastq'\n```\n\nIt is not possible to run a mixture of single-end and paired-end files in one run." + "format": "file-path", + "mimetype": "text/csv", + "pattern": "\\.csv$", + "schema": "assets/schema_input.json", + "description": "Path to comma-separated file containing information about the samples in the experiment.", + "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row. See [usage docs](https://nf-co.re/rnaseq/usage#samplesheet-input).", + "fa_icon": "fas fa-file-csv" }, "outdir": { "type": "string", - "description": "The output directory where the results will be saved.", + "description": "Path to the output directory where the results will be saved.", "default": "./results", "fa_icon": "fas fa-folder-open" }, @@ -38,6 +36,11 @@ "fa_icon": "fas fa-envelope", "help_text": "Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.", "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$" + }, + "multiqc_title": { + "type": "string", + "description": "MultiQC report title. Printed as page header, used for filename if not otherwise specified.", + "fa_icon": "fas fa-file-signature" } } }, @@ -45,22 +48,26 @@ "title": "Reference genome options", "type": "object", "fa_icon": "fas fa-dna", - "description": "Options for the reference genome indices used to align reads.", + "description": "Reference genome related files and options required for the workflow.", "properties": { "genome": { "type": "string", "description": "Name of iGenomes reference.", "fa_icon": "fas fa-book", - "help_text": "If using a reference genome configured in the pipeline using iGenomes, use this parameter to give the ID for the reference. This is then used to build the full paths for all required reference genome files e.g. `--genome GRCh38`.\n\nSee the [nf-core website docs](https://nf-co.re/usage/reference_genomes) for more details." + "help_text": "If using a reference genome configured in the pipeline using iGenomes, use this parameter to give the ID for the reference. This is then used to build the full paths for all required reference genome files e.g. `--genome GRCh38`. \n\nSee the [nf-core website docs](https://nf-co.re/usage/reference_genomes) for more details." }, "fasta": { "type": "string", - "fa_icon": "fas fa-font", + "format": "file-path", + "mimetype": "text/plain", + "pattern": "\\.fn?a(sta)?(\\.gz)?$", "description": "Path to FASTA genome file.", - "help_text": "If you have no genome reference available, the pipeline can build one using a FASTA file. This requires additional time and resources, so it's better to use a pre-build index if possible." + "help_text": "This parameter is *mandatory* if `--genome` is not specified. If you don't have a BWA index available this will be generated for you automatically. Combine with `--save_reference` to save BWA index for future runs.", + "fa_icon": "far fa-file-code" }, "igenomes_base": { "type": "string", + "format": "directory-path", "description": "Directory / URL base for iGenomes references.", "default": "s3://ngi-igenomes/igenomes", "fa_icon": "fas fa-cloud-download-alt", @@ -75,91 +82,57 @@ } } }, - "generic_options": { - "title": "Generic options", + "institutional_config_options": { + "title": "Institutional config options", "type": "object", - "fa_icon": "fas fa-file-import", - "description": "Less common options for the pipeline, typically set in a config file.", - "help_text": "These options are common to all nf-core pipelines and allow you to customise some of the core preferences for how the pipeline runs.\n\nTypically these options would be set in a Nextflow config file loaded for all pipeline runs, such as `~/.nextflow/config`.", + "fa_icon": "fas fa-university", + "description": "Parameters used to describe centralised config profiles. These should not be edited.", + "help_text": "The centralised nf-core configuration profiles use a handful of pipeline parameters to describe themselves. This information is then printed to the Nextflow log when you run a pipeline. You should not need to change these values when you run a pipeline.", "properties": { - "help": { - "type": "boolean", - "description": "Display help text.", - "hidden": true, - "fa_icon": "fas fa-question-circle" - }, - "publish_dir_mode": { + "custom_config_version": { "type": "string", - "default": "copy", + "description": "Git commit id for Institutional configs.", + "default": "master", "hidden": true, - "description": "Method used to save pipeline results to output directory.", - "help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.", - "fa_icon": "fas fa-copy", - "enum": [ - "symlink", - "rellink", - "link", - "copy", - "copyNoFollow", - "move" - ] - }, - "validate_params": { - "type": "boolean", - "description": "Boolean whether to validate parameters against the schema at runtime", - "default": true, - "fa_icon": "fas fa-check-square", - "hidden": true + "fa_icon": "fas fa-users-cog" }, - "email_on_fail": { + "custom_config_base": { "type": "string", - "description": "Email address for completion summary, only when pipeline fails.", - "fa_icon": "fas fa-exclamation-triangle", - "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$", + "description": "Base directory for Institutional configs.", + "default": "https://raw.githubusercontent.com/nf-core/configs/master", "hidden": true, - "help_text": "This works exactly as with `--email`, except emails are only sent if the workflow is not successful." + "help_text": "If you're running offline, Nextflow will not be able to fetch the institutional config files from the internet. If you don't need them, then this is not a problem. If you do need them, you should download the files from the repo and tell Nextflow where to find them with this parameter.", + "fa_icon": "fas fa-users-cog" }, - "plaintext_email": { - "type": "boolean", - "description": "Send plain-text email instead of HTML.", - "fa_icon": "fas fa-remove-format", + "hostnames": { + "type": "string", + "description": "Institutional configs hostname.", "hidden": true, - "help_text": "Set to receive plain-text e-mails instead of HTML formatted." + "fa_icon": "fas fa-users-cog" }, - "max_multiqc_email_size": { + "config_profile_name": { "type": "string", - "description": "File size limit when attaching MultiQC reports to summary emails.", - "default": "25.MB", - "fa_icon": "fas fa-file-upload", + "description": "Institutional config name.", "hidden": true, - "help_text": "If file generated by pipeline exceeds the threshold, it will not be attached." + "fa_icon": "fas fa-users-cog" }, - "monochrome_logs": { - "type": "boolean", - "description": "Do not use coloured log outputs.", - "fa_icon": "fas fa-palette", + "config_profile_description": { + "type": "string", + "description": "Institutional config description.", "hidden": true, - "help_text": "Set to disable colourful command line output and live life in monochrome." + "fa_icon": "fas fa-users-cog" }, - "multiqc_config": { + "config_profile_contact": { "type": "string", - "description": "Custom config file to supply to MultiQC.", - "fa_icon": "fas fa-cog", - "hidden": true + "description": "Institutional config contact information.", + "hidden": true, + "fa_icon": "fas fa-users-cog" }, - "tracedir": { + "config_profile_url": { "type": "string", - "description": "Directory to keep pipeline Nextflow logs and reports.", - "default": "${params.outdir}/pipeline_info", - "fa_icon": "fas fa-cogs", - "hidden": true - }, - "show_hidden_params": { - "type": "boolean", - "fa_icon": "far fa-eye-slash", - "description": "Show all params when using `--help`", + "description": "Institutional config URL link.", "hidden": true, - "help_text": "By default, parameters set as _hidden_ in the schema are not shown on the command line when a user runs with `--help`. Specifying this option will tell the pipeline to show all parameters." + "fa_icon": "fas fa-users-cog" } } }, @@ -172,7 +145,7 @@ "properties": { "max_cpus": { "type": "integer", - "description": "Maximum number of CPUs that can be requested for any single job.", + "description": "Maximum number of CPUs that can be requested for any single job.", "default": 16, "fa_icon": "fas fa-microchip", "hidden": true, @@ -198,58 +171,102 @@ } } }, - "institutional_config_options": { - "title": "Institutional config options", + "generic_options": { + "title": "Generic options", "type": "object", - "fa_icon": "fas fa-university", - "description": "Parameters used to describe centralised config profiles. These should not be edited.", - "help_text": "The centralised nf-core configuration profiles use a handful of pipeline parameters to describe themselves. This information is then printed to the Nextflow log when you run a pipeline. You should not need to change these values when you run a pipeline.", + "fa_icon": "fas fa-file-import", + "description": "Less common options for the pipeline, typically set in a config file.", + "help_text": "These options are common to all nf-core pipelines and allow you to customise some of the core preferences for how the pipeline runs.\n\nTypically these options would be set in a Nextflow config file loaded for all pipeline runs, such as `~/.nextflow/config`.", "properties": { - "custom_config_version": { + "help": { + "type": "boolean", + "description": "Display help text.", + "fa_icon": "fas fa-question-circle", + "hidden": true + }, + "publish_dir_mode": { "type": "string", - "description": "Git commit id for Institutional configs.", - "default": "master", - "hidden": true, - "fa_icon": "fas fa-users-cog", - "help_text": "Provide git commit id for custom Institutional configs hosted at `nf-core/configs`. This was implemented for reproducibility purposes. Default: `master`.\n\n```bash\n## Download and use config file with following git commit id\n--custom_config_version d52db660777c4bf36546ddb188ec530c3ada1b96\n```" + "default": "copy", + "description": "Method used to save pipeline results to output directory.", + "help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.", + "fa_icon": "fas fa-copy", + "enum": [ + "symlink", + "rellink", + "link", + "copy", + "copyNoFollow", + "move" + ], + "hidden": true }, - "custom_config_base": { + "email_on_fail": { "type": "string", - "description": "Base directory for Institutional configs.", - "default": "https://raw.githubusercontent.com/nf-core/configs/master", - "hidden": true, - "help_text": "If you're running offline, nextflow will not be able to fetch the institutional config files from the internet. If you don't need them, then this is not a problem. If you do need them, you should download the files from the repo and tell nextflow where to find them with the `custom_config_base` option. For example:\n\n```bash\n## Download and unzip the config files\ncd /path/to/my/configs\nwget https://github.com/nf-core/configs/archive/master.zip\nunzip master.zip\n\n## Run the pipeline\ncd /path/to/my/data\nnextflow run /path/to/pipeline/ --custom_config_base /path/to/my/configs/configs-master/\n```\n\n> Note that the nf-core/tools helper package has a `download` command to download all required pipeline files + singularity containers + institutional configs in one go for you, to make this process easier.", - "fa_icon": "fas fa-users-cog" + "description": "Email address for completion summary, only when pipeline fails.", + "fa_icon": "fas fa-exclamation-triangle", + "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$", + "help_text": "An email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.", + "hidden": true }, - "hostnames": { + "plaintext_email": { + "type": "boolean", + "description": "Send plain-text email instead of HTML.", + "fa_icon": "fas fa-remove-format", + "hidden": true + }, + "max_multiqc_email_size": { "type": "string", - "description": "Institutional configs hostname.", - "hidden": true, - "fa_icon": "fas fa-users-cog" + "description": "File size limit when attaching MultiQC reports to summary emails.", + "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$", + "default": "25.MB", + "fa_icon": "fas fa-file-upload", + "hidden": true }, - "config_profile_name": { + "monochrome_logs": { + "type": "boolean", + "description": "Do not use coloured log outputs.", + "fa_icon": "fas fa-palette", + "hidden": true + }, + "multiqc_config": { "type": "string", - "description": "Institutional config name.", - "hidden": true, - "fa_icon": "fas fa-users-cog" + "description": "Custom config file to supply to MultiQC.", + "fa_icon": "fas fa-cog", + "hidden": true }, - "config_profile_description": { + "tracedir": { "type": "string", - "description": "Institutional config description.", + "description": "Directory to keep pipeline Nextflow logs and reports.", + "default": "${params.outdir}/pipeline_info", + "fa_icon": "fas fa-cogs", + "hidden": true + }, + "validate_params": { + "type": "boolean", + "description": "Boolean whether to validate parameters against the schema at runtime", + "default": true, + "fa_icon": "fas fa-check-square", + "hidden": true + }, + "show_hidden_params": { + "type": "boolean", + "fa_icon": "far fa-eye-slash", + "description": "Show all params when using `--help`", "hidden": true, - "fa_icon": "fas fa-users-cog" + "help_text": "By default, parameters set as _hidden_ in the schema are not shown on the command line when a user runs with `--help`. Specifying this option will tell the pipeline to show all parameters." }, - "config_profile_contact": { - "type": "string", - "description": "Institutional config contact information.", + "enable_conda": { + "type": "boolean", + "description": "Run this workflow with Conda. You can also use '-profile conda' instead of providing this parameter.", "hidden": true, - "fa_icon": "fas fa-users-cog" + "fa_icon": "fas fa-bacon" }, - "config_profile_url": { - "type": "string", - "description": "Institutional config URL link.", + "singularity_pull_docker_container": { + "type": "boolean", + "description": "Instead of directly downloading Singularity images for use with Singularity, force the workflow to pull and convert Docker containers instead.", "hidden": true, - "fa_icon": "fas fa-users-cog" + "fa_icon": "fas fa-toolbox", + "help_text": "This may be useful for example if you are unable to directly pull Singularity containers to run the pipeline due to http/https proxy issues." } } } @@ -262,13 +279,13 @@ "$ref": "#/definitions/reference_genome_options" }, { - "$ref": "#/definitions/generic_options" + "$ref": "#/definitions/institutional_config_options" }, { "$ref": "#/definitions/max_job_request_options" }, { - "$ref": "#/definitions/institutional_config_options" + "$ref": "#/definitions/generic_options" } ] } diff --git a/subworkflows/local/input_check.nf b/subworkflows/local/input_check.nf new file mode 100644 index 000000000..b664bc8ca --- /dev/null +++ b/subworkflows/local/input_check.nf @@ -0,0 +1,42 @@ +// +// Check input samplesheet and get read channels +// + +params.options = [:] + +include { SAMPLESHEET_CHECK } from '../../modules/local/samplesheet_check' addParams( options: params.options ) + +workflow INPUT_CHECK { + take: + samplesheet // file: /path/to/samplesheet.csv + + main: + SAMPLESHEET_CHECK ( samplesheet ) + .splitCsv ( header:true, sep:',' ) + .map { create_fastq_channels(it) } + .set { reads } + + emit: + reads // channel: [ val(meta), [ reads ] ] +} + +// Function to get list of [ meta, [ fastq_1, fastq_2 ] ] +def create_fastq_channels(LinkedHashMap row) { + def meta = [:] + meta.id = row.sample + meta.single_end = row.single_end.toBoolean() + + def array = [] + if (!file(row.fastq_1).exists()) { + exit 1, "ERROR: Please check input samplesheet -> Read 1 FastQ file does not exist!\n${row.fastq_1}" + } + if (meta.single_end) { + array = [ meta, [ file(row.fastq_1) ] ] + } else { + if (!file(row.fastq_2).exists()) { + exit 1, "ERROR: Please check input samplesheet -> Read 2 FastQ file does not exist!\n${row.fastq_2}" + } + array = [ meta, [ file(row.fastq_1), file(row.fastq_2) ] ] + } + return array +} diff --git a/workflows/rnaseq.nf b/workflows/rnaseq.nf new file mode 100644 index 000000000..bc19af6fc --- /dev/null +++ b/workflows/rnaseq.nf @@ -0,0 +1,141 @@ +/* +======================================================================================== + VALIDATE INPUTS +======================================================================================== +*/ + +def summary_params = NfcoreSchema.paramsSummaryMap(workflow, params) + +// Validate input parameters +WorkflowRnaseq.initialise(params, log) + +// TODO nf-core: Add all file path parameters for the pipeline to the list below +// Check input path parameters to see if they exist +def checkPathParamList = [ params.input, params.multiqc_config, params.fasta ] +for (param in checkPathParamList) { if (param) { file(param, checkIfExists: true) } } + +// Check mandatory parameters +if (params.input) { ch_input = file(params.input) } else { exit 1, 'Input samplesheet not specified!' } + +/* +======================================================================================== + CONFIG FILES +======================================================================================== +*/ + +ch_multiqc_config = file("$projectDir/assets/multiqc_config.yaml", checkIfExists: true) +ch_multiqc_custom_config = params.multiqc_config ? Channel.fromPath(params.multiqc_config) : Channel.empty() + +/* +======================================================================================== + IMPORT LOCAL MODULES/SUBWORKFLOWS +======================================================================================== +*/ + +// Don't overwrite global params.modules, create a copy instead and use that within the main script. +def modules = params.modules.clone() + +// +// MODULE: Local to the pipeline +// +include { GET_SOFTWARE_VERSIONS } from '../modules/local/get_software_versions' addParams( options: [publish_files : ['tsv':'']] ) + +// +// SUBWORKFLOW: Consisting of a mix of local and nf-core/modules +// +include { INPUT_CHECK } from '../subworkflows/local/input_check' addParams( options: [:] ) + +/* +======================================================================================== + IMPORT NF-CORE MODULES/SUBWORKFLOWS +======================================================================================== +*/ + +def multiqc_options = modules['multiqc'] +multiqc_options.args += params.multiqc_title ? Utils.joinModuleArgs(["--title \"$params.multiqc_title\""]) : '' + +// +// MODULE: Installed directly from nf-core/modules +// +include { FASTQC } from '../modules/nf-core/modules/fastqc/main' addParams( options: modules['fastqc'] ) +include { MULTIQC } from '../modules/nf-core/modules/multiqc/main' addParams( options: multiqc_options ) + +/* +======================================================================================== + RUN MAIN WORKFLOW +======================================================================================== +*/ + +// Info required for completion email and summary +def multiqc_report = [] + +workflow RNASEQ { + + ch_software_versions = Channel.empty() + + // + // SUBWORKFLOW: Read in samplesheet, validate and stage input files + // + INPUT_CHECK ( + ch_input + ) + + // + // MODULE: Run FastQC + // + FASTQC ( + INPUT_CHECK.out.reads + ) + ch_software_versions = ch_software_versions.mix(FASTQC.out.version.first().ifEmpty(null)) + + // + // MODULE: Pipeline reporting + // + ch_software_versions + .map { it -> if (it) [ it.baseName, it ] } + .groupTuple() + .map { it[1][0] } + .flatten() + .collect() + .set { ch_software_versions } + + GET_SOFTWARE_VERSIONS ( + ch_software_versions.map { it }.collect() + ) + + // + // MODULE: MultiQC + // + workflow_summary = WorkflowRnaseq.paramsSummaryMultiqc(workflow, summary_params) + ch_workflow_summary = Channel.value(workflow_summary) + + ch_multiqc_files = Channel.empty() + ch_multiqc_files = ch_multiqc_files.mix(Channel.from(ch_multiqc_config)) + ch_multiqc_files = ch_multiqc_files.mix(ch_multiqc_custom_config.collect().ifEmpty([])) + ch_multiqc_files = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml')) + ch_multiqc_files = ch_multiqc_files.mix(GET_SOFTWARE_VERSIONS.out.yaml.collect()) + ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([])) + + MULTIQC ( + ch_multiqc_files.collect() + ) + multiqc_report = MULTIQC.out.report.toList() + ch_software_versions = ch_software_versions.mix(MULTIQC.out.version.ifEmpty(null)) +} + +/* +======================================================================================== + COMPLETION EMAIL AND SUMMARY +======================================================================================== +*/ + +workflow.onComplete { + NfcoreTemplate.email(workflow, params, summary_params, projectDir, log, multiqc_report) + NfcoreTemplate.summary(workflow, params, log) +} + +/* +======================================================================================== + THE END +======================================================================================== +*/ From d333b856bec4ba5e2a00b4efa33255bc8566846c Mon Sep 17 00:00:00 2001 From: nf-core-bot Date: Tue, 13 Jul 2021 15:32:48 +0000 Subject: [PATCH 03/31] Template update for nf-core/tools version 2.0.1 --- .github/workflows/linting.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index 13b4fc818..fbde5cf8b 100644 --- a/.github/workflows/linting.yml +++ b/.github/workflows/linting.yml @@ -127,7 +127,7 @@ jobs: GITHUB_COMMENTS_URL: ${{ github.event.pull_request.comments_url }} GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} GITHUB_PR_COMMIT: ${{ github.event.pull_request.head.sha }} - run: nf-core -l lint_log.txt lint ${GITHUB_WORKSPACE} --markdown lint_results.md + run: nf-core -l lint_log.txt lint --dir ${GITHUB_WORKSPACE} --markdown lint_results.md - name: Save PR number if: ${{ always() }} From c18b4dbc7099bd1dcf949d8e6ccf14e6d5b16b17 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Tue, 13 Jul 2021 22:22:06 +0100 Subject: [PATCH 04/31] Small fixes --- .github/workflows/linting.yml | 10 ++-- .nf-core-lint.yaml | 13 ------ .nf-core.yml | 8 ++++ nextflow_schema.json | 88 +++++++++++------------------------ 4 files changed, 40 insertions(+), 79 deletions(-) delete mode 100644 .nf-core-lint.yaml create mode 100644 .nf-core.yml diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index bce21ecf0..fbde5cf8b 100644 --- a/.github/workflows/linting.yml +++ b/.github/workflows/linting.yml @@ -14,7 +14,7 @@ jobs: - uses: actions/checkout@v2 - uses: actions/setup-node@v1 with: - node-version: "10" + node-version: '10' - name: Install markdownlint run: npm install -g markdownlint-cli - name: Run Markdownlint @@ -67,7 +67,7 @@ jobs: - uses: actions/checkout@v1 - uses: actions/setup-node@v1 with: - node-version: "10" + node-version: '10' - name: Install yaml-lint run: npm install -g yaml-lint - name: Run yaml-lint @@ -101,6 +101,7 @@ jobs: nf-core: runs-on: ubuntu-latest steps: + - name: Check out pipeline code uses: actions/checkout@v2 @@ -113,8 +114,8 @@ jobs: - uses: actions/setup-python@v1 with: - python-version: "3.6" - architecture: "x64" + python-version: '3.6' + architecture: 'x64' - name: Install dependencies run: | @@ -141,3 +142,4 @@ jobs: lint_log.txt lint_results.md PR_number.txt + diff --git a/.nf-core-lint.yaml b/.nf-core-lint.yaml deleted file mode 100644 index 9385194a3..000000000 --- a/.nf-core-lint.yaml +++ /dev/null @@ -1,13 +0,0 @@ -files_unchanged: - - .github/PULL_REQUEST_TEMPLATE.md - - .github/workflows/linting.yml - - assets/email_template.html - - assets/email_template.txt - - assets/multiqc_config.yaml - - assets/sendmail_template.txt - - lib/NfcoreSchema.groovy - - docs/README.md -files_exist: - - .github/markdownlint.yml - - bin/markdown_to_html.py -actions_awsfulltest: False diff --git a/.nf-core.yml b/.nf-core.yml new file mode 100644 index 000000000..87ba601c6 --- /dev/null +++ b/.nf-core.yml @@ -0,0 +1,8 @@ +lint: + files_unchanged: + - .markdownlint.yml + - assets/email_template.html + - assets/email_template.txt + - bin/scrape_software_versions.py + - lib/NfcoreTemplate.groovy + - assets/multiqc_config.yaml diff --git a/nextflow_schema.json b/nextflow_schema.json index 265394afb..2b0b342dc 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -466,27 +466,21 @@ } } }, - "generic_options": { - "title": "Generic options", + "institutional_config_options": { + "title": "Institutional config options", "type": "object", - "fa_icon": "fas fa-file-import", - "description": "Less common options for the pipeline, typically set in a config file.", - "help_text": "These options are common to all nf-core pipelines and allow you to customise some of the core preferences for how the pipeline runs.\n\nTypically these options would be set in a Nextflow config file loaded for all pipeline runs, such as `~/.nextflow/config`.", + "fa_icon": "fas fa-university", + "description": "Parameters used to describe centralised config profiles. These should not be edited.", + "help_text": "The centralised nf-core configuration profiles use a handful of pipeline parameters to describe themselves. This information is then printed to the Nextflow log when you run a pipeline. You should not need to change these values when you run a pipeline.", "properties": { - "help": { - "type": "boolean", - "description": "Display help text.", - "fa_icon": "fas fa-question-circle", - "hidden": true - }, - "publish_dir_mode": { + "custom_config_version": { "type": "string", "description": "Git commit id for Institutional configs.", "default": "master", "hidden": true, "fa_icon": "fas fa-users-cog" }, - "email_on_fail": { + "custom_config_base": { "type": "string", "description": "Base directory for Institutional configs.", "default": "https://raw.githubusercontent.com/nf-core/configs/master", @@ -494,65 +488,35 @@ "help_text": "If you're running offline, Nextflow will not be able to fetch the institutional config files from the internet. If you don't need them, then this is not a problem. If you do need them, you should download the files from the repo and tell Nextflow where to find them with this parameter.", "fa_icon": "fas fa-users-cog" }, - "plaintext_email": { - "type": "boolean", - "description": "Send plain-text email instead of HTML.", - "fa_icon": "fas fa-remove-format", - "hidden": true - }, - "max_multiqc_email_size": { + "hostnames": { "type": "string", - "description": "File size limit when attaching MultiQC reports to summary emails.", - "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$", - "default": "25.MB", - "fa_icon": "fas fa-file-upload", - "hidden": true - }, - "monochrome_logs": { - "type": "boolean", - "description": "Do not use coloured log outputs.", - "fa_icon": "fas fa-palette", - "hidden": true + "description": "Institutional configs hostname.", + "hidden": true, + "fa_icon": "fas fa-users-cog" }, - "multiqc_config": { + "config_profile_name": { "type": "string", - "description": "Custom config file to supply to MultiQC.", - "fa_icon": "fas fa-cog", - "hidden": true + "description": "Institutional config name.", + "hidden": true, + "fa_icon": "fas fa-users-cog" }, - "tracedir": { + "config_profile_description": { "type": "string", - "description": "Directory to keep pipeline Nextflow logs and reports.", - "default": "${params.outdir}/pipeline_info", - "fa_icon": "fas fa-cogs", - "hidden": true - }, - "validate_params": { - "type": "boolean", - "description": "Boolean whether to validate parameters against the schema at runtime", - "default": true, - "fa_icon": "fas fa-check-square", - "hidden": true - }, - "show_hidden_params": { - "type": "boolean", - "fa_icon": "far fa-eye-slash", - "description": "Show all params when using `--help`", + "description": "Institutional config description.", "hidden": true, - "help_text": "By default, parameters set as _hidden_ in the schema are not shown on the command line when a user runs with `--help`. Specifying this option will tell the pipeline to show all parameters." + "fa_icon": "fas fa-users-cog" }, - "enable_conda": { - "type": "boolean", - "description": "Run this workflow with Conda. You can also use '-profile conda' instead of providing this parameter.", + "config_profile_contact": { + "type": "string", + "description": "Institutional config contact information.", "hidden": true, - "fa_icon": "fas fa-bacon" + "fa_icon": "fas fa-users-cog" }, - "singularity_pull_docker_container": { - "type": "boolean", - "description": "Instead of directly downloading Singularity images for use with Singularity, force the workflow to pull and convert Docker containers instead.", + "config_profile_url": { + "type": "string", + "description": "Institutional config URL link.", "hidden": true, - "fa_icon": "fas fa-toolbox", - "help_text": "This may be useful for example if you are unable to directly pull Singularity containers to run the pipeline due to http/https proxy issues." + "fa_icon": "fas fa-users-cog" } } }, From 1293472504f8162745ab9c0cf70611478d585ac1 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Wed, 14 Jul 2021 12:38:50 +0100 Subject: [PATCH 05/31] Update CHANGELOG --- CHANGELOG.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index b8912fba6..379c1f180 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -7,6 +7,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Enhancements & fixes +* Updated pipeline template to [nf-core/tools 2.0.1](https://github.com/nf-core/tools/releases/tag/2.0.1) + ### Parameters ## [[3.2](https://github.com/nf-core/rnaseq/releases/tag/3.2)] - 2021-06-18 From 9d4a5ff737856d7e4b90a49aba28d82c2cb457cf Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Wed, 14 Jul 2021 13:27:14 +0100 Subject: [PATCH 06/31] Remove redundant text introduced by sync --- .editorconfig | 3 +++ docs/usage.md | 44 -------------------------------------------- 2 files changed, 3 insertions(+), 44 deletions(-) diff --git a/.editorconfig b/.editorconfig index afb20bb1e..95549501a 100644 --- a/.editorconfig +++ b/.editorconfig @@ -11,6 +11,9 @@ indent_style = space [*.{yml,yaml}] indent_size = 2 +[*.json] +insert_final_newline = unset + # These files are edited and tested upstream in nf-core/modules [/modules/nf-core/**] charset = unset diff --git a/docs/usage.md b/docs/usage.md index 6bace0402..99b0fbf37 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -75,50 +75,6 @@ If you are using [GENCODE](https://www.gencodegenes.org/) reference genome files * The `--gtf_group_features_type` parameter will automatically be set to `gene_type` as opposed to `gene_biotype`, respectively. * If you are running Salmon, the `--gencode` flag will also be passed to the index building step to overcome parsing issues resulting from the transcript IDs in GENCODE fasta files being separated by vertical pipes (`|`) instead of spaces (see [this issue](https://github.com/COMBINE-lab/salmon/issues/15)). -## Samplesheet input - -You will need to create a samplesheet with information about the samples you would like to analyse before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row as shown in the examples below. - -```console ---input '[path to samplesheet file]' -``` - -### Multiple runs of the same sample - -The `sample` identifiers have to be the same when you have re-sequenced the same sample more than once e.g. to increase sequencing depth. The pipeline will concatenate the raw reads before performing any downstream analysis. Below is an example for the same sample sequenced across 3 lanes: - -```console -sample,fastq_1,fastq_2 -CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz -CONTROL_REP1,AEG588A1_S1_L003_R1_001.fastq.gz,AEG588A1_S1_L003_R2_001.fastq.gz -CONTROL_REP1,AEG588A1_S1_L004_R1_001.fastq.gz,AEG588A1_S1_L004_R2_001.fastq.gz -``` - -### Full samplesheet - -The pipeline will auto-detect whether a sample is single- or paired-end using the information provided in the samplesheet. The samplesheet can have as many columns as you desire, however, there is a strict requirement for the first 3 columns to match those defined in the table below. - -A final samplesheet file consisting of both single- and paired-end data may look something like the one below. This is for 6 samples, where `TREATMENT_REP3` has been sequenced twice. - -```console -sample,fastq_1,fastq_2 -CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz -CONTROL_REP2,AEG588A2_S2_L002_R1_001.fastq.gz,AEG588A2_S2_L002_R2_001.fastq.gz -CONTROL_REP3,AEG588A3_S3_L002_R1_001.fastq.gz,AEG588A3_S3_L002_R2_001.fastq.gz -TREATMENT_REP1,AEG588A4_S4_L003_R1_001.fastq.gz, -TREATMENT_REP2,AEG588A5_S5_L003_R1_001.fastq.gz, -TREATMENT_REP3,AEG588A6_S6_L003_R1_001.fastq.gz, -TREATMENT_REP3,AEG588A6_S6_L004_R1_001.fastq.gz, -``` - -| Column | Description | -|----------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `sample` | Custom sample name. This entry will be identical for multiple sequencing libraries/runs from the same sample. Spaces in sample names are automatically converted to underscores (`_`). | -| `fastq_1` | Full path to FastQ file for Illumina short reads 1. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz". | -| `fastq_2` | Full path to FastQ file for Illumina short reads 2. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz". | - -An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline. - ## Running the pipeline The typical command for running the pipeline is as follows: From 27c5c7ad801a5dec6eafad5db208fad815f54075 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Wed, 14 Jul 2021 13:31:59 +0100 Subject: [PATCH 07/31] Remove modules/nf-core/software --- .../nf-core/software/cat/fastq/functions.nf | 68 -------------- modules/nf-core/software/cat/fastq/main.nf | 47 ---------- modules/nf-core/software/cat/fastq/meta.yml | 33 ------- modules/nf-core/software/fastqc/functions.nf | 68 -------------- modules/nf-core/software/fastqc/main.nf | 47 ---------- modules/nf-core/software/fastqc/meta.yml | 51 ---------- modules/nf-core/software/gffread/functions.nf | 68 -------------- modules/nf-core/software/gffread/main.nf | 34 ------- modules/nf-core/software/gffread/meta.yml | 43 --------- modules/nf-core/software/gunzip/functions.nf | 68 -------------- modules/nf-core/software/gunzip/main.nf | 35 ------- modules/nf-core/software/gunzip/meta.yml | 27 ------ .../software/hisat2/align/functions.nf | 68 -------------- modules/nf-core/software/hisat2/align/main.nf | 93 ------------------- .../nf-core/software/hisat2/align/meta.yml | 57 ------------ .../software/hisat2/build/functions.nf | 68 -------------- modules/nf-core/software/hisat2/build/main.nf | 70 -------------- .../nf-core/software/hisat2/build/meta.yml | 42 --------- .../hisat2/extractsplicesites/functions.nf | 68 -------------- .../hisat2/extractsplicesites/main.nf | 36 ------- .../hisat2/extractsplicesites/meta.yml | 34 ------- .../picard/markduplicates/functions.nf | 68 -------------- .../software/picard/markduplicates/main.nf | 49 ---------- .../software/picard/markduplicates/meta.yml | 46 --------- .../software/preseq/lcextrap/functions.nf | 68 -------------- .../nf-core/software/preseq/lcextrap/main.nf | 45 --------- .../nf-core/software/preseq/lcextrap/meta.yml | 47 ---------- .../software/qualimap/rnaseq/functions.nf | 68 -------------- .../nf-core/software/qualimap/rnaseq/main.nf | 57 ------------ .../rsem/calculateexpression/functions.nf | 68 -------------- .../software/rsem/calculateexpression/main.nf | 61 ------------ .../rsem/preparereference/functions.nf | 68 -------------- .../software/rsem/preparereference/main.nf | 67 ------------- .../software/rseqc/bamstat/functions.nf | 68 -------------- .../nf-core/software/rseqc/bamstat/main.nf | 39 -------- .../nf-core/software/rseqc/bamstat/meta.yml | 36 ------- .../rseqc/inferexperiment/functions.nf | 68 -------------- .../software/rseqc/inferexperiment/main.nf | 41 -------- .../software/rseqc/inferexperiment/meta.yml | 39 -------- .../software/rseqc/innerdistance/functions.nf | 68 -------------- .../software/rseqc/innerdistance/main.nf | 53 ----------- .../software/rseqc/innerdistance/meta.yml | 55 ----------- .../rseqc/junctionannotation/functions.nf | 68 -------------- .../software/rseqc/junctionannotation/main.nf | 48 ---------- .../rseqc/junctionannotation/meta.yml | 61 ------------ .../rseqc/junctionsaturation/functions.nf | 68 -------------- .../software/rseqc/junctionsaturation/main.nf | 42 --------- .../rseqc/readdistribution/functions.nf | 68 -------------- .../software/rseqc/readdistribution/main.nf | 40 -------- .../software/rseqc/readdistribution/meta.yml | 40 -------- .../rseqc/readduplication/functions.nf | 68 -------------- .../software/rseqc/readduplication/main.nf | 42 --------- .../software/rseqc/readduplication/meta.yml | 51 ---------- .../software/salmon/index/functions.nf | 68 -------------- modules/nf-core/software/salmon/index/main.nf | 51 ---------- .../nf-core/software/salmon/index/meta.yml | 35 ------- .../software/salmon/quant/functions.nf | 68 -------------- modules/nf-core/software/salmon/quant/main.nf | 77 --------------- .../nf-core/software/salmon/quant/meta.yml | 55 ----------- .../software/samtools/flagstat/functions.nf | 68 -------------- .../software/samtools/flagstat/main.nf | 34 ------- .../software/samtools/flagstat/meta.yml | 48 ---------- .../software/samtools/idxstats/functions.nf | 68 -------------- .../software/samtools/idxstats/main.nf | 34 ------- .../software/samtools/idxstats/meta.yml | 49 ---------- .../software/samtools/index/functions.nf | 68 -------------- .../nf-core/software/samtools/index/main.nf | 35 ------- .../nf-core/software/samtools/index/meta.yml | 47 ---------- .../software/samtools/sort/functions.nf | 68 -------------- .../nf-core/software/samtools/sort/main.nf | 35 ------- .../nf-core/software/samtools/sort/meta.yml | 43 --------- .../software/samtools/stats/functions.nf | 68 -------------- .../nf-core/software/samtools/stats/main.nf | 34 ------- .../nf-core/software/samtools/stats/meta.yml | 47 ---------- .../nf-core/software/sortmerna/functions.nf | 68 -------------- modules/nf-core/software/sortmerna/main.nf | 73 --------------- .../nf-core/software/star/align/functions.nf | 68 -------------- modules/nf-core/software/star/align/main.nf | 71 -------------- modules/nf-core/software/star/align/meta.yml | 75 --------------- .../software/star/genomegenerate/functions.nf | 68 -------------- .../software/star/genomegenerate/main.nf | 67 ------------- .../software/star/genomegenerate/meta.yml | 36 ------- .../software/stringtie/stringtie/functions.nf | 68 -------------- .../software/stringtie/stringtie/main.nf | 55 ----------- .../software/stringtie/stringtie/meta.yml | 56 ----------- .../subread/featurecounts/functions.nf | 68 -------------- .../software/subread/featurecounts/main.nf | 52 ----------- .../software/subread/featurecounts/meta.yml | 52 ----------- .../nf-core/software/trimgalore/functions.nf | 68 -------------- modules/nf-core/software/trimgalore/main.nf | 83 ----------------- modules/nf-core/software/trimgalore/meta.yml | 58 ------------ .../software/ucsc/bedclip/functions.nf | 68 -------------- modules/nf-core/software/ucsc/bedclip/main.nf | 42 --------- .../nf-core/software/ucsc/bedclip/meta.yml | 41 -------- .../ucsc/bedgraphtobigwig/functions.nf | 68 -------------- .../software/ucsc/bedgraphtobigwig/main.nf | 38 -------- .../software/umitools/dedup/functions.nf | 68 -------------- .../nf-core/software/umitools/dedup/main.nf | 41 -------- .../software/umitools/extract/functions.nf | 68 -------------- .../nf-core/software/umitools/extract/main.nf | 57 ------------ modules/nf-core/software/untar/functions.nf | 68 -------------- modules/nf-core/software/untar/main.nf | 35 ------- modules/nf-core/software/untar/meta.yml | 27 ------ 103 files changed, 5707 deletions(-) delete mode 100644 modules/nf-core/software/cat/fastq/functions.nf delete mode 100644 modules/nf-core/software/cat/fastq/main.nf delete mode 100644 modules/nf-core/software/cat/fastq/meta.yml delete mode 100644 modules/nf-core/software/fastqc/functions.nf delete mode 100644 modules/nf-core/software/fastqc/main.nf delete mode 100644 modules/nf-core/software/fastqc/meta.yml delete mode 100644 modules/nf-core/software/gffread/functions.nf delete mode 100644 modules/nf-core/software/gffread/main.nf delete mode 100644 modules/nf-core/software/gffread/meta.yml delete mode 100644 modules/nf-core/software/gunzip/functions.nf delete mode 100644 modules/nf-core/software/gunzip/main.nf delete mode 100644 modules/nf-core/software/gunzip/meta.yml delete mode 100644 modules/nf-core/software/hisat2/align/functions.nf delete mode 100644 modules/nf-core/software/hisat2/align/main.nf delete mode 100644 modules/nf-core/software/hisat2/align/meta.yml delete mode 100644 modules/nf-core/software/hisat2/build/functions.nf delete mode 100644 modules/nf-core/software/hisat2/build/main.nf delete mode 100644 modules/nf-core/software/hisat2/build/meta.yml delete mode 100644 modules/nf-core/software/hisat2/extractsplicesites/functions.nf delete mode 100644 modules/nf-core/software/hisat2/extractsplicesites/main.nf delete mode 100644 modules/nf-core/software/hisat2/extractsplicesites/meta.yml delete mode 100644 modules/nf-core/software/picard/markduplicates/functions.nf delete mode 100644 modules/nf-core/software/picard/markduplicates/main.nf delete mode 100644 modules/nf-core/software/picard/markduplicates/meta.yml delete mode 100644 modules/nf-core/software/preseq/lcextrap/functions.nf delete mode 100644 modules/nf-core/software/preseq/lcextrap/main.nf delete mode 100644 modules/nf-core/software/preseq/lcextrap/meta.yml delete mode 100644 modules/nf-core/software/qualimap/rnaseq/functions.nf delete mode 100644 modules/nf-core/software/qualimap/rnaseq/main.nf delete mode 100644 modules/nf-core/software/rsem/calculateexpression/functions.nf delete mode 100644 modules/nf-core/software/rsem/calculateexpression/main.nf delete mode 100644 modules/nf-core/software/rsem/preparereference/functions.nf delete mode 100644 modules/nf-core/software/rsem/preparereference/main.nf delete mode 100644 modules/nf-core/software/rseqc/bamstat/functions.nf delete mode 100644 modules/nf-core/software/rseqc/bamstat/main.nf delete mode 100644 modules/nf-core/software/rseqc/bamstat/meta.yml delete mode 100644 modules/nf-core/software/rseqc/inferexperiment/functions.nf delete mode 100644 modules/nf-core/software/rseqc/inferexperiment/main.nf delete mode 100644 modules/nf-core/software/rseqc/inferexperiment/meta.yml delete mode 100644 modules/nf-core/software/rseqc/innerdistance/functions.nf delete mode 100644 modules/nf-core/software/rseqc/innerdistance/main.nf delete mode 100644 modules/nf-core/software/rseqc/innerdistance/meta.yml delete mode 100644 modules/nf-core/software/rseqc/junctionannotation/functions.nf delete mode 100644 modules/nf-core/software/rseqc/junctionannotation/main.nf delete mode 100644 modules/nf-core/software/rseqc/junctionannotation/meta.yml delete mode 100644 modules/nf-core/software/rseqc/junctionsaturation/functions.nf delete mode 100644 modules/nf-core/software/rseqc/junctionsaturation/main.nf delete mode 100644 modules/nf-core/software/rseqc/readdistribution/functions.nf delete mode 100644 modules/nf-core/software/rseqc/readdistribution/main.nf delete mode 100644 modules/nf-core/software/rseqc/readdistribution/meta.yml delete mode 100644 modules/nf-core/software/rseqc/readduplication/functions.nf delete mode 100644 modules/nf-core/software/rseqc/readduplication/main.nf delete mode 100644 modules/nf-core/software/rseqc/readduplication/meta.yml delete mode 100644 modules/nf-core/software/salmon/index/functions.nf delete mode 100644 modules/nf-core/software/salmon/index/main.nf delete mode 100644 modules/nf-core/software/salmon/index/meta.yml delete mode 100644 modules/nf-core/software/salmon/quant/functions.nf delete mode 100644 modules/nf-core/software/salmon/quant/main.nf delete mode 100644 modules/nf-core/software/salmon/quant/meta.yml delete mode 100644 modules/nf-core/software/samtools/flagstat/functions.nf delete mode 100644 modules/nf-core/software/samtools/flagstat/main.nf delete mode 100644 modules/nf-core/software/samtools/flagstat/meta.yml delete mode 100644 modules/nf-core/software/samtools/idxstats/functions.nf delete mode 100644 modules/nf-core/software/samtools/idxstats/main.nf delete mode 100644 modules/nf-core/software/samtools/idxstats/meta.yml delete mode 100644 modules/nf-core/software/samtools/index/functions.nf delete mode 100644 modules/nf-core/software/samtools/index/main.nf delete mode 100644 modules/nf-core/software/samtools/index/meta.yml delete mode 100644 modules/nf-core/software/samtools/sort/functions.nf delete mode 100644 modules/nf-core/software/samtools/sort/main.nf delete mode 100644 modules/nf-core/software/samtools/sort/meta.yml delete mode 100644 modules/nf-core/software/samtools/stats/functions.nf delete mode 100644 modules/nf-core/software/samtools/stats/main.nf delete mode 100644 modules/nf-core/software/samtools/stats/meta.yml delete mode 100644 modules/nf-core/software/sortmerna/functions.nf delete mode 100644 modules/nf-core/software/sortmerna/main.nf delete mode 100644 modules/nf-core/software/star/align/functions.nf delete mode 100644 modules/nf-core/software/star/align/main.nf delete mode 100644 modules/nf-core/software/star/align/meta.yml delete mode 100644 modules/nf-core/software/star/genomegenerate/functions.nf delete mode 100644 modules/nf-core/software/star/genomegenerate/main.nf delete mode 100644 modules/nf-core/software/star/genomegenerate/meta.yml delete mode 100644 modules/nf-core/software/stringtie/stringtie/functions.nf delete mode 100644 modules/nf-core/software/stringtie/stringtie/main.nf delete mode 100644 modules/nf-core/software/stringtie/stringtie/meta.yml delete mode 100644 modules/nf-core/software/subread/featurecounts/functions.nf delete mode 100644 modules/nf-core/software/subread/featurecounts/main.nf delete mode 100644 modules/nf-core/software/subread/featurecounts/meta.yml delete mode 100644 modules/nf-core/software/trimgalore/functions.nf delete mode 100644 modules/nf-core/software/trimgalore/main.nf delete mode 100644 modules/nf-core/software/trimgalore/meta.yml delete mode 100644 modules/nf-core/software/ucsc/bedclip/functions.nf delete mode 100644 modules/nf-core/software/ucsc/bedclip/main.nf delete mode 100644 modules/nf-core/software/ucsc/bedclip/meta.yml delete mode 100644 modules/nf-core/software/ucsc/bedgraphtobigwig/functions.nf delete mode 100644 modules/nf-core/software/ucsc/bedgraphtobigwig/main.nf delete mode 100644 modules/nf-core/software/umitools/dedup/functions.nf delete mode 100644 modules/nf-core/software/umitools/dedup/main.nf delete mode 100644 modules/nf-core/software/umitools/extract/functions.nf delete mode 100644 modules/nf-core/software/umitools/extract/main.nf delete mode 100644 modules/nf-core/software/untar/functions.nf delete mode 100644 modules/nf-core/software/untar/main.nf delete mode 100644 modules/nf-core/software/untar/meta.yml diff --git a/modules/nf-core/software/cat/fastq/functions.nf b/modules/nf-core/software/cat/fastq/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/cat/fastq/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/cat/fastq/main.nf b/modules/nf-core/software/cat/fastq/main.nf deleted file mode 100644 index 55ccca908..000000000 --- a/modules/nf-core/software/cat/fastq/main.nf +++ /dev/null @@ -1,47 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process CAT_FASTQ { - tag "$meta.id" - label 'process_low' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:'merged_fastq', meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "conda-forge::sed=4.7" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img" - } else { - container "biocontainers/biocontainers:v1.2.0_cv1" - } - - input: - tuple val(meta), path(reads) - - output: - tuple val(meta), path("*.merged.fastq.gz"), emit: reads - - script: - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - def readList = reads.collect{ it.toString() } - if (meta.single_end) { - if (readList.size > 1) { - """ - cat ${readList.sort().join(' ')} > ${prefix}.merged.fastq.gz - """ - } - } else { - if (readList.size > 2) { - def read1 = [] - def read2 = [] - readList.eachWithIndex{ v, ix -> ( ix & 1 ? read2 : read1 ) << v } - """ - cat ${read1.sort().join(' ')} > ${prefix}_1.merged.fastq.gz - cat ${read2.sort().join(' ')} > ${prefix}_2.merged.fastq.gz - """ - } - } -} diff --git a/modules/nf-core/software/cat/fastq/meta.yml b/modules/nf-core/software/cat/fastq/meta.yml deleted file mode 100644 index e7b8eebe8..000000000 --- a/modules/nf-core/software/cat/fastq/meta.yml +++ /dev/null @@ -1,33 +0,0 @@ -name: cat_fastq -description: Concatenates fastq files -keywords: - - fastq - - concatenate -tools: - - cat: - description: | - The cat utility reads files sequentially, writing them to the standard output. - documentation: https://www.gnu.org/software/coreutils/manual/html_node/cat-invocation.html -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - reads: - type: list - description: | - List of input FastQ files to be concatenated. -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - reads: - type: file - description: Merged fastq file - pattern: "*.{merged.fastq.gz}" -authors: - - "@joseespinosa" - - "@drpatelh" diff --git a/modules/nf-core/software/fastqc/functions.nf b/modules/nf-core/software/fastqc/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/fastqc/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/fastqc/main.nf b/modules/nf-core/software/fastqc/main.nf deleted file mode 100644 index 7ce76adff..000000000 --- a/modules/nf-core/software/fastqc/main.nf +++ /dev/null @@ -1,47 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process FASTQC { - tag "$meta.id" - label 'process_medium' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::fastqc=0.11.9" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/fastqc:0.11.9--0" - } else { - container "quay.io/biocontainers/fastqc:0.11.9--0" - } - - input: - tuple val(meta), path(reads) - - output: - tuple val(meta), path("*.html"), emit: html - tuple val(meta), path("*.zip") , emit: zip - path "*.version.txt" , emit: version - - script: - // Add soft-links to original FastQs for consistent naming in pipeline - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}.${options.suffix}" : "${meta.id}" - if (meta.single_end) { - """ - [ ! -f ${prefix}.fastq.gz ] && ln -s $reads ${prefix}.fastq.gz - fastqc $options.args --threads $task.cpus ${prefix}.fastq.gz - fastqc --version | sed -e "s/FastQC v//g" > ${software}.version.txt - """ - } else { - """ - [ ! -f ${prefix}_1.fastq.gz ] && ln -s ${reads[0]} ${prefix}_1.fastq.gz - [ ! -f ${prefix}_2.fastq.gz ] && ln -s ${reads[1]} ${prefix}_2.fastq.gz - fastqc $options.args --threads $task.cpus ${prefix}_1.fastq.gz ${prefix}_2.fastq.gz - fastqc --version | sed -e "s/FastQC v//g" > ${software}.version.txt - """ - } -} diff --git a/modules/nf-core/software/fastqc/meta.yml b/modules/nf-core/software/fastqc/meta.yml deleted file mode 100644 index 8eb9953dc..000000000 --- a/modules/nf-core/software/fastqc/meta.yml +++ /dev/null @@ -1,51 +0,0 @@ -name: fastqc -description: Run FastQC on sequenced reads -keywords: - - quality control - - qc - - adapters - - fastq -tools: - - fastqc: - description: | - FastQC gives general quality metrics about your reads. - It provides information about the quality score distribution - across your reads, the per base sequence content (%A/C/G/T). - You get information about adapter contamination and other - overrepresented sequences. - homepage: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/ - documentation: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/ -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - reads: - type: file - description: | - List of input FastQ files of size 1 and 2 for single-end and paired-end data, - respectively. -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - html: - type: file - description: FastQC report - pattern: "*_{fastqc.html}" - - zip: - type: file - description: FastQC report archive - pattern: "*_{fastqc.zip}" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@drpatelh" - - "@grst" - - "@ewels" - - "@FelixKrueger" diff --git a/modules/nf-core/software/gffread/functions.nf b/modules/nf-core/software/gffread/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/gffread/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/gffread/main.nf b/modules/nf-core/software/gffread/main.nf deleted file mode 100644 index 6c5aecbc7..000000000 --- a/modules/nf-core/software/gffread/main.nf +++ /dev/null @@ -1,34 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process GFFREAD { - tag "$gff" - label 'process_low' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) } - - conda (params.enable_conda ? "bioconda::gffread=0.12.1" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/gffread:0.12.1--h8b12597_0" - } else { - container "quay.io/biocontainers/gffread:0.12.1--h8b12597_0" - } - - input: - path gff - - output: - path "*.gtf" , emit: gtf - path "*.version.txt", emit: version - - script: - def software = getSoftwareName(task.process) - """ - gffread $gff $options.args -o ${gff.baseName}.gtf - echo \$(gffread --version 2>&1) > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/gffread/meta.yml b/modules/nf-core/software/gffread/meta.yml deleted file mode 100644 index 63d281f52..000000000 --- a/modules/nf-core/software/gffread/meta.yml +++ /dev/null @@ -1,43 +0,0 @@ -name: gffread -description: Validate, filter, convert and perform various other operations on GFF files -keywords: - - gff - - conversion - - validation -tools: - - gffread: - description: GFF/GTF utility providing format conversions, region filtering, FASTA sequence extraction and more. - homepage: http://ccb.jhu.edu/software/stringtie/gff.shtml#gffread - documentation: http://ccb.jhu.edu/software/stringtie/gff.shtml#gffread - tool_dev_url: https://github.com/gpertea/gffread - doi: 10.12688/f1000research.23297.1 - licence: ['MIT'] - -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - gff: - type: file - description: A GFF file in either the GFF3 or GFF2 format. - patter: "*.gff" - -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - gtf: - type: file - description: GTF file resulting from the conversion of the GFF input file - pattern: "*.gtf" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" - -authors: - - "@emiller88" diff --git a/modules/nf-core/software/gunzip/functions.nf b/modules/nf-core/software/gunzip/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/gunzip/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/gunzip/main.nf b/modules/nf-core/software/gunzip/main.nf deleted file mode 100644 index 292487961..000000000 --- a/modules/nf-core/software/gunzip/main.nf +++ /dev/null @@ -1,35 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process GUNZIP { - tag "$archive" - label 'process_low' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) } - - conda (params.enable_conda ? "conda-forge::sed=4.7" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img" - } else { - container "biocontainers/biocontainers:v1.2.0_cv1" - } - - input: - path archive - - output: - path "$gunzip", emit: gunzip - path "*.version.txt", emit: version - - script: - def software = getSoftwareName(task.process) - gunzip = archive.toString() - '.gz' - """ - gunzip -f $options.args $archive - echo \$(gunzip --version 2>&1) | sed 's/^.*(gzip) //; s/ Copyright.*\$//' > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/gunzip/meta.yml b/modules/nf-core/software/gunzip/meta.yml deleted file mode 100644 index 922e74e61..000000000 --- a/modules/nf-core/software/gunzip/meta.yml +++ /dev/null @@ -1,27 +0,0 @@ -name: gunzip -description: Compresses and decompresses files. -keywords: - - gunzip - - compression -tools: - - gunzip: - description: | - gzip is a file format and a software application used for file compression and decompression. - documentation: https://www.gnu.org/software/gzip/manual/gzip.html -input: - - archive: - type: file - description: File to be compressed/uncompressed - pattern: "*.*" -output: - - gunzip: - type: file - description: Compressed/uncompressed file - pattern: "*.*" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@joseespinosa" - - "@drpatelh" diff --git a/modules/nf-core/software/hisat2/align/functions.nf b/modules/nf-core/software/hisat2/align/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/hisat2/align/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/hisat2/align/main.nf b/modules/nf-core/software/hisat2/align/main.nf deleted file mode 100644 index 17547c91a..000000000 --- a/modules/nf-core/software/hisat2/align/main.nf +++ /dev/null @@ -1,93 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -def VERSION = '2.2.0' - -process HISAT2_ALIGN { - tag "$meta.id" - label 'process_high' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::hisat2=2.2.0 bioconda::samtools=1.10" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/mulled-v2-a97e90b3b802d1da3d6958e0867610c718cb5eb1:2880dd9d8ad0a7b221d4eacda9a818e92983128d-0" - } else { - container "quay.io/biocontainers/mulled-v2-a97e90b3b802d1da3d6958e0867610c718cb5eb1:2880dd9d8ad0a7b221d4eacda9a818e92983128d-0" - } - - input: - tuple val(meta), path(reads) - path index - path splicesites - - output: - tuple val(meta), path("*.bam"), emit: bam - tuple val(meta), path("*.log"), emit: summary - path "*.version.txt" , emit: version - - tuple val(meta), path("*fastq.gz"), optional:true, emit: fastq - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - - def strandedness = '' - if (meta.strandedness == 'forward') { - strandedness = meta.single_end ? '--rna-strandness F' : '--rna-strandness FR' - } else if (meta.strandedness == 'reverse') { - strandedness = meta.single_end ? '--rna-strandness R' : '--rna-strandness RF' - } - def seq_center = params.seq_center ? "--rg-id ${prefix} --rg SM:$prefix --rg CN:${params.seq_center.replaceAll('\\s','_')}" : "--rg-id ${prefix} --rg SM:$prefix" - if (meta.single_end) { - def unaligned = params.save_unaligned ? "--un-gz ${prefix}.unmapped.fastq.gz" : '' - """ - INDEX=`find -L ./ -name "*.1.ht2" | sed 's/.1.ht2//'` - hisat2 \\ - -x \$INDEX \\ - -U $reads \\ - $strandedness \\ - --known-splicesite-infile $splicesites \\ - --summary-file ${prefix}.hisat2.summary.log \\ - --threads $task.cpus \\ - $seq_center \\ - $unaligned \\ - $options.args \\ - | samtools view -bS -F 4 -F 256 - > ${prefix}.bam - - echo $VERSION > ${software}.version.txt - """ - } else { - def unaligned = params.save_unaligned ? "--un-conc-gz ${prefix}.unmapped.fastq.gz" : '' - """ - INDEX=`find -L ./ -name "*.1.ht2" | sed 's/.1.ht2//'` - hisat2 \\ - -x \$INDEX \\ - -1 ${reads[0]} \\ - -2 ${reads[1]} \\ - $strandedness \\ - --known-splicesite-infile $splicesites \\ - --summary-file ${prefix}.hisat2.summary.log \\ - --threads $task.cpus \\ - $seq_center \\ - $unaligned \\ - --no-mixed \\ - --no-discordant \\ - $options.args \\ - | samtools view -bS -F 4 -F 8 -F 256 - > ${prefix}.bam - - if [ -f ${prefix}.unmapped.fastq.1.gz ]; then - mv ${prefix}.unmapped.fastq.1.gz ${prefix}.unmapped_1.fastq.gz - fi - if [ -f ${prefix}.unmapped.fastq.2.gz ]; then - mv ${prefix}.unmapped.fastq.2.gz ${prefix}.unmapped_2.fastq.gz - fi - - echo $VERSION > ${software}.version.txt - """ - } -} diff --git a/modules/nf-core/software/hisat2/align/meta.yml b/modules/nf-core/software/hisat2/align/meta.yml deleted file mode 100644 index bf5570fdf..000000000 --- a/modules/nf-core/software/hisat2/align/meta.yml +++ /dev/null @@ -1,57 +0,0 @@ -name: hisat2_align -description: Align RNA-Seq reads to a reference with HISAT2 -keywords: - - align - - fasta - - genome - - reference - -tools: - - hisat2: - description: HISAT2 is a fast and sensitive alignment program for mapping next-generation sequencing reads (both DNA and RNA) to a population of human genomes as well as to a single reference genome. - homepage: https://daehwankimlab.github.io/hisat2/ - documentation: https://daehwankimlab.github.io/hisat2/manual/ - doi: "10.1038/s41587-019-0201-4" - licence: ['MIT'] - -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - reads: - type: file - description: | - List of input FastQ files of size 1 and 2 for single-end and paired-end data, - respectively. - - index: - type: file - description: HISAT2 genome index file - pattern: "*.ht2" - - splicesites: - type: file - description: Splices sites in gtf file - pattern: "*.{txt}" - -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: Output BAM file containing read alignments - pattern: "*.{bam}" - - summary: - type: file - description: Aligment log - pattern: "*.log" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" - -authors: - - "@ntoda03" diff --git a/modules/nf-core/software/hisat2/build/functions.nf b/modules/nf-core/software/hisat2/build/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/hisat2/build/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/hisat2/build/main.nf b/modules/nf-core/software/hisat2/build/main.nf deleted file mode 100644 index ce8bfb265..000000000 --- a/modules/nf-core/software/hisat2/build/main.nf +++ /dev/null @@ -1,70 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -def VERSION = '2.2.0' - -process HISAT2_BUILD { - tag "$fasta" - label 'process_high' - label 'process_high_memory' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:'index', meta:[:], publish_by_meta:[]) } - - conda (params.enable_conda ? "bioconda::hisat2=2.2.0" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/hisat2:2.2.0--py37hfa133b6_4" - } else { - container "quay.io/biocontainers/hisat2:2.2.0--py37hfa133b6_4" - } - - input: - path fasta - path gtf - path splicesites - - output: - path "hisat2" , emit: index - path "*.version.txt", emit: version - - script: - def avail_mem = 0 - if (!task.memory) { - log.info "[HISAT2 index build] Available memory not known - defaulting to 0. Specify process memory requirements to change this." - } else { - log.info "[HISAT2 index build] Available memory: ${task.memory}" - avail_mem = task.memory.toGiga() - } - - def ss = '' - def exon = '' - def extract_exons = '' - def hisat2_build_memory = params.hisat2_build_memory ? (params.hisat2_build_memory as nextflow.util.MemoryUnit).toGiga() : 0 - if (avail_mem >= hisat2_build_memory) { - log.info "[HISAT2 index build] At least ${hisat2_build_memory} GB available, so using splice sites and exons to build HISAT2 index" - extract_exons = "hisat2_extract_exons.py $gtf > ${gtf.baseName}.exons.txt" - ss = "--ss $splicesites" - exon = "--exon ${gtf.baseName}.exons.txt" - } else { - log.info "[HISAT2 index build] Less than ${hisat2_build_memory} GB available, so NOT using splice sites and exons to build HISAT2 index." - log.info "[HISAT2 index build] Use --hisat2_build_memory [small number] to skip this check." - } - - def software = getSoftwareName(task.process) - """ - mkdir hisat2 - $extract_exons - hisat2-build \\ - -p $task.cpus \\ - $ss \\ - $exon \\ - $options.args \\ - $fasta \\ - hisat2/${fasta.baseName} - - echo $VERSION > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/hisat2/build/meta.yml b/modules/nf-core/software/hisat2/build/meta.yml deleted file mode 100644 index 2f34d9d85..000000000 --- a/modules/nf-core/software/hisat2/build/meta.yml +++ /dev/null @@ -1,42 +0,0 @@ -name: hisat2_build -description: Builds HISAT2 index for reference genome -keywords: - - build - - index - - fasta - - genome - - reference -tools: - - hisat2: - description: HISAT2 is a fast and sensitive alignment program for mapping next-generation sequencing reads (both DNA and RNA) to a population of human genomes as well as to a single reference genome. - homepage: https://daehwankimlab.github.io/hisat2/ - documentation: https://daehwankimlab.github.io/hisat2/manual/ - doi: "10.1038/s41587-019-0201-4" - licence: ['MIT'] - -input: - - fasta: - type: file - description: Reference fasta file - pattern: "*.{fa,fasta,fna}" - - gtf: - type: file - description: Reference gtf annotation file - pattern: "*.{gtf}" - - splicesites: - type: file - description: Splices sites in gtf file - pattern: "*.{txt}" - -output: - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" - - index: - type: file - description: HISAT2 genome index file - pattern: "*.ht2" - -authors: - - "@ntoda03" diff --git a/modules/nf-core/software/hisat2/extractsplicesites/functions.nf b/modules/nf-core/software/hisat2/extractsplicesites/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/hisat2/extractsplicesites/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/hisat2/extractsplicesites/main.nf b/modules/nf-core/software/hisat2/extractsplicesites/main.nf deleted file mode 100644 index 57f4dedbd..000000000 --- a/modules/nf-core/software/hisat2/extractsplicesites/main.nf +++ /dev/null @@ -1,36 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -def VERSION = '2.2.0' - -process HISAT2_EXTRACTSPLICESITES { - tag "$gtf" - label 'process_medium' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) } - - conda (params.enable_conda ? "bioconda::hisat2=2.2.0" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/hisat2:2.2.0--py37hfa133b6_4" - } else { - container "quay.io/biocontainers/hisat2:2.2.0--py37hfa133b6_4" - } - - input: - path gtf - - output: - path "*.splice_sites.txt", emit: txt - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - """ - hisat2_extract_splice_sites.py $gtf > ${gtf.baseName}.splice_sites.txt - echo $VERSION > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/hisat2/extractsplicesites/meta.yml b/modules/nf-core/software/hisat2/extractsplicesites/meta.yml deleted file mode 100644 index 228138a87..000000000 --- a/modules/nf-core/software/hisat2/extractsplicesites/meta.yml +++ /dev/null @@ -1,34 +0,0 @@ -name: hisat2_extractsplicesites -description: Extracts splicing sites from a gtf files -keywords: - - splicing - - gtf - - genome - - reference - -tools: - - hisat2: - description: HISAT2 is a fast and sensitive alignment program for mapping next-generation sequencing reads (both DNA and RNA) to a population of human genomes as well as to a single reference genome. - homepage: https://daehwankimlab.github.io/hisat2/ - documentation: https://daehwankimlab.github.io/hisat2/manual/ - doi: "10.1038/s41587-019-0201-4" - licence: ['MIT'] - -input: - - gtf: - type: file - description: Reference gtf annotation file - pattern: "*.{gtf}" - -output: - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" - - splicesites: - type: file - description: Splices sites in gtf file - pattern: "*.{splice_sites.txt}" - -authors: - - "@ntoda03" diff --git a/modules/nf-core/software/picard/markduplicates/functions.nf b/modules/nf-core/software/picard/markduplicates/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/picard/markduplicates/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/picard/markduplicates/main.nf b/modules/nf-core/software/picard/markduplicates/main.nf deleted file mode 100644 index d76474147..000000000 --- a/modules/nf-core/software/picard/markduplicates/main.nf +++ /dev/null @@ -1,49 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process PICARD_MARKDUPLICATES { - tag "$meta.id" - label 'process_medium' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::picard=2.23.9" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/picard:2.23.9--0" - } else { - container "quay.io/biocontainers/picard:2.23.9--0" - } - - input: - tuple val(meta), path(bam) - - output: - tuple val(meta), path("*.bam") , emit: bam - tuple val(meta), path("*.metrics.txt"), emit: metrics - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - def avail_mem = 3 - if (!task.memory) { - log.info '[Picard MarkDuplicates] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.' - } else { - avail_mem = task.memory.giga - } - """ - picard \\ - -Xmx${avail_mem}g \\ - MarkDuplicates \\ - $options.args \\ - INPUT=$bam \\ - OUTPUT=${prefix}.bam \\ - METRICS_FILE=${prefix}.MarkDuplicates.metrics.txt - - echo \$(picard MarkDuplicates --version 2>&1) | grep -o 'Version:.*' | cut -f2- -d: > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/picard/markduplicates/meta.yml b/modules/nf-core/software/picard/markduplicates/meta.yml deleted file mode 100644 index 6420ce9a4..000000000 --- a/modules/nf-core/software/picard/markduplicates/meta.yml +++ /dev/null @@ -1,46 +0,0 @@ -name: picard_markduplicates -description: Locate and tag duplicate reads in a BAM file -keywords: - - markduplicates - - pcr - - duplicates - - bam - - sam - - cram -tools: - - picard: - description: | - A set of command line tools (in Java) for manipulating high-throughput sequencing (HTS) - data and formats such as SAM/BAM/CRAM and VCF. - homepage: https://broadinstitute.github.io/picard/ - documentation: https://broadinstitute.github.io/picard/ -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: BAM file - pattern: "*.{bam}" -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: BAM file with duplicate reads marked/removed - pattern: "*.{bam}" - - metrics: - type: file - description: Duplicate metrics file generated by picard - pattern: "*.{metrics.txt}" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@drpatelh" diff --git a/modules/nf-core/software/preseq/lcextrap/functions.nf b/modules/nf-core/software/preseq/lcextrap/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/preseq/lcextrap/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/preseq/lcextrap/main.nf b/modules/nf-core/software/preseq/lcextrap/main.nf deleted file mode 100644 index 2f601e4f6..000000000 --- a/modules/nf-core/software/preseq/lcextrap/main.nf +++ /dev/null @@ -1,45 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process PRESEQ_LCEXTRAP { - tag "$meta.id" - label 'process_medium' - label 'error_ignore' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::preseq=3.1.2" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/preseq:3.1.2--h06ef8b0_1" - } else { - container "quay.io/biocontainers/preseq:3.1.2--h06ef8b0_1" - } - - input: - tuple val(meta), path(bam) - - output: - tuple val(meta), path("*.ccurve.txt"), emit: ccurve - tuple val(meta), path("*.log") , emit: log - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - def paired_end = meta.single_end ? '' : '-pe' - """ - preseq \\ - lc_extrap \\ - $options.args \\ - $paired_end \\ - -output ${prefix}.ccurve.txt \\ - $bam - cp .command.err ${prefix}.command.log - - echo \$(preseq 2>&1) | sed 's/^.*Version: //; s/Usage:.*\$//' > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/preseq/lcextrap/meta.yml b/modules/nf-core/software/preseq/lcextrap/meta.yml deleted file mode 100644 index d1716231e..000000000 --- a/modules/nf-core/software/preseq/lcextrap/meta.yml +++ /dev/null @@ -1,47 +0,0 @@ -name: preseq_lcextrap -description: Software for predicting library complexity and genome coverage in high-throughput sequencing -keywords: - - preseq - - library - - complexity -tools: - - preseq: - description: Software for predicting library complexity and genome coverage in high-throughput sequencing - homepage: http://smithlabresearch.org/software/preseq/ - documentation: None - tool_dev_url: None - doi: "" - licence: ['GPL'] - -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: BAM/CRAM/SAM file - pattern: "*.{bam,cram,sam}" - -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" - - ccurve: - type: file - description: File containing output of Preseq lcextrap - pattern: "*.{ccurve.txt}" - - log: - type: file - description: Log file containing stderr produced by Preseq - pattern: "*.{log}" - -authors: - - "@drpatelh" diff --git a/modules/nf-core/software/qualimap/rnaseq/functions.nf b/modules/nf-core/software/qualimap/rnaseq/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/qualimap/rnaseq/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/qualimap/rnaseq/main.nf b/modules/nf-core/software/qualimap/rnaseq/main.nf deleted file mode 100644 index 96fe2cd42..000000000 --- a/modules/nf-core/software/qualimap/rnaseq/main.nf +++ /dev/null @@ -1,57 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process QUALIMAP_RNASEQ { - tag "$meta.id" - label 'process_medium' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::qualimap=2.2.2d" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/qualimap:2.2.2d--1" - } else { - container "quay.io/biocontainers/qualimap:2.2.2d--1" - } - - input: - tuple val(meta), path(bam) - path gtf - - output: - tuple val(meta), path("${prefix}"), emit: results - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - def paired_end = meta.single_end ? '' : '-pe' - def memory = task.memory.toGiga() + "G" - - def strandedness = 'non-strand-specific' - if (meta.strandedness == 'forward') { - strandedness = 'strand-specific-forward' - } else if (meta.strandedness == 'reverse') { - strandedness = 'strand-specific-reverse' - } - """ - unset DISPLAY - mkdir tmp - export _JAVA_OPTIONS=-Djava.io.tmpdir=./tmp - qualimap \\ - --java-mem-size=$memory \\ - rnaseq \\ - $options.args \\ - -bam $bam \\ - -gtf $gtf \\ - -p $strandedness \\ - $paired_end \\ - -outdir $prefix - - echo \$(qualimap 2>&1) | sed 's/^.*QualiMap v.//; s/Built.*\$//' > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/rsem/calculateexpression/functions.nf b/modules/nf-core/software/rsem/calculateexpression/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/rsem/calculateexpression/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/rsem/calculateexpression/main.nf b/modules/nf-core/software/rsem/calculateexpression/main.nf deleted file mode 100644 index 1f9ab854e..000000000 --- a/modules/nf-core/software/rsem/calculateexpression/main.nf +++ /dev/null @@ -1,61 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process RSEM_CALCULATEEXPRESSION { - tag "$meta.id" - label 'process_high' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::rsem=1.3.3 bioconda::star=2.7.6a" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0" - } else { - container "quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0" - } - - input: - tuple val(meta), path(reads) - path index - - output: - tuple val(meta), path("*.genes.results") , emit: counts_gene - tuple val(meta), path("*.isoforms.results"), emit: counts_transcript - tuple val(meta), path("*.stat") , emit: stat - tuple val(meta), path("*.log") , emit: logs - path "*.version.txt" , emit: version - - tuple val(meta), path("*.STAR.genome.bam") , optional:true, emit: bam_star - tuple val(meta), path("${prefix}.genome.bam") , optional:true, emit: bam_genome - tuple val(meta), path("${prefix}.transcript.bam"), optional:true, emit: bam_transcript - - script: - def software = getSoftwareName(task.process) - prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - - def strandedness = '' - if (meta.strandedness == 'forward') { - strandedness = '--strandedness forward' - } else if (meta.strandedness == 'reverse') { - strandedness = '--strandedness reverse' - } - def paired_end = meta.single_end ? "" : "--paired-end" - """ - INDEX=`find -L ./ -name "*.grp" | sed 's/.grp//'` - rsem-calculate-expression \\ - --num-threads $task.cpus \\ - --temporary-folder ./tmp/ \\ - $strandedness \\ - $paired_end \\ - $options.args \\ - $reads \\ - \$INDEX \\ - $prefix - - rsem-calculate-expression --version | sed -e "s/Current version: RSEM v//g" > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/rsem/preparereference/functions.nf b/modules/nf-core/software/rsem/preparereference/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/rsem/preparereference/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/rsem/preparereference/main.nf b/modules/nf-core/software/rsem/preparereference/main.nf deleted file mode 100644 index a378eb6b2..000000000 --- a/modules/nf-core/software/rsem/preparereference/main.nf +++ /dev/null @@ -1,67 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process RSEM_PREPAREREFERENCE { - tag "$fasta" - label 'process_high' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:'index', meta:[:], publish_by_meta:[]) } - - conda (params.enable_conda ? "bioconda::rsem=1.3.3 bioconda::star=2.7.6a" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0" - } else { - container "quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0" - } - - input: - path fasta, stageAs: "rsem/*" - path gtf - - output: - path "rsem" , emit: index - path "rsem/*transcripts.fa", emit: transcript_fasta - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def args = options.args.tokenize() - if (args.contains('--star')) { - args.removeIf { it.contains('--star') } - def memory = task.memory ? "--limitGenomeGenerateRAM ${task.memory.toBytes() - 100000000}" : '' - """ - STAR \\ - --runMode genomeGenerate \\ - --genomeDir rsem/ \\ - --genomeFastaFiles $fasta \\ - --sjdbGTFfile $gtf \\ - --runThreadN $task.cpus \\ - $memory \\ - $options.args2 - - rsem-prepare-reference \\ - --gtf $gtf \\ - --num-threads $task.cpus \\ - ${args.join(' ')} \\ - $fasta \\ - rsem/genome - - rsem-calculate-expression --version | sed -e "s/Current version: RSEM v//g" > ${software}.version.txt - """ - } else { - """ - rsem-prepare-reference \\ - --gtf $gtf \\ - --num-threads $task.cpus \\ - $options.args \\ - $fasta \\ - rsem/genome - - rsem-calculate-expression --version | sed -e "s/Current version: RSEM v//g" > ${software}.version.txt - """ - } -} diff --git a/modules/nf-core/software/rseqc/bamstat/functions.nf b/modules/nf-core/software/rseqc/bamstat/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/rseqc/bamstat/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/rseqc/bamstat/main.nf b/modules/nf-core/software/rseqc/bamstat/main.nf deleted file mode 100644 index ac80b6d01..000000000 --- a/modules/nf-core/software/rseqc/bamstat/main.nf +++ /dev/null @@ -1,39 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process RSEQC_BAMSTAT { - tag "$meta.id" - label 'process_medium' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::rseqc=3.0.1" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1" - } else { - container "quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1" - } - - input: - tuple val(meta), path(bam) - - output: - tuple val(meta), path("*.bam_stat.txt"), emit: txt - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - """ - bam_stat.py \\ - -i $bam \\ - $options.args \\ - > ${prefix}.bam_stat.txt - - bam_stat.py --version | sed -e "s/bam_stat.py //g" > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/rseqc/bamstat/meta.yml b/modules/nf-core/software/rseqc/bamstat/meta.yml deleted file mode 100644 index ff00d8c9b..000000000 --- a/modules/nf-core/software/rseqc/bamstat/meta.yml +++ /dev/null @@ -1,36 +0,0 @@ -name: rseqc_bamstat -description: Generate statistics from a bam file -keywords: - - bam - - qc - - bamstat -tools: - - rseqc: - description: | - RSeQC package provides a number of useful modules that can comprehensively evaluate - high throughput sequence data especially RNA-seq data. - homepage: http://rseqc.sourceforge.net/ - documentation: http://rseqc.sourceforge.net/ - doi: 10.1093/bioinformatics/bts356 -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: the bam file to calculate statistics of - pattern: "*.{bam}" -output: - - txt: - type: file - description: bam statistics report - pattern: "*.bam_stat.txt" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@drpatelh" - - "@kevinmenden" diff --git a/modules/nf-core/software/rseqc/inferexperiment/functions.nf b/modules/nf-core/software/rseqc/inferexperiment/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/rseqc/inferexperiment/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/rseqc/inferexperiment/main.nf b/modules/nf-core/software/rseqc/inferexperiment/main.nf deleted file mode 100644 index da0958d4f..000000000 --- a/modules/nf-core/software/rseqc/inferexperiment/main.nf +++ /dev/null @@ -1,41 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process RSEQC_INFEREXPERIMENT { - tag "$meta.id" - label 'process_medium' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::rseqc=3.0.1" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1" - } else { - container "quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1" - } - - input: - tuple val(meta), path(bam) - path bed - - output: - tuple val(meta), path("*.infer_experiment.txt"), emit: txt - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - """ - infer_experiment.py \\ - -i $bam \\ - -r $bed \\ - $options.args \\ - > ${prefix}.infer_experiment.txt - - infer_experiment.py --version | sed -e "s/infer_experiment.py //g" > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/rseqc/inferexperiment/meta.yml b/modules/nf-core/software/rseqc/inferexperiment/meta.yml deleted file mode 100644 index 366c3e33b..000000000 --- a/modules/nf-core/software/rseqc/inferexperiment/meta.yml +++ /dev/null @@ -1,39 +0,0 @@ -name: rseqc_inferexperiment -description: Infer strandedness from sequencing reads -keywords: - - rnaseq - - experiment -tools: - - rseqc: - description: | - RSeQC package provides a number of useful modules that can comprehensively evaluate - high throughput sequence data especially RNA-seq data. - homepage: http://rseqc.sourceforge.net/ - documentation: http://rseqc.sourceforge.net/ - doi: 10.1093/bioinformatics/bts356 -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: the bam file to calculate statistics of - pattern: "*.{bam}" - - bed: - type: file - description: a bed file for the reference gene model - pattern: "*.{bed}" -output: - - txt: - type: file - description: infer_experiment results report - pattern: "*.infer_experiment.txt" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@drpatelh" - - "@kevinmenden" diff --git a/modules/nf-core/software/rseqc/innerdistance/functions.nf b/modules/nf-core/software/rseqc/innerdistance/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/rseqc/innerdistance/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/rseqc/innerdistance/main.nf b/modules/nf-core/software/rseqc/innerdistance/main.nf deleted file mode 100644 index 2688fca62..000000000 --- a/modules/nf-core/software/rseqc/innerdistance/main.nf +++ /dev/null @@ -1,53 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process RSEQC_INNERDISTANCE { - tag "$meta.id" - label 'process_medium' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::rseqc=3.0.1" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1" - } else { - container "quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1" - } - - input: - tuple val(meta), path(bam) - path bed - - output: - tuple val(meta), path("*distance.txt"), optional:true, emit: distance - tuple val(meta), path("*freq.txt") , optional:true, emit: freq - tuple val(meta), path("*mean.txt") , optional:true, emit: mean - tuple val(meta), path("*.pdf") , optional:true, emit: pdf - tuple val(meta), path("*.r") , optional:true, emit: rscript - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - if (!meta.single_end) { - """ - inner_distance.py \\ - -i $bam \\ - -r $bed \\ - -o $prefix \\ - $options.args \\ - > stdout.txt - head -n 2 stdout.txt > ${prefix}.inner_distance_mean.txt - - inner_distance.py --version | sed -e "s/inner_distance.py //g" > ${software}.version.txt - """ - } else { - """ - inner_distance.py --version | sed -e "s/inner_distance.py //g" > ${software}.version.txt - """ - } -} diff --git a/modules/nf-core/software/rseqc/innerdistance/meta.yml b/modules/nf-core/software/rseqc/innerdistance/meta.yml deleted file mode 100644 index ed72c51cc..000000000 --- a/modules/nf-core/software/rseqc/innerdistance/meta.yml +++ /dev/null @@ -1,55 +0,0 @@ -name: rseqc_innerdistance -description: Calculate inner distance between read pairs. -keywords: - - fragment_size - - inner_distance -tools: - - rseqc: - description: | - RSeQC package provides a number of useful modules that can comprehensively evaluate - high throughput sequence data especially RNA-seq data. - homepage: http://rseqc.sourceforge.net/ - documentation: http://rseqc.sourceforge.net/ - doi: 10.1093/bioinformatics/bts356 -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: the alignment in bam format - pattern: "*.{bam}" - - bed: - type: file - description: a bed file for the reference gene model - pattern: "*.{bed}" -output: - - distance: - type: file - description: the inner distances - pattern: "*.inner_distance.txt" - - freq: - type: file - description: frequencies of different insert sizes - pattern: "*.inner_distance_freq.txt" - - mean: - type: file - description: mean/median values of inner distances - pattern: "*.inner_distance_mean.txt" - - pdf: - type: file - description: distribution plot of inner distances - pattern: "*.inner_distance_plot.pdf" - - rscript: - type: file - description: script to reproduce the plot - pattern: "*.inner_distance_plot.R" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@drpatelh" - - "@kevinmenden" diff --git a/modules/nf-core/software/rseqc/junctionannotation/functions.nf b/modules/nf-core/software/rseqc/junctionannotation/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/rseqc/junctionannotation/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/rseqc/junctionannotation/main.nf b/modules/nf-core/software/rseqc/junctionannotation/main.nf deleted file mode 100644 index 74105c3a6..000000000 --- a/modules/nf-core/software/rseqc/junctionannotation/main.nf +++ /dev/null @@ -1,48 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process RSEQC_JUNCTIONANNOTATION { - tag "$meta.id" - label 'process_medium' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::rseqc=3.0.1" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1" - } else { - container "quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1" - } - - input: - tuple val(meta), path(bam) - path bed - - output: - tuple val(meta), path("*.junction.bed"), emit: bed - tuple val(meta), path("*.Interact.bed"), emit: interact_bed - tuple val(meta), path("*.xls") , emit: xls - tuple val(meta), path("*junction.pdf") , emit: pdf - tuple val(meta), path("*events.pdf") , emit: events_pdf - tuple val(meta), path("*.r") , emit: rscript - tuple val(meta), path("*.log") , emit: log - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - """ - junction_annotation.py \\ - -i $bam \\ - -r $bed \\ - -o $prefix \\ - $options.args \\ - 2> ${prefix}.junction_annotation.log - - junction_annotation.py --version | sed -e "s/junction_annotation.py //g" > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/rseqc/junctionannotation/meta.yml b/modules/nf-core/software/rseqc/junctionannotation/meta.yml deleted file mode 100644 index dd9800094..000000000 --- a/modules/nf-core/software/rseqc/junctionannotation/meta.yml +++ /dev/null @@ -1,61 +0,0 @@ -name: rseqc_innerdistance -description: compare detected splice junctions to reference gene model -keywords: - - junctions - - splicing - - rnaseq -tools: - - rseqc: - description: | - RSeQC package provides a number of useful modules that can comprehensively evaluate - high throughput sequence data especially RNA-seq data. - homepage: http://rseqc.sourceforge.net/ - documentation: http://rseqc.sourceforge.net/ - doi: 10.1093/bioinformatics/bts356 -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: the alignment in bam format - pattern: "*.{bam}" - - bed: - type: file - description: a bed file for the reference gene model - pattern: "*.{bed}" -output: - - bed: - type: file - description: bed file of annotated junctions - pattern: "*.junction.bed" - - interact_bed: - type: file - description: Interact bed file - pattern: "*.Interact.bed" - - xls: - type: file - description: xls file with junction information - pattern: "*.xls" - - pdf: - type: file - description: junction plot - pattern: "*.junction.pdf" - - events_pdf: - type: file - description: events plot - pattern: "*.events.pdf" - - rscript: - type: file - description: Rscript to reproduce the plots - pattern: "*.r" - - log: - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@drpatelh" - - "@kevinmenden" diff --git a/modules/nf-core/software/rseqc/junctionsaturation/functions.nf b/modules/nf-core/software/rseqc/junctionsaturation/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/rseqc/junctionsaturation/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/rseqc/junctionsaturation/main.nf b/modules/nf-core/software/rseqc/junctionsaturation/main.nf deleted file mode 100644 index e6e216380..000000000 --- a/modules/nf-core/software/rseqc/junctionsaturation/main.nf +++ /dev/null @@ -1,42 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process RSEQC_JUNCTIONSATURATION { - tag "$meta.id" - label 'process_medium' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::rseqc=3.0.1" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1" - } else { - container "quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1" - } - - input: - tuple val(meta), path(bam) - path bed - - output: - tuple val(meta), path("*.pdf"), emit: pdf - tuple val(meta), path("*.r") , emit: rscript - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - """ - junction_saturation.py \\ - -i $bam \\ - -r $bed \\ - -o $prefix \\ - $options.args - - junction_saturation.py --version | sed -e "s/junction_saturation.py //g" > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/rseqc/readdistribution/functions.nf b/modules/nf-core/software/rseqc/readdistribution/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/rseqc/readdistribution/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/rseqc/readdistribution/main.nf b/modules/nf-core/software/rseqc/readdistribution/main.nf deleted file mode 100644 index a6ed6c9f1..000000000 --- a/modules/nf-core/software/rseqc/readdistribution/main.nf +++ /dev/null @@ -1,40 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process RSEQC_READDISTRIBUTION { - tag "$meta.id" - label 'process_medium' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::rseqc=3.0.1" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1" - } else { - container "quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1" - } - - input: - tuple val(meta), path(bam) - path bed - - output: - tuple val(meta), path("*.read_distribution.txt"), emit: txt - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - """ - read_distribution.py \\ - -i $bam \\ - -r $bed \\ - > ${prefix}.read_distribution.txt - - read_distribution.py --version | sed -e "s/read_distribution.py //g" > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/rseqc/readdistribution/meta.yml b/modules/nf-core/software/rseqc/readdistribution/meta.yml deleted file mode 100644 index ce2b0f5a9..000000000 --- a/modules/nf-core/software/rseqc/readdistribution/meta.yml +++ /dev/null @@ -1,40 +0,0 @@ -name: rseqc_readdistribution -description: Calculate how mapped reads are distributed over genomic features -keywords: - - read distribution - - genomics - - rnaseq -tools: - - rseqc: - description: | - RSeQC package provides a number of useful modules that can comprehensively evaluate - high throughput sequence data especially RNA-seq data. - homepage: http://rseqc.sourceforge.net/ - documentation: http://rseqc.sourceforge.net/ - doi: 10.1093/bioinformatics/bts356 -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: the alignment in bam format - pattern: "*.{bam}" - - bed: - type: file - description: a bed file for the reference gene model - pattern: "*.{bed}" -output: - - txt: - type: file - description: the read distribution report - pattern: "*.read_distribution.txt" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@drpatelh" - - "@kevinmenden" diff --git a/modules/nf-core/software/rseqc/readduplication/functions.nf b/modules/nf-core/software/rseqc/readduplication/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/rseqc/readduplication/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/rseqc/readduplication/main.nf b/modules/nf-core/software/rseqc/readduplication/main.nf deleted file mode 100644 index 6fb06f637..000000000 --- a/modules/nf-core/software/rseqc/readduplication/main.nf +++ /dev/null @@ -1,42 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process RSEQC_READDUPLICATION { - tag "$meta.id" - label 'process_medium' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::rseqc=3.0.1" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1" - } else { - container "quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1" - } - - input: - tuple val(meta), path(bam) - - output: - tuple val(meta), path("*seq.DupRate.xls"), emit: seq_xls - tuple val(meta), path("*pos.DupRate.xls"), emit: pos_xls - tuple val(meta), path("*.pdf") , emit: pdf - tuple val(meta), path("*.r") , emit: rscript - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - """ - read_duplication.py \\ - -i $bam \\ - -o $prefix \\ - $options.args - - read_duplication.py --version | sed -e "s/read_duplication.py //g" > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/rseqc/readduplication/meta.yml b/modules/nf-core/software/rseqc/readduplication/meta.yml deleted file mode 100644 index c43ea688f..000000000 --- a/modules/nf-core/software/rseqc/readduplication/meta.yml +++ /dev/null @@ -1,51 +0,0 @@ -name: rseqc_readduplication -description: Calculate read duplication rate -keywords: - - rnaseq - - duplication -tools: - - rseqc: - description: | - RSeQC package provides a number of useful modules that can comprehensively evaluate - high throughput sequence data especially RNA-seq data. - homepage: http://rseqc.sourceforge.net/ - documentation: http://rseqc.sourceforge.net/ - doi: 10.1093/bioinformatics/bts356 -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: the alignment in bam format - pattern: "*.{bam}" - - bed: - type: file - description: a bed file for the reference gene model - pattern: "*.{bed}" -output: - - seq_xls: - type: file - description: Read duplication rate determined from mapping position of read - pattern: "*seq.DupRate.xls" - - pos_xls: - type: file - description: Read duplication rate determined from sequence of read - pattern: "*pos.DupRate.xls" - - pdf: - type: file - description: plot of duplication rate - pattern: "*.pdf" - - rscript: - type: file - description: script to reproduce the plot - pattern: "*.R" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@drpatelh" - - "@kevinmenden" diff --git a/modules/nf-core/software/salmon/index/functions.nf b/modules/nf-core/software/salmon/index/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/salmon/index/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/salmon/index/main.nf b/modules/nf-core/software/salmon/index/main.nf deleted file mode 100644 index 17d5bc064..000000000 --- a/modules/nf-core/software/salmon/index/main.nf +++ /dev/null @@ -1,51 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process SALMON_INDEX { - tag "$transcript_fasta" - label "process_medium" - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:'index', meta:[:], publish_by_meta:[]) } - - conda (params.enable_conda ? "bioconda::salmon=1.4.0" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/salmon:1.4.0--hf69c8f4_0" - } else { - container "quay.io/biocontainers/salmon:1.4.0--hf69c8f4_0" - } - - input: - path genome_fasta - path transcript_fasta - - output: - path "salmon" , emit: index - path "*.version.txt", emit: version - - script: - def software = getSoftwareName(task.process) - def get_decoy_ids = "grep '^>' $genome_fasta | cut -d ' ' -f 1 > decoys.txt" - def gentrome = "gentrome.fa" - if (genome_fasta.endsWith('.gz')) { - get_decoy_ids = "grep '^>' <(gunzip -c $genome_fasta) | cut -d ' ' -f 1 > decoys.txt" - gentrome = "gentrome.fa.gz" - } - """ - $get_decoy_ids - sed -i.bak -e 's/>//g' decoys.txt - cat $transcript_fasta $genome_fasta > $gentrome - - salmon \\ - index \\ - --threads $task.cpus \\ - -t $gentrome \\ - -d decoys.txt \\ - $options.args \\ - -i salmon - salmon --version | sed -e "s/salmon //g" > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/salmon/index/meta.yml b/modules/nf-core/software/salmon/index/meta.yml deleted file mode 100644 index 652e2a77a..000000000 --- a/modules/nf-core/software/salmon/index/meta.yml +++ /dev/null @@ -1,35 +0,0 @@ -name: salmon_index -description: Create index for salmon -keywords: - - index - - fasta - - genome - - reference -tools: - - salmon: - description: | - Salmon is a tool for wicked-fast transcript quantification from RNA-seq data - homepage: https://salmon.readthedocs.io/en/latest/salmon.html - manual: https://salmon.readthedocs.io/en/latest/salmon.html - doi: 10.1038/nmeth.4197 -input: - - genome_fasta: - type: file - description: Fasta file of the reference genome - - transcriptome_fasta: - type: file - description: Fasta file of the reference transcriptome - -output: - - index: - type: directory - description: Folder containing the star index files - pattern: "salmon" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" - -authors: - - "@kevinmenden" - - "@drpatelh" diff --git a/modules/nf-core/software/salmon/quant/functions.nf b/modules/nf-core/software/salmon/quant/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/salmon/quant/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/salmon/quant/main.nf b/modules/nf-core/software/salmon/quant/main.nf deleted file mode 100644 index 093137de5..000000000 --- a/modules/nf-core/software/salmon/quant/main.nf +++ /dev/null @@ -1,77 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process SALMON_QUANT { - tag "$meta.id" - label "process_medium" - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::salmon=1.4.0" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/salmon:1.4.0--hf69c8f4_0" - } else { - container "quay.io/biocontainers/salmon:1.4.0--hf69c8f4_0" - } - - input: - tuple val(meta), path(reads) - path index - path gtf - path transcript_fasta - val alignment_mode - val lib_type - - output: - tuple val(meta), path("${prefix}"), emit: results - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - - def reference = "--index $index" - def input_reads = meta.single_end ? "-r $reads" : "-1 ${reads[0]} -2 ${reads[1]}" - if (alignment_mode) { - reference = "-t $transcript_fasta" - input_reads = "-a $reads" - } - - def strandedness_opts = [ - 'A', 'U', 'SF', 'SR', - 'IS', 'IU' , 'ISF', 'ISR', - 'OS', 'OU' , 'OSF', 'OSR', - 'MS', 'MU' , 'MSF', 'MSR' - ] - def strandedness = 'A' - if (lib_type) { - if (strandedness_opts.contains(lib_type)) { - strandedness = lib_type - } else { - log.info "[Salmon Quant] Invalid library type specified '--libType=${lib_type}', defaulting to auto-detection with '--libType=A'." - } - } else { - strandedness = meta.single_end ? 'U' : 'IU' - if (meta.strandedness == 'forward') { - strandedness = meta.single_end ? 'SF' : 'ISF' - } else if (meta.strandedness == 'reverse') { - strandedness = meta.single_end ? 'SR' : 'ISR' - } - } - """ - salmon quant \\ - --geneMap $gtf \\ - --threads $task.cpus \\ - --libType=$strandedness \\ - $reference \\ - $input_reads \\ - $options.args \\ - -o $prefix - - salmon --version | sed -e "s/salmon //g" > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/salmon/quant/meta.yml b/modules/nf-core/software/salmon/quant/meta.yml deleted file mode 100644 index f37c9884a..000000000 --- a/modules/nf-core/software/salmon/quant/meta.yml +++ /dev/null @@ -1,55 +0,0 @@ -name: salmon_quant -description: gene/transcript quantification with Salmon -keywords: - - index - - fasta - - genome - - reference -tools: - - salmon: - description: | - Salmon is a tool for wicked-fast transcript quantification from RNA-seq data - homepage: https://salmon.readthedocs.io/en/latest/salmon.html - manual: https://salmon.readthedocs.io/en/latest/salmon.html - doi: 10.1038/nmeth.4197 -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - reads: - type: file - description: | - List of input FastQ files of size 1 and 2 for single-end and paired-end data, - respectively. - - index: - type: directory - description: Folder containing the star index files - - gtf: - type: file - description: GTF of the reference transcriptome - - transcriptome_fasta: - type: file - description: Fasta file of the reference transcriptome - - alignment_mode: - type: boolean - description: whether to run salmon in alignment mode - - lib_type: - type: string - description: | - Override library type inferred based on strandedness defined in meta object - -output: - - sample_output: - type: directory - description: Folder containing the quantification results for a specific sample - pattern: "${prefix}" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" - -authors: - - "@kevinmenden" - - "@drpatelh" diff --git a/modules/nf-core/software/samtools/flagstat/functions.nf b/modules/nf-core/software/samtools/flagstat/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/samtools/flagstat/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/samtools/flagstat/main.nf b/modules/nf-core/software/samtools/flagstat/main.nf deleted file mode 100644 index 7260f502c..000000000 --- a/modules/nf-core/software/samtools/flagstat/main.nf +++ /dev/null @@ -1,34 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process SAMTOOLS_FLAGSTAT { - tag "$meta.id" - label 'process_low' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::samtools=1.10" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/samtools:1.10--h9402c20_2" - } else { - container "quay.io/biocontainers/samtools:1.10--h9402c20_2" - } - - input: - tuple val(meta), path(bam), path(bai) - - output: - tuple val(meta), path("*.flagstat"), emit: flagstat - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - """ - samtools flagstat $bam > ${bam}.flagstat - echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/samtools/flagstat/meta.yml b/modules/nf-core/software/samtools/flagstat/meta.yml deleted file mode 100644 index 8414bf54b..000000000 --- a/modules/nf-core/software/samtools/flagstat/meta.yml +++ /dev/null @@ -1,48 +0,0 @@ -name: samtools_flagstat -description: Counts the number of alignments in a BAM/CRAM/SAM file for each FLAG type -keywords: - - stats - - mapping - - counts - - bam - - sam - - cram -tools: - - samtools: - description: | - SAMtools is a set of utilities for interacting with and post-processing - short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. - These files are generated as output by short read aligners like BWA. - homepage: http://www.htslib.org/ - documentation: hhttp://www.htslib.org/doc/samtools.html - doi: 10.1093/bioinformatics/btp352 -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: BAM/CRAM/SAM file - pattern: "*.{bam,cram,sam}" - - bai: - type: file - description: Index for BAM/CRAM/SAM file - pattern: "*.{bai,crai,sai}" -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - flagstat: - type: file - description: File containing samtools flagstat output - pattern: "*.{flagstat}" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@drpatelh" diff --git a/modules/nf-core/software/samtools/idxstats/functions.nf b/modules/nf-core/software/samtools/idxstats/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/samtools/idxstats/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/samtools/idxstats/main.nf b/modules/nf-core/software/samtools/idxstats/main.nf deleted file mode 100644 index eb74a25e8..000000000 --- a/modules/nf-core/software/samtools/idxstats/main.nf +++ /dev/null @@ -1,34 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process SAMTOOLS_IDXSTATS { - tag "$meta.id" - label 'process_low' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::samtools=1.10" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/samtools:1.10--h9402c20_2" - } else { - container "quay.io/biocontainers/samtools:1.10--h9402c20_2" - } - - input: - tuple val(meta), path(bam), path(bai) - - output: - tuple val(meta), path("*.idxstats"), emit: idxstats - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - """ - samtools idxstats $bam > ${bam}.idxstats - echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/samtools/idxstats/meta.yml b/modules/nf-core/software/samtools/idxstats/meta.yml deleted file mode 100644 index 530d07724..000000000 --- a/modules/nf-core/software/samtools/idxstats/meta.yml +++ /dev/null @@ -1,49 +0,0 @@ -name: samtools_idxstats -description: Reports alignment summary statistics for a BAM/CRAM/SAM file -keywords: - - stats - - mapping - - counts - - chromosome - - bam - - sam - - cram -tools: - - samtools: - description: | - SAMtools is a set of utilities for interacting with and post-processing - short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. - These files are generated as output by short read aligners like BWA. - homepage: http://www.htslib.org/ - documentation: hhttp://www.htslib.org/doc/samtools.html - doi: 10.1093/bioinformatics/btp352 -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: BAM/CRAM/SAM file - pattern: "*.{bam,cram,sam}" - - bai: - type: file - description: Index for BAM/CRAM/SAM file - pattern: "*.{bai,crai,sai}" -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - idxstats: - type: file - description: File containing samtools idxstats output - pattern: "*.{idxstats}" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@drpatelh" diff --git a/modules/nf-core/software/samtools/index/functions.nf b/modules/nf-core/software/samtools/index/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/samtools/index/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/samtools/index/main.nf b/modules/nf-core/software/samtools/index/main.nf deleted file mode 100644 index 2f323c817..000000000 --- a/modules/nf-core/software/samtools/index/main.nf +++ /dev/null @@ -1,35 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process SAMTOOLS_INDEX { - tag "$meta.id" - label 'process_low' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::samtools=1.10" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/samtools:1.10--h9402c20_2" - } else { - container "quay.io/biocontainers/samtools:1.10--h9402c20_2" - } - - input: - tuple val(meta), path(bam) - - output: - tuple val(meta), path("*.bai"), optional:true, emit: bai - tuple val(meta), path("*.csi"), optional:true, emit: csi - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - """ - samtools index $options.args $bam - echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/samtools/index/meta.yml b/modules/nf-core/software/samtools/index/meta.yml deleted file mode 100644 index 5d076e3be..000000000 --- a/modules/nf-core/software/samtools/index/meta.yml +++ /dev/null @@ -1,47 +0,0 @@ -name: samtools_index -description: Index SAM/BAM/CRAM file -keywords: - - index - - bam - - sam - - cram -tools: - - samtools: - description: | - SAMtools is a set of utilities for interacting with and post-processing - short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. - These files are generated as output by short read aligners like BWA. - homepage: http://www.htslib.org/ - documentation: hhttp://www.htslib.org/doc/samtools.html - doi: 10.1093/bioinformatics/btp352 -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: BAM/CRAM/SAM file - pattern: "*.{bam,cram,sam}" -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bai: - type: file - description: BAM/CRAM/SAM index file - pattern: "*.{bai,crai,sai}" - - csi: - type: file - description: CSI index file - pattern: "*.{csi}" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@drpatelh" - - "@ewels" diff --git a/modules/nf-core/software/samtools/sort/functions.nf b/modules/nf-core/software/samtools/sort/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/samtools/sort/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/samtools/sort/main.nf b/modules/nf-core/software/samtools/sort/main.nf deleted file mode 100644 index ee09c6563..000000000 --- a/modules/nf-core/software/samtools/sort/main.nf +++ /dev/null @@ -1,35 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process SAMTOOLS_SORT { - tag "$meta.id" - label 'process_medium' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::samtools=1.10" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/samtools:1.10--h9402c20_2" - } else { - container "quay.io/biocontainers/samtools:1.10--h9402c20_2" - } - - input: - tuple val(meta), path(bam) - - output: - tuple val(meta), path("*.bam"), emit: bam - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - """ - samtools sort $options.args -@ $task.cpus -o ${prefix}.bam -T $prefix $bam - echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/samtools/sort/meta.yml b/modules/nf-core/software/samtools/sort/meta.yml deleted file mode 100644 index 704e8c1f3..000000000 --- a/modules/nf-core/software/samtools/sort/meta.yml +++ /dev/null @@ -1,43 +0,0 @@ -name: samtools_sort -description: Sort SAM/BAM/CRAM file -keywords: - - sort - - bam - - sam - - cram -tools: - - samtools: - description: | - SAMtools is a set of utilities for interacting with and post-processing - short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. - These files are generated as output by short read aligners like BWA. - homepage: http://www.htslib.org/ - documentation: hhttp://www.htslib.org/doc/samtools.html - doi: 10.1093/bioinformatics/btp352 -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: BAM/CRAM/SAM file - pattern: "*.{bam,cram,sam}" -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: Sorted BAM/CRAM/SAM file - pattern: "*.{bam,cram,sam}" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@drpatelh" - - "@ewels" diff --git a/modules/nf-core/software/samtools/stats/functions.nf b/modules/nf-core/software/samtools/stats/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/samtools/stats/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/samtools/stats/main.nf b/modules/nf-core/software/samtools/stats/main.nf deleted file mode 100644 index c307f9e8c..000000000 --- a/modules/nf-core/software/samtools/stats/main.nf +++ /dev/null @@ -1,34 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process SAMTOOLS_STATS { - tag "$meta.id" - label 'process_low' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::samtools=1.10" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/samtools:1.10--h9402c20_2" - } else { - container "quay.io/biocontainers/samtools:1.10--h9402c20_2" - } - - input: - tuple val(meta), path(bam), path(bai) - - output: - tuple val(meta), path("*.stats"), emit: stats - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - """ - samtools stats $bam > ${bam}.stats - echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/samtools/stats/meta.yml b/modules/nf-core/software/samtools/stats/meta.yml deleted file mode 100644 index b549ff5c8..000000000 --- a/modules/nf-core/software/samtools/stats/meta.yml +++ /dev/null @@ -1,47 +0,0 @@ -name: samtools_stats -description: Produces comprehensive statistics from SAM/BAM/CRAM file -keywords: - - statistics - - counts - - bam - - sam - - cram -tools: - - samtools: - description: | - SAMtools is a set of utilities for interacting with and post-processing - short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. - These files are generated as output by short read aligners like BWA. - homepage: http://www.htslib.org/ - documentation: hhttp://www.htslib.org/doc/samtools.html - doi: 10.1093/bioinformatics/btp352 -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: BAM/CRAM/SAM file - pattern: "*.{bam,cram,sam}" - - bai: - type: file - description: Index for BAM/CRAM/SAM file - pattern: "*.{bai,crai,sai}" -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - stats: - type: file - description: File containing samtools stats output - pattern: "*.{stats}" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@drpatelh" diff --git a/modules/nf-core/software/sortmerna/functions.nf b/modules/nf-core/software/sortmerna/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/sortmerna/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/sortmerna/main.nf b/modules/nf-core/software/sortmerna/main.nf deleted file mode 100644 index 32ca4ca9a..000000000 --- a/modules/nf-core/software/sortmerna/main.nf +++ /dev/null @@ -1,73 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process SORTMERNA { - tag "$meta.id" - label "process_high" - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::sortmerna=4.2.0" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/sortmerna:4.2.0--0" - } else { - container "quay.io/biocontainers/sortmerna:4.2.0--0" - } - - input: - tuple val(meta), path(reads) - path fasta - - output: - tuple val(meta), path("*.fastq.gz"), emit: reads - tuple val(meta), path("*.log") , emit: log - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - - def Refs = "" - for (i=0; i ${prefix}.fastq.gz - mv rRNA_reads.log ${prefix}.sortmerna.log - - echo \$(sortmerna --version 2>&1) | sed 's/^.*SortMeRNA version //; s/ Build Date.*\$//' > ${software}.version.txt - """ - } else { - """ - sortmerna \\ - $Refs \\ - --reads ${reads[0]} \\ - --reads ${reads[1]} \\ - --threads $task.cpus \\ - --workdir . \\ - --aligned rRNA_reads \\ - --other non_rRNA_reads \\ - --paired_in \\ - --out2 \\ - $options.args - - gzip -f < non_rRNA_reads_fwd.fq > ${prefix}_1.fastq.gz - gzip -f < non_rRNA_reads_rev.fq > ${prefix}_2.fastq.gz - mv rRNA_reads.log ${prefix}.sortmerna.log - - echo \$(sortmerna --version 2>&1) | sed 's/^.*SortMeRNA version //; s/ Build Date.*\$//' > ${software}.version.txt - """ - } -} diff --git a/modules/nf-core/software/star/align/functions.nf b/modules/nf-core/software/star/align/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/star/align/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/star/align/main.nf b/modules/nf-core/software/star/align/main.nf deleted file mode 100644 index e85ddb79d..000000000 --- a/modules/nf-core/software/star/align/main.nf +++ /dev/null @@ -1,71 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process STAR_ALIGN { - tag "$meta.id" - label 'process_high' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - // Note: 2.7X indices incompatible with AWS iGenomes. - conda (params.enable_conda ? 'bioconda::star=2.6.1d' : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container 'https://depot.galaxyproject.org/singularity/star:2.6.1d--0' - } else { - container 'quay.io/biocontainers/star:2.6.1d--0' - } - - input: - tuple val(meta), path(reads) - path index - path gtf - - output: - tuple val(meta), path('*d.out.bam') , emit: bam - tuple val(meta), path('*Log.final.out') , emit: log_final - tuple val(meta), path('*Log.out') , emit: log_out - tuple val(meta), path('*Log.progress.out'), emit: log_progress - path '*.version.txt' , emit: version - - tuple val(meta), path('*sortedByCoord.out.bam') , optional:true, emit: bam_sorted - tuple val(meta), path('*toTranscriptome.out.bam'), optional:true, emit: bam_transcript - tuple val(meta), path('*Aligned.unsort.out.bam') , optional:true, emit: bam_unsorted - tuple val(meta), path('*fastq.gz') , optional:true, emit: fastq - tuple val(meta), path('*.tab') , optional:true, emit: tab - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - def ignore_gtf = params.star_ignore_sjdbgtf ? '' : "--sjdbGTFfile $gtf" - def seq_center = params.seq_center ? "--outSAMattrRGline ID:$prefix 'CN:$params.seq_center' 'SM:$prefix'" : "--outSAMattrRGline ID:$prefix 'SM:$prefix'" - def out_sam_type = (options.args.contains('--outSAMtype')) ? '' : '--outSAMtype BAM Unsorted' - def mv_unsorted_bam = (options.args.contains('--outSAMtype BAM Unsorted SortedByCoordinate')) ? "mv ${prefix}.Aligned.out.bam ${prefix}.Aligned.unsort.out.bam" : '' - """ - STAR \\ - --genomeDir $index \\ - --readFilesIn $reads \\ - --runThreadN $task.cpus \\ - --outFileNamePrefix $prefix. \\ - $out_sam_type \\ - $ignore_gtf \\ - $seq_center \\ - $options.args - - $mv_unsorted_bam - - if [ -f ${prefix}.Unmapped.out.mate1 ]; then - mv ${prefix}.Unmapped.out.mate1 ${prefix}.unmapped_1.fastq - gzip ${prefix}.unmapped_1.fastq - fi - if [ -f ${prefix}.Unmapped.out.mate2 ]; then - mv ${prefix}.Unmapped.out.mate2 ${prefix}.unmapped_2.fastq - gzip ${prefix}.unmapped_2.fastq - fi - - STAR --version | sed -e "s/STAR_//g" > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/star/align/meta.yml b/modules/nf-core/software/star/align/meta.yml deleted file mode 100644 index 01bc2ecff..000000000 --- a/modules/nf-core/software/star/align/meta.yml +++ /dev/null @@ -1,75 +0,0 @@ -name: star_align -description: Align reads to a reference genome using STAR -keywords: - - align - - fasta - - genome - - reference -tools: - - star: - description: | - STAR is a software package for mapping DNA sequences against - a large reference genome, such as the human genome. - homepage: https://github.com/alexdobin/STAR - manual: https://github.com/alexdobin/STAR/blob/master/doc/STARmanual.pdf - doi: 10.1093/bioinformatics/bts635 -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - reads: - type: file - description: | - List of input FastQ files of size 1 and 2 for single-end and paired-end data, - respectively. - - index: - type: directory - description: STAR genome index - pattern: "star" -output: - - bam: - type: file - description: Output BAM file containing read alignments - pattern: "*.{bam}" - - log_final: - type: file - description: STAR final log file - pattern: "*Log.final.out" - - log_out: - type: file - description: STAR lot out file - pattern: "*Log.out" - - log_progress: - type: file - description: STAR log progress file - pattern: "*Log.progress.out" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" - - bam_sorted: - type: file - description: Sorted BAM file of read alignments (optional) - pattern: "*sortedByCoord.out.bam" - - bam_transcript: - type: file - description: Output BAM file of transcriptome alignment (optional) - pattern: "*toTranscriptome.out.bam" - - bam_unsorted: - type: file - description: Unsorted BAM file of read alignments (optional) - pattern: "*Aligned.unsort.out.bam" - - fastq: - type: file - description: Unmapped FastQ files (optional) - pattern: "*fastq.gz" - - tab: - type: file - description: STAR output tab file(s) (optional) - pattern: "*.tab" - -authors: - - "@kevinmenden" - - "@drpatelh" diff --git a/modules/nf-core/software/star/genomegenerate/functions.nf b/modules/nf-core/software/star/genomegenerate/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/star/genomegenerate/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/star/genomegenerate/main.nf b/modules/nf-core/software/star/genomegenerate/main.nf deleted file mode 100644 index b440b4158..000000000 --- a/modules/nf-core/software/star/genomegenerate/main.nf +++ /dev/null @@ -1,67 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process STAR_GENOMEGENERATE { - tag "$fasta" - label 'process_high' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:'index', meta:[:], publish_by_meta:[]) } - - // Note: 2.7X indices incompatible with AWS iGenomes. - conda (params.enable_conda ? "bioconda::star=2.6.1d bioconda::samtools=1.10 conda-forge::gawk=5.1.0" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0" - } else { - container "quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0" - } - - input: - path fasta - path gtf - - output: - path "star" , emit: index - path "*.version.txt", emit: version - - script: - def software = getSoftwareName(task.process) - def memory = task.memory ? "--limitGenomeGenerateRAM ${task.memory.toBytes() - 100000000}" : '' - def args = options.args.tokenize() - if (args.contains('--genomeSAindexNbases')) { - """ - mkdir star - STAR \\ - --runMode genomeGenerate \\ - --genomeDir star/ \\ - --genomeFastaFiles $fasta \\ - --sjdbGTFfile $gtf \\ - --runThreadN $task.cpus \\ - $memory \\ - $options.args - - STAR --version | sed -e "s/STAR_//g" > ${software}.version.txt - """ - } else { - """ - samtools faidx $fasta - NUM_BASES=`gawk '{sum = sum + \$2}END{if ((log(sum)/log(2))/2 - 1 > 14) {printf "%.0f", 14} else {printf "%.0f", (log(sum)/log(2))/2 - 1}}' ${fasta}.fai` - - mkdir star - STAR \\ - --runMode genomeGenerate \\ - --genomeDir star/ \\ - --genomeFastaFiles $fasta \\ - --sjdbGTFfile $gtf \\ - --runThreadN $task.cpus \\ - --genomeSAindexNbases \$NUM_BASES \\ - $memory \\ - $options.args - - STAR --version | sed -e "s/STAR_//g" > ${software}.version.txt - """ - } -} diff --git a/modules/nf-core/software/star/genomegenerate/meta.yml b/modules/nf-core/software/star/genomegenerate/meta.yml deleted file mode 100644 index aae0219bc..000000000 --- a/modules/nf-core/software/star/genomegenerate/meta.yml +++ /dev/null @@ -1,36 +0,0 @@ -name: star_genomegenerate -description: Create index for STAR -keywords: - - index - - fasta - - genome - - reference -tools: - - star: - description: | - STAR is a software package for mapping DNA sequences against - a large reference genome, such as the human genome. - homepage: https://github.com/alexdobin/STAR - manual: https://github.com/alexdobin/STAR/blob/master/doc/STARmanual.pdf - doi: 10.1093/bioinformatics/bts635 -input: - - fasta: - type: file - description: Fasta file of the reference genome - - gtf: - type: file - description: GTF file of the reference genome - -output: - - index: - type: directory - description: Folder containing the star index files - pattern: "star" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" - -authors: - - "@kevinmenden" - - "@drpatelh" diff --git a/modules/nf-core/software/stringtie/stringtie/functions.nf b/modules/nf-core/software/stringtie/stringtie/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/stringtie/stringtie/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/stringtie/stringtie/main.nf b/modules/nf-core/software/stringtie/stringtie/main.nf deleted file mode 100644 index eb751321e..000000000 --- a/modules/nf-core/software/stringtie/stringtie/main.nf +++ /dev/null @@ -1,55 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process STRINGTIE { - tag "$meta.id" - label 'process_medium' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::stringtie=2.1.4" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/stringtie:2.1.4--h7e0af3c_0" - } else { - container "quay.io/biocontainers/stringtie:2.1.4--h7e0af3c_0" - } - - input: - tuple val(meta), path(bam) - path gtf - - output: - tuple val(meta), path("*.coverage.gtf") , emit: coverage_gtf - tuple val(meta), path("*.transcripts.gtf"), emit: transcript_gtf - tuple val(meta), path("*.abundance.txt") , emit: abundance - tuple val(meta), path("*.ballgown") , emit: ballgown - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - - def strandedness = '' - if (meta.strandedness == 'forward') { - strandedness = '--fr' - } else if (meta.strandedness == 'reverse') { - strandedness = '--rf' - } - """ - stringtie \\ - $bam \\ - $strandedness \\ - -G $gtf \\ - -o ${prefix}.transcripts.gtf \\ - -A ${prefix}.gene.abundance.txt \\ - -C ${prefix}.coverage.gtf \\ - -b ${prefix}.ballgown \\ - $options.args - - stringtie --version > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/stringtie/stringtie/meta.yml b/modules/nf-core/software/stringtie/stringtie/meta.yml deleted file mode 100644 index 52ec899d9..000000000 --- a/modules/nf-core/software/stringtie/stringtie/meta.yml +++ /dev/null @@ -1,56 +0,0 @@ -name: stringtie -description: Transcript assembly and quantification for RNA-Se -keywords: - - transcript - - assembly - - quantification - - gtf - -tools: - - stringtie2: - description: | - Transcript assembly and quantification for RNA-Seq - homepage: https://ccb.jhu.edu/software/stringtie/index.shtml - documentation: https://ccb.jhu.edu/software/stringtie/index.shtml?t=manual -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: | - Stringtie transcript gtf output(s). - - gtf: - type: file - description: | - Annotation gtf file. -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - transcript_gtf: - type: file - description: transcript gtf - pattern: "*.{transcripts.gtf}" - - coverage_gtf: - type: file - description: coverage gtf - pattern: "*.{coverage.gtf}" - - abudance: - type: file - description: abudance - pattern: "*.{abudance.txt}" - - ballgown: - type: file - description: for running ballgown - pattern: "*.{ballgown}" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@drpatelh" diff --git a/modules/nf-core/software/subread/featurecounts/functions.nf b/modules/nf-core/software/subread/featurecounts/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/subread/featurecounts/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/subread/featurecounts/main.nf b/modules/nf-core/software/subread/featurecounts/main.nf deleted file mode 100644 index cde14a74b..000000000 --- a/modules/nf-core/software/subread/featurecounts/main.nf +++ /dev/null @@ -1,52 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process SUBREAD_FEATURECOUNTS { - tag "$meta.id" - label 'process_medium' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::subread=2.0.1" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/subread:2.0.1--hed695b0_0" - } else { - container "quay.io/biocontainers/subread:2.0.1--hed695b0_0" - } - - input: - tuple val(meta), path(bams), path(annotation) - - output: - tuple val(meta), path("*featureCounts.txt") , emit: counts - tuple val(meta), path("*featureCounts.txt.summary"), emit: summary - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - def paired_end = meta.single_end ? '' : '-p' - - def strandedness = 0 - if (meta.strandedness == 'forward') { - strandedness = 1 - } else if (meta.strandedness == 'reverse') { - strandedness = 2 - } - """ - featureCounts \\ - $options.args \\ - $paired_end \\ - -T $task.cpus \\ - -a $annotation \\ - -s $strandedness \\ - -o ${prefix}.featureCounts.txt \\ - ${bams.join(' ')} - - echo \$(featureCounts -v 2>&1) | sed -e "s/featureCounts v//g" > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/subread/featurecounts/meta.yml b/modules/nf-core/software/subread/featurecounts/meta.yml deleted file mode 100644 index d24f70bdd..000000000 --- a/modules/nf-core/software/subread/featurecounts/meta.yml +++ /dev/null @@ -1,52 +0,0 @@ -name: subread_featurecounts -description: Count reads that map to genomic features -keywords: - - counts - - fasta - - genome - - reference - -tools: - - featurecounts: - description: featureCounts is a highly efficient general-purpose read summarization program that counts mapped reads for genomic features such as genes, exons, promoter, gene bodies, genomic bins and chromosomal locations. It can be used to count both RNA-seq and genomic DNA-seq reads. - homepage: http://bioinf.wehi.edu.au/featureCounts/ - documentation: http://bioinf.wehi.edu.au/subread-package/SubreadUsersGuide.pdf - doi: "10.1093/bioinformatics/btt656" - licence: ['GPL v3'] - -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bam: - type: file - description: BAM/SAM file containing read alignments - pattern: "*.{bam}" - - annotation: - type: file - description: Genomic features annotation in GTF or SAF - pattern: "*.{gtf,saf}" - -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - counts: - type: file - description: Counts of reads mapping to features - pattern: "*featureCounts.txt" - - summary: - type: file - description: Summary log file - pattern: "*.featureCounts.txt.summary" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" - -authors: - - "@ntoda03" diff --git a/modules/nf-core/software/trimgalore/functions.nf b/modules/nf-core/software/trimgalore/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/trimgalore/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/trimgalore/main.nf b/modules/nf-core/software/trimgalore/main.nf deleted file mode 100644 index 44b36e714..000000000 --- a/modules/nf-core/software/trimgalore/main.nf +++ /dev/null @@ -1,83 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process TRIMGALORE { - tag "$meta.id" - label 'process_high' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::trim-galore=0.6.6" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/trim-galore:0.6.6--0" - } else { - container "quay.io/biocontainers/trim-galore:0.6.6--0" - } - - input: - tuple val(meta), path(reads) - - output: - tuple val(meta), path("*.fq.gz") , emit: reads - tuple val(meta), path("*report.txt"), emit: log - path "*.version.txt" , emit: version - - tuple val(meta), path("*.html"), emit: html optional true - tuple val(meta), path("*.zip") , emit: zip optional true - - script: - // Calculate number of --cores for TrimGalore based on value of task.cpus - // See: https://github.com/FelixKrueger/TrimGalore/blob/master/Changelog.md#version-060-release-on-1-mar-2019 - // See: https://github.com/nf-core/atacseq/pull/65 - def cores = 1 - if (task.cpus) { - cores = (task.cpus as int) - 4 - if (meta.single_end) cores = (task.cpus as int) - 3 - if (cores < 1) cores = 1 - if (cores > 4) cores = 4 - } - - // Clipping presets have to be evaluated in the context of SE/PE - def c_r1 = params.clip_r1 > 0 ? "--clip_r1 ${params.clip_r1}" : '' - def c_r2 = params.clip_r2 > 0 ? "--clip_r2 ${params.clip_r2}" : '' - def tpc_r1 = params.three_prime_clip_r1 > 0 ? "--three_prime_clip_r1 ${params.three_prime_clip_r1}" : '' - def tpc_r2 = params.three_prime_clip_r2 > 0 ? "--three_prime_clip_r2 ${params.three_prime_clip_r2}" : '' - - // Added soft-links to original fastqs for consistent naming in MultiQC - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - if (meta.single_end) { - """ - [ ! -f ${prefix}.fastq.gz ] && ln -s $reads ${prefix}.fastq.gz - trim_galore \\ - $options.args \\ - --cores $cores \\ - --gzip \\ - $c_r1 \\ - $tpc_r1 \\ - ${prefix}.fastq.gz - echo \$(trim_galore --version 2>&1) | sed 's/^.*version //; s/Last.*\$//' > ${software}.version.txt - """ - } else { - """ - [ ! -f ${prefix}_1.fastq.gz ] && ln -s ${reads[0]} ${prefix}_1.fastq.gz - [ ! -f ${prefix}_2.fastq.gz ] && ln -s ${reads[1]} ${prefix}_2.fastq.gz - trim_galore \\ - $options.args \\ - --cores $cores \\ - --paired \\ - --gzip \\ - $c_r1 \\ - $c_r2 \\ - $tpc_r1 \\ - $tpc_r2 \\ - ${prefix}_1.fastq.gz \\ - ${prefix}_2.fastq.gz - echo \$(trim_galore --version 2>&1) | sed 's/^.*version //; s/Last.*\$//' > ${software}.version.txt - """ - } -} diff --git a/modules/nf-core/software/trimgalore/meta.yml b/modules/nf-core/software/trimgalore/meta.yml deleted file mode 100644 index 735387076..000000000 --- a/modules/nf-core/software/trimgalore/meta.yml +++ /dev/null @@ -1,58 +0,0 @@ -name: trimgalore -description: Trim FastQ files using Trim Galore! -keywords: - - trimming - - adapters - - sequencing adapters - - fastq -tools: - - trimgalore: - description: | - A wrapper tool around Cutadapt and FastQC to consistently apply quality - and adapter trimming to FastQ files, with some extra functionality for - MspI-digested RRBS-type (Reduced Representation Bisufite-Seq) libraries. - homepage: https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/ - documentation: https://github.com/FelixKrueger/TrimGalore/blob/master/Docs/Trim_Galore_User_Guide.md -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - reads: - type: file - description: | - List of input FastQ files of size 1 and 2 for single-end and paired-end data, - respectively. -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - reads: - type: file - description: | - List of input adapter trimmed FastQ files of size 1 and 2 for - single-end and paired-end data, respectively. - pattern: "*.{fq.gz}" - - html: - type: file - description: FastQC report (optional) - pattern: "*_{fastqc.html}" - - zip: - type: file - description: FastQC report archive (optional) - pattern: "*_{fastqc.zip}" - - log: - type: file - description: Trim Galore! trimming report - pattern: "*_{report.txt}" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@drpatelh" - - "@ewels" - - "@FelixKrueger" diff --git a/modules/nf-core/software/ucsc/bedclip/functions.nf b/modules/nf-core/software/ucsc/bedclip/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/ucsc/bedclip/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/ucsc/bedclip/main.nf b/modules/nf-core/software/ucsc/bedclip/main.nf deleted file mode 100644 index d1a47554e..000000000 --- a/modules/nf-core/software/ucsc/bedclip/main.nf +++ /dev/null @@ -1,42 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -def VERSION = '377' - -process UCSC_BEDCLIP { - tag "$meta.id" - label 'process_medium' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::ucsc-bedclip=377" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/ucsc-bedclip:377--h0b8a92a_2" - } else { - container "quay.io/biocontainers/ucsc-bedclip:377--h0b8a92a_2" - } - - input: - tuple val(meta), path(bedgraph) - path sizes - - output: - tuple val(meta), path("*.bedGraph"), emit: bedgraph - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - """ - bedClip \\ - $bedgraph \\ - $sizes \\ - ${prefix}.bedGraph - - echo $VERSION > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/ucsc/bedclip/meta.yml b/modules/nf-core/software/ucsc/bedclip/meta.yml deleted file mode 100644 index f20b4617e..000000000 --- a/modules/nf-core/software/ucsc/bedclip/meta.yml +++ /dev/null @@ -1,41 +0,0 @@ -name: ucsc_bedclip -description: See http://hgdownload.cse.ucsc.edu/admin/exe/ -keywords: - - sort -tools: - - ucsc: - description: Remove lines from bed file that refer to off-chromosome locations. - homepage: None - documentation: None - tool_dev_url: None - doi: "" - licence: ['varies; see http://genome.ucsc.edu/license'] - -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - bedgraph: - type: file - description: bedGraph file - pattern: "*.{bedgraph}" - -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" - - bedgraph: - type: file - description: bedGraph file - pattern: "*.{bedgraph}" - -authors: - - "@drpatelh" diff --git a/modules/nf-core/software/ucsc/bedgraphtobigwig/functions.nf b/modules/nf-core/software/ucsc/bedgraphtobigwig/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/ucsc/bedgraphtobigwig/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/ucsc/bedgraphtobigwig/main.nf b/modules/nf-core/software/ucsc/bedgraphtobigwig/main.nf deleted file mode 100644 index e5fe3b7f2..000000000 --- a/modules/nf-core/software/ucsc/bedgraphtobigwig/main.nf +++ /dev/null @@ -1,38 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -def VERSION = '377' - -process UCSC_BEDGRAPHTOBIGWIG { - tag "$meta.id" - label 'process_medium' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::ucsc-bedgraphtobigwig=377" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/ucsc-bedgraphtobigwig:377--h446ed27_1" - } else { - container "quay.io/biocontainers/ucsc-bedgraphtobigwig:377--h446ed27_1" - } - - input: - tuple val(meta), path(bedgraph) - path sizes - - output: - tuple val(meta), path("*.bigWig"), emit: bigwig - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - """ - bedGraphToBigWig $bedgraph $sizes ${prefix}.bigWig - echo $VERSION > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/umitools/dedup/functions.nf b/modules/nf-core/software/umitools/dedup/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/umitools/dedup/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/umitools/dedup/main.nf b/modules/nf-core/software/umitools/dedup/main.nf deleted file mode 100644 index 93ea6d451..000000000 --- a/modules/nf-core/software/umitools/dedup/main.nf +++ /dev/null @@ -1,41 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process UMITOOLS_DEDUP { - tag "$meta.id" - label "process_medium" - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::umi_tools=1.1.1" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/umi_tools:1.1.1--py38h0213d0e_1" - } else { - container "quay.io/biocontainers/umi_tools:1.1.1--py38h0213d0e_1" - } - - input: - tuple val(meta), path(bam), path(bai) - - output: - tuple val(meta), path("*.bam"), emit: bam - tuple val(meta), path("*.tsv"), emit: tsv - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - """ - umi_tools dedup \\ - -I $bam \\ - -S ${prefix}.bam \\ - --output-stats=$prefix \\ - $options.args \\ - - umi_tools --version | sed -e "s/UMI-tools version: //g" > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/umitools/extract/functions.nf b/modules/nf-core/software/umitools/extract/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/umitools/extract/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/umitools/extract/main.nf b/modules/nf-core/software/umitools/extract/main.nf deleted file mode 100644 index 581f41c3c..000000000 --- a/modules/nf-core/software/umitools/extract/main.nf +++ /dev/null @@ -1,57 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process UMITOOLS_EXTRACT { - tag "$meta.id" - label "process_low" - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - - conda (params.enable_conda ? "bioconda::umi_tools=1.1.1" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/umi_tools:1.1.1--py38h0213d0e_1" - } else { - container "quay.io/biocontainers/umi_tools:1.1.1--py38h0213d0e_1" - } - - input: - tuple val(meta), path(reads) - - output: - tuple val(meta), path("*.fastq.gz"), emit: reads - tuple val(meta), path("*.log") , emit: log - path "*.version.txt" , emit: version - - script: - def software = getSoftwareName(task.process) - def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" - if (meta.single_end) { - """ - umi_tools \\ - extract \\ - -I $reads \\ - -S ${prefix}.umi_extract.fastq.gz \\ - $options.args \\ - > ${prefix}.umi_extract.log - - umi_tools --version | sed -e "s/UMI-tools version: //g" > ${software}.version.txt - """ - } else { - """ - umi_tools \\ - extract \\ - -I ${reads[0]} \\ - --read2-in=${reads[1]} \\ - -S ${prefix}.umi_extract_1.fastq.gz \\ - --read2-out=${prefix}.umi_extract_2.fastq.gz \\ - $options.args \\ - > ${prefix}.umi_extract.log - - umi_tools --version | sed -e "s/UMI-tools version: //g" > ${software}.version.txt - """ - } -} diff --git a/modules/nf-core/software/untar/functions.nf b/modules/nf-core/software/untar/functions.nf deleted file mode 100644 index da9da093d..000000000 --- a/modules/nf-core/software/untar/functions.nf +++ /dev/null @@ -1,68 +0,0 @@ -// -// Utility functions used in nf-core DSL2 module files -// - -// -// Extract name of software tool from process name using $task.process -// -def getSoftwareName(task_process) { - return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() -} - -// -// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules -// -def initOptions(Map args) { - def Map options = [:] - options.args = args.args ?: '' - options.args2 = args.args2 ?: '' - options.args3 = args.args3 ?: '' - options.publish_by_meta = args.publish_by_meta ?: [] - options.publish_dir = args.publish_dir ?: '' - options.publish_files = args.publish_files - options.suffix = args.suffix ?: '' - return options -} - -// -// Tidy up and join elements of a list to return a path string -// -def getPathFromList(path_list) { - def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries - paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes - return paths.join('/') -} - -// -// Function to save/publish module results -// -def saveFiles(Map args) { - if (!args.filename.endsWith('.version.txt')) { - def ioptions = initOptions(args.options) - def path_list = [ ioptions.publish_dir ?: args.publish_dir ] - if (ioptions.publish_by_meta) { - def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta - for (key in key_list) { - if (args.meta && key instanceof String) { - def path = key - if (args.meta.containsKey(key)) { - path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] - } - path = path instanceof String ? path : '' - path_list.add(path) - } - } - } - if (ioptions.publish_files instanceof Map) { - for (ext in ioptions.publish_files) { - if (args.filename.endsWith(ext.key)) { - def ext_list = path_list.collect() - ext_list.add(ext.value) - return "${getPathFromList(ext_list)}/$args.filename" - } - } - } else if (ioptions.publish_files == null) { - return "${getPathFromList(path_list)}/$args.filename" - } - } -} diff --git a/modules/nf-core/software/untar/main.nf b/modules/nf-core/software/untar/main.nf deleted file mode 100644 index fc6d7ec53..000000000 --- a/modules/nf-core/software/untar/main.nf +++ /dev/null @@ -1,35 +0,0 @@ -// Import generic module functions -include { initOptions; saveFiles; getSoftwareName } from './functions' - -params.options = [:] -options = initOptions(params.options) - -process UNTAR { - tag "$archive" - label 'process_low' - publishDir "${params.outdir}", - mode: params.publish_dir_mode, - saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) } - - conda (params.enable_conda ? "conda-forge::sed=4.7" : null) - if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img" - } else { - container "biocontainers/biocontainers:v1.2.0_cv1" - } - - input: - path archive - - output: - path "$untar" , emit: untar - path "*.version.txt", emit: version - - script: - def software = getSoftwareName(task.process) - untar = archive.toString() - '.tar.gz' - """ - tar -xzvf $options.args $archive - echo \$(tar --version 2>&1) | sed 's/^.*(GNU tar) //; s/ Copyright.*\$//' > ${software}.version.txt - """ -} diff --git a/modules/nf-core/software/untar/meta.yml b/modules/nf-core/software/untar/meta.yml deleted file mode 100644 index af4674f09..000000000 --- a/modules/nf-core/software/untar/meta.yml +++ /dev/null @@ -1,27 +0,0 @@ -name: untar -description: Extract files. -keywords: - - untar - - uncompress -tools: - - untar: - description: | - Extract tar.gz files. - documentation: https://www.gnu.org/software/tar/manual/ -input: - - archive: - type: file - description: File to be untar - pattern: "*.{tar}.{gz}" -output: - - untar: - type: file - description: - pattern: "*.*" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@joseespinosa" - - "@drpatelh" From 3e758de5a78bd146ceba094d205ddcdf330d91d3 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Wed, 14 Jul 2021 13:35:18 +0100 Subject: [PATCH 08/31] Replace software with modules in include statements --- subworkflows/local/prepare_genome.nf | 24 +++++++++---------- subworkflows/local/quantify_rsem.nf | 6 ++--- subworkflows/local/quantify_salmon.nf | 8 +++---- subworkflows/nf-core/align_hisat2.nf | 4 ++-- subworkflows/nf-core/align_star.nf | 4 ++-- subworkflows/nf-core/bam_sort_samtools.nf | 6 ++--- subworkflows/nf-core/bam_stats_samtools.nf | 6 ++--- subworkflows/nf-core/bedgraph_to_bigwig.nf | 4 ++-- subworkflows/nf-core/dedup_umi_umitools.nf | 6 ++--- .../nf-core/fastqc_umitools_trimgalore.nf | 6 ++--- .../nf-core/mark_duplicates_picard.nf | 6 ++--- subworkflows/nf-core/rseqc.nf | 14 +++++------ workflows/rnaseq.nf | 14 +++++------ 13 files changed, 54 insertions(+), 54 deletions(-) diff --git a/subworkflows/local/prepare_genome.nf b/subworkflows/local/prepare_genome.nf index 600642642..5c2c102e6 100644 --- a/subworkflows/local/prepare_genome.nf +++ b/subworkflows/local/prepare_genome.nf @@ -16,18 +16,18 @@ include { GUNZIP as GUNZIP_GFF GUNZIP as GUNZIP_GENE_BED GUNZIP as GUNZIP_TRANSCRIPT_FASTA - GUNZIP as GUNZIP_ADDITIONAL_FASTA } from '../../modules/nf-core/software/gunzip/main' addParams( options: params.genome_options ) -include { UNTAR as UNTAR_STAR_INDEX } from '../../modules/nf-core/software/untar/main' addParams( options: params.star_index_options ) -include { UNTAR as UNTAR_RSEM_INDEX } from '../../modules/nf-core/software/untar/main' addParams( options: params.index_options ) -include { UNTAR as UNTAR_HISAT2_INDEX } from '../../modules/nf-core/software/untar/main' addParams( options: params.hisat2_index_options ) -include { UNTAR as UNTAR_SALMON_INDEX } from '../../modules/nf-core/software/untar/main' addParams( options: params.index_options ) -include { GFFREAD } from '../../modules/nf-core/software/gffread/main' addParams( options: params.gffread_options ) -include { STAR_GENOMEGENERATE } from '../../modules/nf-core/software/star/genomegenerate/main' addParams( options: params.star_index_options ) -include { HISAT2_EXTRACTSPLICESITES } from '../../modules/nf-core/software/hisat2/extractsplicesites/main' addParams( options: params.hisat2_index_options ) -include { HISAT2_BUILD } from '../../modules/nf-core/software/hisat2/build/main' addParams( options: params.hisat2_index_options ) -include { SALMON_INDEX } from '../../modules/nf-core/software/salmon/index/main' addParams( options: params.salmon_index_options ) -include { RSEM_PREPAREREFERENCE as RSEM_PREPAREREFERENCE } from '../../modules/nf-core/software/rsem/preparereference/main' addParams( options: params.rsem_index_options ) -include { RSEM_PREPAREREFERENCE as RSEM_PREPAREREFERENCE_TRANSCRIPTS } from '../../modules/nf-core/software/rsem/preparereference/main' addParams( options: params.genome_options ) + GUNZIP as GUNZIP_ADDITIONAL_FASTA } from '../../modules/nf-core/modules/gunzip/main' addParams( options: params.genome_options ) +include { UNTAR as UNTAR_STAR_INDEX } from '../../modules/nf-core/modules/untar/main' addParams( options: params.star_index_options ) +include { UNTAR as UNTAR_RSEM_INDEX } from '../../modules/nf-core/modules/untar/main' addParams( options: params.index_options ) +include { UNTAR as UNTAR_HISAT2_INDEX } from '../../modules/nf-core/modules/untar/main' addParams( options: params.hisat2_index_options ) +include { UNTAR as UNTAR_SALMON_INDEX } from '../../modules/nf-core/modules/untar/main' addParams( options: params.index_options ) +include { GFFREAD } from '../../modules/nf-core/modules/gffread/main' addParams( options: params.gffread_options ) +include { STAR_GENOMEGENERATE } from '../../modules/nf-core/modules/star/genomegenerate/main' addParams( options: params.star_index_options ) +include { HISAT2_EXTRACTSPLICESITES } from '../../modules/nf-core/modules/hisat2/extractsplicesites/main' addParams( options: params.hisat2_index_options ) +include { HISAT2_BUILD } from '../../modules/nf-core/modules/hisat2/build/main' addParams( options: params.hisat2_index_options ) +include { SALMON_INDEX } from '../../modules/nf-core/modules/salmon/index/main' addParams( options: params.salmon_index_options ) +include { RSEM_PREPAREREFERENCE as RSEM_PREPAREREFERENCE } from '../../modules/nf-core/modules/rsem/preparereference/main' addParams( options: params.rsem_index_options ) +include { RSEM_PREPAREREFERENCE as RSEM_PREPAREREFERENCE_TRANSCRIPTS } from '../../modules/nf-core/modules/rsem/preparereference/main' addParams( options: params.genome_options ) include { GTF2BED } from '../../modules/local/gtf2bed' addParams( options: params.genome_options ) include { CAT_ADDITIONAL_FASTA } from '../../modules/local/cat_additional_fasta' addParams( options: params.genome_options ) diff --git a/subworkflows/local/quantify_rsem.nf b/subworkflows/local/quantify_rsem.nf index 398e9a8cb..187571689 100644 --- a/subworkflows/local/quantify_rsem.nf +++ b/subworkflows/local/quantify_rsem.nf @@ -8,9 +8,9 @@ params.samtools_index_options = [:] params.samtools_stats_options = [:] params.merge_counts_options = [:] -include { RSEM_CALCULATEEXPRESSION } from '../../modules/nf-core/software/rsem/calculateexpression/main' addParams( options: params.calculateexpression_options ) -include { RSEM_MERGE_COUNTS } from '../../modules/local/rsem_merge_counts' addParams( options: params.merge_counts_options ) -include { BAM_SORT_SAMTOOLS } from '../nf-core/bam_sort_samtools' addParams( sort_options: params.samtools_sort_options, index_options: params.samtools_index_options, stats_options: params.samtools_stats_options ) +include { RSEM_CALCULATEEXPRESSION } from '../../modules/nf-core/modules/rsem/calculateexpression/main' addParams( options: params.calculateexpression_options ) +include { RSEM_MERGE_COUNTS } from '../../modules/local/rsem_merge_counts' addParams( options: params.merge_counts_options ) +include { BAM_SORT_SAMTOOLS } from '../nf-core/bam_sort_samtools' addParams( sort_options: params.samtools_sort_options, index_options: params.samtools_index_options, stats_options: params.samtools_stats_options ) workflow QUANTIFY_RSEM { take: diff --git a/subworkflows/local/quantify_salmon.nf b/subworkflows/local/quantify_salmon.nf index 68b9b9760..863b1c395 100644 --- a/subworkflows/local/quantify_salmon.nf +++ b/subworkflows/local/quantify_salmon.nf @@ -7,10 +7,10 @@ params.salmon_quant_options = [:] params.tximport_options = [:] params.merge_counts_options = [:] -include { SALMON_QUANT } from '../../modules/nf-core/software/salmon/quant/main' addParams( options: params.salmon_quant_options ) -include { SALMON_TX2GENE } from '../../modules/local/salmon_tx2gene' addParams( options: params.genome_options ) -include { SALMON_TXIMPORT } from '../../modules/local/salmon_tximport' addParams( options: params.tximport_options ) -include { SALMON_MERGE_COUNTS } from '../../modules/local/salmon_merge_counts' addParams( options: params.merge_counts_options ) +include { SALMON_QUANT } from '../../modules/nf-core/modules/salmon/quant/main' addParams( options: params.salmon_quant_options ) +include { SALMON_TX2GENE } from '../../modules/local/salmon_tx2gene' addParams( options: params.genome_options ) +include { SALMON_TXIMPORT } from '../../modules/local/salmon_tximport' addParams( options: params.tximport_options ) +include { SALMON_MERGE_COUNTS } from '../../modules/local/salmon_merge_counts' addParams( options: params.merge_counts_options ) include { SALMON_SUMMARIZEDEXPERIMENT as SALMON_SE_GENE SALMON_SUMMARIZEDEXPERIMENT as SALMON_SE_GENE_LENGTH_SCALED SALMON_SUMMARIZEDEXPERIMENT as SALMON_SE_GENE_SCALED diff --git a/subworkflows/nf-core/align_hisat2.nf b/subworkflows/nf-core/align_hisat2.nf index 1024cfa7d..a022bf94b 100644 --- a/subworkflows/nf-core/align_hisat2.nf +++ b/subworkflows/nf-core/align_hisat2.nf @@ -7,8 +7,8 @@ params.samtools_sort_options = [:] params.samtools_index_options = [:] params.samtools_stats_options = [:] -include { HISAT2_ALIGN } from '../../modules/nf-core/software/hisat2/align/main' addParams( options: params.align_options ) -include { BAM_SORT_SAMTOOLS } from './bam_sort_samtools' addParams( sort_options: params.samtools_sort_options, index_options: params.samtools_index_options, stats_options: params.samtools_stats_options ) +include { HISAT2_ALIGN } from '../../modules/nf-core/modules/hisat2/align/main' addParams( options: params.align_options ) +include { BAM_SORT_SAMTOOLS } from './bam_sort_samtools' addParams( sort_options: params.samtools_sort_options, index_options: params.samtools_index_options, stats_options: params.samtools_stats_options ) workflow ALIGN_HISAT2 { take: diff --git a/subworkflows/nf-core/align_star.nf b/subworkflows/nf-core/align_star.nf index 7d228e1a9..40cc68b6b 100644 --- a/subworkflows/nf-core/align_star.nf +++ b/subworkflows/nf-core/align_star.nf @@ -7,8 +7,8 @@ params.samtools_sort_options = [:] params.samtools_index_options = [:] params.samtools_stats_options = [:] -include { STAR_ALIGN } from '../../modules/nf-core/software/star/align/main' addParams( options: params.align_options ) -include { BAM_SORT_SAMTOOLS } from './bam_sort_samtools' addParams( sort_options: params.samtools_sort_options, index_options: params.samtools_index_options, stats_options: params.samtools_stats_options ) +include { STAR_ALIGN } from '../../modules/nf-core/modules/star/align/main' addParams( options: params.align_options ) +include { BAM_SORT_SAMTOOLS } from './bam_sort_samtools' addParams( sort_options: params.samtools_sort_options, index_options: params.samtools_index_options, stats_options: params.samtools_stats_options ) workflow ALIGN_STAR { take: diff --git a/subworkflows/nf-core/bam_sort_samtools.nf b/subworkflows/nf-core/bam_sort_samtools.nf index 4ae896dca..ba4d39efb 100644 --- a/subworkflows/nf-core/bam_sort_samtools.nf +++ b/subworkflows/nf-core/bam_sort_samtools.nf @@ -6,9 +6,9 @@ params.sort_options = [:] params.index_options = [:] params.stats_options = [:] -include { SAMTOOLS_SORT } from '../../modules/nf-core/software/samtools/sort/main' addParams( options: params.sort_options ) -include { SAMTOOLS_INDEX } from '../../modules/nf-core/software/samtools/index/main' addParams( options: params.index_options ) -include { BAM_STATS_SAMTOOLS } from './bam_stats_samtools' addParams( options: params.stats_options ) +include { SAMTOOLS_SORT } from '../../modules/nf-core/modules/samtools/sort/main' addParams( options: params.sort_options ) +include { SAMTOOLS_INDEX } from '../../modules/nf-core/modules/samtools/index/main' addParams( options: params.index_options ) +include { BAM_STATS_SAMTOOLS } from './bam_stats_samtools' addParams( options: params.stats_options ) workflow BAM_SORT_SAMTOOLS { take: diff --git a/subworkflows/nf-core/bam_stats_samtools.nf b/subworkflows/nf-core/bam_stats_samtools.nf index eca9b37ab..ca05241cd 100644 --- a/subworkflows/nf-core/bam_stats_samtools.nf +++ b/subworkflows/nf-core/bam_stats_samtools.nf @@ -4,9 +4,9 @@ params.options = [:] -include { SAMTOOLS_STATS } from '../../modules/nf-core/software/samtools/stats/main' addParams( options: params.options ) -include { SAMTOOLS_IDXSTATS } from '../../modules/nf-core/software/samtools/idxstats/main' addParams( options: params.options ) -include { SAMTOOLS_FLAGSTAT } from '../../modules/nf-core/software/samtools/flagstat/main' addParams( options: params.options ) +include { SAMTOOLS_STATS } from '../../modules/nf-core/modules/samtools/stats/main' addParams( options: params.options ) +include { SAMTOOLS_IDXSTATS } from '../../modules/nf-core/modules/samtools/idxstats/main' addParams( options: params.options ) +include { SAMTOOLS_FLAGSTAT } from '../../modules/nf-core/modules/samtools/flagstat/main' addParams( options: params.options ) workflow BAM_STATS_SAMTOOLS { take: diff --git a/subworkflows/nf-core/bedgraph_to_bigwig.nf b/subworkflows/nf-core/bedgraph_to_bigwig.nf index 319db6485..e843f543a 100644 --- a/subworkflows/nf-core/bedgraph_to_bigwig.nf +++ b/subworkflows/nf-core/bedgraph_to_bigwig.nf @@ -5,8 +5,8 @@ params.bedclip_options = [:] params.bedgraphtobigwig_options = [:] -include { UCSC_BEDCLIP } from '../../modules/nf-core/software/ucsc/bedclip/main' addParams( options: params.bedclip_options ) -include { UCSC_BEDGRAPHTOBIGWIG } from '../../modules/nf-core/software/ucsc/bedgraphtobigwig/main' addParams( options: params.bedgraphtobigwig_options ) +include { UCSC_BEDCLIP } from '../../modules/nf-core/modules/ucsc/bedclip/main' addParams( options: params.bedclip_options ) +include { UCSC_BEDGRAPHTOBIGWIG } from '../../modules/nf-core/modules/ucsc/bedgraphtobigwig/main' addParams( options: params.bedgraphtobigwig_options ) workflow BEDGRAPH_TO_BIGWIG { take: diff --git a/subworkflows/nf-core/dedup_umi_umitools.nf b/subworkflows/nf-core/dedup_umi_umitools.nf index d6cf69cf7..f8d9f06a0 100644 --- a/subworkflows/nf-core/dedup_umi_umitools.nf +++ b/subworkflows/nf-core/dedup_umi_umitools.nf @@ -6,9 +6,9 @@ params.umitools_options = [:] params.samtools_index_options = [:] params.samtools_stats_options = [:] -include { UMITOOLS_DEDUP } from '../../modules/nf-core/software/umitools/dedup/main' addParams( options: params.umitools_options ) -include { SAMTOOLS_INDEX } from '../../modules/nf-core/software/samtools/index/main' addParams( options: params.samtools_index_options ) -include { BAM_STATS_SAMTOOLS } from './bam_stats_samtools' addParams( options: params.samtools_stats_options ) +include { UMITOOLS_DEDUP } from '../../modules/nf-core/modules/umitools/dedup/main' addParams( options: params.umitools_options ) +include { SAMTOOLS_INDEX } from '../../modules/nf-core/modules/samtools/index/main' addParams( options: params.samtools_index_options ) +include { BAM_STATS_SAMTOOLS } from './bam_stats_samtools' addParams( options: params.samtools_stats_options ) workflow DEDUP_UMI_UMITOOLS { take: diff --git a/subworkflows/nf-core/fastqc_umitools_trimgalore.nf b/subworkflows/nf-core/fastqc_umitools_trimgalore.nf index 68fb3284e..827e53972 100644 --- a/subworkflows/nf-core/fastqc_umitools_trimgalore.nf +++ b/subworkflows/nf-core/fastqc_umitools_trimgalore.nf @@ -6,9 +6,9 @@ params.fastqc_options = [:] params.umitools_options = [:] params.trimgalore_options = [:] -include { FASTQC } from '../../modules/nf-core/software/fastqc/main' addParams( options: params.fastqc_options ) -include { UMITOOLS_EXTRACT } from '../../modules/nf-core/software/umitools/extract/main' addParams( options: params.umitools_options ) -include { TRIMGALORE } from '../../modules/nf-core/software/trimgalore/main' addParams( options: params.trimgalore_options ) +include { FASTQC } from '../../modules/nf-core/modules/fastqc/main' addParams( options: params.fastqc_options ) +include { UMITOOLS_EXTRACT } from '../../modules/nf-core/modules/umitools/extract/main' addParams( options: params.umitools_options ) +include { TRIMGALORE } from '../../modules/nf-core/modules/trimgalore/main' addParams( options: params.trimgalore_options ) workflow FASTQC_UMITOOLS_TRIMGALORE { take: diff --git a/subworkflows/nf-core/mark_duplicates_picard.nf b/subworkflows/nf-core/mark_duplicates_picard.nf index 7e59ac68c..2e8b676dc 100644 --- a/subworkflows/nf-core/mark_duplicates_picard.nf +++ b/subworkflows/nf-core/mark_duplicates_picard.nf @@ -6,9 +6,9 @@ params.markduplicates_options = [:] params.samtools_index_options = [:] params.samtools_stats_options = [:] -include { PICARD_MARKDUPLICATES } from '../../modules/nf-core/software/picard/markduplicates/main' addParams( options: params.markduplicates_options ) -include { SAMTOOLS_INDEX } from '../../modules/nf-core/software/samtools/index/main' addParams( options: params.samtools_index_options ) -include { BAM_STATS_SAMTOOLS } from './bam_stats_samtools' addParams( options: params.samtools_stats_options ) +include { PICARD_MARKDUPLICATES } from '../../modules/nf-core/modules/picard/markduplicates/main' addParams( options: params.markduplicates_options ) +include { SAMTOOLS_INDEX } from '../../modules/nf-core/modules/samtools/index/main' addParams( options: params.samtools_index_options ) +include { BAM_STATS_SAMTOOLS } from './bam_stats_samtools' addParams( options: params.samtools_stats_options ) workflow MARK_DUPLICATES_PICARD { take: diff --git a/subworkflows/nf-core/rseqc.nf b/subworkflows/nf-core/rseqc.nf index 9e21417d5..2aa5c7f52 100644 --- a/subworkflows/nf-core/rseqc.nf +++ b/subworkflows/nf-core/rseqc.nf @@ -10,13 +10,13 @@ params.junctionsaturation_options = [:] params.readdistribution_options = [:] params.readduplication_options = [:] -include { RSEQC_BAMSTAT } from '../../modules/nf-core/software/rseqc/bamstat/main' addParams( options: params.bamstat_options ) -include { RSEQC_INNERDISTANCE } from '../../modules/nf-core/software/rseqc/innerdistance/main' addParams( options: params.innerdistance_options ) -include { RSEQC_INFEREXPERIMENT } from '../../modules/nf-core/software/rseqc/inferexperiment/main' addParams( options: params.inferexperiment_options ) -include { RSEQC_JUNCTIONANNOTATION } from '../../modules/nf-core/software/rseqc/junctionannotation/main' addParams( options: params.junctionannotation_options ) -include { RSEQC_JUNCTIONSATURATION } from '../../modules/nf-core/software/rseqc/junctionsaturation/main' addParams( options: params.junctionsaturation_options ) -include { RSEQC_READDISTRIBUTION } from '../../modules/nf-core/software/rseqc/readdistribution/main' addParams( options: params.readdistribution_options ) -include { RSEQC_READDUPLICATION } from '../../modules/nf-core/software/rseqc/readduplication/main' addParams( options: params.readduplication_options ) +include { RSEQC_BAMSTAT } from '../../modules/nf-core/modules/rseqc/bamstat/main' addParams( options: params.bamstat_options ) +include { RSEQC_INNERDISTANCE } from '../../modules/nf-core/modules/rseqc/innerdistance/main' addParams( options: params.innerdistance_options ) +include { RSEQC_INFEREXPERIMENT } from '../../modules/nf-core/modules/rseqc/inferexperiment/main' addParams( options: params.inferexperiment_options ) +include { RSEQC_JUNCTIONANNOTATION } from '../../modules/nf-core/modules/rseqc/junctionannotation/main' addParams( options: params.junctionannotation_options ) +include { RSEQC_JUNCTIONSATURATION } from '../../modules/nf-core/modules/rseqc/junctionsaturation/main' addParams( options: params.junctionsaturation_options ) +include { RSEQC_READDISTRIBUTION } from '../../modules/nf-core/modules/rseqc/readdistribution/main' addParams( options: params.readdistribution_options ) +include { RSEQC_READDUPLICATION } from '../../modules/nf-core/modules/rseqc/readduplication/main' addParams( options: params.readduplication_options ) workflow RSEQC { take: diff --git a/workflows/rnaseq.nf b/workflows/rnaseq.nf index bc620af20..dbbc4f51a 100755 --- a/workflows/rnaseq.nf +++ b/workflows/rnaseq.nf @@ -166,13 +166,13 @@ def subread_featurecounts_options = modules['subread_featurecounts'] def biotype = params.gencode ? "gene_type" : params.featurecounts_group_type subread_featurecounts_options.args += Utils.joinModuleArgs(["-g $biotype", "-t $params.featurecounts_feature_type"]) -include { CAT_FASTQ } from '../modules/nf-core/software/cat/fastq/main' addParams( options: cat_fastq_options ) -include { SAMTOOLS_SORT } from '../modules/nf-core/software/samtools/sort/main' addParams( options: modules['umitools_dedup_transcriptome_sort'] ) -include { PRESEQ_LCEXTRAP } from '../modules/nf-core/software/preseq/lcextrap/main' addParams( options: modules['preseq_lcextrap'] ) -include { QUALIMAP_RNASEQ } from '../modules/nf-core/software/qualimap/rnaseq/main' addParams( options: modules['qualimap_rnaseq'] ) -include { SORTMERNA } from '../modules/nf-core/software/sortmerna/main' addParams( options: sortmerna_options ) -include { STRINGTIE } from '../modules/nf-core/software/stringtie/stringtie/main' addParams( options: stringtie_options ) -include { SUBREAD_FEATURECOUNTS } from '../modules/nf-core/software/subread/featurecounts/main' addParams( options: subread_featurecounts_options ) +include { CAT_FASTQ } from '../modules/nf-core/modules/cat/fastq/main' addParams( options: cat_fastq_options ) +include { SAMTOOLS_SORT } from '../modules/nf-core/modules/samtools/sort/main' addParams( options: modules['umitools_dedup_transcriptome_sort'] ) +include { PRESEQ_LCEXTRAP } from '../modules/nf-core/modules/preseq/lcextrap/main' addParams( options: modules['preseq_lcextrap'] ) +include { QUALIMAP_RNASEQ } from '../modules/nf-core/modules/qualimap/rnaseq/main' addParams( options: modules['qualimap_rnaseq'] ) +include { SORTMERNA } from '../modules/nf-core/modules/sortmerna/main' addParams( options: sortmerna_options ) +include { STRINGTIE } from '../modules/nf-core/modules/stringtie/stringtie/main' addParams( options: stringtie_options ) +include { SUBREAD_FEATURECOUNTS } from '../modules/nf-core/modules/subread/featurecounts/main' addParams( options: subread_featurecounts_options ) // // SUBWORKFLOW: Consisting entirely of nf-core/modules From 18551e9a6c3313529c1b03b7a455d35ada2124eb Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Wed, 14 Jul 2021 15:19:49 +0100 Subject: [PATCH 09/31] Re-install all modules --- modules.json | 109 +++++++++++++++++- .../{multiqc => cat/fastq}/functions.nf | 0 modules/nf-core/modules/cat/fastq/main.nf | 47 ++++++++ modules/nf-core/modules/cat/fastq/meta.yml | 33 ++++++ modules/nf-core/modules/gffread/functions.nf | 68 +++++++++++ modules/nf-core/modules/gffread/main.nf | 34 ++++++ modules/nf-core/modules/gffread/meta.yml | 43 +++++++ modules/nf-core/modules/gunzip/functions.nf | 68 +++++++++++ modules/nf-core/modules/gunzip/main.nf | 35 ++++++ modules/nf-core/modules/gunzip/meta.yml | 27 +++++ .../nf-core/modules/hisat2/align/functions.nf | 68 +++++++++++ modules/nf-core/modules/hisat2/align/main.nf | 93 +++++++++++++++ modules/nf-core/modules/hisat2/align/meta.yml | 57 +++++++++ .../nf-core/modules/hisat2/build/functions.nf | 68 +++++++++++ modules/nf-core/modules/hisat2/build/main.nf | 70 +++++++++++ modules/nf-core/modules/hisat2/build/meta.yml | 42 +++++++ .../hisat2/extractsplicesites/functions.nf | 68 +++++++++++ .../extractsplicesites}/main.nf | 23 ++-- .../hisat2/extractsplicesites/meta.yml | 34 ++++++ modules/nf-core/modules/multiqc/meta.yml | 39 ------- .../picard/markduplicates/functions.nf | 68 +++++++++++ .../modules/picard/markduplicates/main.nf | 49 ++++++++ .../modules/picard/markduplicates/meta.yml | 46 ++++++++ .../modules/preseq/lcextrap/functions.nf | 68 +++++++++++ .../nf-core/modules/preseq/lcextrap/main.nf | 45 ++++++++ .../nf-core/modules/preseq/lcextrap/meta.yml | 47 ++++++++ .../modules/qualimap/rnaseq/functions.nf | 68 +++++++++++ .../nf-core/modules/qualimap/rnaseq/main.nf | 57 +++++++++ .../rsem/calculateexpression/functions.nf | 68 +++++++++++ .../modules/rsem/calculateexpression/main.nf | 61 ++++++++++ .../modules/rsem/calculateexpression/meta.yml | 63 ++++++++++ .../rsem/preparereference/functions.nf | 68 +++++++++++ .../modules/rsem/preparereference/main.nf | 67 +++++++++++ .../modules/rsem/preparereference/meta.yml | 37 ++++++ .../modules/rseqc/bamstat/functions.nf | 68 +++++++++++ modules/nf-core/modules/rseqc/bamstat/main.nf | 39 +++++++ .../nf-core/modules/rseqc/bamstat/meta.yml | 36 ++++++ .../rseqc/inferexperiment/functions.nf | 68 +++++++++++ .../modules/rseqc/inferexperiment/main.nf | 41 +++++++ .../modules/rseqc/inferexperiment/meta.yml | 39 +++++++ .../modules/rseqc/innerdistance/functions.nf | 68 +++++++++++ .../modules/rseqc/innerdistance/main.nf | 53 +++++++++ .../modules/rseqc/innerdistance/meta.yml | 55 +++++++++ .../rseqc/junctionannotation/functions.nf | 68 +++++++++++ .../modules/rseqc/junctionannotation/main.nf | 48 ++++++++ .../modules/rseqc/junctionannotation/meta.yml | 61 ++++++++++ .../rseqc/junctionsaturation/functions.nf | 68 +++++++++++ .../modules/rseqc/junctionsaturation/main.nf | 42 +++++++ .../modules/rseqc/junctionsaturation/meta.yml | 44 +++++++ .../rseqc/readdistribution/functions.nf | 68 +++++++++++ .../modules/rseqc/readdistribution/main.nf | 40 +++++++ .../modules/rseqc/readdistribution/meta.yml | 40 +++++++ .../rseqc/readduplication/functions.nf | 68 +++++++++++ .../modules/rseqc/readduplication/main.nf | 42 +++++++ .../modules/rseqc/readduplication/meta.yml | 51 ++++++++ .../nf-core/modules/salmon/index/functions.nf | 68 +++++++++++ modules/nf-core/modules/salmon/index/main.nf | 51 ++++++++ modules/nf-core/modules/salmon/index/meta.yml | 35 ++++++ .../nf-core/modules/salmon/quant/functions.nf | 68 +++++++++++ modules/nf-core/modules/salmon/quant/main.nf | 77 +++++++++++++ modules/nf-core/modules/salmon/quant/meta.yml | 55 +++++++++ .../modules/samtools/flagstat/functions.nf | 68 +++++++++++ .../nf-core/modules/samtools/flagstat/main.nf | 34 ++++++ .../modules/samtools/flagstat/meta.yml | 48 ++++++++ .../modules/samtools/idxstats/functions.nf | 68 +++++++++++ .../nf-core/modules/samtools/idxstats/main.nf | 34 ++++++ .../modules/samtools/idxstats/meta.yml | 49 ++++++++ .../modules/samtools/index/functions.nf | 68 +++++++++++ .../nf-core/modules/samtools/index/main.nf | 35 ++++++ .../nf-core/modules/samtools/index/meta.yml | 47 ++++++++ .../modules/samtools/sort/functions.nf | 68 +++++++++++ modules/nf-core/modules/samtools/sort/main.nf | 35 ++++++ .../nf-core/modules/samtools/sort/meta.yml | 43 +++++++ .../modules/samtools/stats/functions.nf | 68 +++++++++++ .../nf-core/modules/samtools/stats/main.nf | 34 ++++++ .../nf-core/modules/samtools/stats/meta.yml | 47 ++++++++ .../nf-core/modules/sortmerna/functions.nf | 68 +++++++++++ modules/nf-core/modules/sortmerna/main.nf | 73 ++++++++++++ .../nf-core/modules/star/align/functions.nf | 68 +++++++++++ modules/nf-core/modules/star/align/main.nf | 71 ++++++++++++ modules/nf-core/modules/star/align/meta.yml | 75 ++++++++++++ .../modules/star/genomegenerate/functions.nf | 68 +++++++++++ .../modules/star/genomegenerate/main.nf | 67 +++++++++++ .../modules/star/genomegenerate/meta.yml | 36 ++++++ .../modules/stringtie/stringtie/functions.nf | 68 +++++++++++ .../modules/stringtie/stringtie/main.nf | 55 +++++++++ .../modules/stringtie/stringtie/meta.yml | 56 +++++++++ .../subread/featurecounts/functions.nf | 68 +++++++++++ .../modules/subread/featurecounts/main.nf | 52 +++++++++ .../modules/subread/featurecounts/meta.yml | 52 +++++++++ .../nf-core/modules/trimgalore/functions.nf | 68 +++++++++++ modules/nf-core/modules/trimgalore/main.nf | 83 +++++++++++++ modules/nf-core/modules/trimgalore/meta.yml | 58 ++++++++++ .../nf-core/modules/ucsc/bedclip/functions.nf | 68 +++++++++++ modules/nf-core/modules/ucsc/bedclip/main.nf | 42 +++++++ modules/nf-core/modules/ucsc/bedclip/meta.yml | 41 +++++++ .../ucsc/bedgraphtobigwig/functions.nf | 68 +++++++++++ .../modules/ucsc/bedgraphtobigwig/main.nf | 38 ++++++ .../modules/ucsc/bedgraphtobigwig/meta.yml | 46 ++++++++ .../modules/umitools/dedup/functions.nf | 68 +++++++++++ .../nf-core/modules/umitools/dedup/main.nf | 41 +++++++ .../modules/umitools/extract/functions.nf | 68 +++++++++++ .../nf-core/modules/umitools/extract/main.nf | 57 +++++++++ modules/nf-core/modules/untar/functions.nf | 68 +++++++++++ modules/nf-core/modules/untar/main.nf | 35 ++++++ modules/nf-core/modules/untar/meta.yml | 27 +++++ 106 files changed, 5746 insertions(+), 52 deletions(-) rename modules/nf-core/modules/{multiqc => cat/fastq}/functions.nf (100%) create mode 100644 modules/nf-core/modules/cat/fastq/main.nf create mode 100644 modules/nf-core/modules/cat/fastq/meta.yml create mode 100644 modules/nf-core/modules/gffread/functions.nf create mode 100644 modules/nf-core/modules/gffread/main.nf create mode 100644 modules/nf-core/modules/gffread/meta.yml create mode 100644 modules/nf-core/modules/gunzip/functions.nf create mode 100644 modules/nf-core/modules/gunzip/main.nf create mode 100644 modules/nf-core/modules/gunzip/meta.yml create mode 100644 modules/nf-core/modules/hisat2/align/functions.nf create mode 100644 modules/nf-core/modules/hisat2/align/main.nf create mode 100644 modules/nf-core/modules/hisat2/align/meta.yml create mode 100644 modules/nf-core/modules/hisat2/build/functions.nf create mode 100644 modules/nf-core/modules/hisat2/build/main.nf create mode 100644 modules/nf-core/modules/hisat2/build/meta.yml create mode 100644 modules/nf-core/modules/hisat2/extractsplicesites/functions.nf rename modules/nf-core/modules/{multiqc => hisat2/extractsplicesites}/main.nf (53%) create mode 100644 modules/nf-core/modules/hisat2/extractsplicesites/meta.yml delete mode 100644 modules/nf-core/modules/multiqc/meta.yml create mode 100644 modules/nf-core/modules/picard/markduplicates/functions.nf create mode 100644 modules/nf-core/modules/picard/markduplicates/main.nf create mode 100644 modules/nf-core/modules/picard/markduplicates/meta.yml create mode 100644 modules/nf-core/modules/preseq/lcextrap/functions.nf create mode 100644 modules/nf-core/modules/preseq/lcextrap/main.nf create mode 100644 modules/nf-core/modules/preseq/lcextrap/meta.yml create mode 100644 modules/nf-core/modules/qualimap/rnaseq/functions.nf create mode 100644 modules/nf-core/modules/qualimap/rnaseq/main.nf create mode 100644 modules/nf-core/modules/rsem/calculateexpression/functions.nf create mode 100644 modules/nf-core/modules/rsem/calculateexpression/main.nf create mode 100644 modules/nf-core/modules/rsem/calculateexpression/meta.yml create mode 100644 modules/nf-core/modules/rsem/preparereference/functions.nf create mode 100644 modules/nf-core/modules/rsem/preparereference/main.nf create mode 100644 modules/nf-core/modules/rsem/preparereference/meta.yml create mode 100644 modules/nf-core/modules/rseqc/bamstat/functions.nf create mode 100644 modules/nf-core/modules/rseqc/bamstat/main.nf create mode 100644 modules/nf-core/modules/rseqc/bamstat/meta.yml create mode 100644 modules/nf-core/modules/rseqc/inferexperiment/functions.nf create mode 100644 modules/nf-core/modules/rseqc/inferexperiment/main.nf create mode 100644 modules/nf-core/modules/rseqc/inferexperiment/meta.yml create mode 100644 modules/nf-core/modules/rseqc/innerdistance/functions.nf create mode 100644 modules/nf-core/modules/rseqc/innerdistance/main.nf create mode 100644 modules/nf-core/modules/rseqc/innerdistance/meta.yml create mode 100644 modules/nf-core/modules/rseqc/junctionannotation/functions.nf create mode 100644 modules/nf-core/modules/rseqc/junctionannotation/main.nf create mode 100644 modules/nf-core/modules/rseqc/junctionannotation/meta.yml create mode 100644 modules/nf-core/modules/rseqc/junctionsaturation/functions.nf create mode 100644 modules/nf-core/modules/rseqc/junctionsaturation/main.nf create mode 100644 modules/nf-core/modules/rseqc/junctionsaturation/meta.yml create mode 100644 modules/nf-core/modules/rseqc/readdistribution/functions.nf create mode 100644 modules/nf-core/modules/rseqc/readdistribution/main.nf create mode 100644 modules/nf-core/modules/rseqc/readdistribution/meta.yml create mode 100644 modules/nf-core/modules/rseqc/readduplication/functions.nf create mode 100644 modules/nf-core/modules/rseqc/readduplication/main.nf create mode 100644 modules/nf-core/modules/rseqc/readduplication/meta.yml create mode 100644 modules/nf-core/modules/salmon/index/functions.nf create mode 100644 modules/nf-core/modules/salmon/index/main.nf create mode 100644 modules/nf-core/modules/salmon/index/meta.yml create mode 100644 modules/nf-core/modules/salmon/quant/functions.nf create mode 100644 modules/nf-core/modules/salmon/quant/main.nf create mode 100644 modules/nf-core/modules/salmon/quant/meta.yml create mode 100644 modules/nf-core/modules/samtools/flagstat/functions.nf create mode 100644 modules/nf-core/modules/samtools/flagstat/main.nf create mode 100644 modules/nf-core/modules/samtools/flagstat/meta.yml create mode 100644 modules/nf-core/modules/samtools/idxstats/functions.nf create mode 100644 modules/nf-core/modules/samtools/idxstats/main.nf create mode 100644 modules/nf-core/modules/samtools/idxstats/meta.yml create mode 100644 modules/nf-core/modules/samtools/index/functions.nf create mode 100644 modules/nf-core/modules/samtools/index/main.nf create mode 100644 modules/nf-core/modules/samtools/index/meta.yml create mode 100644 modules/nf-core/modules/samtools/sort/functions.nf create mode 100644 modules/nf-core/modules/samtools/sort/main.nf create mode 100644 modules/nf-core/modules/samtools/sort/meta.yml create mode 100644 modules/nf-core/modules/samtools/stats/functions.nf create mode 100644 modules/nf-core/modules/samtools/stats/main.nf create mode 100644 modules/nf-core/modules/samtools/stats/meta.yml create mode 100644 modules/nf-core/modules/sortmerna/functions.nf create mode 100644 modules/nf-core/modules/sortmerna/main.nf create mode 100644 modules/nf-core/modules/star/align/functions.nf create mode 100644 modules/nf-core/modules/star/align/main.nf create mode 100644 modules/nf-core/modules/star/align/meta.yml create mode 100644 modules/nf-core/modules/star/genomegenerate/functions.nf create mode 100644 modules/nf-core/modules/star/genomegenerate/main.nf create mode 100644 modules/nf-core/modules/star/genomegenerate/meta.yml create mode 100644 modules/nf-core/modules/stringtie/stringtie/functions.nf create mode 100644 modules/nf-core/modules/stringtie/stringtie/main.nf create mode 100644 modules/nf-core/modules/stringtie/stringtie/meta.yml create mode 100644 modules/nf-core/modules/subread/featurecounts/functions.nf create mode 100644 modules/nf-core/modules/subread/featurecounts/main.nf create mode 100644 modules/nf-core/modules/subread/featurecounts/meta.yml create mode 100644 modules/nf-core/modules/trimgalore/functions.nf create mode 100644 modules/nf-core/modules/trimgalore/main.nf create mode 100644 modules/nf-core/modules/trimgalore/meta.yml create mode 100644 modules/nf-core/modules/ucsc/bedclip/functions.nf create mode 100644 modules/nf-core/modules/ucsc/bedclip/main.nf create mode 100644 modules/nf-core/modules/ucsc/bedclip/meta.yml create mode 100644 modules/nf-core/modules/ucsc/bedgraphtobigwig/functions.nf create mode 100644 modules/nf-core/modules/ucsc/bedgraphtobigwig/main.nf create mode 100644 modules/nf-core/modules/ucsc/bedgraphtobigwig/meta.yml create mode 100644 modules/nf-core/modules/umitools/dedup/functions.nf create mode 100644 modules/nf-core/modules/umitools/dedup/main.nf create mode 100644 modules/nf-core/modules/umitools/extract/functions.nf create mode 100644 modules/nf-core/modules/umitools/extract/main.nf create mode 100644 modules/nf-core/modules/untar/functions.nf create mode 100644 modules/nf-core/modules/untar/main.nf create mode 100644 modules/nf-core/modules/untar/meta.yml diff --git a/modules.json b/modules.json index e3139db6b..47c7c1fe7 100644 --- a/modules.json +++ b/modules.json @@ -3,12 +3,117 @@ "homePage": "https://github.com/nf-core/rnaseq", "repos": { "nf-core/modules": { + "cat/fastq": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, "fastqc": { "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" }, - "multiqc": { + "gffread": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "gunzip": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "hisat2/align": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "hisat2/build": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "hisat2/extractsplicesites": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "picard/markduplicates": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "preseq/lcextrap": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "qualimap/rnaseq": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "rsem/calculateexpression": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "rsem/preparereference": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "rseqc/bamstat": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "rseqc/inferexperiment": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "rseqc/innerdistance": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "rseqc/junctionannotation": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "rseqc/junctionsaturation": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "rseqc/readdistribution": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "rseqc/readduplication": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "salmon/index": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "salmon/quant": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "samtools/flagstat": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "samtools/idxstats": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "samtools/index": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "samtools/sort": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "samtools/stats": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "sortmerna": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "star/align": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "star/genomegenerate": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "stringtie/stringtie": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "subread/featurecounts": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "trimgalore": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "ucsc/bedclip": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "ucsc/bedgraphtobigwig": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "umitools/dedup": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "umitools/extract": { + "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + }, + "untar": { "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" } } } -} +} \ No newline at end of file diff --git a/modules/nf-core/modules/multiqc/functions.nf b/modules/nf-core/modules/cat/fastq/functions.nf similarity index 100% rename from modules/nf-core/modules/multiqc/functions.nf rename to modules/nf-core/modules/cat/fastq/functions.nf diff --git a/modules/nf-core/modules/cat/fastq/main.nf b/modules/nf-core/modules/cat/fastq/main.nf new file mode 100644 index 000000000..55ccca908 --- /dev/null +++ b/modules/nf-core/modules/cat/fastq/main.nf @@ -0,0 +1,47 @@ +// Import generic module functions +include { initOptions; saveFiles } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process CAT_FASTQ { + tag "$meta.id" + label 'process_low' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:'merged_fastq', meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "conda-forge::sed=4.7" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img" + } else { + container "biocontainers/biocontainers:v1.2.0_cv1" + } + + input: + tuple val(meta), path(reads) + + output: + tuple val(meta), path("*.merged.fastq.gz"), emit: reads + + script: + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + def readList = reads.collect{ it.toString() } + if (meta.single_end) { + if (readList.size > 1) { + """ + cat ${readList.sort().join(' ')} > ${prefix}.merged.fastq.gz + """ + } + } else { + if (readList.size > 2) { + def read1 = [] + def read2 = [] + readList.eachWithIndex{ v, ix -> ( ix & 1 ? read2 : read1 ) << v } + """ + cat ${read1.sort().join(' ')} > ${prefix}_1.merged.fastq.gz + cat ${read2.sort().join(' ')} > ${prefix}_2.merged.fastq.gz + """ + } + } +} diff --git a/modules/nf-core/modules/cat/fastq/meta.yml b/modules/nf-core/modules/cat/fastq/meta.yml new file mode 100644 index 000000000..e7b8eebe8 --- /dev/null +++ b/modules/nf-core/modules/cat/fastq/meta.yml @@ -0,0 +1,33 @@ +name: cat_fastq +description: Concatenates fastq files +keywords: + - fastq + - concatenate +tools: + - cat: + description: | + The cat utility reads files sequentially, writing them to the standard output. + documentation: https://www.gnu.org/software/coreutils/manual/html_node/cat-invocation.html +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - reads: + type: list + description: | + List of input FastQ files to be concatenated. +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - reads: + type: file + description: Merged fastq file + pattern: "*.{merged.fastq.gz}" +authors: + - "@joseespinosa" + - "@drpatelh" diff --git a/modules/nf-core/modules/gffread/functions.nf b/modules/nf-core/modules/gffread/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/gffread/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/gffread/main.nf b/modules/nf-core/modules/gffread/main.nf new file mode 100644 index 000000000..6c5aecbc7 --- /dev/null +++ b/modules/nf-core/modules/gffread/main.nf @@ -0,0 +1,34 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process GFFREAD { + tag "$gff" + label 'process_low' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) } + + conda (params.enable_conda ? "bioconda::gffread=0.12.1" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/gffread:0.12.1--h8b12597_0" + } else { + container "quay.io/biocontainers/gffread:0.12.1--h8b12597_0" + } + + input: + path gff + + output: + path "*.gtf" , emit: gtf + path "*.version.txt", emit: version + + script: + def software = getSoftwareName(task.process) + """ + gffread $gff $options.args -o ${gff.baseName}.gtf + echo \$(gffread --version 2>&1) > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/gffread/meta.yml b/modules/nf-core/modules/gffread/meta.yml new file mode 100644 index 000000000..63d281f52 --- /dev/null +++ b/modules/nf-core/modules/gffread/meta.yml @@ -0,0 +1,43 @@ +name: gffread +description: Validate, filter, convert and perform various other operations on GFF files +keywords: + - gff + - conversion + - validation +tools: + - gffread: + description: GFF/GTF utility providing format conversions, region filtering, FASTA sequence extraction and more. + homepage: http://ccb.jhu.edu/software/stringtie/gff.shtml#gffread + documentation: http://ccb.jhu.edu/software/stringtie/gff.shtml#gffread + tool_dev_url: https://github.com/gpertea/gffread + doi: 10.12688/f1000research.23297.1 + licence: ['MIT'] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - gff: + type: file + description: A GFF file in either the GFF3 or GFF2 format. + patter: "*.gff" + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - gtf: + type: file + description: GTF file resulting from the conversion of the GFF input file + pattern: "*.gtf" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" + +authors: + - "@emiller88" diff --git a/modules/nf-core/modules/gunzip/functions.nf b/modules/nf-core/modules/gunzip/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/gunzip/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/gunzip/main.nf b/modules/nf-core/modules/gunzip/main.nf new file mode 100644 index 000000000..292487961 --- /dev/null +++ b/modules/nf-core/modules/gunzip/main.nf @@ -0,0 +1,35 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process GUNZIP { + tag "$archive" + label 'process_low' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) } + + conda (params.enable_conda ? "conda-forge::sed=4.7" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img" + } else { + container "biocontainers/biocontainers:v1.2.0_cv1" + } + + input: + path archive + + output: + path "$gunzip", emit: gunzip + path "*.version.txt", emit: version + + script: + def software = getSoftwareName(task.process) + gunzip = archive.toString() - '.gz' + """ + gunzip -f $options.args $archive + echo \$(gunzip --version 2>&1) | sed 's/^.*(gzip) //; s/ Copyright.*\$//' > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/gunzip/meta.yml b/modules/nf-core/modules/gunzip/meta.yml new file mode 100644 index 000000000..922e74e61 --- /dev/null +++ b/modules/nf-core/modules/gunzip/meta.yml @@ -0,0 +1,27 @@ +name: gunzip +description: Compresses and decompresses files. +keywords: + - gunzip + - compression +tools: + - gunzip: + description: | + gzip is a file format and a software application used for file compression and decompression. + documentation: https://www.gnu.org/software/gzip/manual/gzip.html +input: + - archive: + type: file + description: File to be compressed/uncompressed + pattern: "*.*" +output: + - gunzip: + type: file + description: Compressed/uncompressed file + pattern: "*.*" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@joseespinosa" + - "@drpatelh" diff --git a/modules/nf-core/modules/hisat2/align/functions.nf b/modules/nf-core/modules/hisat2/align/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/hisat2/align/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/hisat2/align/main.nf b/modules/nf-core/modules/hisat2/align/main.nf new file mode 100644 index 000000000..17547c91a --- /dev/null +++ b/modules/nf-core/modules/hisat2/align/main.nf @@ -0,0 +1,93 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +def VERSION = '2.2.0' + +process HISAT2_ALIGN { + tag "$meta.id" + label 'process_high' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::hisat2=2.2.0 bioconda::samtools=1.10" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/mulled-v2-a97e90b3b802d1da3d6958e0867610c718cb5eb1:2880dd9d8ad0a7b221d4eacda9a818e92983128d-0" + } else { + container "quay.io/biocontainers/mulled-v2-a97e90b3b802d1da3d6958e0867610c718cb5eb1:2880dd9d8ad0a7b221d4eacda9a818e92983128d-0" + } + + input: + tuple val(meta), path(reads) + path index + path splicesites + + output: + tuple val(meta), path("*.bam"), emit: bam + tuple val(meta), path("*.log"), emit: summary + path "*.version.txt" , emit: version + + tuple val(meta), path("*fastq.gz"), optional:true, emit: fastq + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + + def strandedness = '' + if (meta.strandedness == 'forward') { + strandedness = meta.single_end ? '--rna-strandness F' : '--rna-strandness FR' + } else if (meta.strandedness == 'reverse') { + strandedness = meta.single_end ? '--rna-strandness R' : '--rna-strandness RF' + } + def seq_center = params.seq_center ? "--rg-id ${prefix} --rg SM:$prefix --rg CN:${params.seq_center.replaceAll('\\s','_')}" : "--rg-id ${prefix} --rg SM:$prefix" + if (meta.single_end) { + def unaligned = params.save_unaligned ? "--un-gz ${prefix}.unmapped.fastq.gz" : '' + """ + INDEX=`find -L ./ -name "*.1.ht2" | sed 's/.1.ht2//'` + hisat2 \\ + -x \$INDEX \\ + -U $reads \\ + $strandedness \\ + --known-splicesite-infile $splicesites \\ + --summary-file ${prefix}.hisat2.summary.log \\ + --threads $task.cpus \\ + $seq_center \\ + $unaligned \\ + $options.args \\ + | samtools view -bS -F 4 -F 256 - > ${prefix}.bam + + echo $VERSION > ${software}.version.txt + """ + } else { + def unaligned = params.save_unaligned ? "--un-conc-gz ${prefix}.unmapped.fastq.gz" : '' + """ + INDEX=`find -L ./ -name "*.1.ht2" | sed 's/.1.ht2//'` + hisat2 \\ + -x \$INDEX \\ + -1 ${reads[0]} \\ + -2 ${reads[1]} \\ + $strandedness \\ + --known-splicesite-infile $splicesites \\ + --summary-file ${prefix}.hisat2.summary.log \\ + --threads $task.cpus \\ + $seq_center \\ + $unaligned \\ + --no-mixed \\ + --no-discordant \\ + $options.args \\ + | samtools view -bS -F 4 -F 8 -F 256 - > ${prefix}.bam + + if [ -f ${prefix}.unmapped.fastq.1.gz ]; then + mv ${prefix}.unmapped.fastq.1.gz ${prefix}.unmapped_1.fastq.gz + fi + if [ -f ${prefix}.unmapped.fastq.2.gz ]; then + mv ${prefix}.unmapped.fastq.2.gz ${prefix}.unmapped_2.fastq.gz + fi + + echo $VERSION > ${software}.version.txt + """ + } +} diff --git a/modules/nf-core/modules/hisat2/align/meta.yml b/modules/nf-core/modules/hisat2/align/meta.yml new file mode 100644 index 000000000..bf5570fdf --- /dev/null +++ b/modules/nf-core/modules/hisat2/align/meta.yml @@ -0,0 +1,57 @@ +name: hisat2_align +description: Align RNA-Seq reads to a reference with HISAT2 +keywords: + - align + - fasta + - genome + - reference + +tools: + - hisat2: + description: HISAT2 is a fast and sensitive alignment program for mapping next-generation sequencing reads (both DNA and RNA) to a population of human genomes as well as to a single reference genome. + homepage: https://daehwankimlab.github.io/hisat2/ + documentation: https://daehwankimlab.github.io/hisat2/manual/ + doi: "10.1038/s41587-019-0201-4" + licence: ['MIT'] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - reads: + type: file + description: | + List of input FastQ files of size 1 and 2 for single-end and paired-end data, + respectively. + - index: + type: file + description: HISAT2 genome index file + pattern: "*.ht2" + - splicesites: + type: file + description: Splices sites in gtf file + pattern: "*.{txt}" + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: Output BAM file containing read alignments + pattern: "*.{bam}" + - summary: + type: file + description: Aligment log + pattern: "*.log" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" + +authors: + - "@ntoda03" diff --git a/modules/nf-core/modules/hisat2/build/functions.nf b/modules/nf-core/modules/hisat2/build/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/hisat2/build/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/hisat2/build/main.nf b/modules/nf-core/modules/hisat2/build/main.nf new file mode 100644 index 000000000..ce8bfb265 --- /dev/null +++ b/modules/nf-core/modules/hisat2/build/main.nf @@ -0,0 +1,70 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +def VERSION = '2.2.0' + +process HISAT2_BUILD { + tag "$fasta" + label 'process_high' + label 'process_high_memory' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:'index', meta:[:], publish_by_meta:[]) } + + conda (params.enable_conda ? "bioconda::hisat2=2.2.0" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/hisat2:2.2.0--py37hfa133b6_4" + } else { + container "quay.io/biocontainers/hisat2:2.2.0--py37hfa133b6_4" + } + + input: + path fasta + path gtf + path splicesites + + output: + path "hisat2" , emit: index + path "*.version.txt", emit: version + + script: + def avail_mem = 0 + if (!task.memory) { + log.info "[HISAT2 index build] Available memory not known - defaulting to 0. Specify process memory requirements to change this." + } else { + log.info "[HISAT2 index build] Available memory: ${task.memory}" + avail_mem = task.memory.toGiga() + } + + def ss = '' + def exon = '' + def extract_exons = '' + def hisat2_build_memory = params.hisat2_build_memory ? (params.hisat2_build_memory as nextflow.util.MemoryUnit).toGiga() : 0 + if (avail_mem >= hisat2_build_memory) { + log.info "[HISAT2 index build] At least ${hisat2_build_memory} GB available, so using splice sites and exons to build HISAT2 index" + extract_exons = "hisat2_extract_exons.py $gtf > ${gtf.baseName}.exons.txt" + ss = "--ss $splicesites" + exon = "--exon ${gtf.baseName}.exons.txt" + } else { + log.info "[HISAT2 index build] Less than ${hisat2_build_memory} GB available, so NOT using splice sites and exons to build HISAT2 index." + log.info "[HISAT2 index build] Use --hisat2_build_memory [small number] to skip this check." + } + + def software = getSoftwareName(task.process) + """ + mkdir hisat2 + $extract_exons + hisat2-build \\ + -p $task.cpus \\ + $ss \\ + $exon \\ + $options.args \\ + $fasta \\ + hisat2/${fasta.baseName} + + echo $VERSION > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/hisat2/build/meta.yml b/modules/nf-core/modules/hisat2/build/meta.yml new file mode 100644 index 000000000..2f34d9d85 --- /dev/null +++ b/modules/nf-core/modules/hisat2/build/meta.yml @@ -0,0 +1,42 @@ +name: hisat2_build +description: Builds HISAT2 index for reference genome +keywords: + - build + - index + - fasta + - genome + - reference +tools: + - hisat2: + description: HISAT2 is a fast and sensitive alignment program for mapping next-generation sequencing reads (both DNA and RNA) to a population of human genomes as well as to a single reference genome. + homepage: https://daehwankimlab.github.io/hisat2/ + documentation: https://daehwankimlab.github.io/hisat2/manual/ + doi: "10.1038/s41587-019-0201-4" + licence: ['MIT'] + +input: + - fasta: + type: file + description: Reference fasta file + pattern: "*.{fa,fasta,fna}" + - gtf: + type: file + description: Reference gtf annotation file + pattern: "*.{gtf}" + - splicesites: + type: file + description: Splices sites in gtf file + pattern: "*.{txt}" + +output: + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" + - index: + type: file + description: HISAT2 genome index file + pattern: "*.ht2" + +authors: + - "@ntoda03" diff --git a/modules/nf-core/modules/hisat2/extractsplicesites/functions.nf b/modules/nf-core/modules/hisat2/extractsplicesites/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/hisat2/extractsplicesites/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/multiqc/main.nf b/modules/nf-core/modules/hisat2/extractsplicesites/main.nf similarity index 53% rename from modules/nf-core/modules/multiqc/main.nf rename to modules/nf-core/modules/hisat2/extractsplicesites/main.nf index da7808002..57f4dedbd 100644 --- a/modules/nf-core/modules/multiqc/main.nf +++ b/modules/nf-core/modules/hisat2/extractsplicesites/main.nf @@ -4,32 +4,33 @@ include { initOptions; saveFiles; getSoftwareName } from './functions' params.options = [:] options = initOptions(params.options) -process MULTIQC { +def VERSION = '2.2.0' + +process HISAT2_EXTRACTSPLICESITES { + tag "$gtf" label 'process_medium' publishDir "${params.outdir}", mode: params.publish_dir_mode, saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) } - conda (params.enable_conda ? "bioconda::multiqc=1.10.1" : null) + conda (params.enable_conda ? "bioconda::hisat2=2.2.0" : null) if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/multiqc:1.10.1--py_0" + container "https://depot.galaxyproject.org/singularity/hisat2:2.2.0--py37hfa133b6_4" } else { - container "quay.io/biocontainers/multiqc:1.10.1--py_0" + container "quay.io/biocontainers/hisat2:2.2.0--py37hfa133b6_4" } input: - path multiqc_files + path gtf output: - path "*multiqc_report.html", emit: report - path "*_data" , emit: data - path "*_plots" , optional:true, emit: plots - path "*.version.txt" , emit: version + path "*.splice_sites.txt", emit: txt + path "*.version.txt" , emit: version script: def software = getSoftwareName(task.process) """ - multiqc -f $options.args . - multiqc --version | sed -e "s/multiqc, version //g" > ${software}.version.txt + hisat2_extract_splice_sites.py $gtf > ${gtf.baseName}.splice_sites.txt + echo $VERSION > ${software}.version.txt """ } diff --git a/modules/nf-core/modules/hisat2/extractsplicesites/meta.yml b/modules/nf-core/modules/hisat2/extractsplicesites/meta.yml new file mode 100644 index 000000000..228138a87 --- /dev/null +++ b/modules/nf-core/modules/hisat2/extractsplicesites/meta.yml @@ -0,0 +1,34 @@ +name: hisat2_extractsplicesites +description: Extracts splicing sites from a gtf files +keywords: + - splicing + - gtf + - genome + - reference + +tools: + - hisat2: + description: HISAT2 is a fast and sensitive alignment program for mapping next-generation sequencing reads (both DNA and RNA) to a population of human genomes as well as to a single reference genome. + homepage: https://daehwankimlab.github.io/hisat2/ + documentation: https://daehwankimlab.github.io/hisat2/manual/ + doi: "10.1038/s41587-019-0201-4" + licence: ['MIT'] + +input: + - gtf: + type: file + description: Reference gtf annotation file + pattern: "*.{gtf}" + +output: + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" + - splicesites: + type: file + description: Splices sites in gtf file + pattern: "*.{splice_sites.txt}" + +authors: + - "@ntoda03" diff --git a/modules/nf-core/modules/multiqc/meta.yml b/modules/nf-core/modules/multiqc/meta.yml deleted file mode 100644 index 532a8bb1e..000000000 --- a/modules/nf-core/modules/multiqc/meta.yml +++ /dev/null @@ -1,39 +0,0 @@ -name: MultiQC -description: Aggregate results from bioinformatics analyses across many samples into a single report -keywords: - - QC - - bioinformatics tools - - Beautiful stand-alone HTML report -tools: - - multiqc: - description: | - MultiQC searches a given directory for analysis logs and compiles a HTML report. - It's a general use tool, perfect for summarising the output from numerous bioinformatics tools. - homepage: https://multiqc.info/ - documentation: https://multiqc.info/docs/ -input: - - multiqc_files: - type: file - description: | - List of reports / files recognised by MultiQC, for example the html and zip output of FastQC -output: - - report: - type: file - description: MultiQC report file - pattern: "multiqc_report.html" - - data: - type: dir - description: MultiQC data dir - pattern: "multiqc_data" - - plots: - type: file - description: Plots created by MultiQC - pattern: "*_data" - - version: - type: file - description: File containing software version - pattern: "*.{version.txt}" -authors: - - "@abhi18av" - - "@bunop" - - "@drpatelh" diff --git a/modules/nf-core/modules/picard/markduplicates/functions.nf b/modules/nf-core/modules/picard/markduplicates/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/picard/markduplicates/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/picard/markduplicates/main.nf b/modules/nf-core/modules/picard/markduplicates/main.nf new file mode 100644 index 000000000..d76474147 --- /dev/null +++ b/modules/nf-core/modules/picard/markduplicates/main.nf @@ -0,0 +1,49 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process PICARD_MARKDUPLICATES { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::picard=2.23.9" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/picard:2.23.9--0" + } else { + container "quay.io/biocontainers/picard:2.23.9--0" + } + + input: + tuple val(meta), path(bam) + + output: + tuple val(meta), path("*.bam") , emit: bam + tuple val(meta), path("*.metrics.txt"), emit: metrics + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + def avail_mem = 3 + if (!task.memory) { + log.info '[Picard MarkDuplicates] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.' + } else { + avail_mem = task.memory.giga + } + """ + picard \\ + -Xmx${avail_mem}g \\ + MarkDuplicates \\ + $options.args \\ + INPUT=$bam \\ + OUTPUT=${prefix}.bam \\ + METRICS_FILE=${prefix}.MarkDuplicates.metrics.txt + + echo \$(picard MarkDuplicates --version 2>&1) | grep -o 'Version:.*' | cut -f2- -d: > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/picard/markduplicates/meta.yml b/modules/nf-core/modules/picard/markduplicates/meta.yml new file mode 100644 index 000000000..6420ce9a4 --- /dev/null +++ b/modules/nf-core/modules/picard/markduplicates/meta.yml @@ -0,0 +1,46 @@ +name: picard_markduplicates +description: Locate and tag duplicate reads in a BAM file +keywords: + - markduplicates + - pcr + - duplicates + - bam + - sam + - cram +tools: + - picard: + description: | + A set of command line tools (in Java) for manipulating high-throughput sequencing (HTS) + data and formats such as SAM/BAM/CRAM and VCF. + homepage: https://broadinstitute.github.io/picard/ + documentation: https://broadinstitute.github.io/picard/ +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: BAM file + pattern: "*.{bam}" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: BAM file with duplicate reads marked/removed + pattern: "*.{bam}" + - metrics: + type: file + description: Duplicate metrics file generated by picard + pattern: "*.{metrics.txt}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" diff --git a/modules/nf-core/modules/preseq/lcextrap/functions.nf b/modules/nf-core/modules/preseq/lcextrap/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/preseq/lcextrap/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/preseq/lcextrap/main.nf b/modules/nf-core/modules/preseq/lcextrap/main.nf new file mode 100644 index 000000000..2f601e4f6 --- /dev/null +++ b/modules/nf-core/modules/preseq/lcextrap/main.nf @@ -0,0 +1,45 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process PRESEQ_LCEXTRAP { + tag "$meta.id" + label 'process_medium' + label 'error_ignore' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::preseq=3.1.2" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/preseq:3.1.2--h06ef8b0_1" + } else { + container "quay.io/biocontainers/preseq:3.1.2--h06ef8b0_1" + } + + input: + tuple val(meta), path(bam) + + output: + tuple val(meta), path("*.ccurve.txt"), emit: ccurve + tuple val(meta), path("*.log") , emit: log + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + def paired_end = meta.single_end ? '' : '-pe' + """ + preseq \\ + lc_extrap \\ + $options.args \\ + $paired_end \\ + -output ${prefix}.ccurve.txt \\ + $bam + cp .command.err ${prefix}.command.log + + echo \$(preseq 2>&1) | sed 's/^.*Version: //; s/Usage:.*\$//' > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/preseq/lcextrap/meta.yml b/modules/nf-core/modules/preseq/lcextrap/meta.yml new file mode 100644 index 000000000..d1716231e --- /dev/null +++ b/modules/nf-core/modules/preseq/lcextrap/meta.yml @@ -0,0 +1,47 @@ +name: preseq_lcextrap +description: Software for predicting library complexity and genome coverage in high-throughput sequencing +keywords: + - preseq + - library + - complexity +tools: + - preseq: + description: Software for predicting library complexity and genome coverage in high-throughput sequencing + homepage: http://smithlabresearch.org/software/preseq/ + documentation: None + tool_dev_url: None + doi: "" + licence: ['GPL'] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: BAM/CRAM/SAM file + pattern: "*.{bam,cram,sam}" + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" + - ccurve: + type: file + description: File containing output of Preseq lcextrap + pattern: "*.{ccurve.txt}" + - log: + type: file + description: Log file containing stderr produced by Preseq + pattern: "*.{log}" + +authors: + - "@drpatelh" diff --git a/modules/nf-core/modules/qualimap/rnaseq/functions.nf b/modules/nf-core/modules/qualimap/rnaseq/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/qualimap/rnaseq/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/qualimap/rnaseq/main.nf b/modules/nf-core/modules/qualimap/rnaseq/main.nf new file mode 100644 index 000000000..96fe2cd42 --- /dev/null +++ b/modules/nf-core/modules/qualimap/rnaseq/main.nf @@ -0,0 +1,57 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process QUALIMAP_RNASEQ { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::qualimap=2.2.2d" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/qualimap:2.2.2d--1" + } else { + container "quay.io/biocontainers/qualimap:2.2.2d--1" + } + + input: + tuple val(meta), path(bam) + path gtf + + output: + tuple val(meta), path("${prefix}"), emit: results + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + def paired_end = meta.single_end ? '' : '-pe' + def memory = task.memory.toGiga() + "G" + + def strandedness = 'non-strand-specific' + if (meta.strandedness == 'forward') { + strandedness = 'strand-specific-forward' + } else if (meta.strandedness == 'reverse') { + strandedness = 'strand-specific-reverse' + } + """ + unset DISPLAY + mkdir tmp + export _JAVA_OPTIONS=-Djava.io.tmpdir=./tmp + qualimap \\ + --java-mem-size=$memory \\ + rnaseq \\ + $options.args \\ + -bam $bam \\ + -gtf $gtf \\ + -p $strandedness \\ + $paired_end \\ + -outdir $prefix + + echo \$(qualimap 2>&1) | sed 's/^.*QualiMap v.//; s/Built.*\$//' > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/rsem/calculateexpression/functions.nf b/modules/nf-core/modules/rsem/calculateexpression/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/rsem/calculateexpression/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/rsem/calculateexpression/main.nf b/modules/nf-core/modules/rsem/calculateexpression/main.nf new file mode 100644 index 000000000..1f9ab854e --- /dev/null +++ b/modules/nf-core/modules/rsem/calculateexpression/main.nf @@ -0,0 +1,61 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process RSEM_CALCULATEEXPRESSION { + tag "$meta.id" + label 'process_high' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::rsem=1.3.3 bioconda::star=2.7.6a" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0" + } else { + container "quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0" + } + + input: + tuple val(meta), path(reads) + path index + + output: + tuple val(meta), path("*.genes.results") , emit: counts_gene + tuple val(meta), path("*.isoforms.results"), emit: counts_transcript + tuple val(meta), path("*.stat") , emit: stat + tuple val(meta), path("*.log") , emit: logs + path "*.version.txt" , emit: version + + tuple val(meta), path("*.STAR.genome.bam") , optional:true, emit: bam_star + tuple val(meta), path("${prefix}.genome.bam") , optional:true, emit: bam_genome + tuple val(meta), path("${prefix}.transcript.bam"), optional:true, emit: bam_transcript + + script: + def software = getSoftwareName(task.process) + prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + + def strandedness = '' + if (meta.strandedness == 'forward') { + strandedness = '--strandedness forward' + } else if (meta.strandedness == 'reverse') { + strandedness = '--strandedness reverse' + } + def paired_end = meta.single_end ? "" : "--paired-end" + """ + INDEX=`find -L ./ -name "*.grp" | sed 's/.grp//'` + rsem-calculate-expression \\ + --num-threads $task.cpus \\ + --temporary-folder ./tmp/ \\ + $strandedness \\ + $paired_end \\ + $options.args \\ + $reads \\ + \$INDEX \\ + $prefix + + rsem-calculate-expression --version | sed -e "s/Current version: RSEM v//g" > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/rsem/calculateexpression/meta.yml b/modules/nf-core/modules/rsem/calculateexpression/meta.yml new file mode 100644 index 000000000..f85770853 --- /dev/null +++ b/modules/nf-core/modules/rsem/calculateexpression/meta.yml @@ -0,0 +1,63 @@ +name: rsem_calculateexpression +description: Calculate expression with RSEM +keywords: + - rsem + - expression + - quantification +tools: + - rseqc: + description: | + RSEM: accurate transcript quantification from RNA-Seq data with or without a reference genome + homepage: https://github.com/deweylab/RSEM + documentation: https://github.com/deweylab/RSEM + doi: https://doi.org/10.1186/1471-2105-12-323 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - reads: + type: file + description: Input reads for quantification + pattern: "*.fastq.gz"# + - index: + type: file + description: RSEM index + pattern: "rsem/*" +output: + - counts_gene: + type: file + description: Expression counts on gene level + pattern: "*.genes.results" + - counts_transctips: + type: file + description: Expression counts on transcript level + pattern: "*.isoforms.results" + - stat: + type: file + description: RSEM statistics + pattern: "*.stat" + - logs: + type: file + description: RSEM logs + pattern: "*.log" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" + - bam_star: + type: file + description: BAM file generated by STAR (optional) + pattern: "*.STAR.genome.bam" + - bam_genome: + type: file + description: Genome BAM file (optional) + pattern: "*.genome.bam" + - bam_transcript: + type: file + description: Transcript BAM file (optional) + pattern: "*.transcript.bam" +authors: + - "@drpatelh" + - "@kevinmenden" diff --git a/modules/nf-core/modules/rsem/preparereference/functions.nf b/modules/nf-core/modules/rsem/preparereference/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/rsem/preparereference/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/rsem/preparereference/main.nf b/modules/nf-core/modules/rsem/preparereference/main.nf new file mode 100644 index 000000000..a378eb6b2 --- /dev/null +++ b/modules/nf-core/modules/rsem/preparereference/main.nf @@ -0,0 +1,67 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process RSEM_PREPAREREFERENCE { + tag "$fasta" + label 'process_high' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:'index', meta:[:], publish_by_meta:[]) } + + conda (params.enable_conda ? "bioconda::rsem=1.3.3 bioconda::star=2.7.6a" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0" + } else { + container "quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0" + } + + input: + path fasta, stageAs: "rsem/*" + path gtf + + output: + path "rsem" , emit: index + path "rsem/*transcripts.fa", emit: transcript_fasta + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def args = options.args.tokenize() + if (args.contains('--star')) { + args.removeIf { it.contains('--star') } + def memory = task.memory ? "--limitGenomeGenerateRAM ${task.memory.toBytes() - 100000000}" : '' + """ + STAR \\ + --runMode genomeGenerate \\ + --genomeDir rsem/ \\ + --genomeFastaFiles $fasta \\ + --sjdbGTFfile $gtf \\ + --runThreadN $task.cpus \\ + $memory \\ + $options.args2 + + rsem-prepare-reference \\ + --gtf $gtf \\ + --num-threads $task.cpus \\ + ${args.join(' ')} \\ + $fasta \\ + rsem/genome + + rsem-calculate-expression --version | sed -e "s/Current version: RSEM v//g" > ${software}.version.txt + """ + } else { + """ + rsem-prepare-reference \\ + --gtf $gtf \\ + --num-threads $task.cpus \\ + $options.args \\ + $fasta \\ + rsem/genome + + rsem-calculate-expression --version | sed -e "s/Current version: RSEM v//g" > ${software}.version.txt + """ + } +} diff --git a/modules/nf-core/modules/rsem/preparereference/meta.yml b/modules/nf-core/modules/rsem/preparereference/meta.yml new file mode 100644 index 000000000..d7c02154a --- /dev/null +++ b/modules/nf-core/modules/rsem/preparereference/meta.yml @@ -0,0 +1,37 @@ +name: rsem_preparereference +description: Prepare a reference genome for RSEM +keywords: + - rsem + - reference +tools: + - rseqc: + description: | + RSEM: accurate transcript quantification from RNA-Seq data with or without a reference genome + homepage: https://github.com/deweylab/RSEM + documentation: https://github.com/deweylab/RSEM + doi: https://doi.org/10.1186/1471-2105-12-323 +input: + - fasta: + type: file + description: The Fasta file of the reference genome + pattern: "*.{fasta,fa}" + - gtf: + type: file + description: The GTF file of the reference genome + pattern: "*.gtf" +output: + - rsem: + type: directory + description: RSEM index directory + pattern: "rsem" + - transcript_fasta: + type: file + description: Fasta file of transcripts + pattern: "rsem/*transcripts.fa" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" + - "@kevinmenden" diff --git a/modules/nf-core/modules/rseqc/bamstat/functions.nf b/modules/nf-core/modules/rseqc/bamstat/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/rseqc/bamstat/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/rseqc/bamstat/main.nf b/modules/nf-core/modules/rseqc/bamstat/main.nf new file mode 100644 index 000000000..ac80b6d01 --- /dev/null +++ b/modules/nf-core/modules/rseqc/bamstat/main.nf @@ -0,0 +1,39 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process RSEQC_BAMSTAT { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::rseqc=3.0.1" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1" + } else { + container "quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1" + } + + input: + tuple val(meta), path(bam) + + output: + tuple val(meta), path("*.bam_stat.txt"), emit: txt + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + bam_stat.py \\ + -i $bam \\ + $options.args \\ + > ${prefix}.bam_stat.txt + + bam_stat.py --version | sed -e "s/bam_stat.py //g" > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/rseqc/bamstat/meta.yml b/modules/nf-core/modules/rseqc/bamstat/meta.yml new file mode 100644 index 000000000..ff00d8c9b --- /dev/null +++ b/modules/nf-core/modules/rseqc/bamstat/meta.yml @@ -0,0 +1,36 @@ +name: rseqc_bamstat +description: Generate statistics from a bam file +keywords: + - bam + - qc + - bamstat +tools: + - rseqc: + description: | + RSeQC package provides a number of useful modules that can comprehensively evaluate + high throughput sequence data especially RNA-seq data. + homepage: http://rseqc.sourceforge.net/ + documentation: http://rseqc.sourceforge.net/ + doi: 10.1093/bioinformatics/bts356 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: the bam file to calculate statistics of + pattern: "*.{bam}" +output: + - txt: + type: file + description: bam statistics report + pattern: "*.bam_stat.txt" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" + - "@kevinmenden" diff --git a/modules/nf-core/modules/rseqc/inferexperiment/functions.nf b/modules/nf-core/modules/rseqc/inferexperiment/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/rseqc/inferexperiment/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/rseqc/inferexperiment/main.nf b/modules/nf-core/modules/rseqc/inferexperiment/main.nf new file mode 100644 index 000000000..da0958d4f --- /dev/null +++ b/modules/nf-core/modules/rseqc/inferexperiment/main.nf @@ -0,0 +1,41 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process RSEQC_INFEREXPERIMENT { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::rseqc=3.0.1" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1" + } else { + container "quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1" + } + + input: + tuple val(meta), path(bam) + path bed + + output: + tuple val(meta), path("*.infer_experiment.txt"), emit: txt + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + infer_experiment.py \\ + -i $bam \\ + -r $bed \\ + $options.args \\ + > ${prefix}.infer_experiment.txt + + infer_experiment.py --version | sed -e "s/infer_experiment.py //g" > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/rseqc/inferexperiment/meta.yml b/modules/nf-core/modules/rseqc/inferexperiment/meta.yml new file mode 100644 index 000000000..366c3e33b --- /dev/null +++ b/modules/nf-core/modules/rseqc/inferexperiment/meta.yml @@ -0,0 +1,39 @@ +name: rseqc_inferexperiment +description: Infer strandedness from sequencing reads +keywords: + - rnaseq + - experiment +tools: + - rseqc: + description: | + RSeQC package provides a number of useful modules that can comprehensively evaluate + high throughput sequence data especially RNA-seq data. + homepage: http://rseqc.sourceforge.net/ + documentation: http://rseqc.sourceforge.net/ + doi: 10.1093/bioinformatics/bts356 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: the bam file to calculate statistics of + pattern: "*.{bam}" + - bed: + type: file + description: a bed file for the reference gene model + pattern: "*.{bed}" +output: + - txt: + type: file + description: infer_experiment results report + pattern: "*.infer_experiment.txt" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" + - "@kevinmenden" diff --git a/modules/nf-core/modules/rseqc/innerdistance/functions.nf b/modules/nf-core/modules/rseqc/innerdistance/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/rseqc/innerdistance/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/rseqc/innerdistance/main.nf b/modules/nf-core/modules/rseqc/innerdistance/main.nf new file mode 100644 index 000000000..2688fca62 --- /dev/null +++ b/modules/nf-core/modules/rseqc/innerdistance/main.nf @@ -0,0 +1,53 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process RSEQC_INNERDISTANCE { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::rseqc=3.0.1" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1" + } else { + container "quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1" + } + + input: + tuple val(meta), path(bam) + path bed + + output: + tuple val(meta), path("*distance.txt"), optional:true, emit: distance + tuple val(meta), path("*freq.txt") , optional:true, emit: freq + tuple val(meta), path("*mean.txt") , optional:true, emit: mean + tuple val(meta), path("*.pdf") , optional:true, emit: pdf + tuple val(meta), path("*.r") , optional:true, emit: rscript + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + if (!meta.single_end) { + """ + inner_distance.py \\ + -i $bam \\ + -r $bed \\ + -o $prefix \\ + $options.args \\ + > stdout.txt + head -n 2 stdout.txt > ${prefix}.inner_distance_mean.txt + + inner_distance.py --version | sed -e "s/inner_distance.py //g" > ${software}.version.txt + """ + } else { + """ + inner_distance.py --version | sed -e "s/inner_distance.py //g" > ${software}.version.txt + """ + } +} diff --git a/modules/nf-core/modules/rseqc/innerdistance/meta.yml b/modules/nf-core/modules/rseqc/innerdistance/meta.yml new file mode 100644 index 000000000..ed72c51cc --- /dev/null +++ b/modules/nf-core/modules/rseqc/innerdistance/meta.yml @@ -0,0 +1,55 @@ +name: rseqc_innerdistance +description: Calculate inner distance between read pairs. +keywords: + - fragment_size + - inner_distance +tools: + - rseqc: + description: | + RSeQC package provides a number of useful modules that can comprehensively evaluate + high throughput sequence data especially RNA-seq data. + homepage: http://rseqc.sourceforge.net/ + documentation: http://rseqc.sourceforge.net/ + doi: 10.1093/bioinformatics/bts356 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: the alignment in bam format + pattern: "*.{bam}" + - bed: + type: file + description: a bed file for the reference gene model + pattern: "*.{bed}" +output: + - distance: + type: file + description: the inner distances + pattern: "*.inner_distance.txt" + - freq: + type: file + description: frequencies of different insert sizes + pattern: "*.inner_distance_freq.txt" + - mean: + type: file + description: mean/median values of inner distances + pattern: "*.inner_distance_mean.txt" + - pdf: + type: file + description: distribution plot of inner distances + pattern: "*.inner_distance_plot.pdf" + - rscript: + type: file + description: script to reproduce the plot + pattern: "*.inner_distance_plot.R" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" + - "@kevinmenden" diff --git a/modules/nf-core/modules/rseqc/junctionannotation/functions.nf b/modules/nf-core/modules/rseqc/junctionannotation/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/rseqc/junctionannotation/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/rseqc/junctionannotation/main.nf b/modules/nf-core/modules/rseqc/junctionannotation/main.nf new file mode 100644 index 000000000..909ee9aef --- /dev/null +++ b/modules/nf-core/modules/rseqc/junctionannotation/main.nf @@ -0,0 +1,48 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process RSEQC_JUNCTIONANNOTATION { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::rseqc=3.0.1" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1" + } else { + container "quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1" + } + + input: + tuple val(meta), path(bam) + path bed + + output: + tuple val(meta), path("*.xls") , emit: xls + tuple val(meta), path("*.r") , emit: rscript + tuple val(meta), path("*.log") , emit: log + tuple val(meta), path("*.junction.bed"), optional:true, emit: bed + tuple val(meta), path("*.interact.bed"), optional:true, emit: interact_bed + tuple val(meta), path("*junction.pdf") , optional:true, emit: pdf + tuple val(meta), path("*events.pdf") , optional:true, emit: events_pdf + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + junction_annotation.py \\ + -i $bam \\ + -r $bed \\ + -o $prefix \\ + $options.args \\ + 2> ${prefix}.junction_annotation.log + + junction_annotation.py --version | sed -e "s/junction_annotation.py //g" > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/rseqc/junctionannotation/meta.yml b/modules/nf-core/modules/rseqc/junctionannotation/meta.yml new file mode 100644 index 000000000..64926ce0f --- /dev/null +++ b/modules/nf-core/modules/rseqc/junctionannotation/meta.yml @@ -0,0 +1,61 @@ +name: rseqc_junctionannotation +description: compare detected splice junctions to reference gene model +keywords: + - junctions + - splicing + - rnaseq +tools: + - rseqc: + description: | + RSeQC package provides a number of useful modules that can comprehensively evaluate + high throughput sequence data especially RNA-seq data. + homepage: http://rseqc.sourceforge.net/ + documentation: http://rseqc.sourceforge.net/ + doi: 10.1093/bioinformatics/bts356 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: the alignment in bam format + pattern: "*.{bam}" + - bed: + type: file + description: a bed file for the reference gene model + pattern: "*.{bed}" +output: + - bed: + type: file + description: bed file of annotated junctions + pattern: "*.junction.bed" + - interact_bed: + type: file + description: Interact bed file + pattern: "*.Interact.bed" + - xls: + type: file + description: xls file with junction information + pattern: "*.xls" + - pdf: + type: file + description: junction plot + pattern: "*.junction.pdf" + - events_pdf: + type: file + description: events plot + pattern: "*.events.pdf" + - rscript: + type: file + description: Rscript to reproduce the plots + pattern: "*.r" + - log: + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" + - "@kevinmenden" diff --git a/modules/nf-core/modules/rseqc/junctionsaturation/functions.nf b/modules/nf-core/modules/rseqc/junctionsaturation/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/rseqc/junctionsaturation/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/rseqc/junctionsaturation/main.nf b/modules/nf-core/modules/rseqc/junctionsaturation/main.nf new file mode 100644 index 000000000..e6e216380 --- /dev/null +++ b/modules/nf-core/modules/rseqc/junctionsaturation/main.nf @@ -0,0 +1,42 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process RSEQC_JUNCTIONSATURATION { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::rseqc=3.0.1" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1" + } else { + container "quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1" + } + + input: + tuple val(meta), path(bam) + path bed + + output: + tuple val(meta), path("*.pdf"), emit: pdf + tuple val(meta), path("*.r") , emit: rscript + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + junction_saturation.py \\ + -i $bam \\ + -r $bed \\ + -o $prefix \\ + $options.args + + junction_saturation.py --version | sed -e "s/junction_saturation.py //g" > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/rseqc/junctionsaturation/meta.yml b/modules/nf-core/modules/rseqc/junctionsaturation/meta.yml new file mode 100644 index 000000000..38008577a --- /dev/null +++ b/modules/nf-core/modules/rseqc/junctionsaturation/meta.yml @@ -0,0 +1,44 @@ +name: rseqc_junctionsaturation +description: compare detected splice junctions to reference gene model +keywords: + - junctions + - splicing + - rnaseq +tools: + - rseqc: + description: | + RSeQC package provides a number of useful modules that can comprehensively evaluate + high throughput sequence data especially RNA-seq data. + homepage: http://rseqc.sourceforge.net/ + documentation: http://rseqc.sourceforge.net/ + doi: 10.1093/bioinformatics/bts356 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: the alignment in bam format + pattern: "*.{bam}" + - bed: + type: file + description: a bed file for the reference gene model + pattern: "*.{bed}" +output: + - pdf: + type: file + description: Junction saturation report + pattern: "*.pdf" + - rscript: + type: file + description: Junction saturation R-script + pattern: "*.r" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" + - "@kevinmenden" diff --git a/modules/nf-core/modules/rseqc/readdistribution/functions.nf b/modules/nf-core/modules/rseqc/readdistribution/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/rseqc/readdistribution/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/rseqc/readdistribution/main.nf b/modules/nf-core/modules/rseqc/readdistribution/main.nf new file mode 100644 index 000000000..a6ed6c9f1 --- /dev/null +++ b/modules/nf-core/modules/rseqc/readdistribution/main.nf @@ -0,0 +1,40 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process RSEQC_READDISTRIBUTION { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::rseqc=3.0.1" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1" + } else { + container "quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1" + } + + input: + tuple val(meta), path(bam) + path bed + + output: + tuple val(meta), path("*.read_distribution.txt"), emit: txt + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + read_distribution.py \\ + -i $bam \\ + -r $bed \\ + > ${prefix}.read_distribution.txt + + read_distribution.py --version | sed -e "s/read_distribution.py //g" > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/rseqc/readdistribution/meta.yml b/modules/nf-core/modules/rseqc/readdistribution/meta.yml new file mode 100644 index 000000000..ce2b0f5a9 --- /dev/null +++ b/modules/nf-core/modules/rseqc/readdistribution/meta.yml @@ -0,0 +1,40 @@ +name: rseqc_readdistribution +description: Calculate how mapped reads are distributed over genomic features +keywords: + - read distribution + - genomics + - rnaseq +tools: + - rseqc: + description: | + RSeQC package provides a number of useful modules that can comprehensively evaluate + high throughput sequence data especially RNA-seq data. + homepage: http://rseqc.sourceforge.net/ + documentation: http://rseqc.sourceforge.net/ + doi: 10.1093/bioinformatics/bts356 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: the alignment in bam format + pattern: "*.{bam}" + - bed: + type: file + description: a bed file for the reference gene model + pattern: "*.{bed}" +output: + - txt: + type: file + description: the read distribution report + pattern: "*.read_distribution.txt" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" + - "@kevinmenden" diff --git a/modules/nf-core/modules/rseqc/readduplication/functions.nf b/modules/nf-core/modules/rseqc/readduplication/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/rseqc/readduplication/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/rseqc/readduplication/main.nf b/modules/nf-core/modules/rseqc/readduplication/main.nf new file mode 100644 index 000000000..6fb06f637 --- /dev/null +++ b/modules/nf-core/modules/rseqc/readduplication/main.nf @@ -0,0 +1,42 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process RSEQC_READDUPLICATION { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::rseqc=3.0.1" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1" + } else { + container "quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1" + } + + input: + tuple val(meta), path(bam) + + output: + tuple val(meta), path("*seq.DupRate.xls"), emit: seq_xls + tuple val(meta), path("*pos.DupRate.xls"), emit: pos_xls + tuple val(meta), path("*.pdf") , emit: pdf + tuple val(meta), path("*.r") , emit: rscript + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + read_duplication.py \\ + -i $bam \\ + -o $prefix \\ + $options.args + + read_duplication.py --version | sed -e "s/read_duplication.py //g" > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/rseqc/readduplication/meta.yml b/modules/nf-core/modules/rseqc/readduplication/meta.yml new file mode 100644 index 000000000..c43ea688f --- /dev/null +++ b/modules/nf-core/modules/rseqc/readduplication/meta.yml @@ -0,0 +1,51 @@ +name: rseqc_readduplication +description: Calculate read duplication rate +keywords: + - rnaseq + - duplication +tools: + - rseqc: + description: | + RSeQC package provides a number of useful modules that can comprehensively evaluate + high throughput sequence data especially RNA-seq data. + homepage: http://rseqc.sourceforge.net/ + documentation: http://rseqc.sourceforge.net/ + doi: 10.1093/bioinformatics/bts356 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: the alignment in bam format + pattern: "*.{bam}" + - bed: + type: file + description: a bed file for the reference gene model + pattern: "*.{bed}" +output: + - seq_xls: + type: file + description: Read duplication rate determined from mapping position of read + pattern: "*seq.DupRate.xls" + - pos_xls: + type: file + description: Read duplication rate determined from sequence of read + pattern: "*pos.DupRate.xls" + - pdf: + type: file + description: plot of duplication rate + pattern: "*.pdf" + - rscript: + type: file + description: script to reproduce the plot + pattern: "*.R" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" + - "@kevinmenden" diff --git a/modules/nf-core/modules/salmon/index/functions.nf b/modules/nf-core/modules/salmon/index/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/salmon/index/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/salmon/index/main.nf b/modules/nf-core/modules/salmon/index/main.nf new file mode 100644 index 000000000..17d5bc064 --- /dev/null +++ b/modules/nf-core/modules/salmon/index/main.nf @@ -0,0 +1,51 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process SALMON_INDEX { + tag "$transcript_fasta" + label "process_medium" + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:'index', meta:[:], publish_by_meta:[]) } + + conda (params.enable_conda ? "bioconda::salmon=1.4.0" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/salmon:1.4.0--hf69c8f4_0" + } else { + container "quay.io/biocontainers/salmon:1.4.0--hf69c8f4_0" + } + + input: + path genome_fasta + path transcript_fasta + + output: + path "salmon" , emit: index + path "*.version.txt", emit: version + + script: + def software = getSoftwareName(task.process) + def get_decoy_ids = "grep '^>' $genome_fasta | cut -d ' ' -f 1 > decoys.txt" + def gentrome = "gentrome.fa" + if (genome_fasta.endsWith('.gz')) { + get_decoy_ids = "grep '^>' <(gunzip -c $genome_fasta) | cut -d ' ' -f 1 > decoys.txt" + gentrome = "gentrome.fa.gz" + } + """ + $get_decoy_ids + sed -i.bak -e 's/>//g' decoys.txt + cat $transcript_fasta $genome_fasta > $gentrome + + salmon \\ + index \\ + --threads $task.cpus \\ + -t $gentrome \\ + -d decoys.txt \\ + $options.args \\ + -i salmon + salmon --version | sed -e "s/salmon //g" > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/salmon/index/meta.yml b/modules/nf-core/modules/salmon/index/meta.yml new file mode 100644 index 000000000..652e2a77a --- /dev/null +++ b/modules/nf-core/modules/salmon/index/meta.yml @@ -0,0 +1,35 @@ +name: salmon_index +description: Create index for salmon +keywords: + - index + - fasta + - genome + - reference +tools: + - salmon: + description: | + Salmon is a tool for wicked-fast transcript quantification from RNA-seq data + homepage: https://salmon.readthedocs.io/en/latest/salmon.html + manual: https://salmon.readthedocs.io/en/latest/salmon.html + doi: 10.1038/nmeth.4197 +input: + - genome_fasta: + type: file + description: Fasta file of the reference genome + - transcriptome_fasta: + type: file + description: Fasta file of the reference transcriptome + +output: + - index: + type: directory + description: Folder containing the star index files + pattern: "salmon" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" + +authors: + - "@kevinmenden" + - "@drpatelh" diff --git a/modules/nf-core/modules/salmon/quant/functions.nf b/modules/nf-core/modules/salmon/quant/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/salmon/quant/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/salmon/quant/main.nf b/modules/nf-core/modules/salmon/quant/main.nf new file mode 100644 index 000000000..093137de5 --- /dev/null +++ b/modules/nf-core/modules/salmon/quant/main.nf @@ -0,0 +1,77 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process SALMON_QUANT { + tag "$meta.id" + label "process_medium" + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::salmon=1.4.0" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/salmon:1.4.0--hf69c8f4_0" + } else { + container "quay.io/biocontainers/salmon:1.4.0--hf69c8f4_0" + } + + input: + tuple val(meta), path(reads) + path index + path gtf + path transcript_fasta + val alignment_mode + val lib_type + + output: + tuple val(meta), path("${prefix}"), emit: results + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + + def reference = "--index $index" + def input_reads = meta.single_end ? "-r $reads" : "-1 ${reads[0]} -2 ${reads[1]}" + if (alignment_mode) { + reference = "-t $transcript_fasta" + input_reads = "-a $reads" + } + + def strandedness_opts = [ + 'A', 'U', 'SF', 'SR', + 'IS', 'IU' , 'ISF', 'ISR', + 'OS', 'OU' , 'OSF', 'OSR', + 'MS', 'MU' , 'MSF', 'MSR' + ] + def strandedness = 'A' + if (lib_type) { + if (strandedness_opts.contains(lib_type)) { + strandedness = lib_type + } else { + log.info "[Salmon Quant] Invalid library type specified '--libType=${lib_type}', defaulting to auto-detection with '--libType=A'." + } + } else { + strandedness = meta.single_end ? 'U' : 'IU' + if (meta.strandedness == 'forward') { + strandedness = meta.single_end ? 'SF' : 'ISF' + } else if (meta.strandedness == 'reverse') { + strandedness = meta.single_end ? 'SR' : 'ISR' + } + } + """ + salmon quant \\ + --geneMap $gtf \\ + --threads $task.cpus \\ + --libType=$strandedness \\ + $reference \\ + $input_reads \\ + $options.args \\ + -o $prefix + + salmon --version | sed -e "s/salmon //g" > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/salmon/quant/meta.yml b/modules/nf-core/modules/salmon/quant/meta.yml new file mode 100644 index 000000000..f37c9884a --- /dev/null +++ b/modules/nf-core/modules/salmon/quant/meta.yml @@ -0,0 +1,55 @@ +name: salmon_quant +description: gene/transcript quantification with Salmon +keywords: + - index + - fasta + - genome + - reference +tools: + - salmon: + description: | + Salmon is a tool for wicked-fast transcript quantification from RNA-seq data + homepage: https://salmon.readthedocs.io/en/latest/salmon.html + manual: https://salmon.readthedocs.io/en/latest/salmon.html + doi: 10.1038/nmeth.4197 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - reads: + type: file + description: | + List of input FastQ files of size 1 and 2 for single-end and paired-end data, + respectively. + - index: + type: directory + description: Folder containing the star index files + - gtf: + type: file + description: GTF of the reference transcriptome + - transcriptome_fasta: + type: file + description: Fasta file of the reference transcriptome + - alignment_mode: + type: boolean + description: whether to run salmon in alignment mode + - lib_type: + type: string + description: | + Override library type inferred based on strandedness defined in meta object + +output: + - sample_output: + type: directory + description: Folder containing the quantification results for a specific sample + pattern: "${prefix}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" + +authors: + - "@kevinmenden" + - "@drpatelh" diff --git a/modules/nf-core/modules/samtools/flagstat/functions.nf b/modules/nf-core/modules/samtools/flagstat/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/samtools/flagstat/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/samtools/flagstat/main.nf b/modules/nf-core/modules/samtools/flagstat/main.nf new file mode 100644 index 000000000..a66ea56df --- /dev/null +++ b/modules/nf-core/modules/samtools/flagstat/main.nf @@ -0,0 +1,34 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process SAMTOOLS_FLAGSTAT { + tag "$meta.id" + label 'process_low' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::samtools=1.12" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/samtools:1.12--hd5e65b6_0" + } else { + container "quay.io/biocontainers/samtools:1.12--hd5e65b6_0" + } + + input: + tuple val(meta), path(bam), path(bai) + + output: + tuple val(meta), path("*.flagstat"), emit: flagstat + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + """ + samtools flagstat $bam > ${bam}.flagstat + echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/samtools/flagstat/meta.yml b/modules/nf-core/modules/samtools/flagstat/meta.yml new file mode 100644 index 000000000..8414bf54b --- /dev/null +++ b/modules/nf-core/modules/samtools/flagstat/meta.yml @@ -0,0 +1,48 @@ +name: samtools_flagstat +description: Counts the number of alignments in a BAM/CRAM/SAM file for each FLAG type +keywords: + - stats + - mapping + - counts + - bam + - sam + - cram +tools: + - samtools: + description: | + SAMtools is a set of utilities for interacting with and post-processing + short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. + These files are generated as output by short read aligners like BWA. + homepage: http://www.htslib.org/ + documentation: hhttp://www.htslib.org/doc/samtools.html + doi: 10.1093/bioinformatics/btp352 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: BAM/CRAM/SAM file + pattern: "*.{bam,cram,sam}" + - bai: + type: file + description: Index for BAM/CRAM/SAM file + pattern: "*.{bai,crai,sai}" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - flagstat: + type: file + description: File containing samtools flagstat output + pattern: "*.{flagstat}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" diff --git a/modules/nf-core/modules/samtools/idxstats/functions.nf b/modules/nf-core/modules/samtools/idxstats/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/samtools/idxstats/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/samtools/idxstats/main.nf b/modules/nf-core/modules/samtools/idxstats/main.nf new file mode 100644 index 000000000..ff3cd9a68 --- /dev/null +++ b/modules/nf-core/modules/samtools/idxstats/main.nf @@ -0,0 +1,34 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process SAMTOOLS_IDXSTATS { + tag "$meta.id" + label 'process_low' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::samtools=1.12" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/samtools:1.12--hd5e65b6_0" + } else { + container "quay.io/biocontainers/samtools:1.12--hd5e65b6_0" + } + + input: + tuple val(meta), path(bam), path(bai) + + output: + tuple val(meta), path("*.idxstats"), emit: idxstats + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + """ + samtools idxstats $bam > ${bam}.idxstats + echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/samtools/idxstats/meta.yml b/modules/nf-core/modules/samtools/idxstats/meta.yml new file mode 100644 index 000000000..530d07724 --- /dev/null +++ b/modules/nf-core/modules/samtools/idxstats/meta.yml @@ -0,0 +1,49 @@ +name: samtools_idxstats +description: Reports alignment summary statistics for a BAM/CRAM/SAM file +keywords: + - stats + - mapping + - counts + - chromosome + - bam + - sam + - cram +tools: + - samtools: + description: | + SAMtools is a set of utilities for interacting with and post-processing + short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. + These files are generated as output by short read aligners like BWA. + homepage: http://www.htslib.org/ + documentation: hhttp://www.htslib.org/doc/samtools.html + doi: 10.1093/bioinformatics/btp352 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: BAM/CRAM/SAM file + pattern: "*.{bam,cram,sam}" + - bai: + type: file + description: Index for BAM/CRAM/SAM file + pattern: "*.{bai,crai,sai}" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - idxstats: + type: file + description: File containing samtools idxstats output + pattern: "*.{idxstats}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" diff --git a/modules/nf-core/modules/samtools/index/functions.nf b/modules/nf-core/modules/samtools/index/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/samtools/index/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/samtools/index/main.nf b/modules/nf-core/modules/samtools/index/main.nf new file mode 100644 index 000000000..778e9384e --- /dev/null +++ b/modules/nf-core/modules/samtools/index/main.nf @@ -0,0 +1,35 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process SAMTOOLS_INDEX { + tag "$meta.id" + label 'process_low' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::samtools=1.12" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/samtools:1.12--hd5e65b6_0" + } else { + container "quay.io/biocontainers/samtools:1.12--hd5e65b6_0" + } + + input: + tuple val(meta), path(bam) + + output: + tuple val(meta), path("*.bai"), optional:true, emit: bai + tuple val(meta), path("*.csi"), optional:true, emit: csi + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + """ + samtools index $options.args $bam + echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/samtools/index/meta.yml b/modules/nf-core/modules/samtools/index/meta.yml new file mode 100644 index 000000000..5d076e3be --- /dev/null +++ b/modules/nf-core/modules/samtools/index/meta.yml @@ -0,0 +1,47 @@ +name: samtools_index +description: Index SAM/BAM/CRAM file +keywords: + - index + - bam + - sam + - cram +tools: + - samtools: + description: | + SAMtools is a set of utilities for interacting with and post-processing + short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. + These files are generated as output by short read aligners like BWA. + homepage: http://www.htslib.org/ + documentation: hhttp://www.htslib.org/doc/samtools.html + doi: 10.1093/bioinformatics/btp352 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: BAM/CRAM/SAM file + pattern: "*.{bam,cram,sam}" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bai: + type: file + description: BAM/CRAM/SAM index file + pattern: "*.{bai,crai,sai}" + - csi: + type: file + description: CSI index file + pattern: "*.{csi}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" + - "@ewels" diff --git a/modules/nf-core/modules/samtools/sort/functions.nf b/modules/nf-core/modules/samtools/sort/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/samtools/sort/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/samtools/sort/main.nf b/modules/nf-core/modules/samtools/sort/main.nf new file mode 100644 index 000000000..240e8e9f1 --- /dev/null +++ b/modules/nf-core/modules/samtools/sort/main.nf @@ -0,0 +1,35 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process SAMTOOLS_SORT { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::samtools=1.12" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/samtools:1.12--hd5e65b6_0" + } else { + container "quay.io/biocontainers/samtools:1.12--hd5e65b6_0" + } + + input: + tuple val(meta), path(bam) + + output: + tuple val(meta), path("*.bam"), emit: bam + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + samtools sort $options.args -@ $task.cpus -o ${prefix}.bam -T $prefix $bam + echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/samtools/sort/meta.yml b/modules/nf-core/modules/samtools/sort/meta.yml new file mode 100644 index 000000000..704e8c1f3 --- /dev/null +++ b/modules/nf-core/modules/samtools/sort/meta.yml @@ -0,0 +1,43 @@ +name: samtools_sort +description: Sort SAM/BAM/CRAM file +keywords: + - sort + - bam + - sam + - cram +tools: + - samtools: + description: | + SAMtools is a set of utilities for interacting with and post-processing + short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. + These files are generated as output by short read aligners like BWA. + homepage: http://www.htslib.org/ + documentation: hhttp://www.htslib.org/doc/samtools.html + doi: 10.1093/bioinformatics/btp352 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: BAM/CRAM/SAM file + pattern: "*.{bam,cram,sam}" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: Sorted BAM/CRAM/SAM file + pattern: "*.{bam,cram,sam}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" + - "@ewels" diff --git a/modules/nf-core/modules/samtools/stats/functions.nf b/modules/nf-core/modules/samtools/stats/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/samtools/stats/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/samtools/stats/main.nf b/modules/nf-core/modules/samtools/stats/main.nf new file mode 100644 index 000000000..6bb0a4c78 --- /dev/null +++ b/modules/nf-core/modules/samtools/stats/main.nf @@ -0,0 +1,34 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process SAMTOOLS_STATS { + tag "$meta.id" + label 'process_low' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::samtools=1.12" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/samtools:1.12--hd5e65b6_0" + } else { + container "quay.io/biocontainers/samtools:1.12--hd5e65b6_0" + } + + input: + tuple val(meta), path(bam), path(bai) + + output: + tuple val(meta), path("*.stats"), emit: stats + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + """ + samtools stats $bam > ${bam}.stats + echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/samtools/stats/meta.yml b/modules/nf-core/modules/samtools/stats/meta.yml new file mode 100644 index 000000000..b549ff5c8 --- /dev/null +++ b/modules/nf-core/modules/samtools/stats/meta.yml @@ -0,0 +1,47 @@ +name: samtools_stats +description: Produces comprehensive statistics from SAM/BAM/CRAM file +keywords: + - statistics + - counts + - bam + - sam + - cram +tools: + - samtools: + description: | + SAMtools is a set of utilities for interacting with and post-processing + short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. + These files are generated as output by short read aligners like BWA. + homepage: http://www.htslib.org/ + documentation: hhttp://www.htslib.org/doc/samtools.html + doi: 10.1093/bioinformatics/btp352 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: BAM/CRAM/SAM file + pattern: "*.{bam,cram,sam}" + - bai: + type: file + description: Index for BAM/CRAM/SAM file + pattern: "*.{bai,crai,sai}" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - stats: + type: file + description: File containing samtools stats output + pattern: "*.{stats}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" diff --git a/modules/nf-core/modules/sortmerna/functions.nf b/modules/nf-core/modules/sortmerna/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/sortmerna/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/sortmerna/main.nf b/modules/nf-core/modules/sortmerna/main.nf new file mode 100644 index 000000000..32ca4ca9a --- /dev/null +++ b/modules/nf-core/modules/sortmerna/main.nf @@ -0,0 +1,73 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process SORTMERNA { + tag "$meta.id" + label "process_high" + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::sortmerna=4.2.0" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/sortmerna:4.2.0--0" + } else { + container "quay.io/biocontainers/sortmerna:4.2.0--0" + } + + input: + tuple val(meta), path(reads) + path fasta + + output: + tuple val(meta), path("*.fastq.gz"), emit: reads + tuple val(meta), path("*.log") , emit: log + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + + def Refs = "" + for (i=0; i ${prefix}.fastq.gz + mv rRNA_reads.log ${prefix}.sortmerna.log + + echo \$(sortmerna --version 2>&1) | sed 's/^.*SortMeRNA version //; s/ Build Date.*\$//' > ${software}.version.txt + """ + } else { + """ + sortmerna \\ + $Refs \\ + --reads ${reads[0]} \\ + --reads ${reads[1]} \\ + --threads $task.cpus \\ + --workdir . \\ + --aligned rRNA_reads \\ + --other non_rRNA_reads \\ + --paired_in \\ + --out2 \\ + $options.args + + gzip -f < non_rRNA_reads_fwd.fq > ${prefix}_1.fastq.gz + gzip -f < non_rRNA_reads_rev.fq > ${prefix}_2.fastq.gz + mv rRNA_reads.log ${prefix}.sortmerna.log + + echo \$(sortmerna --version 2>&1) | sed 's/^.*SortMeRNA version //; s/ Build Date.*\$//' > ${software}.version.txt + """ + } +} diff --git a/modules/nf-core/modules/star/align/functions.nf b/modules/nf-core/modules/star/align/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/star/align/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/star/align/main.nf b/modules/nf-core/modules/star/align/main.nf new file mode 100644 index 000000000..e85ddb79d --- /dev/null +++ b/modules/nf-core/modules/star/align/main.nf @@ -0,0 +1,71 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process STAR_ALIGN { + tag "$meta.id" + label 'process_high' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + // Note: 2.7X indices incompatible with AWS iGenomes. + conda (params.enable_conda ? 'bioconda::star=2.6.1d' : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container 'https://depot.galaxyproject.org/singularity/star:2.6.1d--0' + } else { + container 'quay.io/biocontainers/star:2.6.1d--0' + } + + input: + tuple val(meta), path(reads) + path index + path gtf + + output: + tuple val(meta), path('*d.out.bam') , emit: bam + tuple val(meta), path('*Log.final.out') , emit: log_final + tuple val(meta), path('*Log.out') , emit: log_out + tuple val(meta), path('*Log.progress.out'), emit: log_progress + path '*.version.txt' , emit: version + + tuple val(meta), path('*sortedByCoord.out.bam') , optional:true, emit: bam_sorted + tuple val(meta), path('*toTranscriptome.out.bam'), optional:true, emit: bam_transcript + tuple val(meta), path('*Aligned.unsort.out.bam') , optional:true, emit: bam_unsorted + tuple val(meta), path('*fastq.gz') , optional:true, emit: fastq + tuple val(meta), path('*.tab') , optional:true, emit: tab + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + def ignore_gtf = params.star_ignore_sjdbgtf ? '' : "--sjdbGTFfile $gtf" + def seq_center = params.seq_center ? "--outSAMattrRGline ID:$prefix 'CN:$params.seq_center' 'SM:$prefix'" : "--outSAMattrRGline ID:$prefix 'SM:$prefix'" + def out_sam_type = (options.args.contains('--outSAMtype')) ? '' : '--outSAMtype BAM Unsorted' + def mv_unsorted_bam = (options.args.contains('--outSAMtype BAM Unsorted SortedByCoordinate')) ? "mv ${prefix}.Aligned.out.bam ${prefix}.Aligned.unsort.out.bam" : '' + """ + STAR \\ + --genomeDir $index \\ + --readFilesIn $reads \\ + --runThreadN $task.cpus \\ + --outFileNamePrefix $prefix. \\ + $out_sam_type \\ + $ignore_gtf \\ + $seq_center \\ + $options.args + + $mv_unsorted_bam + + if [ -f ${prefix}.Unmapped.out.mate1 ]; then + mv ${prefix}.Unmapped.out.mate1 ${prefix}.unmapped_1.fastq + gzip ${prefix}.unmapped_1.fastq + fi + if [ -f ${prefix}.Unmapped.out.mate2 ]; then + mv ${prefix}.Unmapped.out.mate2 ${prefix}.unmapped_2.fastq + gzip ${prefix}.unmapped_2.fastq + fi + + STAR --version | sed -e "s/STAR_//g" > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/star/align/meta.yml b/modules/nf-core/modules/star/align/meta.yml new file mode 100644 index 000000000..01bc2ecff --- /dev/null +++ b/modules/nf-core/modules/star/align/meta.yml @@ -0,0 +1,75 @@ +name: star_align +description: Align reads to a reference genome using STAR +keywords: + - align + - fasta + - genome + - reference +tools: + - star: + description: | + STAR is a software package for mapping DNA sequences against + a large reference genome, such as the human genome. + homepage: https://github.com/alexdobin/STAR + manual: https://github.com/alexdobin/STAR/blob/master/doc/STARmanual.pdf + doi: 10.1093/bioinformatics/bts635 +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - reads: + type: file + description: | + List of input FastQ files of size 1 and 2 for single-end and paired-end data, + respectively. + - index: + type: directory + description: STAR genome index + pattern: "star" +output: + - bam: + type: file + description: Output BAM file containing read alignments + pattern: "*.{bam}" + - log_final: + type: file + description: STAR final log file + pattern: "*Log.final.out" + - log_out: + type: file + description: STAR lot out file + pattern: "*Log.out" + - log_progress: + type: file + description: STAR log progress file + pattern: "*Log.progress.out" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" + - bam_sorted: + type: file + description: Sorted BAM file of read alignments (optional) + pattern: "*sortedByCoord.out.bam" + - bam_transcript: + type: file + description: Output BAM file of transcriptome alignment (optional) + pattern: "*toTranscriptome.out.bam" + - bam_unsorted: + type: file + description: Unsorted BAM file of read alignments (optional) + pattern: "*Aligned.unsort.out.bam" + - fastq: + type: file + description: Unmapped FastQ files (optional) + pattern: "*fastq.gz" + - tab: + type: file + description: STAR output tab file(s) (optional) + pattern: "*.tab" + +authors: + - "@kevinmenden" + - "@drpatelh" diff --git a/modules/nf-core/modules/star/genomegenerate/functions.nf b/modules/nf-core/modules/star/genomegenerate/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/star/genomegenerate/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/star/genomegenerate/main.nf b/modules/nf-core/modules/star/genomegenerate/main.nf new file mode 100644 index 000000000..b440b4158 --- /dev/null +++ b/modules/nf-core/modules/star/genomegenerate/main.nf @@ -0,0 +1,67 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process STAR_GENOMEGENERATE { + tag "$fasta" + label 'process_high' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:'index', meta:[:], publish_by_meta:[]) } + + // Note: 2.7X indices incompatible with AWS iGenomes. + conda (params.enable_conda ? "bioconda::star=2.6.1d bioconda::samtools=1.10 conda-forge::gawk=5.1.0" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0" + } else { + container "quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0" + } + + input: + path fasta + path gtf + + output: + path "star" , emit: index + path "*.version.txt", emit: version + + script: + def software = getSoftwareName(task.process) + def memory = task.memory ? "--limitGenomeGenerateRAM ${task.memory.toBytes() - 100000000}" : '' + def args = options.args.tokenize() + if (args.contains('--genomeSAindexNbases')) { + """ + mkdir star + STAR \\ + --runMode genomeGenerate \\ + --genomeDir star/ \\ + --genomeFastaFiles $fasta \\ + --sjdbGTFfile $gtf \\ + --runThreadN $task.cpus \\ + $memory \\ + $options.args + + STAR --version | sed -e "s/STAR_//g" > ${software}.version.txt + """ + } else { + """ + samtools faidx $fasta + NUM_BASES=`gawk '{sum = sum + \$2}END{if ((log(sum)/log(2))/2 - 1 > 14) {printf "%.0f", 14} else {printf "%.0f", (log(sum)/log(2))/2 - 1}}' ${fasta}.fai` + + mkdir star + STAR \\ + --runMode genomeGenerate \\ + --genomeDir star/ \\ + --genomeFastaFiles $fasta \\ + --sjdbGTFfile $gtf \\ + --runThreadN $task.cpus \\ + --genomeSAindexNbases \$NUM_BASES \\ + $memory \\ + $options.args + + STAR --version | sed -e "s/STAR_//g" > ${software}.version.txt + """ + } +} diff --git a/modules/nf-core/modules/star/genomegenerate/meta.yml b/modules/nf-core/modules/star/genomegenerate/meta.yml new file mode 100644 index 000000000..aae0219bc --- /dev/null +++ b/modules/nf-core/modules/star/genomegenerate/meta.yml @@ -0,0 +1,36 @@ +name: star_genomegenerate +description: Create index for STAR +keywords: + - index + - fasta + - genome + - reference +tools: + - star: + description: | + STAR is a software package for mapping DNA sequences against + a large reference genome, such as the human genome. + homepage: https://github.com/alexdobin/STAR + manual: https://github.com/alexdobin/STAR/blob/master/doc/STARmanual.pdf + doi: 10.1093/bioinformatics/bts635 +input: + - fasta: + type: file + description: Fasta file of the reference genome + - gtf: + type: file + description: GTF file of the reference genome + +output: + - index: + type: directory + description: Folder containing the star index files + pattern: "star" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" + +authors: + - "@kevinmenden" + - "@drpatelh" diff --git a/modules/nf-core/modules/stringtie/stringtie/functions.nf b/modules/nf-core/modules/stringtie/stringtie/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/stringtie/stringtie/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/stringtie/stringtie/main.nf b/modules/nf-core/modules/stringtie/stringtie/main.nf new file mode 100644 index 000000000..eb751321e --- /dev/null +++ b/modules/nf-core/modules/stringtie/stringtie/main.nf @@ -0,0 +1,55 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process STRINGTIE { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::stringtie=2.1.4" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/stringtie:2.1.4--h7e0af3c_0" + } else { + container "quay.io/biocontainers/stringtie:2.1.4--h7e0af3c_0" + } + + input: + tuple val(meta), path(bam) + path gtf + + output: + tuple val(meta), path("*.coverage.gtf") , emit: coverage_gtf + tuple val(meta), path("*.transcripts.gtf"), emit: transcript_gtf + tuple val(meta), path("*.abundance.txt") , emit: abundance + tuple val(meta), path("*.ballgown") , emit: ballgown + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + + def strandedness = '' + if (meta.strandedness == 'forward') { + strandedness = '--fr' + } else if (meta.strandedness == 'reverse') { + strandedness = '--rf' + } + """ + stringtie \\ + $bam \\ + $strandedness \\ + -G $gtf \\ + -o ${prefix}.transcripts.gtf \\ + -A ${prefix}.gene.abundance.txt \\ + -C ${prefix}.coverage.gtf \\ + -b ${prefix}.ballgown \\ + $options.args + + stringtie --version > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/stringtie/stringtie/meta.yml b/modules/nf-core/modules/stringtie/stringtie/meta.yml new file mode 100644 index 000000000..52ec899d9 --- /dev/null +++ b/modules/nf-core/modules/stringtie/stringtie/meta.yml @@ -0,0 +1,56 @@ +name: stringtie +description: Transcript assembly and quantification for RNA-Se +keywords: + - transcript + - assembly + - quantification + - gtf + +tools: + - stringtie2: + description: | + Transcript assembly and quantification for RNA-Seq + homepage: https://ccb.jhu.edu/software/stringtie/index.shtml + documentation: https://ccb.jhu.edu/software/stringtie/index.shtml?t=manual +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: | + Stringtie transcript gtf output(s). + - gtf: + type: file + description: | + Annotation gtf file. +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - transcript_gtf: + type: file + description: transcript gtf + pattern: "*.{transcripts.gtf}" + - coverage_gtf: + type: file + description: coverage gtf + pattern: "*.{coverage.gtf}" + - abudance: + type: file + description: abudance + pattern: "*.{abudance.txt}" + - ballgown: + type: file + description: for running ballgown + pattern: "*.{ballgown}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" diff --git a/modules/nf-core/modules/subread/featurecounts/functions.nf b/modules/nf-core/modules/subread/featurecounts/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/subread/featurecounts/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/subread/featurecounts/main.nf b/modules/nf-core/modules/subread/featurecounts/main.nf new file mode 100644 index 000000000..cde14a74b --- /dev/null +++ b/modules/nf-core/modules/subread/featurecounts/main.nf @@ -0,0 +1,52 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process SUBREAD_FEATURECOUNTS { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::subread=2.0.1" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/subread:2.0.1--hed695b0_0" + } else { + container "quay.io/biocontainers/subread:2.0.1--hed695b0_0" + } + + input: + tuple val(meta), path(bams), path(annotation) + + output: + tuple val(meta), path("*featureCounts.txt") , emit: counts + tuple val(meta), path("*featureCounts.txt.summary"), emit: summary + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + def paired_end = meta.single_end ? '' : '-p' + + def strandedness = 0 + if (meta.strandedness == 'forward') { + strandedness = 1 + } else if (meta.strandedness == 'reverse') { + strandedness = 2 + } + """ + featureCounts \\ + $options.args \\ + $paired_end \\ + -T $task.cpus \\ + -a $annotation \\ + -s $strandedness \\ + -o ${prefix}.featureCounts.txt \\ + ${bams.join(' ')} + + echo \$(featureCounts -v 2>&1) | sed -e "s/featureCounts v//g" > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/subread/featurecounts/meta.yml b/modules/nf-core/modules/subread/featurecounts/meta.yml new file mode 100644 index 000000000..d24f70bdd --- /dev/null +++ b/modules/nf-core/modules/subread/featurecounts/meta.yml @@ -0,0 +1,52 @@ +name: subread_featurecounts +description: Count reads that map to genomic features +keywords: + - counts + - fasta + - genome + - reference + +tools: + - featurecounts: + description: featureCounts is a highly efficient general-purpose read summarization program that counts mapped reads for genomic features such as genes, exons, promoter, gene bodies, genomic bins and chromosomal locations. It can be used to count both RNA-seq and genomic DNA-seq reads. + homepage: http://bioinf.wehi.edu.au/featureCounts/ + documentation: http://bioinf.wehi.edu.au/subread-package/SubreadUsersGuide.pdf + doi: "10.1093/bioinformatics/btt656" + licence: ['GPL v3'] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: BAM/SAM file containing read alignments + pattern: "*.{bam}" + - annotation: + type: file + description: Genomic features annotation in GTF or SAF + pattern: "*.{gtf,saf}" + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - counts: + type: file + description: Counts of reads mapping to features + pattern: "*featureCounts.txt" + - summary: + type: file + description: Summary log file + pattern: "*.featureCounts.txt.summary" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" + +authors: + - "@ntoda03" diff --git a/modules/nf-core/modules/trimgalore/functions.nf b/modules/nf-core/modules/trimgalore/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/trimgalore/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/trimgalore/main.nf b/modules/nf-core/modules/trimgalore/main.nf new file mode 100644 index 000000000..44b36e714 --- /dev/null +++ b/modules/nf-core/modules/trimgalore/main.nf @@ -0,0 +1,83 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process TRIMGALORE { + tag "$meta.id" + label 'process_high' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::trim-galore=0.6.6" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/trim-galore:0.6.6--0" + } else { + container "quay.io/biocontainers/trim-galore:0.6.6--0" + } + + input: + tuple val(meta), path(reads) + + output: + tuple val(meta), path("*.fq.gz") , emit: reads + tuple val(meta), path("*report.txt"), emit: log + path "*.version.txt" , emit: version + + tuple val(meta), path("*.html"), emit: html optional true + tuple val(meta), path("*.zip") , emit: zip optional true + + script: + // Calculate number of --cores for TrimGalore based on value of task.cpus + // See: https://github.com/FelixKrueger/TrimGalore/blob/master/Changelog.md#version-060-release-on-1-mar-2019 + // See: https://github.com/nf-core/atacseq/pull/65 + def cores = 1 + if (task.cpus) { + cores = (task.cpus as int) - 4 + if (meta.single_end) cores = (task.cpus as int) - 3 + if (cores < 1) cores = 1 + if (cores > 4) cores = 4 + } + + // Clipping presets have to be evaluated in the context of SE/PE + def c_r1 = params.clip_r1 > 0 ? "--clip_r1 ${params.clip_r1}" : '' + def c_r2 = params.clip_r2 > 0 ? "--clip_r2 ${params.clip_r2}" : '' + def tpc_r1 = params.three_prime_clip_r1 > 0 ? "--three_prime_clip_r1 ${params.three_prime_clip_r1}" : '' + def tpc_r2 = params.three_prime_clip_r2 > 0 ? "--three_prime_clip_r2 ${params.three_prime_clip_r2}" : '' + + // Added soft-links to original fastqs for consistent naming in MultiQC + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + if (meta.single_end) { + """ + [ ! -f ${prefix}.fastq.gz ] && ln -s $reads ${prefix}.fastq.gz + trim_galore \\ + $options.args \\ + --cores $cores \\ + --gzip \\ + $c_r1 \\ + $tpc_r1 \\ + ${prefix}.fastq.gz + echo \$(trim_galore --version 2>&1) | sed 's/^.*version //; s/Last.*\$//' > ${software}.version.txt + """ + } else { + """ + [ ! -f ${prefix}_1.fastq.gz ] && ln -s ${reads[0]} ${prefix}_1.fastq.gz + [ ! -f ${prefix}_2.fastq.gz ] && ln -s ${reads[1]} ${prefix}_2.fastq.gz + trim_galore \\ + $options.args \\ + --cores $cores \\ + --paired \\ + --gzip \\ + $c_r1 \\ + $c_r2 \\ + $tpc_r1 \\ + $tpc_r2 \\ + ${prefix}_1.fastq.gz \\ + ${prefix}_2.fastq.gz + echo \$(trim_galore --version 2>&1) | sed 's/^.*version //; s/Last.*\$//' > ${software}.version.txt + """ + } +} diff --git a/modules/nf-core/modules/trimgalore/meta.yml b/modules/nf-core/modules/trimgalore/meta.yml new file mode 100644 index 000000000..735387076 --- /dev/null +++ b/modules/nf-core/modules/trimgalore/meta.yml @@ -0,0 +1,58 @@ +name: trimgalore +description: Trim FastQ files using Trim Galore! +keywords: + - trimming + - adapters + - sequencing adapters + - fastq +tools: + - trimgalore: + description: | + A wrapper tool around Cutadapt and FastQC to consistently apply quality + and adapter trimming to FastQ files, with some extra functionality for + MspI-digested RRBS-type (Reduced Representation Bisufite-Seq) libraries. + homepage: https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/ + documentation: https://github.com/FelixKrueger/TrimGalore/blob/master/Docs/Trim_Galore_User_Guide.md +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - reads: + type: file + description: | + List of input FastQ files of size 1 and 2 for single-end and paired-end data, + respectively. +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - reads: + type: file + description: | + List of input adapter trimmed FastQ files of size 1 and 2 for + single-end and paired-end data, respectively. + pattern: "*.{fq.gz}" + - html: + type: file + description: FastQC report (optional) + pattern: "*_{fastqc.html}" + - zip: + type: file + description: FastQC report archive (optional) + pattern: "*_{fastqc.zip}" + - log: + type: file + description: Trim Galore! trimming report + pattern: "*_{report.txt}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" + - "@ewels" + - "@FelixKrueger" diff --git a/modules/nf-core/modules/ucsc/bedclip/functions.nf b/modules/nf-core/modules/ucsc/bedclip/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/ucsc/bedclip/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/ucsc/bedclip/main.nf b/modules/nf-core/modules/ucsc/bedclip/main.nf new file mode 100644 index 000000000..d1a47554e --- /dev/null +++ b/modules/nf-core/modules/ucsc/bedclip/main.nf @@ -0,0 +1,42 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +def VERSION = '377' + +process UCSC_BEDCLIP { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::ucsc-bedclip=377" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/ucsc-bedclip:377--h0b8a92a_2" + } else { + container "quay.io/biocontainers/ucsc-bedclip:377--h0b8a92a_2" + } + + input: + tuple val(meta), path(bedgraph) + path sizes + + output: + tuple val(meta), path("*.bedGraph"), emit: bedgraph + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + bedClip \\ + $bedgraph \\ + $sizes \\ + ${prefix}.bedGraph + + echo $VERSION > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/ucsc/bedclip/meta.yml b/modules/nf-core/modules/ucsc/bedclip/meta.yml new file mode 100644 index 000000000..f20b4617e --- /dev/null +++ b/modules/nf-core/modules/ucsc/bedclip/meta.yml @@ -0,0 +1,41 @@ +name: ucsc_bedclip +description: See http://hgdownload.cse.ucsc.edu/admin/exe/ +keywords: + - sort +tools: + - ucsc: + description: Remove lines from bed file that refer to off-chromosome locations. + homepage: None + documentation: None + tool_dev_url: None + doi: "" + licence: ['varies; see http://genome.ucsc.edu/license'] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bedgraph: + type: file + description: bedGraph file + pattern: "*.{bedgraph}" + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" + - bedgraph: + type: file + description: bedGraph file + pattern: "*.{bedgraph}" + +authors: + - "@drpatelh" diff --git a/modules/nf-core/modules/ucsc/bedgraphtobigwig/functions.nf b/modules/nf-core/modules/ucsc/bedgraphtobigwig/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/ucsc/bedgraphtobigwig/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/ucsc/bedgraphtobigwig/main.nf b/modules/nf-core/modules/ucsc/bedgraphtobigwig/main.nf new file mode 100644 index 000000000..e5fe3b7f2 --- /dev/null +++ b/modules/nf-core/modules/ucsc/bedgraphtobigwig/main.nf @@ -0,0 +1,38 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +def VERSION = '377' + +process UCSC_BEDGRAPHTOBIGWIG { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::ucsc-bedgraphtobigwig=377" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/ucsc-bedgraphtobigwig:377--h446ed27_1" + } else { + container "quay.io/biocontainers/ucsc-bedgraphtobigwig:377--h446ed27_1" + } + + input: + tuple val(meta), path(bedgraph) + path sizes + + output: + tuple val(meta), path("*.bigWig"), emit: bigwig + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + bedGraphToBigWig $bedgraph $sizes ${prefix}.bigWig + echo $VERSION > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/ucsc/bedgraphtobigwig/meta.yml b/modules/nf-core/modules/ucsc/bedgraphtobigwig/meta.yml new file mode 100644 index 000000000..31365f48f --- /dev/null +++ b/modules/nf-core/modules/ucsc/bedgraphtobigwig/meta.yml @@ -0,0 +1,46 @@ +name: ucsc_bedgraphtobigwig +description: Convert a bedGraph file to bigWig format. +keywords: + - bedgraph + - bigwig +tools: + - ucsc: + description: Convert a bedGraph file to bigWig format. + homepage: None + documentation: None + tool_dev_url: None + doi: "" + licence: ["varies; see http://genome.ucsc.edu/license"] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bedgraph: + type: file + description: bedGraph file + pattern: "*.{bedGraph}" + - sizes: + type: file + description: chromosome sizes file + pattern: "*.{sizes}" + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" + - bigwig: + type: file + description: bigWig file + pattern: "*.{bigWig}" + +authors: + - "@drpatelh" diff --git a/modules/nf-core/modules/umitools/dedup/functions.nf b/modules/nf-core/modules/umitools/dedup/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/umitools/dedup/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/umitools/dedup/main.nf b/modules/nf-core/modules/umitools/dedup/main.nf new file mode 100644 index 000000000..93ea6d451 --- /dev/null +++ b/modules/nf-core/modules/umitools/dedup/main.nf @@ -0,0 +1,41 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process UMITOOLS_DEDUP { + tag "$meta.id" + label "process_medium" + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::umi_tools=1.1.1" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/umi_tools:1.1.1--py38h0213d0e_1" + } else { + container "quay.io/biocontainers/umi_tools:1.1.1--py38h0213d0e_1" + } + + input: + tuple val(meta), path(bam), path(bai) + + output: + tuple val(meta), path("*.bam"), emit: bam + tuple val(meta), path("*.tsv"), emit: tsv + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + umi_tools dedup \\ + -I $bam \\ + -S ${prefix}.bam \\ + --output-stats=$prefix \\ + $options.args \\ + + umi_tools --version | sed -e "s/UMI-tools version: //g" > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/umitools/extract/functions.nf b/modules/nf-core/modules/umitools/extract/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/umitools/extract/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/umitools/extract/main.nf b/modules/nf-core/modules/umitools/extract/main.nf new file mode 100644 index 000000000..581f41c3c --- /dev/null +++ b/modules/nf-core/modules/umitools/extract/main.nf @@ -0,0 +1,57 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process UMITOOLS_EXTRACT { + tag "$meta.id" + label "process_low" + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } + + conda (params.enable_conda ? "bioconda::umi_tools=1.1.1" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/umi_tools:1.1.1--py38h0213d0e_1" + } else { + container "quay.io/biocontainers/umi_tools:1.1.1--py38h0213d0e_1" + } + + input: + tuple val(meta), path(reads) + + output: + tuple val(meta), path("*.fastq.gz"), emit: reads + tuple val(meta), path("*.log") , emit: log + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + if (meta.single_end) { + """ + umi_tools \\ + extract \\ + -I $reads \\ + -S ${prefix}.umi_extract.fastq.gz \\ + $options.args \\ + > ${prefix}.umi_extract.log + + umi_tools --version | sed -e "s/UMI-tools version: //g" > ${software}.version.txt + """ + } else { + """ + umi_tools \\ + extract \\ + -I ${reads[0]} \\ + --read2-in=${reads[1]} \\ + -S ${prefix}.umi_extract_1.fastq.gz \\ + --read2-out=${prefix}.umi_extract_2.fastq.gz \\ + $options.args \\ + > ${prefix}.umi_extract.log + + umi_tools --version | sed -e "s/UMI-tools version: //g" > ${software}.version.txt + """ + } +} diff --git a/modules/nf-core/modules/untar/functions.nf b/modules/nf-core/modules/untar/functions.nf new file mode 100644 index 000000000..da9da093d --- /dev/null +++ b/modules/nf-core/modules/untar/functions.nf @@ -0,0 +1,68 @@ +// +// Utility functions used in nf-core DSL2 module files +// + +// +// Extract name of software tool from process name using $task.process +// +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +// +// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules +// +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.args3 = args.args3 ?: '' + options.publish_by_meta = args.publish_by_meta ?: [] + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +// +// Tidy up and join elements of a list to return a path string +// +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +// +// Function to save/publish module results +// +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_meta) { + def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta + for (key in key_list) { + if (args.meta && key instanceof String) { + def path = key + if (args.meta.containsKey(key)) { + path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key] + } + path = path instanceof String ? path : '' + path_list.add(path) + } + } + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/modules/nf-core/modules/untar/main.nf b/modules/nf-core/modules/untar/main.nf new file mode 100644 index 000000000..fc6d7ec53 --- /dev/null +++ b/modules/nf-core/modules/untar/main.nf @@ -0,0 +1,35 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +options = initOptions(params.options) + +process UNTAR { + tag "$archive" + label 'process_low' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) } + + conda (params.enable_conda ? "conda-forge::sed=4.7" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img" + } else { + container "biocontainers/biocontainers:v1.2.0_cv1" + } + + input: + path archive + + output: + path "$untar" , emit: untar + path "*.version.txt", emit: version + + script: + def software = getSoftwareName(task.process) + untar = archive.toString() - '.tar.gz' + """ + tar -xzvf $options.args $archive + echo \$(tar --version 2>&1) | sed 's/^.*(GNU tar) //; s/ Copyright.*\$//' > ${software}.version.txt + """ +} diff --git a/modules/nf-core/modules/untar/meta.yml b/modules/nf-core/modules/untar/meta.yml new file mode 100644 index 000000000..af4674f09 --- /dev/null +++ b/modules/nf-core/modules/untar/meta.yml @@ -0,0 +1,27 @@ +name: untar +description: Extract files. +keywords: + - untar + - uncompress +tools: + - untar: + description: | + Extract tar.gz files. + documentation: https://www.gnu.org/software/tar/manual/ +input: + - archive: + type: file + description: File to be untar + pattern: "*.{tar}.{gz}" +output: + - untar: + type: file + description: + pattern: "*.*" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@joseespinosa" + - "@drpatelh" From 0128818e7a0f4b22e0d9cba933b9115d2a8073da Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Wed, 14 Jul 2021 16:13:26 +0100 Subject: [PATCH 10/31] Bump MultiQC version --- modules/local/multiqc.nf | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/modules/local/multiqc.nf b/modules/local/multiqc.nf index f09a797a8..654ec957a 100644 --- a/modules/local/multiqc.nf +++ b/modules/local/multiqc.nf @@ -10,11 +10,11 @@ process MULTIQC { mode: params.publish_dir_mode, saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) } - conda (params.enable_conda ? "bioconda::multiqc=1.10.1" : null) + conda (params.enable_conda ? "bioconda::multiqc=1.11" : null) if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/multiqc:1.10.1--pyhdfd78af_1" + container "https://depot.galaxyproject.org/singularity/multiqc:1.11--pyhdfd78af_0" } else { - container "quay.io/biocontainers/multiqc:1.10.1--pyhdfd78af_1" + container "quay.io/biocontainers/multiqc:1.11--pyhdfd78af_0" } input: From 47a9ceeeb777c8f936ce78101a0ee5215fd4e200 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Wed, 14 Jul 2021 17:51:01 +0100 Subject: [PATCH 11/31] Downgrade MultiQC version --- modules/local/multiqc.nf | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/modules/local/multiqc.nf b/modules/local/multiqc.nf index 654ec957a..f09a797a8 100644 --- a/modules/local/multiqc.nf +++ b/modules/local/multiqc.nf @@ -10,11 +10,11 @@ process MULTIQC { mode: params.publish_dir_mode, saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) } - conda (params.enable_conda ? "bioconda::multiqc=1.11" : null) + conda (params.enable_conda ? "bioconda::multiqc=1.10.1" : null) if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/multiqc:1.11--pyhdfd78af_0" + container "https://depot.galaxyproject.org/singularity/multiqc:1.10.1--pyhdfd78af_1" } else { - container "quay.io/biocontainers/multiqc:1.11--pyhdfd78af_0" + container "quay.io/biocontainers/multiqc:1.10.1--pyhdfd78af_1" } input: From b3256e9e24f099ffb08487317daa59efbf911418 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Fri, 16 Jul 2021 14:35:29 +0100 Subject: [PATCH 12/31] Fix #668 --- CHANGELOG.md | 13 +++++++++++++ modules.json | 4 ++-- modules/nf-core/modules/umitools/dedup/main.nf | 14 +++++++------- modules/nf-core/modules/umitools/extract/main.nf | 10 +++++----- 4 files changed, 27 insertions(+), 14 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 379c1f180..d4472cdb1 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -8,9 +8,22 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Enhancements & fixes * Updated pipeline template to [nf-core/tools 2.0.1](https://github.com/nf-core/tools/releases/tag/2.0.1) +* [[#668](https://github.com/nf-core/rnaseq/issues/668)] - Salmon quant with UMI-tools does not work ### Parameters +### Software dependencies + +Note, since the pipeline is now using Nextflow DSL2, each process will be run with its own [Biocontainer](https://biocontainers.pro/#/registry). This means that on occasion it is entirely possible for the pipeline to be using different versions of the same tool. However, the overall software dependency changes compared to the last release have been listed below for reference. + +| Dependency | Old version | New version | +|-------------|-------------|-------------| +| `umi_tools` | 1.1.1 | 1.1.2 | + +> **NB:** Dependency has been __updated__ if both old and new version information is present. +> **NB:** Dependency has been __added__ if just the new version information is present. +> **NB:** Dependency has been __removed__ if version information isn't present. + ## [[3.2](https://github.com/nf-core/rnaseq/releases/tag/3.2)] - 2021-06-18 ### Enhancements & fixes diff --git a/modules.json b/modules.json index 47c7c1fe7..0a6479e09 100644 --- a/modules.json +++ b/modules.json @@ -106,10 +106,10 @@ "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" }, "umitools/dedup": { - "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + "git_sha": "2ade120249b92e382f964bd75701befa2c2dc75d" }, "umitools/extract": { - "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + "git_sha": "2ade120249b92e382f964bd75701befa2c2dc75d" }, "untar": { "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" diff --git a/modules/nf-core/modules/umitools/dedup/main.nf b/modules/nf-core/modules/umitools/dedup/main.nf index 93ea6d451..f30ab1641 100644 --- a/modules/nf-core/modules/umitools/dedup/main.nf +++ b/modules/nf-core/modules/umitools/dedup/main.nf @@ -11,11 +11,11 @@ process UMITOOLS_DEDUP { mode: params.publish_dir_mode, saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - conda (params.enable_conda ? "bioconda::umi_tools=1.1.1" : null) + conda (params.enable_conda ? "bioconda::umi_tools=1.1.2" : null) if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/umi_tools:1.1.1--py38h0213d0e_1" + container "https://depot.galaxyproject.org/singularity/umi_tools:1.1.2--py38h4a8c8d9_0" } else { - container "quay.io/biocontainers/umi_tools:1.1.1--py38h0213d0e_1" + container "quay.io/biocontainers/umi_tools:1.1.2--py38h4a8c8d9_0" } input: @@ -23,19 +23,19 @@ process UMITOOLS_DEDUP { output: tuple val(meta), path("*.bam"), emit: bam - tuple val(meta), path("*.tsv"), emit: tsv path "*.version.txt" , emit: version script: def software = getSoftwareName(task.process) def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + def paired = meta.single_end ? "" : "--paired" """ umi_tools dedup \\ -I $bam \\ -S ${prefix}.bam \\ - --output-stats=$prefix \\ - $options.args \\ + $paired \\ + $options.args - umi_tools --version | sed -e "s/UMI-tools version: //g" > ${software}.version.txt + echo \$(umi_tools --version 2>&1) | sed 's/^.*UMI-tools version://; s/ *\$//' > ${software}.version.txt """ } diff --git a/modules/nf-core/modules/umitools/extract/main.nf b/modules/nf-core/modules/umitools/extract/main.nf index 581f41c3c..e5c4e21c8 100644 --- a/modules/nf-core/modules/umitools/extract/main.nf +++ b/modules/nf-core/modules/umitools/extract/main.nf @@ -11,11 +11,11 @@ process UMITOOLS_EXTRACT { mode: params.publish_dir_mode, saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - conda (params.enable_conda ? "bioconda::umi_tools=1.1.1" : null) + conda (params.enable_conda ? "bioconda::umi_tools=1.1.2" : null) if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/umi_tools:1.1.1--py38h0213d0e_1" + container "https://depot.galaxyproject.org/singularity/umi_tools:1.1.2--py38h4a8c8d9_0" } else { - container "quay.io/biocontainers/umi_tools:1.1.1--py38h0213d0e_1" + container "quay.io/biocontainers/umi_tools:1.1.2--py38h4a8c8d9_0" } input: @@ -38,7 +38,7 @@ process UMITOOLS_EXTRACT { $options.args \\ > ${prefix}.umi_extract.log - umi_tools --version | sed -e "s/UMI-tools version: //g" > ${software}.version.txt + echo \$(umi_tools --version 2>&1) | sed 's/^.*UMI-tools version://; s/ *\$//' > ${software}.version.txt """ } else { """ @@ -51,7 +51,7 @@ process UMITOOLS_EXTRACT { $options.args \\ > ${prefix}.umi_extract.log - umi_tools --version | sed -e "s/UMI-tools version: //g" > ${software}.version.txt + echo \$(umi_tools --version 2>&1) | sed 's/^.*UMI-tools version://; s/ *\$//' > ${software}.version.txt """ } } From 35cea2ba6bad55f54563cc35e3956cb17ae98ee9 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Fri, 16 Jul 2021 14:40:14 +0100 Subject: [PATCH 13/31] Adjust spacing --- CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index d4472cdb1..6795ab004 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -18,7 +18,7 @@ Note, since the pipeline is now using Nextflow DSL2, each process will be run wi | Dependency | Old version | New version | |-------------|-------------|-------------| -| `umi_tools` | 1.1.1 | 1.1.2 | +| `umi_tools` | 1.1.1 | 1.1.2 | > **NB:** Dependency has been __updated__ if both old and new version information is present. > **NB:** Dependency has been __added__ if just the new version information is present. From 0ade86ef6e7cf56540b0ec61d30fda8ccbc4c651 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Fri, 16 Jul 2021 15:07:13 +0100 Subject: [PATCH 14/31] Remove deleted output channel --- subworkflows/nf-core/dedup_umi_umitools.nf | 1 - 1 file changed, 1 deletion(-) diff --git a/subworkflows/nf-core/dedup_umi_umitools.nf b/subworkflows/nf-core/dedup_umi_umitools.nf index f8d9f06a0..7ed6e7a54 100644 --- a/subworkflows/nf-core/dedup_umi_umitools.nf +++ b/subworkflows/nf-core/dedup_umi_umitools.nf @@ -43,7 +43,6 @@ workflow DEDUP_UMI_UMITOOLS { emit: bam = UMITOOLS_DEDUP.out.bam // channel: [ val(meta), [ bam ] ] - tsv = UMITOOLS_DEDUP.out.tsv // channel: [ val(meta), [ tsv ] ] umitools_version = UMITOOLS_DEDUP.out.version // path: *.version.txt bai = SAMTOOLS_INDEX.out.bai // channel: [ val(meta), [ bai ] ] From 8a32800e9e23c8e38471fc6730062451cecedea2 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Tue, 20 Jul 2021 10:42:50 +0100 Subject: [PATCH 15/31] Execute email code on params.email or params.email_on_fail --- workflows/rnaseq.nf | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/workflows/rnaseq.nf b/workflows/rnaseq.nf index dbbc4f51a..8c17d5633 100755 --- a/workflows/rnaseq.nf +++ b/workflows/rnaseq.nf @@ -772,7 +772,9 @@ workflow RNASEQ { */ workflow.onComplete { - NfcoreTemplate.email(workflow, params, summary_params, projectDir, log, multiqc_report, fail_percent_mapped) + if (params.email || params.email_on_fail) { + NfcoreTemplate.email(workflow, params, summary_params, projectDir, log, multiqc_report, fail_percent_mapped) + } NfcoreTemplate.summary(workflow, params, log, fail_percent_mapped, pass_percent_mapped) } From 654d45d549c0ab80cb5fa46f3698e1b954f8f1f4 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Tue, 20 Jul 2021 11:04:27 +0100 Subject: [PATCH 16/31] Change hostname command to use babs001 --- lib/NfcoreTemplate.groovy | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/NfcoreTemplate.groovy b/lib/NfcoreTemplate.groovy index 4b317e22b..28ae774c4 100755 --- a/lib/NfcoreTemplate.groovy +++ b/lib/NfcoreTemplate.groovy @@ -24,7 +24,7 @@ class NfcoreTemplate { public static void hostName(workflow, params, log) { Map colors = logColours(params.monochrome_logs) if (params.hostnames) { - def hostname = "hostname".execute().text.trim() + def hostname = ['sh', '-c', 'echo $HOSTNAME'].execute().text.trim() params.hostnames.each { prof, hnames -> hnames.each { hname -> if (hostname.contains(hname) && !workflow.profile.contains(prof)) { From fd5c9ebbb8e7895e6d1d58472a7aeb70e0895d7c Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Tue, 20 Jul 2021 12:04:58 +0100 Subject: [PATCH 17/31] Use try/catch block instead --- lib/NfcoreTemplate.groovy | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/lib/NfcoreTemplate.groovy b/lib/NfcoreTemplate.groovy index 28ae774c4..ef7b6a49e 100755 --- a/lib/NfcoreTemplate.groovy +++ b/lib/NfcoreTemplate.groovy @@ -24,17 +24,21 @@ class NfcoreTemplate { public static void hostName(workflow, params, log) { Map colors = logColours(params.monochrome_logs) if (params.hostnames) { - def hostname = ['sh', '-c', 'echo $HOSTNAME'].execute().text.trim() - params.hostnames.each { prof, hnames -> - hnames.each { hname -> - if (hostname.contains(hname) && !workflow.profile.contains(prof)) { - log.info "=${colors.yellow}====================================================${colors.reset}=\n" + - "${colors.yellow}WARN: You are running with `-profile $workflow.profile`\n" + - " but your machine hostname is ${colors.white}'$hostname'${colors.reset}.\n" + - " ${colors.yellow_bold}Please use `-profile $prof${colors.reset}`\n" + - "=${colors.yellow}====================================================${colors.reset}=" + try { + def hostname = "hostname".execute().text.trim() + params.hostnames.each { prof, hnames -> + hnames.each { hname -> + if (hostname.contains(hname) && !workflow.profile.contains(prof)) { + log.info "=${colors.yellow}====================================================${colors.reset}=\n" + + "${colors.yellow}WARN: You are running with `-profile $workflow.profile`\n" + + " but your machine hostname is ${colors.white}'$hostname'${colors.reset}.\n" + + " ${colors.yellow_bold}Please use `-profile $prof${colors.reset}`\n" + + "=${colors.yellow}====================================================${colors.reset}=" + } } } + } catch (all) { + log.warn "[$workflow.manifest.name] Could not determine 'hostname'. Skipping check." } } } From 83d7406e3ebe660adfc871fa12719cb9b9cccbaa Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Tue, 20 Jul 2021 12:23:29 +0100 Subject: [PATCH 18/31] Update rseqc/junctionannotation/main.nf module --- modules.json | 2 +- modules/nf-core/modules/rseqc/junctionannotation/main.nf | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/modules.json b/modules.json index 0a6479e09..cd32b2c6f 100644 --- a/modules.json +++ b/modules.json @@ -49,7 +49,7 @@ "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" }, "rseqc/junctionannotation": { - "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + "git_sha": "5dd049047d01e72c01a519422f17e203bca343ac" }, "rseqc/junctionsaturation": { "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" diff --git a/modules/nf-core/modules/rseqc/junctionannotation/main.nf b/modules/nf-core/modules/rseqc/junctionannotation/main.nf index 909ee9aef..ace4fe613 100644 --- a/modules/nf-core/modules/rseqc/junctionannotation/main.nf +++ b/modules/nf-core/modules/rseqc/junctionannotation/main.nf @@ -27,7 +27,7 @@ process RSEQC_JUNCTIONANNOTATION { tuple val(meta), path("*.r") , emit: rscript tuple val(meta), path("*.log") , emit: log tuple val(meta), path("*.junction.bed"), optional:true, emit: bed - tuple val(meta), path("*.interact.bed"), optional:true, emit: interact_bed + tuple val(meta), path("*.Interact.bed"), optional:true, emit: interact_bed tuple val(meta), path("*junction.pdf") , optional:true, emit: pdf tuple val(meta), path("*events.pdf") , optional:true, emit: events_pdf path "*.version.txt" , emit: version From 98d4304e6c59a845b8499721f9606116253f60f5 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Tue, 20 Jul 2021 13:36:43 +0100 Subject: [PATCH 19/31] Use Exception e --- lib/NfcoreTemplate.groovy | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/NfcoreTemplate.groovy b/lib/NfcoreTemplate.groovy index ef7b6a49e..70d6751be 100755 --- a/lib/NfcoreTemplate.groovy +++ b/lib/NfcoreTemplate.groovy @@ -37,7 +37,7 @@ class NfcoreTemplate { } } } - } catch (all) { + } catch (Exception e) { log.warn "[$workflow.manifest.name] Could not determine 'hostname'. Skipping check." } } From b699c1581b38e7bb0f710c110ec3126469f727ca Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Tue, 20 Jul 2021 13:58:17 +0100 Subject: [PATCH 20/31] Nicer error message --- lib/NfcoreTemplate.groovy | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/NfcoreTemplate.groovy b/lib/NfcoreTemplate.groovy index 70d6751be..e3513902e 100755 --- a/lib/NfcoreTemplate.groovy +++ b/lib/NfcoreTemplate.groovy @@ -38,7 +38,7 @@ class NfcoreTemplate { } } } catch (Exception e) { - log.warn "[$workflow.manifest.name] Could not determine 'hostname'. Skipping check." + log.warn "[$workflow.manifest.name] Could not determine 'hostname' - skipping check. Reason: ${e.message}." } } } From a39715844e4ee0a46973680ba34a13563ef27ef0 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Tue, 20 Jul 2021 20:32:02 +0100 Subject: [PATCH 21/31] Bump version to v3.3 --- CHANGELOG.md | 5 ++--- nextflow.config | 2 +- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 6795ab004..d5bb9d900 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,15 +3,13 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). -## [Unpublished Version / DEV] +## [[3.3](https://github.com/nf-core/rnaseq/releases/tag/3.3)] - 2021-07-26 ### Enhancements & fixes * Updated pipeline template to [nf-core/tools 2.0.1](https://github.com/nf-core/tools/releases/tag/2.0.1) * [[#668](https://github.com/nf-core/rnaseq/issues/668)] - Salmon quant with UMI-tools does not work -### Parameters - ### Software dependencies Note, since the pipeline is now using Nextflow DSL2, each process will be run with its own [Biocontainer](https://biocontainers.pro/#/registry). This means that on occasion it is entirely possible for the pipeline to be using different versions of the same tool. However, the overall software dependency changes compared to the last release have been listed below for reference. @@ -19,6 +17,7 @@ Note, since the pipeline is now using Nextflow DSL2, each process will be run wi | Dependency | Old version | New version | |-------------|-------------|-------------| | `umi_tools` | 1.1.1 | 1.1.2 | +| `samtools` | 1.10 | 1.12 | > **NB:** Dependency has been __updated__ if both old and new version information is present. > **NB:** Dependency has been __added__ if just the new version information is present. diff --git a/nextflow.config b/nextflow.config index 0a3e7ed88..714ac80d9 100644 --- a/nextflow.config +++ b/nextflow.config @@ -221,7 +221,7 @@ manifest { description = 'Nextflow RNA-Seq analysis pipeline, part of the nf-core community.' mainScript = 'main.nf' nextflowVersion = '!>=21.04.0' - version = '3.3dev' + version = '3.3' } // Function to ensure that resource requirements don't go beyond From 3cd89ba31e21b2011afc6b77f88d8cce8385acf8 Mon Sep 17 00:00:00 2001 From: matthiasho Date: Wed, 21 Jul 2021 16:08:26 +0200 Subject: [PATCH 22/31] fix regex for file extension, such that it matches the whole file name fixes #674 --- nextflow_schema.json | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/nextflow_schema.json b/nextflow_schema.json index 2b0b342dc..933f875b1 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -15,7 +15,7 @@ "type": "string", "format": "file-path", "mimetype": "text/csv", - "pattern": "\\.csv$", + "pattern": "\\S*\\.csv$", "schema": "assets/schema_input.json", "description": "Path to comma-separated file containing information about the samples in the experiment.", "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 4 columns, and a header row. See [usage docs](https://nf-co.re/rnaseq/usage#samplesheet-input).", @@ -121,7 +121,7 @@ "type": "string", "format": "file-path", "mimetype": "text/plain", - "pattern": "\\.fn?a(sta)?(\\.gz)?$", + "pattern": "\\S*\\.fn?a(sta)?(\\.gz)?$", "description": "Path to FASTA genome file.", "help_text": "This parameter is *mandatory* if `--genome` is not specified. If you don't have a BWA index available this will be generated for you automatically. Combine with `--save_reference` to save BWA index for future runs.", "fa_icon": "far fa-file-code" @@ -130,7 +130,7 @@ "type": "string", "format": "file-path", "mimetype": "text/plain", - "pattern": "\\.gtf(\\.gz)?$", + "pattern": "\\S*\\.gtf(\\.gz)?$", "description": "Path to GTF annotation file.", "fa_icon": "fas fa-code-branch", "help_text": "This parameter is *mandatory* if `--genome` is not specified." @@ -139,7 +139,7 @@ "type": "string", "format": "file-path", "mimetype": "text/plain", - "pattern": "\\.gff(\\.gz)?$", + "pattern": "\\S*\\.gff(\\.gz)?$", "fa_icon": "fas fa-code-branch", "description": "Path to GFF3 annotation file.", "help_text": "This parameter must be specified if `--genome` or `--gtf` are not specified." @@ -148,7 +148,7 @@ "type": "string", "format": "file-path", "mimetype": "text/plain", - "pattern": "\\.bed(\\.gz)?$", + "pattern": "\\S*\\.bed(\\.gz)?$", "fa_icon": "fas fa-procedures", "description": "Path to BED file containing gene intervals. This will be created from the GTF file if not specified." }, @@ -156,7 +156,7 @@ "type": "string", "format": "file-path", "mimetype": "text/plain", - "pattern": "\\.fn?a(sta)?(\\.gz)?$", + "pattern": "\\S*\\.fn?a(sta)?(\\.gz)?$", "fa_icon": "far fa-file-code", "description": "Path to FASTA transcriptome file." }, @@ -164,7 +164,7 @@ "type": "string", "format": "file-path", "mimetype": "text/plain", - "pattern": "\\.fn?a(sta)?(\\.gz)?$", + "pattern": "\\S*\\.fn?a(sta)?(\\.gz)?$", "fa_icon": "far fa-file-code", "description": "FASTA file to concatenate to genome FASTA file e.g. containing spike-in sequences.", "help_text": "If provided, the sequences in this file will get concatenated to the existing genome FASTA file, a GTF file will be automatically created using the entire sequence as the gene, transcript, and exon features, and any alignment index will get created from the combined FASTA and GTF. It is recommended to save the reference with `--save_reference` to re-use the index for future runs so you do not need to create it again." @@ -686,4 +686,4 @@ "$ref": "#/definitions/generic_options" } ] -} +} \ No newline at end of file From 59ab3e0a2f2c3909961891f76a24ec0e714d1747 Mon Sep 17 00:00:00 2001 From: matthiasho Date: Wed, 21 Jul 2021 16:21:13 +0200 Subject: [PATCH 23/31] update changelog --- CHANGELOG.md | 1 + 1 file changed, 1 insertion(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 6795ab004..6c1045762 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 * Updated pipeline template to [nf-core/tools 2.0.1](https://github.com/nf-core/tools/releases/tag/2.0.1) * [[#668](https://github.com/nf-core/rnaseq/issues/668)] - Salmon quant with UMI-tools does not work +* [[#674](https://github.com/nf-core/rnaseq/issues/674)] - Launch pipeline regex fails ### Parameters From aa7daac267a2740fea5ad178cf611badb7a0d1e9 Mon Sep 17 00:00:00 2001 From: matthiasho Date: Wed, 21 Jul 2021 16:57:33 +0200 Subject: [PATCH 24/31] use more precise regex pattern --- nextflow_schema.json | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/nextflow_schema.json b/nextflow_schema.json index 933f875b1..9c8f69543 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -15,7 +15,7 @@ "type": "string", "format": "file-path", "mimetype": "text/csv", - "pattern": "\\S*\\.csv$", + "pattern": "^\\S+\\.csv$", "schema": "assets/schema_input.json", "description": "Path to comma-separated file containing information about the samples in the experiment.", "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 4 columns, and a header row. See [usage docs](https://nf-co.re/rnaseq/usage#samplesheet-input).", @@ -121,7 +121,7 @@ "type": "string", "format": "file-path", "mimetype": "text/plain", - "pattern": "\\S*\\.fn?a(sta)?(\\.gz)?$", + "pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$", "description": "Path to FASTA genome file.", "help_text": "This parameter is *mandatory* if `--genome` is not specified. If you don't have a BWA index available this will be generated for you automatically. Combine with `--save_reference` to save BWA index for future runs.", "fa_icon": "far fa-file-code" @@ -130,7 +130,7 @@ "type": "string", "format": "file-path", "mimetype": "text/plain", - "pattern": "\\S*\\.gtf(\\.gz)?$", + "pattern": "^\\S+\\.gtf(\\.gz)?$", "description": "Path to GTF annotation file.", "fa_icon": "fas fa-code-branch", "help_text": "This parameter is *mandatory* if `--genome` is not specified." @@ -139,7 +139,7 @@ "type": "string", "format": "file-path", "mimetype": "text/plain", - "pattern": "\\S*\\.gff(\\.gz)?$", + "pattern": "^\\S+\\.gff(\\.gz)?$", "fa_icon": "fas fa-code-branch", "description": "Path to GFF3 annotation file.", "help_text": "This parameter must be specified if `--genome` or `--gtf` are not specified." @@ -148,7 +148,7 @@ "type": "string", "format": "file-path", "mimetype": "text/plain", - "pattern": "\\S*\\.bed(\\.gz)?$", + "pattern": "^\\S+\\.bed(\\.gz)?$", "fa_icon": "fas fa-procedures", "description": "Path to BED file containing gene intervals. This will be created from the GTF file if not specified." }, @@ -156,7 +156,7 @@ "type": "string", "format": "file-path", "mimetype": "text/plain", - "pattern": "\\S*\\.fn?a(sta)?(\\.gz)?$", + "pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$", "fa_icon": "far fa-file-code", "description": "Path to FASTA transcriptome file." }, @@ -164,7 +164,7 @@ "type": "string", "format": "file-path", "mimetype": "text/plain", - "pattern": "\\S*\\.fn?a(sta)?(\\.gz)?$", + "pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$", "fa_icon": "far fa-file-code", "description": "FASTA file to concatenate to genome FASTA file e.g. containing spike-in sequences.", "help_text": "If provided, the sequences in this file will get concatenated to the existing genome FASTA file, a GTF file will be automatically created using the entire sequence as the gene, transcript, and exon features, and any alignment index will get created from the combined FASTA and GTF. It is recommended to save the reference with `--save_reference` to re-use the index for future runs so you do not need to create it again." From 2e1e206beeddcd7547ead0785f98c2a915bf7f70 Mon Sep 17 00:00:00 2001 From: JoseEspinosa Date: Fri, 23 Jul 2021 09:55:51 +0200 Subject: [PATCH 25/31] Bump stringtie version to 2.1.7 --- CHANGELOG.md | 1 + modules.json | 2 +- modules/nf-core/modules/stringtie/stringtie/main.nf | 9 +++++---- 3 files changed, 7 insertions(+), 5 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 703f0e4f0..5ca752026 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -19,6 +19,7 @@ Note, since the pipeline is now using Nextflow DSL2, each process will be run wi |-------------|-------------|-------------| | `umi_tools` | 1.1.1 | 1.1.2 | | `samtools` | 1.10 | 1.12 | +| `stringtie` | 2.1.4 | 2.1.7 | > **NB:** Dependency has been __updated__ if both old and new version information is present. > **NB:** Dependency has been __added__ if just the new version information is present. diff --git a/modules.json b/modules.json index cd32b2c6f..95db70d36 100644 --- a/modules.json +++ b/modules.json @@ -91,7 +91,7 @@ "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" }, "stringtie/stringtie": { - "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" + "git_sha": "217303f5c1a92effb8a97c29294ee9f2e19f697e" }, "subread/featurecounts": { "git_sha": "e937c7950af70930d1f34bb961403d9d2aa81c7d" diff --git a/modules/nf-core/modules/stringtie/stringtie/main.nf b/modules/nf-core/modules/stringtie/stringtie/main.nf index eb751321e..6cff993a1 100644 --- a/modules/nf-core/modules/stringtie/stringtie/main.nf +++ b/modules/nf-core/modules/stringtie/stringtie/main.nf @@ -11,11 +11,11 @@ process STRINGTIE { mode: params.publish_dir_mode, saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) } - conda (params.enable_conda ? "bioconda::stringtie=2.1.4" : null) + conda (params.enable_conda ? "bioconda::stringtie=2.1.7" : null) if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { - container "https://depot.galaxyproject.org/singularity/stringtie:2.1.4--h7e0af3c_0" + container "https://depot.galaxyproject.org/singularity/stringtie:2.1.7--h978d192_0" } else { - container "quay.io/biocontainers/stringtie:2.1.4--h7e0af3c_0" + container "quay.io/biocontainers/stringtie:2.1.7--h978d192_0" } input: @@ -48,8 +48,9 @@ process STRINGTIE { -A ${prefix}.gene.abundance.txt \\ -C ${prefix}.coverage.gtf \\ -b ${prefix}.ballgown \\ + -p $task.cpus \\ $options.args - stringtie --version > ${software}.version.txt + echo \$(stringtie --version 2>&1) > ${software}.version.txt """ } From 3d931f3f5737783fd98fcad6a5f10059ab85ed6e Mon Sep 17 00:00:00 2001 From: nf-core-bot Date: Tue, 27 Jul 2021 16:11:04 +0000 Subject: [PATCH 26/31] Template update for nf-core/tools version 2.1 --- .editorconfig | 3 +++ .github/CONTRIBUTING.md | 6 +++--- .github/PULL_REQUEST_TEMPLATE.md | 2 +- .github/workflows/linting.yml | 2 +- CHANGELOG.md | 2 +- README.md | 2 +- bin/scrape_software_versions.py | 2 +- lib/NfcoreTemplate.groovy | 22 +++++++++++++--------- nextflow.config | 2 +- nextflow_schema.json | 4 ++-- workflows/rnaseq.nf | 4 +++- 11 files changed, 30 insertions(+), 21 deletions(-) diff --git a/.editorconfig b/.editorconfig index afb20bb1e..95549501a 100644 --- a/.editorconfig +++ b/.editorconfig @@ -11,6 +11,9 @@ indent_style = space [*.{yml,yaml}] indent_size = 2 +[*.json] +insert_final_newline = unset + # These files are edited and tested upstream in nf-core/modules [/modules/nf-core/**] charset = unset diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md index f17299425..85674bb3b 100644 --- a/.github/CONTRIBUTING.md +++ b/.github/CONTRIBUTING.md @@ -19,7 +19,7 @@ If you'd like to write some code for nf-core/rnaseq, the standard workflow is as * If there isn't one already, please create one so that others know you're working on this 2. [Fork](https://help.github.com/en/github/getting-started-with-github/fork-a-repo) the [nf-core/rnaseq repository](https://github.com/nf-core/rnaseq) to your GitHub account 3. Make the necessary changes / additions within your forked repository following [Pipeline conventions](#pipeline-contribution-conventions) -4. Use `nf-core schema build .` and add any new parameters to the pipeline JSON schema (requires [nf-core tools](https://github.com/nf-core/tools) >= 1.10). +4. Use `nf-core schema build` and add any new parameters to the pipeline JSON schema (requires [nf-core tools](https://github.com/nf-core/tools) >= 1.10). 5. Submit a Pull Request against the `dev` branch and wait for the code to be reviewed and merged If you're not used to this workflow with git, you can start with some [docs from GitHub](https://help.github.com/en/github/collaborating-with-issues-and-pull-requests) or even their [excellent `git` resources](https://try.github.io/). @@ -69,7 +69,7 @@ If you wish to contribute a new step, please use the following coding standards: 2. Write the process block (see below). 3. Define the output channel if needed (see below). 4. Add any new flags/options to `nextflow.config` with a default (see below). -5. Add any new flags/options to `nextflow_schema.json` with help text (with `nf-core schema build .`). +5. Add any new flags/options to `nextflow_schema.json` with help text (with `nf-core schema build`). 6. Add any new flags/options to the help message (for integer/text parameters, print to help the corresponding `nextflow.config` parameter). 7. Add sanity checks for all relevant parameters. 8. Add any new software to the `scrape_software_versions.py` script in `bin/` and the version command to the `scrape_software_versions` process in `main.nf`. @@ -83,7 +83,7 @@ If you wish to contribute a new step, please use the following coding standards: Parameters should be initialised / defined with default values in `nextflow.config` under the `params` scope. -Once there, use `nf-core schema build .` to add to `nextflow_schema.json`. +Once there, use `nf-core schema build` to add to `nextflow_schema.json`. ### Default processes resource requirements diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index 31ed7da27..c6225f340 100644 --- a/.github/PULL_REQUEST_TEMPLATE.md +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -18,7 +18,7 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/rnas - [ ] If you've fixed a bug or added code that should be tested, add tests! - [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/rnaseq/tree/master/.github/CONTRIBUTING.md) - [ ] If necessary, also make a PR on the nf-core/rnaseq _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository. -- [ ] Make sure your code lints (`nf-core lint .`). +- [ ] Make sure your code lints (`nf-core lint`). - [ ] Ensure the test suite passes (`nextflow run . -profile test,docker`). - [ ] Usage Documentation in `docs/usage.md` is updated. - [ ] Output Documentation in `docs/output.md` is updated. diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index fbde5cf8b..3b448773c 100644 --- a/.github/workflows/linting.yml +++ b/.github/workflows/linting.yml @@ -53,7 +53,7 @@ jobs: - uses: actions/setup-node@v1 with: - node-version: "10" + node-version: '10' - name: Install editorconfig-checker run: npm install -g editorconfig-checker diff --git a/CHANGELOG.md b/CHANGELOG.md index 44b32fe48..5b1da18fb 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,7 +3,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). -## v3.3dev - [date] +## v3.3 - [date] Initial release of nf-core/rnaseq, created with the [nf-core](https://nf-co.re/) template. diff --git a/README.md b/README.md index 330a70165..7a66ea061 100644 --- a/README.md +++ b/README.md @@ -33,7 +33,7 @@ On release, automated continuous integration tests run the pipeline on a full-si ## Quick Start -1. Install [`Nextflow`](https://nf-co.re/usage/installation) (`>=21.04.0`) +1. Install [`Nextflow`](https://www.nextflow.io/docs/latest/getstarted.html#installation) (`>=21.04.0`) 2. Install any of [`Docker`](https://docs.docker.com/engine/installation/), [`Singularity`](https://www.sylabs.io/guides/3.0/user-guide/), [`Podman`](https://podman.io/), [`Shifter`](https://nersc.gitlab.io/development/shifter/how-to-use/) or [`Charliecloud`](https://hpc.github.io/charliecloud/) for full pipeline reproducibility _(please only use [`Conda`](https://conda.io/miniconda.html) as a last resort; see [docs](https://nf-co.re/usage/configuration#basic-configuration-profiles))_ diff --git a/bin/scrape_software_versions.py b/bin/scrape_software_versions.py index 518ee4220..e1519ee13 100755 --- a/bin/scrape_software_versions.py +++ b/bin/scrape_software_versions.py @@ -30,7 +30,7 @@ print("
{}
{}
".format(k, v)) print(" ") -# Write out regexes as csv file: +# Write out as tsv file: with open("software_versions.tsv", "w") as f: for k, v in sorted(results.items()): f.write("{}\t{}\n".format(k, v)) diff --git a/lib/NfcoreTemplate.groovy b/lib/NfcoreTemplate.groovy index b6e689ec8..44551e0a3 100755 --- a/lib/NfcoreTemplate.groovy +++ b/lib/NfcoreTemplate.groovy @@ -24,17 +24,21 @@ class NfcoreTemplate { public static void hostName(workflow, params, log) { Map colors = logColours(params.monochrome_logs) if (params.hostnames) { - def hostname = "hostname".execute().text.trim() - params.hostnames.each { prof, hnames -> - hnames.each { hname -> - if (hostname.contains(hname) && !workflow.profile.contains(prof)) { - log.info "=${colors.yellow}====================================================${colors.reset}=\n" + - "${colors.yellow}WARN: You are running with `-profile $workflow.profile`\n" + - " but your machine hostname is ${colors.white}'$hostname'${colors.reset}.\n" + - " ${colors.yellow_bold}Please use `-profile $prof${colors.reset}`\n" + - "=${colors.yellow}====================================================${colors.reset}=" + try { + def hostname = "hostname".execute().text.trim() + params.hostnames.each { prof, hnames -> + hnames.each { hname -> + if (hostname.contains(hname) && !workflow.profile.contains(prof)) { + log.info "=${colors.yellow}====================================================${colors.reset}=\n" + + "${colors.yellow}WARN: You are running with `-profile $workflow.profile`\n" + + " but your machine hostname is ${colors.white}'$hostname'${colors.reset}.\n" + + " ${colors.yellow_bold}Please use `-profile $prof${colors.reset}`\n" + + "=${colors.yellow}====================================================${colors.reset}=" + } } } + } catch (Exception e) { + log.warn "[$workflow.manifest.name] Could not determine 'hostname' - skipping check. Reason: ${e.message}." } } } diff --git a/nextflow.config b/nextflow.config index 8f1ed9c5a..1df80271a 100644 --- a/nextflow.config +++ b/nextflow.config @@ -161,7 +161,7 @@ manifest { description = 'Nextflow RNA-Seq analysis pipeline, part of the nf-core community.' mainScript = 'main.nf' nextflowVersion = '!>=21.04.0' - version = '3.3dev' + version = '3.3' } // Function to ensure that resource requirements don't go beyond diff --git a/nextflow_schema.json b/nextflow_schema.json index 7e4c45fa5..201479bec 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -18,7 +18,7 @@ "type": "string", "format": "file-path", "mimetype": "text/csv", - "pattern": "\\.csv$", + "pattern": "^\\S+\\.csv$", "schema": "assets/schema_input.json", "description": "Path to comma-separated file containing information about the samples in the experiment.", "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row. See [usage docs](https://nf-co.re/rnaseq/usage#samplesheet-input).", @@ -60,7 +60,7 @@ "type": "string", "format": "file-path", "mimetype": "text/plain", - "pattern": "\\.fn?a(sta)?(\\.gz)?$", + "pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$", "description": "Path to FASTA genome file.", "help_text": "This parameter is *mandatory* if `--genome` is not specified. If you don't have a BWA index available this will be generated for you automatically. Combine with `--save_reference` to save BWA index for future runs.", "fa_icon": "far fa-file-code" diff --git a/workflows/rnaseq.nf b/workflows/rnaseq.nf index bc19af6fc..340b30764 100644 --- a/workflows/rnaseq.nf +++ b/workflows/rnaseq.nf @@ -130,7 +130,9 @@ workflow RNASEQ { */ workflow.onComplete { - NfcoreTemplate.email(workflow, params, summary_params, projectDir, log, multiqc_report) + if (params.email || params.email_on_fail) { + NfcoreTemplate.email(workflow, params, summary_params, projectDir, log, multiqc_report) + } NfcoreTemplate.summary(workflow, params, log) } From e64561a8d12fd7901ab3029bbaf8ac6545507f5a Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Tue, 27 Jul 2021 22:32:02 +0100 Subject: [PATCH 27/31] Update CHANGELOG --- CHANGELOG.md | 1 + 1 file changed, 1 insertion(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index cabba9c8f..178916a7d 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -8,6 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Enhancements & fixes * Updated pipeline template to [nf-core/tools 2.1](https://github.com/nf-core/tools/releases/tag/2.1) +* [[#556](https://github.com/nf-core/rnaseq/issues/556)] - Genome index isn't recreated with --additional_fasta unless --star_index false * [[#668](https://github.com/nf-core/rnaseq/issues/668)] - Salmon quant with UMI-tools does not work * [[#674](https://github.com/nf-core/rnaseq/issues/674)] - Launch pipeline regex fails From 53fdef1b8117d3d248c5a94060dd46bd011aae35 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Tue, 27 Jul 2021 22:32:57 +0100 Subject: [PATCH 28/31] Fix #556 --- lib/WorkflowRnaseq.groovy | 28 + workflows/rnaseq.nf | 1058 ++++++++++++++++++------------------- 2 files changed, 557 insertions(+), 529 deletions(-) diff --git a/lib/WorkflowRnaseq.groovy b/lib/WorkflowRnaseq.groovy index 5cdc71acd..55df2289d 100755 --- a/lib/WorkflowRnaseq.groovy +++ b/lib/WorkflowRnaseq.groovy @@ -67,6 +67,18 @@ class WorkflowRnaseq { } } + // Warn if --additional_fasta provided with aligner index + if (!params.skip_alignment && params.additional_fasta) { + def index = 'star' + if (params.aligner == 'star_rsem' && params.rsem_index) { + index = 'rsem' + } + if (params.aligner == 'hisat2' && params.hisat2_index) { + index = 'hisat2' + } + additionaFastaIndexWarn(index, log) + } + // Check which RSeQC modules we are running def rseqc_modules = params.rseqc_modules ? params.rseqc_modules.split(',').collect{ it.trim().toLowerCase() } : [] if ((valid_params['rseqc_modules'] + rseqc_modules).unique().size() != valid_params['rseqc_modules'].size()) { @@ -260,4 +272,20 @@ class WorkflowRnaseq { " https://github.com/nf-core/rnaseq/issues/568\n" + "===================================================================================" } + + // + // Print a warning if using '--additional_fasta' and '--_index' + // + private static void additionaFastaIndexWarn(index, log) { + log.warn "=============================================================================\n" + + " When using '--additional_fasta --${index}_index '\n" + + " the index will not be re-built with the transgenes incorporated by default since\n" + + " you have already provided an index via '--${index}_index '.\n\n" + + " Set '--additional_fasta --${index}_index false --save_reference'\n" + + " to re-build the index including transgenes and save for re-use with\n" + + " '--${index}_index' in 'results/genome/index/${index}/'.\n\n" + + " Please see:\n" + + " https://github.com/nf-core/rnaseq/issues/556\n" + + "===================================================================================" + } } diff --git a/workflows/rnaseq.nf b/workflows/rnaseq.nf index 8c17d5633..3fd1cc90a 100755 --- a/workflows/rnaseq.nf +++ b/workflows/rnaseq.nf @@ -234,535 +234,535 @@ def fail_percent_mapped = [:] workflow RNASEQ { - // - // SUBWORKFLOW: Uncompress and prepare reference genome files - // - PREPARE_GENOME ( - prepareToolIndices, - biotype - ) - ch_software_versions = Channel.empty() - ch_software_versions = ch_software_versions.mix(PREPARE_GENOME.out.gffread_version.ifEmpty(null)) - - // - // SUBWORKFLOW: Read in samplesheet, validate and stage input files - // - INPUT_CHECK ( - ch_input - ) - .map { - meta, fastq -> - meta.id = meta.id.split('_')[0..-2].join('_') - [ meta, fastq ] } - .groupTuple(by: [0]) - .branch { - meta, fastq -> - single : fastq.size() == 1 - return [ meta, fastq.flatten() ] - multiple: fastq.size() > 1 - return [ meta, fastq.flatten() ] - } - .set { ch_fastq } - - // - // MODULE: Concatenate FastQ files from same sample if required - // - CAT_FASTQ ( - ch_fastq.multiple - ) - .mix(ch_fastq.single) - .set { ch_cat_fastq } - - // - // SUBWORKFLOW: Read QC, extract UMI and trim adapters - // - FASTQC_UMITOOLS_TRIMGALORE ( - ch_cat_fastq, - params.skip_fastqc || params.skip_qc, - params.with_umi, - params.skip_trimming - ) - ch_software_versions = ch_software_versions.mix(FASTQC_UMITOOLS_TRIMGALORE.out.fastqc_version.first().ifEmpty(null)) - ch_software_versions = ch_software_versions.mix(FASTQC_UMITOOLS_TRIMGALORE.out.umitools_version.first().ifEmpty(null)) - ch_software_versions = ch_software_versions.mix(FASTQC_UMITOOLS_TRIMGALORE.out.trimgalore_version.first().ifEmpty(null)) - - // - // MODULE: Remove ribosomal RNA reads - // - ch_trimmed_reads = FASTQC_UMITOOLS_TRIMGALORE.out.reads - ch_sortmerna_multiqc = Channel.empty() - if (params.remove_ribo_rna) { - ch_sortmerna_fasta = Channel.from(ch_ribo_db.readLines()).map { row -> file(row) }.collect() - - SORTMERNA ( - ch_trimmed_reads, - ch_sortmerna_fasta - ) - .reads - .set { ch_trimmed_reads } - - ch_sortmerna_multiqc = SORTMERNA.out.log - ch_software_versions = ch_software_versions.mix(SORTMERNA.out.version.first().ifEmpty(null)) - } - - // - // SUBWORKFLOW: Alignment with STAR and gene/transcript quantification with Salmon - // - ch_genome_bam = Channel.empty() - ch_genome_bam_index = Channel.empty() - ch_samtools_stats = Channel.empty() - ch_samtools_flagstat = Channel.empty() - ch_samtools_idxstats = Channel.empty() - ch_star_multiqc = Channel.empty() - ch_aligner_pca_multiqc = Channel.empty() - ch_aligner_clustering_multiqc = Channel.empty() - if (!params.skip_alignment && params.aligner == 'star_salmon') { - ALIGN_STAR ( - ch_trimmed_reads, - PREPARE_GENOME.out.star_index, - PREPARE_GENOME.out.gtf - ) - ch_genome_bam = ALIGN_STAR.out.bam - ch_genome_bam_index = ALIGN_STAR.out.bai - ch_transcriptome_bam = ALIGN_STAR.out.bam_transcript - ch_samtools_stats = ALIGN_STAR.out.stats - ch_samtools_flagstat = ALIGN_STAR.out.flagstat - ch_samtools_idxstats = ALIGN_STAR.out.idxstats - ch_star_multiqc = ALIGN_STAR.out.log_final - if (params.bam_csi_index) { - ch_genome_bam_index = ALIGN_STAR.out.csi - } - ch_software_versions = ch_software_versions.mix(ALIGN_STAR.out.star_version.first().ifEmpty(null)) - ch_software_versions = ch_software_versions.mix(ALIGN_STAR.out.samtools_version.first().ifEmpty(null)) - - // - // SUBWORKFLOW: Remove duplicate reads from BAM file based on UMIs - // - if (params.with_umi) { - // Deduplicate genome BAM file before downstream analysis - DEDUP_UMI_UMITOOLS_GENOME ( - ch_genome_bam.join(ch_genome_bam_index, by: [0]) - ) - ch_genome_bam = DEDUP_UMI_UMITOOLS_GENOME.out.bam - ch_genome_bam_index = DEDUP_UMI_UMITOOLS_GENOME.out.bai - ch_samtools_stats = DEDUP_UMI_UMITOOLS_GENOME.out.stats - ch_samtools_flagstat = DEDUP_UMI_UMITOOLS_GENOME.out.flagstat - ch_samtools_idxstats = DEDUP_UMI_UMITOOLS_GENOME.out.idxstats - if (params.bam_csi_index) { - ch_genome_bam_index = DEDUP_UMI_UMITOOLS_GENOME.out.csi - } - - // Co-ordinate sort, index and run stats on transcriptome BAM - BAM_SORT_SAMTOOLS ( - ch_transcriptome_bam - ) - ch_transcriptome_sorted_bam = BAM_SORT_SAMTOOLS.out.bam - ch_transcriptome_sorted_bai = BAM_SORT_SAMTOOLS.out.bai - - // Deduplicate transcriptome BAM file before read counting with Salmon - DEDUP_UMI_UMITOOLS_TRANSCRIPTOME ( - ch_transcriptome_sorted_bam.join(ch_transcriptome_sorted_bai, by: [0]) - ) - - // Name sort BAM before passing to Salmon - SAMTOOLS_SORT ( - DEDUP_UMI_UMITOOLS_TRANSCRIPTOME.out.bam - ) - ch_transcriptome_bam = SAMTOOLS_SORT.out.bam - } - - // - // SUBWORKFLOW: Count reads from BAM alignments using Salmon - // - QUANTIFY_STAR_SALMON ( - ch_transcriptome_bam, - ch_dummy_file, - PREPARE_GENOME.out.transcript_fasta, - PREPARE_GENOME.out.gtf, - true, - params.salmon_quant_libtype ?: '' - ) - ch_software_versions = ch_software_versions.mix(QUANTIFY_STAR_SALMON.out.salmon_version.first().ifEmpty(null)) - ch_software_versions = ch_software_versions.mix(QUANTIFY_STAR_SALMON.out.tximeta_version.ifEmpty(null)) - ch_software_versions = ch_software_versions.mix(QUANTIFY_STAR_SALMON.out.summarizedexperiment_version.ifEmpty(null)) - - if (!params.skip_qc & !params.skip_deseq2_qc) { - DESEQ2_QC_STAR_SALMON ( - QUANTIFY_STAR_SALMON.out.counts_gene_length_scaled, - ch_pca_header_multiqc, - ch_clustering_header_multiqc - ) - ch_aligner_pca_multiqc = DESEQ2_QC_STAR_SALMON.out.pca_multiqc - ch_aligner_clustering_multiqc = DESEQ2_QC_STAR_SALMON.out.dists_multiqc - ch_software_versions = ch_software_versions.mix(DESEQ2_QC_STAR_SALMON.out.version.ifEmpty(null)) - } - } - - // - // SUBWORKFLOW: Alignment with STAR and gene/transcript quantification with RSEM - // - ch_rsem_multiqc = Channel.empty() - if (!params.skip_alignment && params.aligner == 'star_rsem') { - QUANTIFY_RSEM ( - ch_trimmed_reads, - PREPARE_GENOME.out.rsem_index - ) - ch_genome_bam = QUANTIFY_RSEM.out.bam - ch_genome_bam_index = QUANTIFY_RSEM.out.bai - ch_samtools_stats = QUANTIFY_RSEM.out.stats - ch_samtools_flagstat = QUANTIFY_RSEM.out.flagstat - ch_samtools_idxstats = QUANTIFY_RSEM.out.idxstats - ch_star_multiqc = QUANTIFY_RSEM.out.logs - ch_rsem_multiqc = QUANTIFY_RSEM.out.stat - if (params.bam_csi_index) { - ch_genome_bam_index = QUANTIFY_RSEM.out.csi - } - ch_software_versions = ch_software_versions.mix(QUANTIFY_RSEM.out.rsem_version.first().ifEmpty(null)) - ch_software_versions = ch_software_versions.mix(QUANTIFY_RSEM.out.samtools_version.first().ifEmpty(null)) - - if (!params.skip_qc & !params.skip_deseq2_qc) { - DESEQ2_QC_RSEM ( - QUANTIFY_RSEM.out.merged_counts_gene, - ch_pca_header_multiqc, - ch_clustering_header_multiqc - ) - ch_aligner_pca_multiqc = DESEQ2_QC_RSEM.out.pca_multiqc - ch_aligner_clustering_multiqc = DESEQ2_QC_RSEM.out.dists_multiqc - ch_software_versions = ch_software_versions.mix(DESEQ2_QC_RSEM.out.version.ifEmpty(null)) - } - } - - // - // SUBWORKFLOW: Alignment with HISAT2 - // - ch_hisat2_multiqc = Channel.empty() - if (!params.skip_alignment && params.aligner == 'hisat2') { - ALIGN_HISAT2 ( - ch_trimmed_reads, - PREPARE_GENOME.out.hisat2_index, - PREPARE_GENOME.out.splicesites - ) - ch_genome_bam = ALIGN_HISAT2.out.bam - ch_genome_bam_index = ALIGN_HISAT2.out.bai - ch_samtools_stats = ALIGN_HISAT2.out.stats - ch_samtools_flagstat = ALIGN_HISAT2.out.flagstat - ch_samtools_idxstats = ALIGN_HISAT2.out.idxstats - ch_hisat2_multiqc = ALIGN_HISAT2.out.summary - if (params.bam_csi_index) { - ch_genome_bam_index = ALIGN_HISAT2.out.csi - } - ch_software_versions = ch_software_versions.mix(ALIGN_HISAT2.out.hisat2_version.first().ifEmpty(null)) - ch_software_versions = ch_software_versions.mix(ALIGN_HISAT2.out.samtools_version.first().ifEmpty(null)) - - // - // SUBWORKFLOW: Remove duplicate reads from BAM file based on UMIs - // - if (params.with_umi) { - DEDUP_UMI_UMITOOLS_GENOME ( - ch_genome_bam.join(ch_genome_bam_index, by: [0]) - ) - ch_genome_bam = DEDUP_UMI_UMITOOLS_GENOME.out.bam - ch_genome_bam_index = DEDUP_UMI_UMITOOLS_GENOME.out.bai - ch_samtools_stats = DEDUP_UMI_UMITOOLS_GENOME.out.stats - ch_samtools_flagstat = DEDUP_UMI_UMITOOLS_GENOME.out.flagstat - ch_samtools_idxstats = DEDUP_UMI_UMITOOLS_GENOME.out.idxstats - if (params.bam_csi_index) { - ch_genome_bam_index = DEDUP_UMI_UMITOOLS_GENOME.out.csi - } - } - } - - // - // Filter channels to get samples that passed STAR minimum mapping percentage - // - ch_fail_mapping_multiqc = Channel.empty() - if (!params.skip_alignment && params.aligner.contains('star')) { - ch_star_multiqc - .map { meta, align_log -> [ meta ] + WorkflowRnaseq.getStarPercentMapped(params, align_log) } - .set { ch_percent_mapped } - - ch_genome_bam - .join(ch_percent_mapped, by: [0]) - .map { meta, ofile, mapped, pass -> if (pass) [ meta, ofile ] } - .set { ch_genome_bam } - - ch_genome_bam_index - .join(ch_percent_mapped, by: [0]) - .map { meta, ofile, mapped, pass -> if (pass) [ meta, ofile ] } - .set { ch_genome_bam_index } - - ch_percent_mapped - .branch { meta, mapped, pass -> - pass: pass - pass_percent_mapped[meta.id] = mapped - return [ "$meta.id\t$mapped" ] - fail: !pass - fail_percent_mapped[meta.id] = mapped - return [ "$meta.id\t$mapped" ] - } - .set { ch_pass_fail_mapped } - - MULTIQC_CUSTOM_FAIL_MAPPED ( - ch_pass_fail_mapped.fail.collect() - ) - .set { ch_fail_mapping_multiqc } - } - - // - // MODULE: Run Preseq - // - ch_preseq_multiqc = Channel.empty() - if (!params.skip_alignment && !params.skip_qc && !params.skip_preseq) { - PRESEQ_LCEXTRAP ( - ch_genome_bam - ) - ch_preseq_multiqc = PRESEQ_LCEXTRAP.out.ccurve - ch_software_versions = ch_software_versions.mix(PRESEQ_LCEXTRAP.out.version.first().ifEmpty(null)) - } - - // - // SUBWORKFLOW: Mark duplicate reads - // - ch_markduplicates_multiqc = Channel.empty() - if (!params.skip_alignment && !params.skip_markduplicates) { - MARK_DUPLICATES_PICARD ( - ch_genome_bam - ) - ch_genome_bam = MARK_DUPLICATES_PICARD.out.bam - ch_genome_bam_index = MARK_DUPLICATES_PICARD.out.bai - ch_samtools_stats = MARK_DUPLICATES_PICARD.out.stats - ch_samtools_flagstat = MARK_DUPLICATES_PICARD.out.flagstat - ch_samtools_idxstats = MARK_DUPLICATES_PICARD.out.idxstats - ch_markduplicates_multiqc = MARK_DUPLICATES_PICARD.out.metrics - if (params.bam_csi_index) { - ch_genome_bam_index = MARK_DUPLICATES_PICARD.out.csi - } - ch_software_versions = ch_software_versions.mix(MARK_DUPLICATES_PICARD.out.picard_version.first().ifEmpty(null)) - } - - // - // MODULE: STRINGTIE - // - if (!params.skip_alignment && !params.skip_stringtie) { - STRINGTIE ( - ch_genome_bam, - PREPARE_GENOME.out.gtf - ) - ch_software_versions = ch_software_versions.mix(STRINGTIE.out.version.first().ifEmpty(null)) - } - - // - // MODULE: Feature biotype QC using featureCounts - // - ch_featurecounts_multiqc = Channel.empty() - if (!params.skip_alignment && !params.skip_qc && !params.skip_biotype_qc && biotype) { - - PREPARE_GENOME - .out - .gtf - .map { WorkflowRnaseq.biotypeInGtf(it, biotype, log) } - .set { biotype_in_gtf } - - // Prevent any samples from running if GTF file doesn't have a valid biotype - ch_genome_bam - .combine(PREPARE_GENOME.out.gtf) - .combine(biotype_in_gtf) - .filter { it[-1] } - .map { it[0.. 0) { - RSEQC ( - ch_genome_bam, - PREPARE_GENOME.out.gene_bed, - rseqc_modules - ) - ch_bamstat_multiqc = RSEQC.out.bamstat_txt - ch_inferexperiment_multiqc = RSEQC.out.inferexperiment_txt - ch_innerdistance_multiqc = RSEQC.out.innerdistance_freq - ch_junctionannotation_multiqc = RSEQC.out.junctionannotation_log - ch_junctionsaturation_multiqc = RSEQC.out.junctionsaturation_rscript - ch_readdistribution_multiqc = RSEQC.out.readdistribution_txt - ch_readduplication_multiqc = RSEQC.out.readduplication_pos_xls - ch_software_versions = ch_software_versions.mix(RSEQC.out.version.first().ifEmpty(null)) - - ch_inferexperiment_multiqc - .map { meta, strand_log -> [ meta ] + WorkflowRnaseq.getInferexperimentStrandedness(strand_log, 30) } - .filter { it[0].strandedness != it[1] } - .map { meta, strandedness, sense, antisense, undetermined -> - [ "$meta.id\t$meta.strandedness\t$strandedness\t$sense\t$antisense\t$undetermined" ] - } - .set { ch_fail_strand } - - MULTIQC_CUSTOM_STRAND_CHECK ( - ch_fail_strand.collect() - ) - .set { ch_fail_strand_multiqc } - } - } - - // - // SUBWORKFLOW: Pseudo-alignment and quantification with Salmon - // - ch_salmon_multiqc = Channel.empty() - ch_pseudoaligner_pca_multiqc = Channel.empty() - ch_pseudoaligner_clustering_multiqc = Channel.empty() - if (params.pseudo_aligner == 'salmon') { - QUANTIFY_SALMON ( - ch_trimmed_reads, - PREPARE_GENOME.out.salmon_index, - ch_dummy_file, - PREPARE_GENOME.out.gtf, - false, - params.salmon_quant_libtype ?: '' - ) - ch_salmon_multiqc = QUANTIFY_SALMON.out.results - if (params.skip_alignment && params.aligner != 'star_salmon') { - ch_software_versions = ch_software_versions.mix(QUANTIFY_SALMON.out.salmon_version.first().ifEmpty(null)) - ch_software_versions = ch_software_versions.mix(QUANTIFY_SALMON.out.tximeta_version.ifEmpty(null)) - ch_software_versions = ch_software_versions.mix(QUANTIFY_SALMON.out.summarizedexperiment_version.ifEmpty(null)) - } - - if (!params.skip_qc & !params.skip_deseq2_qc) { - DESEQ2_QC_SALMON ( - QUANTIFY_SALMON.out.counts_gene_length_scaled, - ch_pca_header_multiqc, - ch_clustering_header_multiqc - ) - ch_pseudoaligner_pca_multiqc = DESEQ2_QC_SALMON.out.pca_multiqc - ch_pseudoaligner_clustering_multiqc = DESEQ2_QC_SALMON.out.dists_multiqc - if (params.skip_alignment) { - ch_software_versions = ch_software_versions.mix(DESEQ2_QC_SALMON.out.version.ifEmpty(null)) - } - } - } - - // - // MODULE: Pipeline reporting - // - ch_software_versions - .map { it -> if (it) [ it.baseName, it ] } - .groupTuple() - .map { it[1][0] } - .flatten() - .collect() - .set { ch_software_versions } - - GET_SOFTWARE_VERSIONS ( - ch_software_versions.map { it }.collect() - ) - - // - // MODULE: MultiQC - // - if (!params.skip_multiqc) { - workflow_summary = WorkflowRnaseq.paramsSummaryMultiqc(workflow, summary_params) - ch_workflow_summary = Channel.value(workflow_summary) - - MULTIQC ( - ch_multiqc_config, - ch_multiqc_custom_config.collect().ifEmpty([]), - GET_SOFTWARE_VERSIONS.out.yaml.collect(), - ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'), - ch_fail_mapping_multiqc.ifEmpty([]), - ch_fail_strand_multiqc.ifEmpty([]), - FASTQC_UMITOOLS_TRIMGALORE.out.fastqc_zip.collect{it[1]}.ifEmpty([]), - FASTQC_UMITOOLS_TRIMGALORE.out.trim_zip.collect{it[1]}.ifEmpty([]), - FASTQC_UMITOOLS_TRIMGALORE.out.trim_log.collect{it[1]}.ifEmpty([]), - ch_sortmerna_multiqc.collect{it[1]}.ifEmpty([]), - ch_star_multiqc.collect{it[1]}.ifEmpty([]), - ch_hisat2_multiqc.collect{it[1]}.ifEmpty([]), - ch_rsem_multiqc.collect{it[1]}.ifEmpty([]), - ch_salmon_multiqc.collect{it[1]}.ifEmpty([]), - ch_samtools_stats.collect{it[1]}.ifEmpty([]), - ch_samtools_flagstat.collect{it[1]}.ifEmpty([]), - ch_samtools_idxstats.collect{it[1]}.ifEmpty([]), - ch_markduplicates_multiqc.collect{it[1]}.ifEmpty([]), - ch_featurecounts_multiqc.collect{it[1]}.ifEmpty([]), - ch_aligner_pca_multiqc.collect().ifEmpty([]), - ch_aligner_clustering_multiqc.collect().ifEmpty([]), - ch_pseudoaligner_pca_multiqc.collect().ifEmpty([]), - ch_pseudoaligner_clustering_multiqc.collect().ifEmpty([]), - ch_preseq_multiqc.collect{it[1]}.ifEmpty([]), - ch_qualimap_multiqc.collect{it[1]}.ifEmpty([]), - ch_dupradar_multiqc.collect{it[1]}.ifEmpty([]), - ch_bamstat_multiqc.collect{it[1]}.ifEmpty([]), - ch_inferexperiment_multiqc.collect{it[1]}.ifEmpty([]), - ch_innerdistance_multiqc.collect{it[1]}.ifEmpty([]), - ch_junctionannotation_multiqc.collect{it[1]}.ifEmpty([]), - ch_junctionsaturation_multiqc.collect{it[1]}.ifEmpty([]), - ch_readdistribution_multiqc.collect{it[1]}.ifEmpty([]), - ch_readduplication_multiqc.collect{it[1]}.ifEmpty([]) - ) - multiqc_report = MULTIQC.out.report.toList() - } + // // + // // SUBWORKFLOW: Uncompress and prepare reference genome files + // // + // PREPARE_GENOME ( + // prepareToolIndices, + // biotype + // ) + // ch_software_versions = Channel.empty() + // ch_software_versions = ch_software_versions.mix(PREPARE_GENOME.out.gffread_version.ifEmpty(null)) + + // // + // // SUBWORKFLOW: Read in samplesheet, validate and stage input files + // // + // INPUT_CHECK ( + // ch_input + // ) + // .map { + // meta, fastq -> + // meta.id = meta.id.split('_')[0..-2].join('_') + // [ meta, fastq ] } + // .groupTuple(by: [0]) + // .branch { + // meta, fastq -> + // single : fastq.size() == 1 + // return [ meta, fastq.flatten() ] + // multiple: fastq.size() > 1 + // return [ meta, fastq.flatten() ] + // } + // .set { ch_fastq } + + // // + // // MODULE: Concatenate FastQ files from same sample if required + // // + // CAT_FASTQ ( + // ch_fastq.multiple + // ) + // .mix(ch_fastq.single) + // .set { ch_cat_fastq } + + // // + // // SUBWORKFLOW: Read QC, extract UMI and trim adapters + // // + // FASTQC_UMITOOLS_TRIMGALORE ( + // ch_cat_fastq, + // params.skip_fastqc || params.skip_qc, + // params.with_umi, + // params.skip_trimming + // ) + // ch_software_versions = ch_software_versions.mix(FASTQC_UMITOOLS_TRIMGALORE.out.fastqc_version.first().ifEmpty(null)) + // ch_software_versions = ch_software_versions.mix(FASTQC_UMITOOLS_TRIMGALORE.out.umitools_version.first().ifEmpty(null)) + // ch_software_versions = ch_software_versions.mix(FASTQC_UMITOOLS_TRIMGALORE.out.trimgalore_version.first().ifEmpty(null)) + + // // + // // MODULE: Remove ribosomal RNA reads + // // + // ch_trimmed_reads = FASTQC_UMITOOLS_TRIMGALORE.out.reads + // ch_sortmerna_multiqc = Channel.empty() + // if (params.remove_ribo_rna) { + // ch_sortmerna_fasta = Channel.from(ch_ribo_db.readLines()).map { row -> file(row) }.collect() + + // SORTMERNA ( + // ch_trimmed_reads, + // ch_sortmerna_fasta + // ) + // .reads + // .set { ch_trimmed_reads } + + // ch_sortmerna_multiqc = SORTMERNA.out.log + // ch_software_versions = ch_software_versions.mix(SORTMERNA.out.version.first().ifEmpty(null)) + // } + + // // + // // SUBWORKFLOW: Alignment with STAR and gene/transcript quantification with Salmon + // // + // ch_genome_bam = Channel.empty() + // ch_genome_bam_index = Channel.empty() + // ch_samtools_stats = Channel.empty() + // ch_samtools_flagstat = Channel.empty() + // ch_samtools_idxstats = Channel.empty() + // ch_star_multiqc = Channel.empty() + // ch_aligner_pca_multiqc = Channel.empty() + // ch_aligner_clustering_multiqc = Channel.empty() + // if (!params.skip_alignment && params.aligner == 'star_salmon') { + // ALIGN_STAR ( + // ch_trimmed_reads, + // PREPARE_GENOME.out.star_index, + // PREPARE_GENOME.out.gtf + // ) + // ch_genome_bam = ALIGN_STAR.out.bam + // ch_genome_bam_index = ALIGN_STAR.out.bai + // ch_transcriptome_bam = ALIGN_STAR.out.bam_transcript + // ch_samtools_stats = ALIGN_STAR.out.stats + // ch_samtools_flagstat = ALIGN_STAR.out.flagstat + // ch_samtools_idxstats = ALIGN_STAR.out.idxstats + // ch_star_multiqc = ALIGN_STAR.out.log_final + // if (params.bam_csi_index) { + // ch_genome_bam_index = ALIGN_STAR.out.csi + // } + // ch_software_versions = ch_software_versions.mix(ALIGN_STAR.out.star_version.first().ifEmpty(null)) + // ch_software_versions = ch_software_versions.mix(ALIGN_STAR.out.samtools_version.first().ifEmpty(null)) + + // // + // // SUBWORKFLOW: Remove duplicate reads from BAM file based on UMIs + // // + // if (params.with_umi) { + // // Deduplicate genome BAM file before downstream analysis + // DEDUP_UMI_UMITOOLS_GENOME ( + // ch_genome_bam.join(ch_genome_bam_index, by: [0]) + // ) + // ch_genome_bam = DEDUP_UMI_UMITOOLS_GENOME.out.bam + // ch_genome_bam_index = DEDUP_UMI_UMITOOLS_GENOME.out.bai + // ch_samtools_stats = DEDUP_UMI_UMITOOLS_GENOME.out.stats + // ch_samtools_flagstat = DEDUP_UMI_UMITOOLS_GENOME.out.flagstat + // ch_samtools_idxstats = DEDUP_UMI_UMITOOLS_GENOME.out.idxstats + // if (params.bam_csi_index) { + // ch_genome_bam_index = DEDUP_UMI_UMITOOLS_GENOME.out.csi + // } + + // // Co-ordinate sort, index and run stats on transcriptome BAM + // BAM_SORT_SAMTOOLS ( + // ch_transcriptome_bam + // ) + // ch_transcriptome_sorted_bam = BAM_SORT_SAMTOOLS.out.bam + // ch_transcriptome_sorted_bai = BAM_SORT_SAMTOOLS.out.bai + + // // Deduplicate transcriptome BAM file before read counting with Salmon + // DEDUP_UMI_UMITOOLS_TRANSCRIPTOME ( + // ch_transcriptome_sorted_bam.join(ch_transcriptome_sorted_bai, by: [0]) + // ) + + // // Name sort BAM before passing to Salmon + // SAMTOOLS_SORT ( + // DEDUP_UMI_UMITOOLS_TRANSCRIPTOME.out.bam + // ) + // ch_transcriptome_bam = SAMTOOLS_SORT.out.bam + // } + + // // + // // SUBWORKFLOW: Count reads from BAM alignments using Salmon + // // + // QUANTIFY_STAR_SALMON ( + // ch_transcriptome_bam, + // ch_dummy_file, + // PREPARE_GENOME.out.transcript_fasta, + // PREPARE_GENOME.out.gtf, + // true, + // params.salmon_quant_libtype ?: '' + // ) + // ch_software_versions = ch_software_versions.mix(QUANTIFY_STAR_SALMON.out.salmon_version.first().ifEmpty(null)) + // ch_software_versions = ch_software_versions.mix(QUANTIFY_STAR_SALMON.out.tximeta_version.ifEmpty(null)) + // ch_software_versions = ch_software_versions.mix(QUANTIFY_STAR_SALMON.out.summarizedexperiment_version.ifEmpty(null)) + + // if (!params.skip_qc & !params.skip_deseq2_qc) { + // DESEQ2_QC_STAR_SALMON ( + // QUANTIFY_STAR_SALMON.out.counts_gene_length_scaled, + // ch_pca_header_multiqc, + // ch_clustering_header_multiqc + // ) + // ch_aligner_pca_multiqc = DESEQ2_QC_STAR_SALMON.out.pca_multiqc + // ch_aligner_clustering_multiqc = DESEQ2_QC_STAR_SALMON.out.dists_multiqc + // ch_software_versions = ch_software_versions.mix(DESEQ2_QC_STAR_SALMON.out.version.ifEmpty(null)) + // } + // } + + // // + // // SUBWORKFLOW: Alignment with STAR and gene/transcript quantification with RSEM + // // + // ch_rsem_multiqc = Channel.empty() + // if (!params.skip_alignment && params.aligner == 'star_rsem') { + // QUANTIFY_RSEM ( + // ch_trimmed_reads, + // PREPARE_GENOME.out.rsem_index + // ) + // ch_genome_bam = QUANTIFY_RSEM.out.bam + // ch_genome_bam_index = QUANTIFY_RSEM.out.bai + // ch_samtools_stats = QUANTIFY_RSEM.out.stats + // ch_samtools_flagstat = QUANTIFY_RSEM.out.flagstat + // ch_samtools_idxstats = QUANTIFY_RSEM.out.idxstats + // ch_star_multiqc = QUANTIFY_RSEM.out.logs + // ch_rsem_multiqc = QUANTIFY_RSEM.out.stat + // if (params.bam_csi_index) { + // ch_genome_bam_index = QUANTIFY_RSEM.out.csi + // } + // ch_software_versions = ch_software_versions.mix(QUANTIFY_RSEM.out.rsem_version.first().ifEmpty(null)) + // ch_software_versions = ch_software_versions.mix(QUANTIFY_RSEM.out.samtools_version.first().ifEmpty(null)) + + // if (!params.skip_qc & !params.skip_deseq2_qc) { + // DESEQ2_QC_RSEM ( + // QUANTIFY_RSEM.out.merged_counts_gene, + // ch_pca_header_multiqc, + // ch_clustering_header_multiqc + // ) + // ch_aligner_pca_multiqc = DESEQ2_QC_RSEM.out.pca_multiqc + // ch_aligner_clustering_multiqc = DESEQ2_QC_RSEM.out.dists_multiqc + // ch_software_versions = ch_software_versions.mix(DESEQ2_QC_RSEM.out.version.ifEmpty(null)) + // } + // } + + // // + // // SUBWORKFLOW: Alignment with HISAT2 + // // + // ch_hisat2_multiqc = Channel.empty() + // if (!params.skip_alignment && params.aligner == 'hisat2') { + // ALIGN_HISAT2 ( + // ch_trimmed_reads, + // PREPARE_GENOME.out.hisat2_index, + // PREPARE_GENOME.out.splicesites + // ) + // ch_genome_bam = ALIGN_HISAT2.out.bam + // ch_genome_bam_index = ALIGN_HISAT2.out.bai + // ch_samtools_stats = ALIGN_HISAT2.out.stats + // ch_samtools_flagstat = ALIGN_HISAT2.out.flagstat + // ch_samtools_idxstats = ALIGN_HISAT2.out.idxstats + // ch_hisat2_multiqc = ALIGN_HISAT2.out.summary + // if (params.bam_csi_index) { + // ch_genome_bam_index = ALIGN_HISAT2.out.csi + // } + // ch_software_versions = ch_software_versions.mix(ALIGN_HISAT2.out.hisat2_version.first().ifEmpty(null)) + // ch_software_versions = ch_software_versions.mix(ALIGN_HISAT2.out.samtools_version.first().ifEmpty(null)) + + // // + // // SUBWORKFLOW: Remove duplicate reads from BAM file based on UMIs + // // + // if (params.with_umi) { + // DEDUP_UMI_UMITOOLS_GENOME ( + // ch_genome_bam.join(ch_genome_bam_index, by: [0]) + // ) + // ch_genome_bam = DEDUP_UMI_UMITOOLS_GENOME.out.bam + // ch_genome_bam_index = DEDUP_UMI_UMITOOLS_GENOME.out.bai + // ch_samtools_stats = DEDUP_UMI_UMITOOLS_GENOME.out.stats + // ch_samtools_flagstat = DEDUP_UMI_UMITOOLS_GENOME.out.flagstat + // ch_samtools_idxstats = DEDUP_UMI_UMITOOLS_GENOME.out.idxstats + // if (params.bam_csi_index) { + // ch_genome_bam_index = DEDUP_UMI_UMITOOLS_GENOME.out.csi + // } + // } + // } + + // // + // // Filter channels to get samples that passed STAR minimum mapping percentage + // // + // ch_fail_mapping_multiqc = Channel.empty() + // if (!params.skip_alignment && params.aligner.contains('star')) { + // ch_star_multiqc + // .map { meta, align_log -> [ meta ] + WorkflowRnaseq.getStarPercentMapped(params, align_log) } + // .set { ch_percent_mapped } + + // ch_genome_bam + // .join(ch_percent_mapped, by: [0]) + // .map { meta, ofile, mapped, pass -> if (pass) [ meta, ofile ] } + // .set { ch_genome_bam } + + // ch_genome_bam_index + // .join(ch_percent_mapped, by: [0]) + // .map { meta, ofile, mapped, pass -> if (pass) [ meta, ofile ] } + // .set { ch_genome_bam_index } + + // ch_percent_mapped + // .branch { meta, mapped, pass -> + // pass: pass + // pass_percent_mapped[meta.id] = mapped + // return [ "$meta.id\t$mapped" ] + // fail: !pass + // fail_percent_mapped[meta.id] = mapped + // return [ "$meta.id\t$mapped" ] + // } + // .set { ch_pass_fail_mapped } + + // MULTIQC_CUSTOM_FAIL_MAPPED ( + // ch_pass_fail_mapped.fail.collect() + // ) + // .set { ch_fail_mapping_multiqc } + // } + + // // + // // MODULE: Run Preseq + // // + // ch_preseq_multiqc = Channel.empty() + // if (!params.skip_alignment && !params.skip_qc && !params.skip_preseq) { + // PRESEQ_LCEXTRAP ( + // ch_genome_bam + // ) + // ch_preseq_multiqc = PRESEQ_LCEXTRAP.out.ccurve + // ch_software_versions = ch_software_versions.mix(PRESEQ_LCEXTRAP.out.version.first().ifEmpty(null)) + // } + + // // + // // SUBWORKFLOW: Mark duplicate reads + // // + // ch_markduplicates_multiqc = Channel.empty() + // if (!params.skip_alignment && !params.skip_markduplicates) { + // MARK_DUPLICATES_PICARD ( + // ch_genome_bam + // ) + // ch_genome_bam = MARK_DUPLICATES_PICARD.out.bam + // ch_genome_bam_index = MARK_DUPLICATES_PICARD.out.bai + // ch_samtools_stats = MARK_DUPLICATES_PICARD.out.stats + // ch_samtools_flagstat = MARK_DUPLICATES_PICARD.out.flagstat + // ch_samtools_idxstats = MARK_DUPLICATES_PICARD.out.idxstats + // ch_markduplicates_multiqc = MARK_DUPLICATES_PICARD.out.metrics + // if (params.bam_csi_index) { + // ch_genome_bam_index = MARK_DUPLICATES_PICARD.out.csi + // } + // ch_software_versions = ch_software_versions.mix(MARK_DUPLICATES_PICARD.out.picard_version.first().ifEmpty(null)) + // } + + // // + // // MODULE: STRINGTIE + // // + // if (!params.skip_alignment && !params.skip_stringtie) { + // STRINGTIE ( + // ch_genome_bam, + // PREPARE_GENOME.out.gtf + // ) + // ch_software_versions = ch_software_versions.mix(STRINGTIE.out.version.first().ifEmpty(null)) + // } + + // // + // // MODULE: Feature biotype QC using featureCounts + // // + // ch_featurecounts_multiqc = Channel.empty() + // if (!params.skip_alignment && !params.skip_qc && !params.skip_biotype_qc && biotype) { + + // PREPARE_GENOME + // .out + // .gtf + // .map { WorkflowRnaseq.biotypeInGtf(it, biotype, log) } + // .set { biotype_in_gtf } + + // // Prevent any samples from running if GTF file doesn't have a valid biotype + // ch_genome_bam + // .combine(PREPARE_GENOME.out.gtf) + // .combine(biotype_in_gtf) + // .filter { it[-1] } + // .map { it[0.. 0) { + // RSEQC ( + // ch_genome_bam, + // PREPARE_GENOME.out.gene_bed, + // rseqc_modules + // ) + // ch_bamstat_multiqc = RSEQC.out.bamstat_txt + // ch_inferexperiment_multiqc = RSEQC.out.inferexperiment_txt + // ch_innerdistance_multiqc = RSEQC.out.innerdistance_freq + // ch_junctionannotation_multiqc = RSEQC.out.junctionannotation_log + // ch_junctionsaturation_multiqc = RSEQC.out.junctionsaturation_rscript + // ch_readdistribution_multiqc = RSEQC.out.readdistribution_txt + // ch_readduplication_multiqc = RSEQC.out.readduplication_pos_xls + // ch_software_versions = ch_software_versions.mix(RSEQC.out.version.first().ifEmpty(null)) + + // ch_inferexperiment_multiqc + // .map { meta, strand_log -> [ meta ] + WorkflowRnaseq.getInferexperimentStrandedness(strand_log, 30) } + // .filter { it[0].strandedness != it[1] } + // .map { meta, strandedness, sense, antisense, undetermined -> + // [ "$meta.id\t$meta.strandedness\t$strandedness\t$sense\t$antisense\t$undetermined" ] + // } + // .set { ch_fail_strand } + + // MULTIQC_CUSTOM_STRAND_CHECK ( + // ch_fail_strand.collect() + // ) + // .set { ch_fail_strand_multiqc } + // } + // } + + // // + // // SUBWORKFLOW: Pseudo-alignment and quantification with Salmon + // // + // ch_salmon_multiqc = Channel.empty() + // ch_pseudoaligner_pca_multiqc = Channel.empty() + // ch_pseudoaligner_clustering_multiqc = Channel.empty() + // if (params.pseudo_aligner == 'salmon') { + // QUANTIFY_SALMON ( + // ch_trimmed_reads, + // PREPARE_GENOME.out.salmon_index, + // ch_dummy_file, + // PREPARE_GENOME.out.gtf, + // false, + // params.salmon_quant_libtype ?: '' + // ) + // ch_salmon_multiqc = QUANTIFY_SALMON.out.results + // if (params.skip_alignment && params.aligner != 'star_salmon') { + // ch_software_versions = ch_software_versions.mix(QUANTIFY_SALMON.out.salmon_version.first().ifEmpty(null)) + // ch_software_versions = ch_software_versions.mix(QUANTIFY_SALMON.out.tximeta_version.ifEmpty(null)) + // ch_software_versions = ch_software_versions.mix(QUANTIFY_SALMON.out.summarizedexperiment_version.ifEmpty(null)) + // } + + // if (!params.skip_qc & !params.skip_deseq2_qc) { + // DESEQ2_QC_SALMON ( + // QUANTIFY_SALMON.out.counts_gene_length_scaled, + // ch_pca_header_multiqc, + // ch_clustering_header_multiqc + // ) + // ch_pseudoaligner_pca_multiqc = DESEQ2_QC_SALMON.out.pca_multiqc + // ch_pseudoaligner_clustering_multiqc = DESEQ2_QC_SALMON.out.dists_multiqc + // if (params.skip_alignment) { + // ch_software_versions = ch_software_versions.mix(DESEQ2_QC_SALMON.out.version.ifEmpty(null)) + // } + // } + // } + + // // + // // MODULE: Pipeline reporting + // // + // ch_software_versions + // .map { it -> if (it) [ it.baseName, it ] } + // .groupTuple() + // .map { it[1][0] } + // .flatten() + // .collect() + // .set { ch_software_versions } + + // GET_SOFTWARE_VERSIONS ( + // ch_software_versions.map { it }.collect() + // ) + + // // + // // MODULE: MultiQC + // // + // if (!params.skip_multiqc) { + // workflow_summary = WorkflowRnaseq.paramsSummaryMultiqc(workflow, summary_params) + // ch_workflow_summary = Channel.value(workflow_summary) + + // MULTIQC ( + // ch_multiqc_config, + // ch_multiqc_custom_config.collect().ifEmpty([]), + // GET_SOFTWARE_VERSIONS.out.yaml.collect(), + // ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'), + // ch_fail_mapping_multiqc.ifEmpty([]), + // ch_fail_strand_multiqc.ifEmpty([]), + // FASTQC_UMITOOLS_TRIMGALORE.out.fastqc_zip.collect{it[1]}.ifEmpty([]), + // FASTQC_UMITOOLS_TRIMGALORE.out.trim_zip.collect{it[1]}.ifEmpty([]), + // FASTQC_UMITOOLS_TRIMGALORE.out.trim_log.collect{it[1]}.ifEmpty([]), + // ch_sortmerna_multiqc.collect{it[1]}.ifEmpty([]), + // ch_star_multiqc.collect{it[1]}.ifEmpty([]), + // ch_hisat2_multiqc.collect{it[1]}.ifEmpty([]), + // ch_rsem_multiqc.collect{it[1]}.ifEmpty([]), + // ch_salmon_multiqc.collect{it[1]}.ifEmpty([]), + // ch_samtools_stats.collect{it[1]}.ifEmpty([]), + // ch_samtools_flagstat.collect{it[1]}.ifEmpty([]), + // ch_samtools_idxstats.collect{it[1]}.ifEmpty([]), + // ch_markduplicates_multiqc.collect{it[1]}.ifEmpty([]), + // ch_featurecounts_multiqc.collect{it[1]}.ifEmpty([]), + // ch_aligner_pca_multiqc.collect().ifEmpty([]), + // ch_aligner_clustering_multiqc.collect().ifEmpty([]), + // ch_pseudoaligner_pca_multiqc.collect().ifEmpty([]), + // ch_pseudoaligner_clustering_multiqc.collect().ifEmpty([]), + // ch_preseq_multiqc.collect{it[1]}.ifEmpty([]), + // ch_qualimap_multiqc.collect{it[1]}.ifEmpty([]), + // ch_dupradar_multiqc.collect{it[1]}.ifEmpty([]), + // ch_bamstat_multiqc.collect{it[1]}.ifEmpty([]), + // ch_inferexperiment_multiqc.collect{it[1]}.ifEmpty([]), + // ch_innerdistance_multiqc.collect{it[1]}.ifEmpty([]), + // ch_junctionannotation_multiqc.collect{it[1]}.ifEmpty([]), + // ch_junctionsaturation_multiqc.collect{it[1]}.ifEmpty([]), + // ch_readdistribution_multiqc.collect{it[1]}.ifEmpty([]), + // ch_readduplication_multiqc.collect{it[1]}.ifEmpty([]) + // ) + // multiqc_report = MULTIQC.out.report.toList() + // } } /* From 010f08f8ae6a8b455851da37349fa9f76fdace2a Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Tue, 27 Jul 2021 22:39:20 +0100 Subject: [PATCH 29/31] Fix logic after testing --- lib/WorkflowRnaseq.groovy | 9 +- workflows/rnaseq.nf | 1058 ++++++++++++++++++------------------- 2 files changed, 536 insertions(+), 531 deletions(-) diff --git a/lib/WorkflowRnaseq.groovy b/lib/WorkflowRnaseq.groovy index 55df2289d..a496815c3 100755 --- a/lib/WorkflowRnaseq.groovy +++ b/lib/WorkflowRnaseq.groovy @@ -69,14 +69,19 @@ class WorkflowRnaseq { // Warn if --additional_fasta provided with aligner index if (!params.skip_alignment && params.additional_fasta) { - def index = 'star' + def index = '' + if (params.aligner == 'star_salmon' && params.star_index) { + index = 'star' + } if (params.aligner == 'star_rsem' && params.rsem_index) { index = 'rsem' } if (params.aligner == 'hisat2' && params.hisat2_index) { index = 'hisat2' } - additionaFastaIndexWarn(index, log) + if (index) { + additionaFastaIndexWarn(index, log) + } } // Check which RSeQC modules we are running diff --git a/workflows/rnaseq.nf b/workflows/rnaseq.nf index 3fd1cc90a..8c17d5633 100755 --- a/workflows/rnaseq.nf +++ b/workflows/rnaseq.nf @@ -234,535 +234,535 @@ def fail_percent_mapped = [:] workflow RNASEQ { - // // - // // SUBWORKFLOW: Uncompress and prepare reference genome files - // // - // PREPARE_GENOME ( - // prepareToolIndices, - // biotype - // ) - // ch_software_versions = Channel.empty() - // ch_software_versions = ch_software_versions.mix(PREPARE_GENOME.out.gffread_version.ifEmpty(null)) - - // // - // // SUBWORKFLOW: Read in samplesheet, validate and stage input files - // // - // INPUT_CHECK ( - // ch_input - // ) - // .map { - // meta, fastq -> - // meta.id = meta.id.split('_')[0..-2].join('_') - // [ meta, fastq ] } - // .groupTuple(by: [0]) - // .branch { - // meta, fastq -> - // single : fastq.size() == 1 - // return [ meta, fastq.flatten() ] - // multiple: fastq.size() > 1 - // return [ meta, fastq.flatten() ] - // } - // .set { ch_fastq } - - // // - // // MODULE: Concatenate FastQ files from same sample if required - // // - // CAT_FASTQ ( - // ch_fastq.multiple - // ) - // .mix(ch_fastq.single) - // .set { ch_cat_fastq } - - // // - // // SUBWORKFLOW: Read QC, extract UMI and trim adapters - // // - // FASTQC_UMITOOLS_TRIMGALORE ( - // ch_cat_fastq, - // params.skip_fastqc || params.skip_qc, - // params.with_umi, - // params.skip_trimming - // ) - // ch_software_versions = ch_software_versions.mix(FASTQC_UMITOOLS_TRIMGALORE.out.fastqc_version.first().ifEmpty(null)) - // ch_software_versions = ch_software_versions.mix(FASTQC_UMITOOLS_TRIMGALORE.out.umitools_version.first().ifEmpty(null)) - // ch_software_versions = ch_software_versions.mix(FASTQC_UMITOOLS_TRIMGALORE.out.trimgalore_version.first().ifEmpty(null)) - - // // - // // MODULE: Remove ribosomal RNA reads - // // - // ch_trimmed_reads = FASTQC_UMITOOLS_TRIMGALORE.out.reads - // ch_sortmerna_multiqc = Channel.empty() - // if (params.remove_ribo_rna) { - // ch_sortmerna_fasta = Channel.from(ch_ribo_db.readLines()).map { row -> file(row) }.collect() - - // SORTMERNA ( - // ch_trimmed_reads, - // ch_sortmerna_fasta - // ) - // .reads - // .set { ch_trimmed_reads } - - // ch_sortmerna_multiqc = SORTMERNA.out.log - // ch_software_versions = ch_software_versions.mix(SORTMERNA.out.version.first().ifEmpty(null)) - // } - - // // - // // SUBWORKFLOW: Alignment with STAR and gene/transcript quantification with Salmon - // // - // ch_genome_bam = Channel.empty() - // ch_genome_bam_index = Channel.empty() - // ch_samtools_stats = Channel.empty() - // ch_samtools_flagstat = Channel.empty() - // ch_samtools_idxstats = Channel.empty() - // ch_star_multiqc = Channel.empty() - // ch_aligner_pca_multiqc = Channel.empty() - // ch_aligner_clustering_multiqc = Channel.empty() - // if (!params.skip_alignment && params.aligner == 'star_salmon') { - // ALIGN_STAR ( - // ch_trimmed_reads, - // PREPARE_GENOME.out.star_index, - // PREPARE_GENOME.out.gtf - // ) - // ch_genome_bam = ALIGN_STAR.out.bam - // ch_genome_bam_index = ALIGN_STAR.out.bai - // ch_transcriptome_bam = ALIGN_STAR.out.bam_transcript - // ch_samtools_stats = ALIGN_STAR.out.stats - // ch_samtools_flagstat = ALIGN_STAR.out.flagstat - // ch_samtools_idxstats = ALIGN_STAR.out.idxstats - // ch_star_multiqc = ALIGN_STAR.out.log_final - // if (params.bam_csi_index) { - // ch_genome_bam_index = ALIGN_STAR.out.csi - // } - // ch_software_versions = ch_software_versions.mix(ALIGN_STAR.out.star_version.first().ifEmpty(null)) - // ch_software_versions = ch_software_versions.mix(ALIGN_STAR.out.samtools_version.first().ifEmpty(null)) - - // // - // // SUBWORKFLOW: Remove duplicate reads from BAM file based on UMIs - // // - // if (params.with_umi) { - // // Deduplicate genome BAM file before downstream analysis - // DEDUP_UMI_UMITOOLS_GENOME ( - // ch_genome_bam.join(ch_genome_bam_index, by: [0]) - // ) - // ch_genome_bam = DEDUP_UMI_UMITOOLS_GENOME.out.bam - // ch_genome_bam_index = DEDUP_UMI_UMITOOLS_GENOME.out.bai - // ch_samtools_stats = DEDUP_UMI_UMITOOLS_GENOME.out.stats - // ch_samtools_flagstat = DEDUP_UMI_UMITOOLS_GENOME.out.flagstat - // ch_samtools_idxstats = DEDUP_UMI_UMITOOLS_GENOME.out.idxstats - // if (params.bam_csi_index) { - // ch_genome_bam_index = DEDUP_UMI_UMITOOLS_GENOME.out.csi - // } - - // // Co-ordinate sort, index and run stats on transcriptome BAM - // BAM_SORT_SAMTOOLS ( - // ch_transcriptome_bam - // ) - // ch_transcriptome_sorted_bam = BAM_SORT_SAMTOOLS.out.bam - // ch_transcriptome_sorted_bai = BAM_SORT_SAMTOOLS.out.bai - - // // Deduplicate transcriptome BAM file before read counting with Salmon - // DEDUP_UMI_UMITOOLS_TRANSCRIPTOME ( - // ch_transcriptome_sorted_bam.join(ch_transcriptome_sorted_bai, by: [0]) - // ) - - // // Name sort BAM before passing to Salmon - // SAMTOOLS_SORT ( - // DEDUP_UMI_UMITOOLS_TRANSCRIPTOME.out.bam - // ) - // ch_transcriptome_bam = SAMTOOLS_SORT.out.bam - // } - - // // - // // SUBWORKFLOW: Count reads from BAM alignments using Salmon - // // - // QUANTIFY_STAR_SALMON ( - // ch_transcriptome_bam, - // ch_dummy_file, - // PREPARE_GENOME.out.transcript_fasta, - // PREPARE_GENOME.out.gtf, - // true, - // params.salmon_quant_libtype ?: '' - // ) - // ch_software_versions = ch_software_versions.mix(QUANTIFY_STAR_SALMON.out.salmon_version.first().ifEmpty(null)) - // ch_software_versions = ch_software_versions.mix(QUANTIFY_STAR_SALMON.out.tximeta_version.ifEmpty(null)) - // ch_software_versions = ch_software_versions.mix(QUANTIFY_STAR_SALMON.out.summarizedexperiment_version.ifEmpty(null)) - - // if (!params.skip_qc & !params.skip_deseq2_qc) { - // DESEQ2_QC_STAR_SALMON ( - // QUANTIFY_STAR_SALMON.out.counts_gene_length_scaled, - // ch_pca_header_multiqc, - // ch_clustering_header_multiqc - // ) - // ch_aligner_pca_multiqc = DESEQ2_QC_STAR_SALMON.out.pca_multiqc - // ch_aligner_clustering_multiqc = DESEQ2_QC_STAR_SALMON.out.dists_multiqc - // ch_software_versions = ch_software_versions.mix(DESEQ2_QC_STAR_SALMON.out.version.ifEmpty(null)) - // } - // } - - // // - // // SUBWORKFLOW: Alignment with STAR and gene/transcript quantification with RSEM - // // - // ch_rsem_multiqc = Channel.empty() - // if (!params.skip_alignment && params.aligner == 'star_rsem') { - // QUANTIFY_RSEM ( - // ch_trimmed_reads, - // PREPARE_GENOME.out.rsem_index - // ) - // ch_genome_bam = QUANTIFY_RSEM.out.bam - // ch_genome_bam_index = QUANTIFY_RSEM.out.bai - // ch_samtools_stats = QUANTIFY_RSEM.out.stats - // ch_samtools_flagstat = QUANTIFY_RSEM.out.flagstat - // ch_samtools_idxstats = QUANTIFY_RSEM.out.idxstats - // ch_star_multiqc = QUANTIFY_RSEM.out.logs - // ch_rsem_multiqc = QUANTIFY_RSEM.out.stat - // if (params.bam_csi_index) { - // ch_genome_bam_index = QUANTIFY_RSEM.out.csi - // } - // ch_software_versions = ch_software_versions.mix(QUANTIFY_RSEM.out.rsem_version.first().ifEmpty(null)) - // ch_software_versions = ch_software_versions.mix(QUANTIFY_RSEM.out.samtools_version.first().ifEmpty(null)) - - // if (!params.skip_qc & !params.skip_deseq2_qc) { - // DESEQ2_QC_RSEM ( - // QUANTIFY_RSEM.out.merged_counts_gene, - // ch_pca_header_multiqc, - // ch_clustering_header_multiqc - // ) - // ch_aligner_pca_multiqc = DESEQ2_QC_RSEM.out.pca_multiqc - // ch_aligner_clustering_multiqc = DESEQ2_QC_RSEM.out.dists_multiqc - // ch_software_versions = ch_software_versions.mix(DESEQ2_QC_RSEM.out.version.ifEmpty(null)) - // } - // } - - // // - // // SUBWORKFLOW: Alignment with HISAT2 - // // - // ch_hisat2_multiqc = Channel.empty() - // if (!params.skip_alignment && params.aligner == 'hisat2') { - // ALIGN_HISAT2 ( - // ch_trimmed_reads, - // PREPARE_GENOME.out.hisat2_index, - // PREPARE_GENOME.out.splicesites - // ) - // ch_genome_bam = ALIGN_HISAT2.out.bam - // ch_genome_bam_index = ALIGN_HISAT2.out.bai - // ch_samtools_stats = ALIGN_HISAT2.out.stats - // ch_samtools_flagstat = ALIGN_HISAT2.out.flagstat - // ch_samtools_idxstats = ALIGN_HISAT2.out.idxstats - // ch_hisat2_multiqc = ALIGN_HISAT2.out.summary - // if (params.bam_csi_index) { - // ch_genome_bam_index = ALIGN_HISAT2.out.csi - // } - // ch_software_versions = ch_software_versions.mix(ALIGN_HISAT2.out.hisat2_version.first().ifEmpty(null)) - // ch_software_versions = ch_software_versions.mix(ALIGN_HISAT2.out.samtools_version.first().ifEmpty(null)) - - // // - // // SUBWORKFLOW: Remove duplicate reads from BAM file based on UMIs - // // - // if (params.with_umi) { - // DEDUP_UMI_UMITOOLS_GENOME ( - // ch_genome_bam.join(ch_genome_bam_index, by: [0]) - // ) - // ch_genome_bam = DEDUP_UMI_UMITOOLS_GENOME.out.bam - // ch_genome_bam_index = DEDUP_UMI_UMITOOLS_GENOME.out.bai - // ch_samtools_stats = DEDUP_UMI_UMITOOLS_GENOME.out.stats - // ch_samtools_flagstat = DEDUP_UMI_UMITOOLS_GENOME.out.flagstat - // ch_samtools_idxstats = DEDUP_UMI_UMITOOLS_GENOME.out.idxstats - // if (params.bam_csi_index) { - // ch_genome_bam_index = DEDUP_UMI_UMITOOLS_GENOME.out.csi - // } - // } - // } - - // // - // // Filter channels to get samples that passed STAR minimum mapping percentage - // // - // ch_fail_mapping_multiqc = Channel.empty() - // if (!params.skip_alignment && params.aligner.contains('star')) { - // ch_star_multiqc - // .map { meta, align_log -> [ meta ] + WorkflowRnaseq.getStarPercentMapped(params, align_log) } - // .set { ch_percent_mapped } - - // ch_genome_bam - // .join(ch_percent_mapped, by: [0]) - // .map { meta, ofile, mapped, pass -> if (pass) [ meta, ofile ] } - // .set { ch_genome_bam } - - // ch_genome_bam_index - // .join(ch_percent_mapped, by: [0]) - // .map { meta, ofile, mapped, pass -> if (pass) [ meta, ofile ] } - // .set { ch_genome_bam_index } - - // ch_percent_mapped - // .branch { meta, mapped, pass -> - // pass: pass - // pass_percent_mapped[meta.id] = mapped - // return [ "$meta.id\t$mapped" ] - // fail: !pass - // fail_percent_mapped[meta.id] = mapped - // return [ "$meta.id\t$mapped" ] - // } - // .set { ch_pass_fail_mapped } - - // MULTIQC_CUSTOM_FAIL_MAPPED ( - // ch_pass_fail_mapped.fail.collect() - // ) - // .set { ch_fail_mapping_multiqc } - // } - - // // - // // MODULE: Run Preseq - // // - // ch_preseq_multiqc = Channel.empty() - // if (!params.skip_alignment && !params.skip_qc && !params.skip_preseq) { - // PRESEQ_LCEXTRAP ( - // ch_genome_bam - // ) - // ch_preseq_multiqc = PRESEQ_LCEXTRAP.out.ccurve - // ch_software_versions = ch_software_versions.mix(PRESEQ_LCEXTRAP.out.version.first().ifEmpty(null)) - // } - - // // - // // SUBWORKFLOW: Mark duplicate reads - // // - // ch_markduplicates_multiqc = Channel.empty() - // if (!params.skip_alignment && !params.skip_markduplicates) { - // MARK_DUPLICATES_PICARD ( - // ch_genome_bam - // ) - // ch_genome_bam = MARK_DUPLICATES_PICARD.out.bam - // ch_genome_bam_index = MARK_DUPLICATES_PICARD.out.bai - // ch_samtools_stats = MARK_DUPLICATES_PICARD.out.stats - // ch_samtools_flagstat = MARK_DUPLICATES_PICARD.out.flagstat - // ch_samtools_idxstats = MARK_DUPLICATES_PICARD.out.idxstats - // ch_markduplicates_multiqc = MARK_DUPLICATES_PICARD.out.metrics - // if (params.bam_csi_index) { - // ch_genome_bam_index = MARK_DUPLICATES_PICARD.out.csi - // } - // ch_software_versions = ch_software_versions.mix(MARK_DUPLICATES_PICARD.out.picard_version.first().ifEmpty(null)) - // } - - // // - // // MODULE: STRINGTIE - // // - // if (!params.skip_alignment && !params.skip_stringtie) { - // STRINGTIE ( - // ch_genome_bam, - // PREPARE_GENOME.out.gtf - // ) - // ch_software_versions = ch_software_versions.mix(STRINGTIE.out.version.first().ifEmpty(null)) - // } - - // // - // // MODULE: Feature biotype QC using featureCounts - // // - // ch_featurecounts_multiqc = Channel.empty() - // if (!params.skip_alignment && !params.skip_qc && !params.skip_biotype_qc && biotype) { - - // PREPARE_GENOME - // .out - // .gtf - // .map { WorkflowRnaseq.biotypeInGtf(it, biotype, log) } - // .set { biotype_in_gtf } - - // // Prevent any samples from running if GTF file doesn't have a valid biotype - // ch_genome_bam - // .combine(PREPARE_GENOME.out.gtf) - // .combine(biotype_in_gtf) - // .filter { it[-1] } - // .map { it[0.. 0) { - // RSEQC ( - // ch_genome_bam, - // PREPARE_GENOME.out.gene_bed, - // rseqc_modules - // ) - // ch_bamstat_multiqc = RSEQC.out.bamstat_txt - // ch_inferexperiment_multiqc = RSEQC.out.inferexperiment_txt - // ch_innerdistance_multiqc = RSEQC.out.innerdistance_freq - // ch_junctionannotation_multiqc = RSEQC.out.junctionannotation_log - // ch_junctionsaturation_multiqc = RSEQC.out.junctionsaturation_rscript - // ch_readdistribution_multiqc = RSEQC.out.readdistribution_txt - // ch_readduplication_multiqc = RSEQC.out.readduplication_pos_xls - // ch_software_versions = ch_software_versions.mix(RSEQC.out.version.first().ifEmpty(null)) - - // ch_inferexperiment_multiqc - // .map { meta, strand_log -> [ meta ] + WorkflowRnaseq.getInferexperimentStrandedness(strand_log, 30) } - // .filter { it[0].strandedness != it[1] } - // .map { meta, strandedness, sense, antisense, undetermined -> - // [ "$meta.id\t$meta.strandedness\t$strandedness\t$sense\t$antisense\t$undetermined" ] - // } - // .set { ch_fail_strand } - - // MULTIQC_CUSTOM_STRAND_CHECK ( - // ch_fail_strand.collect() - // ) - // .set { ch_fail_strand_multiqc } - // } - // } - - // // - // // SUBWORKFLOW: Pseudo-alignment and quantification with Salmon - // // - // ch_salmon_multiqc = Channel.empty() - // ch_pseudoaligner_pca_multiqc = Channel.empty() - // ch_pseudoaligner_clustering_multiqc = Channel.empty() - // if (params.pseudo_aligner == 'salmon') { - // QUANTIFY_SALMON ( - // ch_trimmed_reads, - // PREPARE_GENOME.out.salmon_index, - // ch_dummy_file, - // PREPARE_GENOME.out.gtf, - // false, - // params.salmon_quant_libtype ?: '' - // ) - // ch_salmon_multiqc = QUANTIFY_SALMON.out.results - // if (params.skip_alignment && params.aligner != 'star_salmon') { - // ch_software_versions = ch_software_versions.mix(QUANTIFY_SALMON.out.salmon_version.first().ifEmpty(null)) - // ch_software_versions = ch_software_versions.mix(QUANTIFY_SALMON.out.tximeta_version.ifEmpty(null)) - // ch_software_versions = ch_software_versions.mix(QUANTIFY_SALMON.out.summarizedexperiment_version.ifEmpty(null)) - // } - - // if (!params.skip_qc & !params.skip_deseq2_qc) { - // DESEQ2_QC_SALMON ( - // QUANTIFY_SALMON.out.counts_gene_length_scaled, - // ch_pca_header_multiqc, - // ch_clustering_header_multiqc - // ) - // ch_pseudoaligner_pca_multiqc = DESEQ2_QC_SALMON.out.pca_multiqc - // ch_pseudoaligner_clustering_multiqc = DESEQ2_QC_SALMON.out.dists_multiqc - // if (params.skip_alignment) { - // ch_software_versions = ch_software_versions.mix(DESEQ2_QC_SALMON.out.version.ifEmpty(null)) - // } - // } - // } - - // // - // // MODULE: Pipeline reporting - // // - // ch_software_versions - // .map { it -> if (it) [ it.baseName, it ] } - // .groupTuple() - // .map { it[1][0] } - // .flatten() - // .collect() - // .set { ch_software_versions } - - // GET_SOFTWARE_VERSIONS ( - // ch_software_versions.map { it }.collect() - // ) - - // // - // // MODULE: MultiQC - // // - // if (!params.skip_multiqc) { - // workflow_summary = WorkflowRnaseq.paramsSummaryMultiqc(workflow, summary_params) - // ch_workflow_summary = Channel.value(workflow_summary) - - // MULTIQC ( - // ch_multiqc_config, - // ch_multiqc_custom_config.collect().ifEmpty([]), - // GET_SOFTWARE_VERSIONS.out.yaml.collect(), - // ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'), - // ch_fail_mapping_multiqc.ifEmpty([]), - // ch_fail_strand_multiqc.ifEmpty([]), - // FASTQC_UMITOOLS_TRIMGALORE.out.fastqc_zip.collect{it[1]}.ifEmpty([]), - // FASTQC_UMITOOLS_TRIMGALORE.out.trim_zip.collect{it[1]}.ifEmpty([]), - // FASTQC_UMITOOLS_TRIMGALORE.out.trim_log.collect{it[1]}.ifEmpty([]), - // ch_sortmerna_multiqc.collect{it[1]}.ifEmpty([]), - // ch_star_multiqc.collect{it[1]}.ifEmpty([]), - // ch_hisat2_multiqc.collect{it[1]}.ifEmpty([]), - // ch_rsem_multiqc.collect{it[1]}.ifEmpty([]), - // ch_salmon_multiqc.collect{it[1]}.ifEmpty([]), - // ch_samtools_stats.collect{it[1]}.ifEmpty([]), - // ch_samtools_flagstat.collect{it[1]}.ifEmpty([]), - // ch_samtools_idxstats.collect{it[1]}.ifEmpty([]), - // ch_markduplicates_multiqc.collect{it[1]}.ifEmpty([]), - // ch_featurecounts_multiqc.collect{it[1]}.ifEmpty([]), - // ch_aligner_pca_multiqc.collect().ifEmpty([]), - // ch_aligner_clustering_multiqc.collect().ifEmpty([]), - // ch_pseudoaligner_pca_multiqc.collect().ifEmpty([]), - // ch_pseudoaligner_clustering_multiqc.collect().ifEmpty([]), - // ch_preseq_multiqc.collect{it[1]}.ifEmpty([]), - // ch_qualimap_multiqc.collect{it[1]}.ifEmpty([]), - // ch_dupradar_multiqc.collect{it[1]}.ifEmpty([]), - // ch_bamstat_multiqc.collect{it[1]}.ifEmpty([]), - // ch_inferexperiment_multiqc.collect{it[1]}.ifEmpty([]), - // ch_innerdistance_multiqc.collect{it[1]}.ifEmpty([]), - // ch_junctionannotation_multiqc.collect{it[1]}.ifEmpty([]), - // ch_junctionsaturation_multiqc.collect{it[1]}.ifEmpty([]), - // ch_readdistribution_multiqc.collect{it[1]}.ifEmpty([]), - // ch_readduplication_multiqc.collect{it[1]}.ifEmpty([]) - // ) - // multiqc_report = MULTIQC.out.report.toList() - // } + // + // SUBWORKFLOW: Uncompress and prepare reference genome files + // + PREPARE_GENOME ( + prepareToolIndices, + biotype + ) + ch_software_versions = Channel.empty() + ch_software_versions = ch_software_versions.mix(PREPARE_GENOME.out.gffread_version.ifEmpty(null)) + + // + // SUBWORKFLOW: Read in samplesheet, validate and stage input files + // + INPUT_CHECK ( + ch_input + ) + .map { + meta, fastq -> + meta.id = meta.id.split('_')[0..-2].join('_') + [ meta, fastq ] } + .groupTuple(by: [0]) + .branch { + meta, fastq -> + single : fastq.size() == 1 + return [ meta, fastq.flatten() ] + multiple: fastq.size() > 1 + return [ meta, fastq.flatten() ] + } + .set { ch_fastq } + + // + // MODULE: Concatenate FastQ files from same sample if required + // + CAT_FASTQ ( + ch_fastq.multiple + ) + .mix(ch_fastq.single) + .set { ch_cat_fastq } + + // + // SUBWORKFLOW: Read QC, extract UMI and trim adapters + // + FASTQC_UMITOOLS_TRIMGALORE ( + ch_cat_fastq, + params.skip_fastqc || params.skip_qc, + params.with_umi, + params.skip_trimming + ) + ch_software_versions = ch_software_versions.mix(FASTQC_UMITOOLS_TRIMGALORE.out.fastqc_version.first().ifEmpty(null)) + ch_software_versions = ch_software_versions.mix(FASTQC_UMITOOLS_TRIMGALORE.out.umitools_version.first().ifEmpty(null)) + ch_software_versions = ch_software_versions.mix(FASTQC_UMITOOLS_TRIMGALORE.out.trimgalore_version.first().ifEmpty(null)) + + // + // MODULE: Remove ribosomal RNA reads + // + ch_trimmed_reads = FASTQC_UMITOOLS_TRIMGALORE.out.reads + ch_sortmerna_multiqc = Channel.empty() + if (params.remove_ribo_rna) { + ch_sortmerna_fasta = Channel.from(ch_ribo_db.readLines()).map { row -> file(row) }.collect() + + SORTMERNA ( + ch_trimmed_reads, + ch_sortmerna_fasta + ) + .reads + .set { ch_trimmed_reads } + + ch_sortmerna_multiqc = SORTMERNA.out.log + ch_software_versions = ch_software_versions.mix(SORTMERNA.out.version.first().ifEmpty(null)) + } + + // + // SUBWORKFLOW: Alignment with STAR and gene/transcript quantification with Salmon + // + ch_genome_bam = Channel.empty() + ch_genome_bam_index = Channel.empty() + ch_samtools_stats = Channel.empty() + ch_samtools_flagstat = Channel.empty() + ch_samtools_idxstats = Channel.empty() + ch_star_multiqc = Channel.empty() + ch_aligner_pca_multiqc = Channel.empty() + ch_aligner_clustering_multiqc = Channel.empty() + if (!params.skip_alignment && params.aligner == 'star_salmon') { + ALIGN_STAR ( + ch_trimmed_reads, + PREPARE_GENOME.out.star_index, + PREPARE_GENOME.out.gtf + ) + ch_genome_bam = ALIGN_STAR.out.bam + ch_genome_bam_index = ALIGN_STAR.out.bai + ch_transcriptome_bam = ALIGN_STAR.out.bam_transcript + ch_samtools_stats = ALIGN_STAR.out.stats + ch_samtools_flagstat = ALIGN_STAR.out.flagstat + ch_samtools_idxstats = ALIGN_STAR.out.idxstats + ch_star_multiqc = ALIGN_STAR.out.log_final + if (params.bam_csi_index) { + ch_genome_bam_index = ALIGN_STAR.out.csi + } + ch_software_versions = ch_software_versions.mix(ALIGN_STAR.out.star_version.first().ifEmpty(null)) + ch_software_versions = ch_software_versions.mix(ALIGN_STAR.out.samtools_version.first().ifEmpty(null)) + + // + // SUBWORKFLOW: Remove duplicate reads from BAM file based on UMIs + // + if (params.with_umi) { + // Deduplicate genome BAM file before downstream analysis + DEDUP_UMI_UMITOOLS_GENOME ( + ch_genome_bam.join(ch_genome_bam_index, by: [0]) + ) + ch_genome_bam = DEDUP_UMI_UMITOOLS_GENOME.out.bam + ch_genome_bam_index = DEDUP_UMI_UMITOOLS_GENOME.out.bai + ch_samtools_stats = DEDUP_UMI_UMITOOLS_GENOME.out.stats + ch_samtools_flagstat = DEDUP_UMI_UMITOOLS_GENOME.out.flagstat + ch_samtools_idxstats = DEDUP_UMI_UMITOOLS_GENOME.out.idxstats + if (params.bam_csi_index) { + ch_genome_bam_index = DEDUP_UMI_UMITOOLS_GENOME.out.csi + } + + // Co-ordinate sort, index and run stats on transcriptome BAM + BAM_SORT_SAMTOOLS ( + ch_transcriptome_bam + ) + ch_transcriptome_sorted_bam = BAM_SORT_SAMTOOLS.out.bam + ch_transcriptome_sorted_bai = BAM_SORT_SAMTOOLS.out.bai + + // Deduplicate transcriptome BAM file before read counting with Salmon + DEDUP_UMI_UMITOOLS_TRANSCRIPTOME ( + ch_transcriptome_sorted_bam.join(ch_transcriptome_sorted_bai, by: [0]) + ) + + // Name sort BAM before passing to Salmon + SAMTOOLS_SORT ( + DEDUP_UMI_UMITOOLS_TRANSCRIPTOME.out.bam + ) + ch_transcriptome_bam = SAMTOOLS_SORT.out.bam + } + + // + // SUBWORKFLOW: Count reads from BAM alignments using Salmon + // + QUANTIFY_STAR_SALMON ( + ch_transcriptome_bam, + ch_dummy_file, + PREPARE_GENOME.out.transcript_fasta, + PREPARE_GENOME.out.gtf, + true, + params.salmon_quant_libtype ?: '' + ) + ch_software_versions = ch_software_versions.mix(QUANTIFY_STAR_SALMON.out.salmon_version.first().ifEmpty(null)) + ch_software_versions = ch_software_versions.mix(QUANTIFY_STAR_SALMON.out.tximeta_version.ifEmpty(null)) + ch_software_versions = ch_software_versions.mix(QUANTIFY_STAR_SALMON.out.summarizedexperiment_version.ifEmpty(null)) + + if (!params.skip_qc & !params.skip_deseq2_qc) { + DESEQ2_QC_STAR_SALMON ( + QUANTIFY_STAR_SALMON.out.counts_gene_length_scaled, + ch_pca_header_multiqc, + ch_clustering_header_multiqc + ) + ch_aligner_pca_multiqc = DESEQ2_QC_STAR_SALMON.out.pca_multiqc + ch_aligner_clustering_multiqc = DESEQ2_QC_STAR_SALMON.out.dists_multiqc + ch_software_versions = ch_software_versions.mix(DESEQ2_QC_STAR_SALMON.out.version.ifEmpty(null)) + } + } + + // + // SUBWORKFLOW: Alignment with STAR and gene/transcript quantification with RSEM + // + ch_rsem_multiqc = Channel.empty() + if (!params.skip_alignment && params.aligner == 'star_rsem') { + QUANTIFY_RSEM ( + ch_trimmed_reads, + PREPARE_GENOME.out.rsem_index + ) + ch_genome_bam = QUANTIFY_RSEM.out.bam + ch_genome_bam_index = QUANTIFY_RSEM.out.bai + ch_samtools_stats = QUANTIFY_RSEM.out.stats + ch_samtools_flagstat = QUANTIFY_RSEM.out.flagstat + ch_samtools_idxstats = QUANTIFY_RSEM.out.idxstats + ch_star_multiqc = QUANTIFY_RSEM.out.logs + ch_rsem_multiqc = QUANTIFY_RSEM.out.stat + if (params.bam_csi_index) { + ch_genome_bam_index = QUANTIFY_RSEM.out.csi + } + ch_software_versions = ch_software_versions.mix(QUANTIFY_RSEM.out.rsem_version.first().ifEmpty(null)) + ch_software_versions = ch_software_versions.mix(QUANTIFY_RSEM.out.samtools_version.first().ifEmpty(null)) + + if (!params.skip_qc & !params.skip_deseq2_qc) { + DESEQ2_QC_RSEM ( + QUANTIFY_RSEM.out.merged_counts_gene, + ch_pca_header_multiqc, + ch_clustering_header_multiqc + ) + ch_aligner_pca_multiqc = DESEQ2_QC_RSEM.out.pca_multiqc + ch_aligner_clustering_multiqc = DESEQ2_QC_RSEM.out.dists_multiqc + ch_software_versions = ch_software_versions.mix(DESEQ2_QC_RSEM.out.version.ifEmpty(null)) + } + } + + // + // SUBWORKFLOW: Alignment with HISAT2 + // + ch_hisat2_multiqc = Channel.empty() + if (!params.skip_alignment && params.aligner == 'hisat2') { + ALIGN_HISAT2 ( + ch_trimmed_reads, + PREPARE_GENOME.out.hisat2_index, + PREPARE_GENOME.out.splicesites + ) + ch_genome_bam = ALIGN_HISAT2.out.bam + ch_genome_bam_index = ALIGN_HISAT2.out.bai + ch_samtools_stats = ALIGN_HISAT2.out.stats + ch_samtools_flagstat = ALIGN_HISAT2.out.flagstat + ch_samtools_idxstats = ALIGN_HISAT2.out.idxstats + ch_hisat2_multiqc = ALIGN_HISAT2.out.summary + if (params.bam_csi_index) { + ch_genome_bam_index = ALIGN_HISAT2.out.csi + } + ch_software_versions = ch_software_versions.mix(ALIGN_HISAT2.out.hisat2_version.first().ifEmpty(null)) + ch_software_versions = ch_software_versions.mix(ALIGN_HISAT2.out.samtools_version.first().ifEmpty(null)) + + // + // SUBWORKFLOW: Remove duplicate reads from BAM file based on UMIs + // + if (params.with_umi) { + DEDUP_UMI_UMITOOLS_GENOME ( + ch_genome_bam.join(ch_genome_bam_index, by: [0]) + ) + ch_genome_bam = DEDUP_UMI_UMITOOLS_GENOME.out.bam + ch_genome_bam_index = DEDUP_UMI_UMITOOLS_GENOME.out.bai + ch_samtools_stats = DEDUP_UMI_UMITOOLS_GENOME.out.stats + ch_samtools_flagstat = DEDUP_UMI_UMITOOLS_GENOME.out.flagstat + ch_samtools_idxstats = DEDUP_UMI_UMITOOLS_GENOME.out.idxstats + if (params.bam_csi_index) { + ch_genome_bam_index = DEDUP_UMI_UMITOOLS_GENOME.out.csi + } + } + } + + // + // Filter channels to get samples that passed STAR minimum mapping percentage + // + ch_fail_mapping_multiqc = Channel.empty() + if (!params.skip_alignment && params.aligner.contains('star')) { + ch_star_multiqc + .map { meta, align_log -> [ meta ] + WorkflowRnaseq.getStarPercentMapped(params, align_log) } + .set { ch_percent_mapped } + + ch_genome_bam + .join(ch_percent_mapped, by: [0]) + .map { meta, ofile, mapped, pass -> if (pass) [ meta, ofile ] } + .set { ch_genome_bam } + + ch_genome_bam_index + .join(ch_percent_mapped, by: [0]) + .map { meta, ofile, mapped, pass -> if (pass) [ meta, ofile ] } + .set { ch_genome_bam_index } + + ch_percent_mapped + .branch { meta, mapped, pass -> + pass: pass + pass_percent_mapped[meta.id] = mapped + return [ "$meta.id\t$mapped" ] + fail: !pass + fail_percent_mapped[meta.id] = mapped + return [ "$meta.id\t$mapped" ] + } + .set { ch_pass_fail_mapped } + + MULTIQC_CUSTOM_FAIL_MAPPED ( + ch_pass_fail_mapped.fail.collect() + ) + .set { ch_fail_mapping_multiqc } + } + + // + // MODULE: Run Preseq + // + ch_preseq_multiqc = Channel.empty() + if (!params.skip_alignment && !params.skip_qc && !params.skip_preseq) { + PRESEQ_LCEXTRAP ( + ch_genome_bam + ) + ch_preseq_multiqc = PRESEQ_LCEXTRAP.out.ccurve + ch_software_versions = ch_software_versions.mix(PRESEQ_LCEXTRAP.out.version.first().ifEmpty(null)) + } + + // + // SUBWORKFLOW: Mark duplicate reads + // + ch_markduplicates_multiqc = Channel.empty() + if (!params.skip_alignment && !params.skip_markduplicates) { + MARK_DUPLICATES_PICARD ( + ch_genome_bam + ) + ch_genome_bam = MARK_DUPLICATES_PICARD.out.bam + ch_genome_bam_index = MARK_DUPLICATES_PICARD.out.bai + ch_samtools_stats = MARK_DUPLICATES_PICARD.out.stats + ch_samtools_flagstat = MARK_DUPLICATES_PICARD.out.flagstat + ch_samtools_idxstats = MARK_DUPLICATES_PICARD.out.idxstats + ch_markduplicates_multiqc = MARK_DUPLICATES_PICARD.out.metrics + if (params.bam_csi_index) { + ch_genome_bam_index = MARK_DUPLICATES_PICARD.out.csi + } + ch_software_versions = ch_software_versions.mix(MARK_DUPLICATES_PICARD.out.picard_version.first().ifEmpty(null)) + } + + // + // MODULE: STRINGTIE + // + if (!params.skip_alignment && !params.skip_stringtie) { + STRINGTIE ( + ch_genome_bam, + PREPARE_GENOME.out.gtf + ) + ch_software_versions = ch_software_versions.mix(STRINGTIE.out.version.first().ifEmpty(null)) + } + + // + // MODULE: Feature biotype QC using featureCounts + // + ch_featurecounts_multiqc = Channel.empty() + if (!params.skip_alignment && !params.skip_qc && !params.skip_biotype_qc && biotype) { + + PREPARE_GENOME + .out + .gtf + .map { WorkflowRnaseq.biotypeInGtf(it, biotype, log) } + .set { biotype_in_gtf } + + // Prevent any samples from running if GTF file doesn't have a valid biotype + ch_genome_bam + .combine(PREPARE_GENOME.out.gtf) + .combine(biotype_in_gtf) + .filter { it[-1] } + .map { it[0.. 0) { + RSEQC ( + ch_genome_bam, + PREPARE_GENOME.out.gene_bed, + rseqc_modules + ) + ch_bamstat_multiqc = RSEQC.out.bamstat_txt + ch_inferexperiment_multiqc = RSEQC.out.inferexperiment_txt + ch_innerdistance_multiqc = RSEQC.out.innerdistance_freq + ch_junctionannotation_multiqc = RSEQC.out.junctionannotation_log + ch_junctionsaturation_multiqc = RSEQC.out.junctionsaturation_rscript + ch_readdistribution_multiqc = RSEQC.out.readdistribution_txt + ch_readduplication_multiqc = RSEQC.out.readduplication_pos_xls + ch_software_versions = ch_software_versions.mix(RSEQC.out.version.first().ifEmpty(null)) + + ch_inferexperiment_multiqc + .map { meta, strand_log -> [ meta ] + WorkflowRnaseq.getInferexperimentStrandedness(strand_log, 30) } + .filter { it[0].strandedness != it[1] } + .map { meta, strandedness, sense, antisense, undetermined -> + [ "$meta.id\t$meta.strandedness\t$strandedness\t$sense\t$antisense\t$undetermined" ] + } + .set { ch_fail_strand } + + MULTIQC_CUSTOM_STRAND_CHECK ( + ch_fail_strand.collect() + ) + .set { ch_fail_strand_multiqc } + } + } + + // + // SUBWORKFLOW: Pseudo-alignment and quantification with Salmon + // + ch_salmon_multiqc = Channel.empty() + ch_pseudoaligner_pca_multiqc = Channel.empty() + ch_pseudoaligner_clustering_multiqc = Channel.empty() + if (params.pseudo_aligner == 'salmon') { + QUANTIFY_SALMON ( + ch_trimmed_reads, + PREPARE_GENOME.out.salmon_index, + ch_dummy_file, + PREPARE_GENOME.out.gtf, + false, + params.salmon_quant_libtype ?: '' + ) + ch_salmon_multiqc = QUANTIFY_SALMON.out.results + if (params.skip_alignment && params.aligner != 'star_salmon') { + ch_software_versions = ch_software_versions.mix(QUANTIFY_SALMON.out.salmon_version.first().ifEmpty(null)) + ch_software_versions = ch_software_versions.mix(QUANTIFY_SALMON.out.tximeta_version.ifEmpty(null)) + ch_software_versions = ch_software_versions.mix(QUANTIFY_SALMON.out.summarizedexperiment_version.ifEmpty(null)) + } + + if (!params.skip_qc & !params.skip_deseq2_qc) { + DESEQ2_QC_SALMON ( + QUANTIFY_SALMON.out.counts_gene_length_scaled, + ch_pca_header_multiqc, + ch_clustering_header_multiqc + ) + ch_pseudoaligner_pca_multiqc = DESEQ2_QC_SALMON.out.pca_multiqc + ch_pseudoaligner_clustering_multiqc = DESEQ2_QC_SALMON.out.dists_multiqc + if (params.skip_alignment) { + ch_software_versions = ch_software_versions.mix(DESEQ2_QC_SALMON.out.version.ifEmpty(null)) + } + } + } + + // + // MODULE: Pipeline reporting + // + ch_software_versions + .map { it -> if (it) [ it.baseName, it ] } + .groupTuple() + .map { it[1][0] } + .flatten() + .collect() + .set { ch_software_versions } + + GET_SOFTWARE_VERSIONS ( + ch_software_versions.map { it }.collect() + ) + + // + // MODULE: MultiQC + // + if (!params.skip_multiqc) { + workflow_summary = WorkflowRnaseq.paramsSummaryMultiqc(workflow, summary_params) + ch_workflow_summary = Channel.value(workflow_summary) + + MULTIQC ( + ch_multiqc_config, + ch_multiqc_custom_config.collect().ifEmpty([]), + GET_SOFTWARE_VERSIONS.out.yaml.collect(), + ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'), + ch_fail_mapping_multiqc.ifEmpty([]), + ch_fail_strand_multiqc.ifEmpty([]), + FASTQC_UMITOOLS_TRIMGALORE.out.fastqc_zip.collect{it[1]}.ifEmpty([]), + FASTQC_UMITOOLS_TRIMGALORE.out.trim_zip.collect{it[1]}.ifEmpty([]), + FASTQC_UMITOOLS_TRIMGALORE.out.trim_log.collect{it[1]}.ifEmpty([]), + ch_sortmerna_multiqc.collect{it[1]}.ifEmpty([]), + ch_star_multiqc.collect{it[1]}.ifEmpty([]), + ch_hisat2_multiqc.collect{it[1]}.ifEmpty([]), + ch_rsem_multiqc.collect{it[1]}.ifEmpty([]), + ch_salmon_multiqc.collect{it[1]}.ifEmpty([]), + ch_samtools_stats.collect{it[1]}.ifEmpty([]), + ch_samtools_flagstat.collect{it[1]}.ifEmpty([]), + ch_samtools_idxstats.collect{it[1]}.ifEmpty([]), + ch_markduplicates_multiqc.collect{it[1]}.ifEmpty([]), + ch_featurecounts_multiqc.collect{it[1]}.ifEmpty([]), + ch_aligner_pca_multiqc.collect().ifEmpty([]), + ch_aligner_clustering_multiqc.collect().ifEmpty([]), + ch_pseudoaligner_pca_multiqc.collect().ifEmpty([]), + ch_pseudoaligner_clustering_multiqc.collect().ifEmpty([]), + ch_preseq_multiqc.collect{it[1]}.ifEmpty([]), + ch_qualimap_multiqc.collect{it[1]}.ifEmpty([]), + ch_dupradar_multiqc.collect{it[1]}.ifEmpty([]), + ch_bamstat_multiqc.collect{it[1]}.ifEmpty([]), + ch_inferexperiment_multiqc.collect{it[1]}.ifEmpty([]), + ch_innerdistance_multiqc.collect{it[1]}.ifEmpty([]), + ch_junctionannotation_multiqc.collect{it[1]}.ifEmpty([]), + ch_junctionsaturation_multiqc.collect{it[1]}.ifEmpty([]), + ch_readdistribution_multiqc.collect{it[1]}.ifEmpty([]), + ch_readduplication_multiqc.collect{it[1]}.ifEmpty([]) + ) + multiqc_report = MULTIQC.out.report.toList() + } } /* From a56c00c1acbd1dedf04d0c78af14ed54f5fa6d31 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Tue, 27 Jul 2021 23:21:53 +0100 Subject: [PATCH 30/31] Update warning text --- lib/WorkflowRnaseq.groovy | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/lib/WorkflowRnaseq.groovy b/lib/WorkflowRnaseq.groovy index a496815c3..8f80e2653 100755 --- a/lib/WorkflowRnaseq.groovy +++ b/lib/WorkflowRnaseq.groovy @@ -283,12 +283,13 @@ class WorkflowRnaseq { // private static void additionaFastaIndexWarn(index, log) { log.warn "=============================================================================\n" + - " When using '--additional_fasta --${index}_index '\n" + - " the index will not be re-built with the transgenes incorporated by default since\n" + - " you have already provided an index via '--${index}_index '.\n\n" + - " Set '--additional_fasta --${index}_index false --save_reference'\n" + - " to re-build the index including transgenes and save for re-use with\n" + - " '--${index}_index' in 'results/genome/index/${index}/'.\n\n" + + " When using '--additional_fasta ' the aligner index will not\n" + + " be re-built with the transgenes incorporated by default since you have \n" + + " already provided an index via '--${index}_index '.\n\n" + + " Set '--additional_fasta --${index}_index false --save_reference' to\n" + + " re-build the index with transgenes included and the index will be saved in\n" + + " 'results/genome/index/${index}/' for re-use with '--${index}_index'.\n\n" + + " Ignore this warning if you know that the index already contains transgenes.\n\n" + " Please see:\n" + " https://github.com/nf-core/rnaseq/issues/556\n" + "===================================================================================" From a45d0f314002617d9c98b5674054413b8569a8b4 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Wed, 28 Jul 2021 19:55:40 +0100 Subject: [PATCH 31/31] Update CHANGELOG.md --- CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 178916a7d..55d6e5d18 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,7 +3,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). -## [[3.3](https://github.com/nf-core/rnaseq/releases/tag/3.3)] - 2021-07-28 +## [[3.3](https://github.com/nf-core/rnaseq/releases/tag/3.3)] - 2021-07-29 ### Enhancements & fixes
\n" + for (param in group_params.keySet()) { + summary_section += "
$param
${group_params.get(param) ?: 'N/A'}
\n" + } + summary_section += "