diff --git a/.devcontainer/devcontainer.json b/.devcontainer/devcontainer.json index 4ecfbfe3..b290e090 100644 --- a/.devcontainer/devcontainer.json +++ b/.devcontainer/devcontainer.json @@ -10,15 +10,7 @@ "vscode": { // Set *default* container specific settings.json values on container create. "settings": { - "python.defaultInterpreterPath": "/opt/conda/bin/python", - "python.linting.enabled": true, - "python.linting.pylintEnabled": true, - "python.formatting.autopep8Path": "/opt/conda/bin/autopep8", - "python.formatting.yapfPath": "/opt/conda/bin/yapf", - "python.linting.flake8Path": "/opt/conda/bin/flake8", - "python.linting.pycodestylePath": "/opt/conda/bin/pycodestyle", - "python.linting.pydocstylePath": "/opt/conda/bin/pydocstyle", - "python.linting.pylintPath": "/opt/conda/bin/pylint" + "python.defaultInterpreterPath": "/opt/conda/bin/python" }, // Add the IDs of extensions you want installed when the container is created. diff --git a/.editorconfig b/.editorconfig index 9b990088..dd9ffa53 100644 --- a/.editorconfig +++ b/.editorconfig @@ -18,7 +18,12 @@ end_of_line = unset insert_final_newline = unset trim_trailing_whitespace = unset indent_style = unset -indent_size = unset +[/subworkflows/nf-core/**] +charset = unset +end_of_line = unset +insert_final_newline = unset +trim_trailing_whitespace = unset +indent_style = unset [/assets/email*] indent_size = unset @@ -28,5 +33,5 @@ indent_size = unset indent_style = unset # ignore python -[*.{py}] +[*.{py,md}] indent_style = unset diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md index 88675b1a..4355e2dd 100644 --- a/.github/CONTRIBUTING.md +++ b/.github/CONTRIBUTING.md @@ -9,9 +9,8 @@ Please use the pre-filled template to save time. However, don't be put off by this template - other more general issues and suggestions are welcome! Contributions to the code are even more welcome ;) -:::info -If you need help using or modifying nf-core/taxprofiler then the best place to ask is on the nf-core Slack [#taxprofiler](https://nfcore.slack.com/channels/taxprofiler) channel ([join our Slack here](https://nf-co.re/join/slack)). -::: +> [!NOTE] +> If you need help using or modifying nf-core/taxprofiler then the best place to ask is on the nf-core Slack [#taxprofiler](https://nfcore.slack.com/channels/taxprofiler) channel ([join our Slack here](https://nf-co.re/join/slack)). ## Contribution workflow @@ -27,8 +26,11 @@ If you're not used to this workflow with git, you can start with some [docs from ## Tests -You can optionally test your changes by running the pipeline locally. Then it is recommended to use the `debug` profile to -receive warnings about process selectors and other debug info. Example: `nextflow run . -profile debug,test,docker --outdir `. +You have the option to test your changes locally by running the pipeline. For receiving warnings about process selectors and other `debug` information, it is recommended to use the debug profile. Execute all the tests with the following command: + +```bash +nf-test test --profile debug,test,docker --verbose +``` When you create a pull request with changes, [GitHub Actions](https://github.com/features/actions) will run automatic tests. Typically, pull-requests are only fully reviewed when these tests are passing, though of course we can help out before then. @@ -90,7 +92,7 @@ Once there, use `nf-core schema build` to add to `nextflow_schema.json`. Sensible defaults for process resource requirements (CPUs / memory / time) for a process should be defined in `conf/base.config`. These should generally be specified generic with `withLabel:` selectors so they can be shared across multiple processes/steps of the pipeline. A nf-core standard set of labels that should be followed where possible can be seen in the [nf-core pipeline template](https://github.com/nf-core/tools/blob/master/nf_core/pipeline-template/conf/base.config), which has the default process as a single core-process, and then different levels of multi-core configurations for increasingly large memory requirements defined with standardised labels. -The process resources can be passed on to the tool dynamically within the process with the `${task.cpu}` and `${task.memory}` variables in the `script:` block. +The process resources can be passed on to the tool dynamically within the process with the `${task.cpus}` and `${task.memory}` variables in the `script:` block. ### Naming schemes diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index 69a2dd8e..888970b6 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/taxp - [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/taxprofiler/tree/master/.github/CONTRIBUTING.md) - [ ] If necessary, also make a PR on the nf-core/taxprofiler _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 --outdir `). +- [ ] Ensure the test suite passes (`nf-test test main.nf.test -profile test,docker`). - [ ] Check for unexpected warnings in debug mode (`nextflow run . -profile debug,test,docker --outdir `). - [ ] Usage Documentation in `docs/usage.md` is updated. - [ ] Output Documentation in `docs/output.md` is updated. diff --git a/.github/workflows/branch.yml b/.github/workflows/branch.yml index 6a3b05e6..e5e57686 100644 --- a/.github/workflows/branch.yml +++ b/.github/workflows/branch.yml @@ -19,7 +19,7 @@ jobs: # NOTE - this doesn't currently work if the PR is coming from a fork, due to limitations in GitHub actions secrets - name: Post PR comment if: failure() - uses: mshick/add-pr-comment@v2 + uses: mshick/add-pr-comment@b8f338c590a895d50bcbfa6c5859251edc8952fc # v2 with: message: | ## This PR is against the `master` branch :x: diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 7c027331..e6d5d4df 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -42,17 +42,20 @@ jobs: steps: - name: Check out pipeline code - uses: actions/checkout@v4 + uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4 - name: Install Nextflow uses: nf-core/setup-nextflow@v1 with: version: "${{ matrix.NXF_VER }}" - - name: Show current locale - run: locale + - name: Disk space cleanup + uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1 - - name: Set UTF-8 enabled locale + - name: Run pipeline with test data + # TODO nf-core: You can customise CI pipeline run tests as required + # For example: adding multiple test runs with different parameters + # Remember that you can parallelise this by using strategy.matrix run: | sudo locale-gen en_US.UTF-8 sudo update-locale LANG=en_US.UTF-8 @@ -61,9 +64,9 @@ jobs: run: | if [[ "${{ matrix.tags }}" == "test_motus" ]]; then wget https://raw.githubusercontent.com/motu-tool/mOTUs/master/motus/downloadDB.py - python downloadDB.py > download_db_log.txt + python downloadDB.py --no-download-progress echo 'tool,db_name,db_params,db_path' > 'database_motus.csv' - echo 'motus,db_mOTU,,db_mOTU' >> 'database_motus.csv' + echo "motus,db_mOTU,,db_mOTU" >> 'database_motus.csv' nextflow run ${GITHUB_WORKSPACE} -profile docker,${{ matrix.tags }} --databases ./database_motus.csv --outdir ./results_${{ matrix.tags }}; else nextflow run ${GITHUB_WORKSPACE} -profile docker,${{ matrix.tags }} --outdir ./results_${{ matrix.tags }}; diff --git a/.github/workflows/clean-up.yml b/.github/workflows/clean-up.yml index e37cfda5..0b6b1f27 100644 --- a/.github/workflows/clean-up.yml +++ b/.github/workflows/clean-up.yml @@ -10,7 +10,7 @@ jobs: issues: write pull-requests: write steps: - - uses: actions/stale@v9 + - uses: actions/stale@28ca1036281a5e5922ead5184a1bbf96e5fc984e # v9 with: stale-issue-message: "This issue has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor. Remove stale label or add a comment otherwise this issue will be closed in 20 days." stale-pr-message: "This PR has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor. Remove stale label or add a comment if it is still useful." diff --git a/.github/workflows/download_pipeline.yml b/.github/workflows/download_pipeline.yml index 8a330045..2bcf451a 100644 --- a/.github/workflows/download_pipeline.yml +++ b/.github/workflows/download_pipeline.yml @@ -6,9 +6,16 @@ name: Test successful pipeline download with 'nf-core download' # - the head branch of the pull request is updated, i.e. if fixes for a release are pushed last minute to dev. on: workflow_dispatch: + inputs: + testbranch: + description: "The specific branch you wish to utilize for the test execution of nf-core download." + required: true + default: "dev" pull_request: types: - opened + - edited + - synchronize branches: - master pull_request_target: @@ -23,13 +30,13 @@ jobs: runs-on: ubuntu-latest steps: - name: Install Nextflow - uses: nf-core/setup-nextflow@v1 + uses: nf-core/setup-nextflow@v2 - - uses: actions/setup-python@v5 + - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 with: - python-version: "3.11" + python-version: "3.12" architecture: "x64" - - uses: eWaterCycle/setup-singularity@v7 + - uses: eWaterCycle/setup-singularity@931d4e31109e875b13309ae1d07c70ca8fbc8537 # v7 with: singularity-version: 3.8.3 @@ -42,13 +49,13 @@ jobs: run: | echo "REPO_LOWERCASE=${GITHUB_REPOSITORY,,}" >> ${GITHUB_ENV} echo "REPOTITLE_LOWERCASE=$(basename ${GITHUB_REPOSITORY,,})" >> ${GITHUB_ENV} - echo "REPO_BRANCH=${GITHUB_REF#refs/heads/}" >> ${GITHUB_ENV} + echo "REPO_BRANCH=${{ github.event.inputs.testbranch || 'dev' }}" >> ${GITHUB_ENV} - name: Download the pipeline env: NXF_SINGULARITY_CACHEDIR: ./ run: | - nf-core download ${{ env.REPO_LOWERCASE }} \ + nf-core download ${{ env.REPO_LOWERCASE }} \ --revision ${{ env.REPO_BRANCH }} \ --outdir ./${{ env.REPOTITLE_LOWERCASE }} \ --compress "none" \ @@ -64,4 +71,4 @@ jobs: env: NXF_SINGULARITY_CACHEDIR: ./ NXF_SINGULARITY_HOME_MOUNT: true - run: nextflow run ./${{ env.REPOTITLE_LOWERCASE }}/$( sed 's/\W/_/g' <<< ${{ env.REPO_BRANCH }}) -stub -profile test,singularity --outdir ./results + run: nextflow run ./${{ env.REPOTITLE_LOWERCASE }}/$( sed 's/\W/_/g' <<< ${{ env.REPO_BRANCH }}) -profile test_nothing,singularity --outdir ./results diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index 81cd098e..073e1876 100644 --- a/.github/workflows/linting.yml +++ b/.github/workflows/linting.yml @@ -14,10 +14,10 @@ jobs: pre-commit: runs-on: ubuntu-latest steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4 - name: Set up Python 3.11 - uses: actions/setup-python@v5 + uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 with: python-version: 3.11 cache: "pip" @@ -32,12 +32,12 @@ jobs: runs-on: ubuntu-latest steps: - name: Check out pipeline code - uses: actions/checkout@v4 + uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4 - name: Install Nextflow uses: nf-core/setup-nextflow@v1 - - uses: actions/setup-python@v5 + - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 with: python-version: "3.11" architecture: "x64" @@ -60,7 +60,7 @@ jobs: - name: Upload linting log file artifact if: ${{ always() }} - uses: actions/upload-artifact@v4 + uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4 with: name: linting-logs path: | diff --git a/.github/workflows/linting_comment.yml b/.github/workflows/linting_comment.yml index 147bcd10..b706875f 100644 --- a/.github/workflows/linting_comment.yml +++ b/.github/workflows/linting_comment.yml @@ -11,7 +11,7 @@ jobs: runs-on: ubuntu-latest steps: - name: Download lint results - uses: dawidd6/action-download-artifact@v3 + uses: dawidd6/action-download-artifact@f6b0bace624032e30a85a8fd9c1a7f8f611f5737 # v3 with: workflow: linting.yml workflow_conclusion: completed @@ -21,7 +21,7 @@ jobs: run: echo "pr_number=$(cat linting-logs/PR_number.txt)" >> $GITHUB_OUTPUT - name: Post PR comment - uses: marocchino/sticky-pull-request-comment@v2 + uses: marocchino/sticky-pull-request-comment@331f8f5b4215f0445d3c07b4967662a32a2d3e31 # v2 with: GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} number: ${{ steps.pr_number.outputs.pr_number }} diff --git a/.github/workflows/release-announcements.yml b/.github/workflows/release-announcements.yml index 21ac3f06..d468aeaa 100644 --- a/.github/workflows/release-announcements.yml +++ b/.github/workflows/release-announcements.yml @@ -9,6 +9,11 @@ jobs: toot: runs-on: ubuntu-latest steps: + - name: get topics and convert to hashtags + id: get_topics + run: | + curl -s https://nf-co.re/pipelines.json | jq -r '.remote_workflows[] | select(.full_name == "${{ github.repository }}") | .topics[]' | awk '{print "#"$0}' | tr '\n' ' ' >> $GITHUB_OUTPUT + - uses: rzr/fediverse-action@master with: access-token: ${{ secrets.MASTODON_ACCESS_TOKEN }} @@ -20,11 +25,13 @@ jobs: Please see the changelog: ${{ github.event.release.html_url }} + ${{ steps.get_topics.outputs.GITHUB_OUTPUT }} #nfcore #openscience #nextflow #bioinformatics + send-tweet: runs-on: ubuntu-latest steps: - - uses: actions/setup-python@v5 + - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 with: python-version: "3.10" - name: Install dependencies @@ -56,7 +63,7 @@ jobs: bsky-post: runs-on: ubuntu-latest steps: - - uses: zentered/bluesky-post-action@v0.1.0 + - uses: zentered/bluesky-post-action@80dbe0a7697de18c15ad22f4619919ceb5ccf597 # v0.1.0 with: post: | Pipeline release! ${{ github.repository }} v${{ github.event.release.tag_name }} - ${{ github.event.release.name }}! diff --git a/.gitpod.yml b/.gitpod.yml index 363d5b1d..105a1821 100644 --- a/.gitpod.yml +++ b/.gitpod.yml @@ -10,13 +10,11 @@ tasks: vscode: extensions: # based on nf-core.nf-core-extensionpack - - codezombiech.gitignore # Language support for .gitignore files - # - cssho.vscode-svgviewer # SVG viewer - esbenp.prettier-vscode # Markdown/CommonMark linting and style checking for Visual Studio Code - - eamodio.gitlens # Quickly glimpse into whom, why, and when a line or code block was changed - EditorConfig.EditorConfig # override user/workspace settings with settings found in .editorconfig files - Gruntfuggly.todo-tree # Display TODO and FIXME in a tree view in the activity bar - mechatroner.rainbow-csv # Highlight columns in csv files in different colors - # - nextflow.nextflow # Nextflow syntax highlighting + # - nextflow.nextflow # Nextflow syntax highlighting - oderwat.indent-rainbow # Highlight indentation level - streetsidesoftware.code-spell-checker # Spelling checker for source code + - charliermarsh.ruff # Code linter Ruff diff --git a/CHANGELOG.md b/CHANGELOG.md index 23e932d7..16cf4825 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,6 +3,25 @@ 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). +## v1.1.6 - Augmented Akita Patch [2024-04-16] + +### `Added` + +- [#454](https://github.com/nf-core/taxprofiler/pull/454) Updated to nf-core pipeline template v2.13.1 (added by @LilyAnderssonLee & @sofstam) +- [#461](https://github.com/nf-core/taxprofiler/pull/461) Turned on 'strict' Nextflow evaluation runs (added by @jfy133) +- [#461](https://github.com/nf-core/taxprofiler/pull/461) Optimised database compression so each compressed input database is untarred once, and shared amongst each run with different parameters (added by @jfy133) +- [#461](https://github.com/nf-core/taxprofiler/pull/461) Added new parameter to optionally save uncompressed databases (added by @jfy133) +- [#471](https://github.com/nf-core/taxprofiler/pull/471) Remove `-stub` run in the `download_pipeline.yml` because the pipeline does not support stub runs on dev (fixed by @LilyAnderssonLee) + +### `Fixed` + +- [#336](https://github.com/nf-core/taxprofiler/issues/336) Replace samplesheet check with nf-validation for both sample and database input sheets (fix by @LilyAnderssonLee) +- [#460](https://github.com/nf-core/taxprofiler/issues/460) corrected the channel transformations to combine Kaiju and mOTUs reports with their reference databases (fix by @Midnighter) + +### `Dependencies` + +### `Deprecated` + ## v1.1.5 - Augmented Akita Patch [2024-02-08] ### `Added` diff --git a/README.md b/README.md index e03ef331..1661c024 100644 --- a/README.md +++ b/README.md @@ -4,14 +4,16 @@ nf-core/taxprofiler -[![GitHub Actions CI Status](https://github.com/nf-core/taxprofiler/workflows/nf-core%20CI/badge.svg)](https://github.com/nf-core/taxprofiler/actions?query=workflow%3A%22nf-core+CI%22) -[![GitHub Actions Linting Status](https://github.com/nf-core/taxprofiler/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/taxprofiler/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/taxprofiler/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.7728364-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.7728364) + +[![GitHub Actions CI Status](https://github.com/nf-core/taxprofiler/actions/workflows/ci.yml/badge.svg)](https://github.com/nf-core/taxprofiler/actions/workflows/ci.yml) +[![GitHub Actions Linting Status](https://github.com/nf-core/taxprofiler/actions/workflows/linting.yml/badge.svg)](https://github.com/nf-core/taxprofiler/actions/workflows/linting.yml)[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/taxprofiler/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.7728364-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.7728364) +[![nf-test](https://img.shields.io/badge/unit_tests-nf--test-337ab7.svg)](https://www.nf-test.com) [![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A523.04.0-23aa62.svg)](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/) -[![Launch on Nextflow Tower](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Nextflow%20Tower-%234256e7)](https://tower.nf/launch?pipeline=https://github.com/nf-core/taxprofiler) +[![Launch on Seqera Platform](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Seqera%20Platform-%234256e7)](https://tower.nf/launch?pipeline=https://github.com/nf-core/taxprofiler) [![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23taxprofiler-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/taxprofiler)[![Follow on Twitter](http://img.shields.io/badge/twitter-%40nf__core-1DA1F2?labelColor=000000&logo=twitter)](https://twitter.com/nf_core)[![Follow on Mastodon](https://img.shields.io/badge/mastodon-nf__core-6364ff?labelColor=FFFFFF&logo=mastodon)](https://mstdn.science/@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) diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml index 2ed16397..702afed1 100644 --- a/assets/multiqc_config.yml +++ b/assets/multiqc_config.yml @@ -1,7 +1,7 @@ report_comment: > - This report has been generated by the nf-core/taxprofiler + This report has been generated by the nf-core/taxprofiler analysis pipeline. For information about how to interpret these results, please see the - documentation. + documentation. report_section_order: "nf-core-taxprofiler-methods-description": @@ -13,6 +13,7 @@ report_section_order: export_plots: true +disable_version_detection: true custom_logo: "nf-core-taxprofiler_logo_custom_light.png" custom_logo_url: https://nf-co.re/taxprofiler custom_logo_title: "nf-core/taxprofiler" diff --git a/assets/schema_database.json b/assets/schema_database.json new file mode 100644 index 00000000..1f52a25c --- /dev/null +++ b/assets/schema_database.json @@ -0,0 +1,70 @@ +{ + "$schema": "http://json-schema.org/draft-07/schema", + "$id": "https://raw.githubusercontent.com/nf-core/taxprofiler/master/assets/schema_database.json", + "title": "nf-core/taxprofiler pipeline - params.database schema", + "description": "Schema for the file provided with params.database", + "type": "array", + "items": { + "type": "object", + "properties": { + "tool": { + "type": "string", + "exists": true, + "enum": [ + "bracken", + "centrifuge", + "diamond", + "ganon", + "kaiju", + "kmcp", + "kraken2", + "krakenuniq", + "malt", + "metaphlan", + "motus" + ], + "errorMessage": "Invalid tool name. Please see documentation for all supported profilers. Currently these classifers are included: bracken, centrifuge, diamond, ganon, kaiju, kmcp, kraken2, krakenuniq, malt, metaphlan, motus.", + "meta": ["tool"] + }, + "db_name": { + "type": "string", + "exists": true, + "pattern": "^\\S+$", + "errorMessage": "The unique name of the database should be provided.", + "meta": ["db_name"] + }, + "db_params": { + "type": "string", + "pattern": "^[^\"']*$", + "anyOf": [ + { + "properties": { + "tool": { "const": "bracken" } + }, + "not": { + "pattern": ".*;" + }, + "errorMessage": "Invalid database db_params entry. Bracken requires a semi-colon for passing one or more parameters." + }, + { + "properties": { + "tool": { "const": "kmcp" } + }, + "pattern": ".*;$", + "errorMessage": "Invalid database `db_params` entry. KMCP only requires a semi-colon if passing arguments to KMCP profile, in cases of which the arguments should go after the semi-colon." + } + ], + "errorMessage": "Invalid database db_params entry. No quotes allowed.", + "meta": ["db_params"] + }, + "db_path": { + "type": "string", + "exists": true, + "format": "path", + "errorMessage": "db_path should be either a file path or a directory." + } + }, + "required": ["tool", "db_name", "db_path"], + "uniqueEntries": ["tool", "db_name"] + } +} diff --git a/assets/schema_input.json b/assets/schema_input.json index ed098df1..6acc00f7 100644 --- a/assets/schema_input.json +++ b/assets/schema_input.json @@ -9,28 +9,49 @@ "properties": { "sample": { "type": "string", - "pattern": "^\\S+$", - "errorMessage": "Sample name must be provided and cannot contain spaces" + "errorMessage": "Sample name must be provided and cannot contain spaces", + "meta": ["id"] + }, + "run_accession": { + "type": "string", + "errorMessage": "Run accession must be provided and cannot contain spaces." + }, + "instrument_platform": { + "type": "string", + "enum": [ + "ABI_SOLID", + "BGISEQ", + "CAPILLARY", + "COMPLETE_GENOMICS", + "DNBSEQ", + "HELICOS", + "ILLUMINA", + "ION_TORRENT", + "LS454", + "OXFORD_NANOPORE", + "PACBIO_SMRT" + ], + "errorMessage": "Sequencing platform must be provided." }, "fastq_1": { "type": "string", + "format": "file-path", "pattern": "^\\S+\\.f(ast)?q\\.gz$", "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$" - }, - { - "type": "string", - "maxLength": 0 - } - ] + "type": "string", + "format": "file-path", + "pattern": "^\\S+\\.f(ast)?q\\.gz$", + "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'. If not applicable, leave it empty." + }, + "fasta": { + "type": "string", + "format": "file-path", + "pattern": "^\\S+\\.(f(ast)?q|fa(sta)?)\\.gz$", + "errorMessage": "FastA file must be provided, cannot contain spaces and must have extension '.fa.gz' or '.fasta.gz'. If not applicable, leave it empty." } }, - "required": ["sample", "fastq_1"] + "required": ["sample", "run_accession", "instrument_platform"] } } diff --git a/bin/check_samplesheet.py b/bin/check_samplesheet.py deleted file mode 100755 index 9f0f7a65..00000000 --- a/bin/check_samplesheet.py +++ /dev/null @@ -1,231 +0,0 @@ -#!/usr/bin/env python - -from distutils import extension -import os -import sys -import errno -import argparse - - -def parse_args(args=None): - Description = "Reformat nf-core/taxprofiler 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) - - -def check_samplesheet(file_in, file_out): - """ - This function checks that the samplesheet follows the following structure: - - sample,run_accession,instrument_platform,fastq_1,fastq_2,fasta - 2611,ERR5766174,ILLUMINA,,,ERX5474930_ERR5766174_1.fa.gz - 2612,ERR5766176,ILLUMINA,ERX5474932_ERR5766176_1.fastq.gz,ERX5474932_ERR5766176_2.fastq.gz, - 2612,ERR5766174,ILLUMINA,ERX5474936_ERR5766180_1.fastq.gz,, - 2613,ERR5766181,ILLUMINA,ERX5474937_ERR5766181_1.fastq.gz,ERX5474937_ERR5766181_2.fastq.gz, - """ - - FQ_EXTENSIONS = (".fq.gz", ".fastq.gz") - FA_EXTENSIONS = ( - ".fa.gz", - ".fasta.gz", - ".fna.gz", - ".fas.gz", - ) - INSTRUMENT_PLATFORMS = [ - "ABI_SOLID", - "BGISEQ", - "CAPILLARY", - "COMPLETE_GENOMICS", - "DNBSEQ", - "HELICOS", - "ILLUMINA", - "ION_TORRENT", - "LS454", - "OXFORD_NANOPORE", - "PACBIO_SMRT", - ] - - sample_mapping_dict = {} - with open(file_in, "r") as fin: - ## Check header - MIN_COLS = 4 - HEADER = [ - "sample", - "run_accession", - "instrument_platform", - "fastq_1", - "fastq_2", - "fasta", - ] - header = [x.strip('"') for x in fin.readline().strip().split(",")] - - ## Check for missing mandatory columns - missing_columns = list(set(HEADER) - set(header)) - if len(missing_columns) > 0: - print( - "ERROR: Missing required column header -> {}. Note some columns can otherwise be empty. See pipeline documentation (https://nf-co.re/taxprofiler/usage).".format( - ",".join(missing_columns) - ) - ) - sys.exit(1) - - ## Find locations of mandatory columns - header_locs = {} - for i in HEADER: - header_locs[i] = header.index(i) - - ## Check sample entries - for line in fin: - ## Pull out only relevant columns for downstream checking - line_parsed = [x.strip().strip('"') for x in line.strip().split(",")] - - # Check valid number of columns per row - if len(line_parsed) < len(HEADER): - print_error( - "Invalid number of columns (minimum = {})!".format(len(HEADER)), - "Line", - line, - ) - num_cols = len([x for x in line_parsed if x]) - if num_cols < MIN_COLS: - print_error( - "Invalid number of populated columns (minimum = {})!".format(MIN_COLS), - "Line", - line, - ) - - lspl = [line_parsed[i] for i in header_locs.values()] - - ## Check sample name entries - - ( - sample, - run_accession, - instrument_platform, - fastq_1, - fastq_2, - fasta, - ) = 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(FQ_EXTENSIONS): - print_error( - f"FastQ file does not have extension {' or '.join(list(FQ_EXTENSIONS))} !", - "Line", - line, - ) - if fasta: - if fasta.find(" ") != -1: - print_error("FastA file contains spaces!", "Line", line) - if not fasta.endswith(FA_EXTENSIONS): - print_error( - f"FastA file does not have extension {' or '.join(list(FA_EXTENSIONS))}!", - "Line", - line, - ) - sample_info = [] - - # Check run_accession - if not run_accession: - print_error("Run accession has not been specified!", "Line", line) - else: - sample_info.append(run_accession) - - # Check instrument_platform - if not instrument_platform: - print_error("Instrument platform has not been specified!", "Line", line) - else: - if instrument_platform not in INSTRUMENT_PLATFORMS: - print_error( - f"Instrument platform {instrument_platform} is not supported! " - f"List of supported platforms {', '.join(INSTRUMENT_PLATFORMS)}", - "Line", - line, - ) - sample_info.append(instrument_platform) - - ## Auto-detect paired-end/single-end - if sample and fastq_1 and fastq_2: ## Paired-end short reads - sample_info.extend(["0", fastq_1, fastq_2, fasta]) - elif sample and fastq_1 and not fastq_2: ## Single-end short/long fastq reads - sample_info.extend(["1", fastq_1, fastq_2, fasta]) - elif sample and fasta and not fastq_1 and not fastq_2: ## Single-end long reads - sample_info.extend(["1", fastq_1, fastq_2, fasta]) - elif fasta and (fastq_1 or fastq_2): - print_error( - "FastQ and FastA files cannot be specified together in the same library!", - "Line", - line, - ) - else: - print_error("Invalid combination of columns provided!", "Line", line) - - ## Create sample mapping dictionary = { sample: [ run_accession, instrument_platform, single_end, fastq_1, fastq_2 , fasta ] } - 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 - HEADER_OUT = [ - "sample", - "run_accession", - "instrument_platform", - "single_end", - "fastq_1", - "fastq_2", - "fasta", - ] - 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(HEADER_OUT) + "\n") - for sample in sorted(sample_mapping_dict.keys()): - for idx, val in enumerate(sample_mapping_dict[sample]): - fout.write(f"{sample},{','.join(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/conf/base.config b/conf/base.config index 12ca2afa..6a116bf8 100644 --- a/conf/base.config +++ b/conf/base.config @@ -57,9 +57,6 @@ process { errorStrategy = 'retry' maxRetries = 2 } - withName:CUSTOM_DUMPSOFTWAREVERSIONS { - cache = false - } withName: BRACKEN_BRACKEN { errorStrategy = 'ignore' diff --git a/conf/modules.config b/conf/modules.config index 795c192a..1956605e 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -12,6 +12,21 @@ process { + publishDir = [ + path: { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }, + mode: params.publish_dir_mode, + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + ] + + withName: UNTAR { + ext.prefix = { "${archive.simpleName}" } + publishDir = [ + path: { "${params.outdir}/untar/databases" }, + mode: params.publish_dir_mode, + enabled: params.save_untarred_databases + ] + } + withName: FASTQC { ext.args = '--quiet' ext.prefix = { "${meta.id}_${meta.run_accession}_raw" } @@ -487,7 +502,7 @@ process { } withName: KRAKENTOOLS_COMBINEKREPORTS_KRAKEN { - ext.prefix = { "kraken2_${meta.db_name}_combined_reports" } + ext.prefix = { "kraken2_${meta.id}_combined_reports" } publishDir = [ path: { "${params.outdir}/kraken2/" }, mode: params.publish_dir_mode, @@ -506,6 +521,14 @@ process { ] } + withName: KRAKENTOOLS_KREPORT2KRONA { + publishDir = [ + enabled: false, + mode: params.publish_dir_mode, + pattern: '*.txt' + ] + } + withName: KRONA_CLEANUP { ext.prefix = params.perform_runmerging ? { "${meta.id}_${meta.db_name}" } : { "${meta.id}_${meta.run_accession}_${meta.db_name}" } publishDir = [ @@ -627,6 +650,10 @@ process { withName: KAIJU_KAIJU2KRONA { tag = {"${meta.db_name}|${meta.id}"} ext.args = '-v -u' + publishDir = [ + path: { "${params.outdir}/kaiju/" }, + enabled : false + ] } withName: DIAMOND_BLASTX { @@ -762,14 +789,6 @@ process { ] } - withName: CUSTOM_DUMPSOFTWAREVERSIONS { - publishDir = [ - path: { "${params.outdir}/pipeline_info" }, - mode: params.publish_dir_mode, - pattern: '*_versions.yml' - ] - } - withName: 'MULTIQC' { ext.args = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' } publishDir = [ diff --git a/docs/images/nf-core-taxprofiler_logo_custom_dark_fullpath.svg b/docs/images/nf-core-taxprofiler_logo_custom_dark_fullpath.svg new file mode 100644 index 00000000..95b2b998 --- /dev/null +++ b/docs/images/nf-core-taxprofiler_logo_custom_dark_fullpath.svg @@ -0,0 +1,2297 @@ + + + +taxfinder/ diff --git a/docs/images/nf-core-taxprofiler_logo_custom_light_fullpath.svg b/docs/images/nf-core-taxprofiler_logo_custom_light_fullpath.svg new file mode 100644 index 00000000..ddcb3e07 --- /dev/null +++ b/docs/images/nf-core-taxprofiler_logo_custom_light_fullpath.svg @@ -0,0 +1,2300 @@ + + + +taxfinder/ diff --git a/docs/images/taxprofiler_tube.png b/docs/images/taxprofiler_tube.png index b9119af4..301d406a 100644 Binary files a/docs/images/taxprofiler_tube.png and b/docs/images/taxprofiler_tube.png differ diff --git a/docs/images/taxprofiler_tube.svg b/docs/images/taxprofiler_tube.svg index b7d52428..6914d622 100644 --- a/docs/images/taxprofiler_tube.svg +++ b/docs/images/taxprofiler_tube.svg @@ -7,7 +7,7 @@ viewBox="0 0 571.87306 239.90903" version="1.1" id="svg5" - inkscape:version="1.3 (1:1.3+202307231459+0e150ed6c4)" + inkscape:version="1.3.2 (1:1.3.2+202311252150+091e20ef0f)" sodipodi:docname="taxprofiler_tube.svg" xml:space="preserve" inkscape:export-filename="taxprofiler_tube.png" @@ -36,9 +36,9 @@ fit-margin-left="0" fit-margin-right="0" fit-margin-bottom="0" - inkscape:zoom="13.663808" - inkscape:cx="1597.7976" - inkscape:cy="120.574" + inkscape:zoom="1.4206694" + inkscape:cx="408.96215" + inkscape:cy="673.62613" inkscape:window-width="1920" inkscape:window-height="1136" inkscape:window-x="0" @@ -2371,7 +2371,7 @@ id="path2500-5-22-0-4-8-9-6-9-0-6-4-6-2-8-3-6-2-1-8-3-2" sodipodi:nodetypes="ccccc" /> + + + diff --git a/docs/output.md b/docs/output.md index cf4678c3..2cebd463 100644 --- a/docs/output.md +++ b/docs/output.md @@ -10,6 +10,7 @@ The directories listed below will be created in the results directory after the The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes data using the following steps: +- [UNTAR](#untar) - Optionally saved decompressed input databases - [FastQC](#fastqc) - Raw read QC - [falco](#fastqc) - Alternative to FastQC for raw read QC - [fastp](#fastp) - Adapter trimming for Illumina data @@ -40,6 +41,21 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d ![](images/taxprofiler_tube.png) +### untar + +untar is used in nf-core/taxprofiler to decompress various input files ending in `.tar.gz`. This process is mainly used for decompressing input database archive files. + +
+Output files + +- `untar/` + - `database/` + - ``: directory containing contents of the decompressed archive + +
+ +This directory will only be present if `--save_untarred_databases` is supplied. The contained directories can be useful for moving the decompressed directories to a central 'cache' location allowing users to re-use the same databases. This is useful to save unnecessary computational time of decompressing the archives on every run. + ### FastQC or Falco
diff --git a/lib/NfcoreTemplate.groovy b/lib/NfcoreTemplate.groovy deleted file mode 100755 index e248e4c3..00000000 --- a/lib/NfcoreTemplate.groovy +++ /dev/null @@ -1,356 +0,0 @@ -// -// This file holds several functions used within the nf-core pipeline template. -// - -import org.yaml.snakeyaml.Yaml -import groovy.json.JsonOutput -import nextflow.extension.FilesEx - -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!" - } - } - - // - // Warn if a -profile or Nextflow config has not been provided to run the pipeline - // - public static void checkConfigProvided(workflow, log) { - if (workflow.profile == 'standard' && workflow.configFiles.size() <= 1) { - log.warn "[$workflow.manifest.name] You are attempting to run the pipeline without any custom configuration!\n\n" + - "This will be dependent on your local compute environment but can be achieved via one or more of the following:\n" + - " (1) Using an existing pipeline profile e.g. `-profile docker` or `-profile singularity`\n" + - " (2) Using an existing nf-core/configs for your Institution e.g. `-profile crick` or `-profile uppmax`\n" + - " (3) Using your own local custom config e.g. `-c /path/to/your/custom.config`\n\n" + - "Please refer to the quick start section and usage docs for the pipeline.\n " - } - } - - // - // Generate version string - // - public static String version(workflow) { - String version_string = "" - - if (workflow.manifest.version) { - def prefix_v = workflow.manifest.version[0] != 'v' ? 'v' : '' - version_string += "${prefix_v}${workflow.manifest.version}" - } - - if (workflow.commitId) { - def git_shortsha = workflow.commitId.substring(0, 7) - version_string += "-g${git_shortsha}" - } - - return version_string - } - - // - // 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: $workflow.runName" - } - - def summary = [:] - for (group in summary_params.keySet()) { - summary << summary_params[group] - } - - def misc_fields = [:] - misc_fields['Date Started'] = workflow.start - misc_fields['Date Completed'] = workflow.complete - misc_fields['Pipeline script file path'] = workflow.scriptFile - misc_fields['Pipeline script hash ID'] = workflow.scriptId - if (workflow.repository) misc_fields['Pipeline repository Git URL'] = workflow.repository - if (workflow.commitId) misc_fields['Pipeline repository Git Commit'] = workflow.commitId - if (workflow.revision) misc_fields['Pipeline Git branch/tag'] = workflow.revision - misc_fields['Nextflow Version'] = workflow.nextflow.version - misc_fields['Nextflow Build'] = workflow.nextflow.build - misc_fields['Nextflow Compile Timestamp'] = workflow.nextflow.timestamp - - def email_fields = [:] - email_fields['version'] = NfcoreTemplate.version(workflow) - email_fields['runName'] = workflow.runName - email_fields['success'] = workflow.success - email_fields['dateComplete'] = workflow.complete - email_fields['duration'] = workflow.duration - email_fields['exitStatus'] = workflow.exitStatus - email_fields['errorMessage'] = (workflow.errorMessage ?: 'None') - email_fields['errorReport'] = (workflow.errorReport ?: 'None') - email_fields['commandLine'] = workflow.commandLine - email_fields['projectDir'] = workflow.projectDir - email_fields['summary'] = summary << misc_fields - - // On success try attach the multiqc report - def mqc_report = null - try { - if (workflow.success) { - mqc_report = multiqc_report.getVal() - if (mqc_report.getClass() == ArrayList && mqc_report.size() >= 1) { - if (mqc_report.size() > 1) { - log.warn "[$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("$projectDir/assets/email_template.html") - def html_template = engine.createTemplate(hf).make(email_fields) - def email_html = html_template.toString() - - // Render the sendmail template - def max_multiqc_email_size = (params.containsKey('max_multiqc_email_size') ? params.max_multiqc_email_size : 0) as nextflow.util.MemoryUnit - def smail_fields = [ email: email_address, subject: subject, email_txt: email_txt, email_html: email_html, projectDir: "$projectDir", mqcFile: mqc_report, mqcMaxSize: max_multiqc_email_size.toBytes() ] - def sf = new File("$projectDir/assets/sendmail_template.txt") - def sendmail_template = engine.createTemplate(sf).make(smail_fields) - def sendmail_html = sendmail_template.toString() - - // Send the HTML e-mail - Map colors = logColours(params.monochrome_logs) - if (email_address) { - try { - if (params.plaintext_email) { throw GroovyException('Send plaintext e-mail, not HTML') } - // Try to send HTML e-mail using sendmail - def sendmail_tf = new File(workflow.launchDir.toString(), ".sendmail_tmp.html") - sendmail_tf.withWriter { w -> w << sendmail_html } - [ 'sendmail', '-t' ].execute() << sendmail_html - log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Sent summary e-mail to $email_address (sendmail)-" - } catch (all) { - // Catch failures and try with plaintext - def mail_cmd = [ 'mail', '-s', subject, '--content-type=text/html', email_address ] - if ( mqc_report != null && mqc_report.size() <= max_multiqc_email_size.toBytes() ) { - mail_cmd += [ '-A', mqc_report ] - } - mail_cmd.execute() << email_html - log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Sent summary e-mail to $email_address (mail)-" - } - } - - // Write summary e-mail HTML to a file - def output_hf = new File(workflow.launchDir.toString(), ".pipeline_report.html") - output_hf.withWriter { w -> w << email_html } - FilesEx.copyTo(output_hf.toPath(), "${params.outdir}/pipeline_info/pipeline_report.html"); - output_hf.delete() - - // Write summary e-mail TXT to a file - def output_tf = new File(workflow.launchDir.toString(), ".pipeline_report.txt") - output_tf.withWriter { w -> w << email_txt } - FilesEx.copyTo(output_tf.toPath(), "${params.outdir}/pipeline_info/pipeline_report.txt"); - output_tf.delete() - } - - // - // Construct and send a notification to a web server as JSON - // e.g. Microsoft Teams and Slack - // - public static void IM_notification(workflow, params, summary_params, projectDir, log) { - def hook_url = params.hook_url - - def summary = [:] - for (group in summary_params.keySet()) { - summary << summary_params[group] - } - - def misc_fields = [:] - misc_fields['start'] = workflow.start - misc_fields['complete'] = workflow.complete - misc_fields['scriptfile'] = workflow.scriptFile - misc_fields['scriptid'] = workflow.scriptId - if (workflow.repository) misc_fields['repository'] = workflow.repository - if (workflow.commitId) misc_fields['commitid'] = workflow.commitId - if (workflow.revision) misc_fields['revision'] = workflow.revision - misc_fields['nxf_version'] = workflow.nextflow.version - misc_fields['nxf_build'] = workflow.nextflow.build - misc_fields['nxf_timestamp'] = workflow.nextflow.timestamp - - def msg_fields = [:] - msg_fields['version'] = NfcoreTemplate.version(workflow) - msg_fields['runName'] = workflow.runName - msg_fields['success'] = workflow.success - msg_fields['dateComplete'] = workflow.complete - msg_fields['duration'] = workflow.duration - msg_fields['exitStatus'] = workflow.exitStatus - msg_fields['errorMessage'] = (workflow.errorMessage ?: 'None') - msg_fields['errorReport'] = (workflow.errorReport ?: 'None') - msg_fields['commandLine'] = workflow.commandLine.replaceFirst(/ +--hook_url +[^ ]+/, "") - msg_fields['projectDir'] = workflow.projectDir - msg_fields['summary'] = summary << misc_fields - - // Render the JSON template - def engine = new groovy.text.GStringTemplateEngine() - // Different JSON depending on the service provider - // Defaults to "Adaptive Cards" (https://adaptivecards.io), except Slack which has its own format - def json_path = hook_url.contains("hooks.slack.com") ? "slackreport.json" : "adaptivecard.json" - def hf = new File("$projectDir/assets/${json_path}") - def json_template = engine.createTemplate(hf).make(msg_fields) - def json_message = json_template.toString() - - // POST - def post = new URL(hook_url).openConnection(); - post.setRequestMethod("POST") - post.setDoOutput(true) - post.setRequestProperty("Content-Type", "application/json") - post.getOutputStream().write(json_message.getBytes("UTF-8")); - def postRC = post.getResponseCode(); - if (! postRC.equals(200)) { - log.warn(post.getErrorStream().getText()); - } - } - - // - // Dump pipeline parameters in a json file - // - public static void dump_parameters(workflow, params) { - def timestamp = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss') - def filename = "params_${timestamp}.json" - def temp_pf = new File(workflow.launchDir.toString(), ".${filename}") - def jsonStr = JsonOutput.toJson(params) - temp_pf.text = JsonOutput.prettyPrint(jsonStr) - - FilesEx.copyTo(temp_pf.toPath(), "${params.outdir}/pipeline_info/params_${timestamp}.json") - temp_pf.delete() - } - - // - // Print pipeline summary on completion - // - public static void summary(workflow, params, log) { - Map colors = logColours(params.monochrome_logs) - if (workflow.success) { - if (workflow.stats.ignoredCount == 0) { - log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Pipeline completed successfully${colors.reset}-" - } else { - log.info "-${colors.purple}[$workflow.manifest.name]${colors.yellow} Pipeline completed successfully, but with errored process(es) ${colors.reset}-" - } - } else { - log.info "-${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 workflow_version = NfcoreTemplate.version(workflow) - 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} ${workflow_version}${colors.reset} - ${dashedLine(monochrome_logs)} - """.stripIndent() - ) - } -} diff --git a/lib/Utils.groovy b/lib/Utils.groovy deleted file mode 100644 index 8d030f4e..00000000 --- a/lib/Utils.groovy +++ /dev/null @@ -1,47 +0,0 @@ -// -// 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 - // This channel list is ordered by required channel priority. - def required_channels_in_order = ['conda-forge', 'bioconda', 'defaults'] - def channels_missing = ((required_channels_in_order as Set) - (channels as Set)) as Boolean - - // Check that they are in the right order - def channel_priority_violation = false - def n = required_channels_in_order.size() - for (int i = 0; i < n - 1; i++) { - channel_priority_violation |= !(channels.indexOf(required_channels_in_order[i]) < channels.indexOf(required_channels_in_order[i+1])) - } - - if (channels_missing | channel_priority_violation) { - 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/\n" + - " The observed channel order is \n" + - " ${channels}\n" + - " but the following channel order is required:\n" + - " ${required_channels_in_order}\n" + - "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~" - } - } -} diff --git a/lib/WorkflowMain.groovy b/lib/WorkflowMain.groovy deleted file mode 100755 index 9f577f58..00000000 --- a/lib/WorkflowMain.groovy +++ /dev/null @@ -1,76 +0,0 @@ -// -// This file holds several functions specific to the main.nf workflow in the nf-core/taxprofiler pipeline -// - -import nextflow.Nextflow - -class WorkflowMain { - - // - // Citation string for pipeline - // - public static String citation(workflow) { - return "If you use ${workflow.manifest.name} for your analysis please cite:\n\n" + - "* The pipeline\n" + - " https://doi.org/10.5281/zenodo.7728364\n\n" + - '* The nf-core framework\n' + - ' https://doi.org/10.1038/s41587-020-0439-x\n\n' + - '* Software dependencies\n' + - " https://github.com/${workflow.manifest.name}/blob/master/CITATIONS.md" - } - - - // - // Validate parameters and print summary to screen - // - public static void initialise(workflow, params, log, args) { - - // Print workflow version and exit on --version - if (params.version) { - String workflow_version = NfcoreTemplate.version(workflow) - log.info "${workflow.manifest.name} ${workflow_version}" - System.exit(0) - } - - // Check that a -profile or Nextflow config has been provided to run the pipeline - NfcoreTemplate.checkConfigProvided(workflow, log) - // Check that the profile doesn't contain spaces and doesn't end with a trailing comma - checkProfile(workflow.profile, args, log) - - // Check that conda channels are set-up correctly - if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) { - Utils.checkCondaChannels(log) - } - - // Check AWS batch settings - NfcoreTemplate.awsBatch(workflow, params) - - // Check input has been provided - if (!params.input) { - Nextflow.error("Please provide an input samplesheet to the pipeline e.g. '--input samplesheet.csv'") - } - } - // - // Get attribute from genome config file e.g. fasta - // - public static Object getGenomeAttribute(params, attribute) { - if (params.genomes && params.genome && params.genomes.containsKey(params.genome)) { - if (params.genomes[ params.genome ].containsKey(attribute)) { - return params.genomes[ params.genome ][ attribute ] - } - } - return null - } - - // - // Exit pipeline if --profile contains spaces - // - private static void checkProfile(profile, args, log) { - if (profile.endsWith(',')) { - Nextflow.error "Profile cannot end with a trailing comma. Please remove the comma from the end of the profile string.\nHint: A common mistake is to provide multiple values to `-profile` separated by spaces. Please use commas to separate profiles instead,e.g., `-profile docker,test`." - } - if (args[0]) { - log.warn "nf-core pipelines do not accept positional arguments. The positional argument `${args[0]}` has been detected.\n Hint: A common mistake is to provide multiple values to `-profile` separated by spaces. Please use commas to separate profiles instead,e.g., `-profile docker,test`." - } - } -} diff --git a/lib/WorkflowTaxprofiler.groovy b/lib/WorkflowTaxprofiler.groovy deleted file mode 100755 index d6f45909..00000000 --- a/lib/WorkflowTaxprofiler.groovy +++ /dev/null @@ -1,249 +0,0 @@ -// -// This file holds several functions specific to the workflow/taxprofiler.nf in the nf-core/taxprofiler pipeline -// - -import nextflow.Nextflow -import groovy.text.SimpleTemplateEngine - -class WorkflowTaxprofiler { - - // - // Check and validate parameters - // - - public static void initialise(params, log) { - - genomeExistsError(params, log) - //if (!params.fasta) { - // Nextflow.error "Genome fasta file not specified with e.g. '--fasta genome.fa' or via a detectable config file." - //} - } - - - // - // 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" - for (param in group_params.keySet()) { - summary_section += "
$param
${group_params.get(param) ?: 'N/A'}
\n" - } - summary_section += "
\n" - } - } - - String yaml_file_text = "id: '${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 - } - - /// - /// Automatic publication methods text generation - /// - - public static String toolCitationText(params) { - - // Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "Tool (Foo et al. 2023)" : "", - // Uncomment function in methodsDescriptionText to render in MultiQC report - def text_seq_qc = [ - "Sequencing quality control was carried out with:", - params.preprocessing_qc_tool == "falco" ? "Falco (de Sena Brandine and Smith 2021)." : "FastQC (Andrews 2010)." - ].join(' ').trim() - - def text_shortread_qc = [ - "Short read preprocessing was performed with:", - params.shortread_qc_tool == "adapterremoval" ? "AdapterRemoval (Schubert et al. 2016)." : "", - params.shortread_qc_tool == "fastp" ? "fastp (Chen et al. 2018)." : "", - ].join(' ').trim() - - def text_longread_qc = [ - "Long read preprocessing was performed with:", - !params.longread_qc_skipadaptertrim ? "Porechop (Wick et al. 2017)," : "", - !params.longread_qc_skipqualityfilter ? "Filtlong (Wick 2021)," : "", - "." - ].join(' ').trim() - - def text_shortreadcomplexity = [ - "Low-complexity sequence filtering was carried out with:", - params.shortread_complexityfilter_tool == "bbduk" ? "BBDuk (Bushnell 2022)." : "", - params.shortread_complexityfilter_tool == "prinseqplusplus" ? "PRINSEQ++ (Cantu et al. 2019)." : "", - params.shortread_complexityfilter_tool == "fastp" ? "fastp (Chen et al. 2018)." : "", - ].join(' ').trim() - - def text_shortreadhostremoval = [ - "Host read removal was performed for short reads with Bowtie2 (Langmead and Salzberg 2012) and SAMtools (Danecek et al. 2021)." - ].join(' ').trim() - - def text_longreadhostremoval = [ - "Host read removal was performed for long reads with minimap2 (Li et al. 2018) and SAMtools (Danecek et al. 2021)." - ].join(' ').trim() - - - def text_classification = [ - "Taxonomic classification or profiling was carried out with:", - params.run_bracken ? "Bracken (Lu et al. 2017)," : "", - params.run_kraken2 ? "Kraken2 (Wood et al. 2019)," : "", - params.run_krakenuniq ? "KrakenUniq (Breitwieser et al. 2018)," : "", - params.run_metaphlan ? "MetaPhlAn (Blanco-Míguez et al. 2023)," : "", - params.run_malt ? "MALT (Vågene et al. 2018) and MEGAN6 CE (Huson et al. 2016)," : "", - params.run_diamond ? "DIAMOND (Buchfink et al. 2015)," : "", - params.run_centrifuge ? "Centrifuge (Kim et al. 2016)," : "", - params.run_kaiju ? "Kaiju (Menzel et al. 2016)," : "", - params.run_motus ? "mOTUs (Ruscheweyh et al. 2022)," : "", - params.run_ganon ? "ganon (Piro et al. 2020)" : "", - params.run_kmcp ? "KMCP (Shen et al. 2023)" : "", - "." - ].join(' ').trim() - - def text_visualisation = [ - "Visualisation of results, where supported, was performed with Krona (Ondov et al. 2011)." - ].join(' ').trim() - - def text_postprocessing = [ - "Standardisation of taxonomic profiles was carried out with TAXPASTA (Beber et al. 2023).", - ].join(' ').trim() - - def citation_text = [ - "Tools used in the workflow included:", - text_seq_qc, - params.perform_shortread_qc ? text_shortread_qc : "", - params.perform_longread_qc ? text_longread_qc : "", - params.perform_shortread_complexityfilter ? text_shortreadcomplexity : "", - params.perform_shortread_hostremoval ? text_shortreadhostremoval : "", - params.perform_longread_hostremoval ? text_longreadhostremoval : "", - text_classification, - params.run_krona ? text_visualisation : "", - params.run_profile_standardisation ? text_postprocessing : "", - "Pipeline results statistics were summarised with MultiQC (Ewels et al. 2016)." - ].join(' ').trim().replaceAll("[,|.] +\\.", ".") - - return citation_text - } - - public static String toolBibliographyText(params) { - - def text_seq_qc = [ - params.preprocessing_qc_tool == "falco" ? "
  • de Sena Brandine, G., & Smith, A. D. (2021). Falco: high-speed FastQC emulation for quality control of sequencing data. F1000Research, 8(1874), 1874. 10.12688/f1000research.21142.2
    • " : "", - params.preprocessing_qc_tool == "fastqc" ? "
  • Andrews S. (2010) FastQC: A Quality Control Tool for High Throughput Sequence Data, URL: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/
    • " : "", - ].join(' ').trim() - - - def text_shortread_qc = [ - params.shortread_qc_tool == "adapterremoval" ? "
  • Schubert, M., Lindgreen, S., & Orlando, L. (2016). AdapterRemoval v2: rapid adapter trimming, identification, and read merging. BMC Research Notes, 9, 88. 10.1186/s13104-016-1900-2
    • " : "", - ].join(' ').trim() - - def text_longread_qc = [ - !params.longread_qc_skipadaptertrim ? "
  • Wick, R. R., Judd, L. M., Gorrie, C. L., & Holt, K. E. (2017). Completing bacterial genome assemblies with multiplex MinION sequencing. Microbial Genomics, 3(10), e000132. 10.1099/mgen.0.000132
    • " : "", - !params.longread_qc_skipqualityfilter ? "
  • Wick R. (2021) Filtlong, URL: https://github.com/rrwick/Filtlong
    • " : "" - ].join(' ').trim() - - def text_shortreadcomplexity = [ - params.shortread_complexityfilter_tool == "bbduk" ? "
  • Bushnell B. (2022) BBMap, URL: http://sourceforge.net/projects/bbmap/
    • " : "", - params.shortread_complexityfilter_tool == "prinseqplusplus" ? "
  • Cantu, V. A., Sadural, J., & Edwards, R. (2019). PRINSEQ++, a multi-threaded tool for fast and efficient quality control and preprocessing of sequencing datasets (e27553v1). PeerJ Preprints. 10.7287/peerj.preprints.27553v1
    • " : "", - ].join(' ').trim() - - def text_shortreadhostremoval = [ - "
  • Langmead, B., & Salzberg, S. L. (2012). Fast gapped-read alignment with Bowtie 2. Nature Methods, 9(4), 357–359. 10.1038/nmeth.1923
    • ", - ].join(' ').trim() - - def text_longreadhostremoval = [ - "
  • Li, H. (2018). Minimap2: pairwise alignment for nucleotide sequences. Bioinformatics , 34(18), 3094–3100. 10.1093/bioinformatics/bty191
    • ", - ].join(' ').trim() - - - def text_classification = [ - params.run_bracken ? "
  • Lu, J., Breitwieser, F. P., Thielen, P., & Salzberg, S. L. (2017). Bracken: estimating species abundance in metagenomics data. PeerJ. Computer Science, 3(e104), e104. 10.7717/peerj-cs.104
    • " : "", - params.run_kraken2 ? "
  • Wood, D. E., Lu, J., & Langmead, B. (2019). Improved metagenomic analysis with Kraken 2. Genome Biology, 20(1), 257. 10.1186/s13059-019-1891-0
    • " : "", - params.run_krakenuniq ? "
  • Breitwieser, F. P., Baker, D. N., & Salzberg, S. L. (2018). KrakenUniq: confident and fast metagenomics classification using unique k-mer counts. Genome Biology, 19(1), 198. 10.1186/s13059-018-1568-0
    • " : "", - params.run_metaphlan ? "
  • Blanco-Míguez, A., Beghini, F., Cumbo, F., McIver, L. J., Thompson, K. N., Zolfo, M., Manghi, P., Dubois, L., Huang, K. D., Thomas, A. M., Nickols, W. A., Piccinno, G., Piperni, E., Punčochář, M., Valles-Colomer, M., Tett, A., Giordano, F., Davies, R., Wolf, J., … Segata, N. (2023). Extending and improving metagenomic taxonomic profiling with uncharacterized species using MetaPhlAn 4. Nature Biotechnology, 1–12. 10.1038/s41587-023-01688-w
    • " : "", - params.run_malt ? "
  • Vågene, Å. J., Herbig, A., Campana, M. G., Robles García, N. M., Warinner, C., Sabin, S., Spyrou, M. A., Andrades Valtueña, A., Huson, D., Tuross, N., Bos, K. I., & Krause, J. (2018). Salmonella enterica genomes from victims of a major sixteenth-century epidemic in Mexico. Nature Ecology & Evolution, 2(3), 520–528. 10.1038/s41559-017-0446-6
    • " : "", - params.run_malt ? "
  • Huson, D. H., Beier, S., Flade, I., Górska, A., El-Hadidi, M., Mitra, S., Ruscheweyh, H.-J., & Tappu, R. (2016). MEGAN Community Edition - Interactive Exploration and Analysis of Large-Scale Microbiome Sequencing Data. PLoS Computational Biology, 12(6), e1004957. 10.1371/journal.pcbi.1004957
    • " : "", - params.run_diamond ? "
  • Buchfink, B., Xie, C., & Huson, D. H. (2015). Fast and sensitive protein alignment using DIAMOND. Nature Methods, 12(1), 59–60. 10.1038/nmeth.3176
    • " : "", - params.run_centrifuge ? "
  • Kim, D., Song, L., Breitwieser, F. P., & Salzberg, S. L. (2016). Centrifuge: rapid and sensitive classification of metagenomic sequences. Genome Research, 26(12), 1721–1729. 10.1101/gr.210641.116
    • " : "", - params.run_kaiju ? "
  • Menzel, P., Ng, K. L., & Krogh, A. (2016). Fast and sensitive taxonomic classification for metagenomics with Kaiju. Nature Communications, 7, 11257. 10.1038/ncomms11257
    • " : "", - params.run_motus ? "
  • Ruscheweyh, H.-J., Milanese, A., Paoli, L., Karcher, N., Clayssen, Q., Keller, M. I., Wirbel, J., Bork, P., Mende, D. R., Zeller, G., & Sunagawa, S. (2022). Cultivation-independent genomes greatly expand taxonomic-profiling capabilities of mOTUs across various environments. Microbiome, 10(1), 212. 10.1186/s40168-022-01410-z
    • " : "", - params.run_ganon ? "
  • Piro, V. C., Dadi, T. H., Seiler, E., Reinert, K., & Renard, B. Y. (2020). Ganon: Precise metagenomics classification against large and up-to-date sets of reference sequences. Bioinformatics (Oxford, England), 36(Suppl_1), i12–i20. 10.1093/bioinformatics/btaa458
    • " : "", - params.run_kmcp ? "
  • Shen, W., Xiang, H., Huang, T., Tang, H., Peng, M., Cai, D., Hu, P., & Ren, H. (2023). KMCP: accurate metagenomic profiling of both prokaryotic and viral populations by pseudo-mapping. Bioinformatics (Oxford, England), 39(1). 10.1093/bioinformatics/btac845
    • " : "", - ].join(' ').trim() - - def text_visualisation = [ - "
  • Ondov, B. D., Bergman, N. H., & Phillippy, A. M. (2011). Interactive metagenomic visualization in a Web browser. BMC Bioinformatics, 12(1), 385. 10.1186/1471-2105-12-385
    • " - ].join(' ').trim() - - def text_postprocessing = [ - "
  • Beber, M. E., Borry, M., Stamouli, S., & Fellows Yates, J. A. (2023). TAXPASTA: TAXonomic Profile Aggregation and STAndardisation. Journal of Open Source Software, 8(87), 5627. 10.21105/joss.05627
    • ", - ].join(' ').trim() - - def text_extras = [ - // fastp shortread qc / complexity filtering - ( params.perform_shortread_qc && params.shortread_qc_tool == "fastp" ) || ( params.perform_shortread_complexityfilter && params.shortread_complexityfilter_tool == "fastp" ) ? "
  • Chen, S., Zhou, Y., Chen, Y., & Gu, J. (2018). fastp: an ultra-fast all-in-one FASTQ preprocessor. Bioinformatics , 34(17), i884–i890. 10.1093/bioinformatics/bty560
    • " : "", - // samtools long / short hostremoval - params.perform_shortread_hostremoval || params.perform_longread_hostremoval ? "
  • Danecek, P., Bonfield, J. K., Liddle, J., Marshall, J., Ohan, V., Pollard, M. O., Whitwham, A., Keane, T., McCarthy, S. A., Davies, R. M., & Li, H. (2021). Twelve years of SAMtools and BCFtools. GigaScience, 10(2). 10.1093/gigascience/giab008
    • " : "", - ].join(' ').trim() - - def reference_text = [ - text_seq_qc, - params.perform_shortread_qc ? text_shortread_qc : "", - params.perform_longread_qc ? text_longread_qc : "", - params.perform_shortread_complexityfilter ? text_shortreadcomplexity : "", - params.perform_shortread_hostremoval ? text_shortreadhostremoval : "", - params.perform_longread_hostremoval ? text_longreadhostremoval : "", - text_extras, - text_classification, - params.run_krona ? text_visualisation : "", - params.run_profile_standardisation ? text_postprocessing : "", - "
  • Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics , 32(19), 3047–3048. 10.1093/bioinformatics/btw354.
    • " - ].join(' ').trim().replaceAll("[,|.] +\\.", ".") - - return reference_text - } - - public static String methodsDescriptionText(run_workflow, mqc_methods_yaml, params) { - // Convert to a named map so can be used as with familar NXF ${workflow} variable syntax in the MultiQC YML file - def meta = [:] - - meta.workflow = run_workflow.toMap() - meta["manifest_map"] = run_workflow.manifest.toMap() - - // Pipeline DOI - meta["doi_text"] = meta.manifest_map.doi ? "(doi: Stamouli et al. 2023)" : "" - meta["nodoi_text"] = meta.manifest_map.doi ? "": "
  • If available, make sure to update the text to include the Zenodo DOI of version of the pipeline used.
    • " - - meta["tool_citations"] = "" - meta["tool_bibliography"] = "" - - meta["tool_citations"] = toolCitationText(params) - meta["tool_bibliography"] = toolBibliographyText(params) - - def methods_text = mqc_methods_yaml.text - - def engine = new SimpleTemplateEngine() - def description_html = engine.createTemplate(methods_text).make(meta) - - return description_html - } - - // - // Exit pipeline if incorrect --genome key provided - // - private static void genomeExistsError(params, log) { - if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) { - def error_string = "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" + - " Genome '${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" + - "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~" - Nextflow.error(error_string) - } - } -} diff --git a/main.nf b/main.nf index d10d46a6..1cca7494 100644 --- a/main.nf +++ b/main.nf @@ -13,61 +13,95 @@ nextflow.enable.dsl = 2 /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - GENOME PARAMETER VALUES + IMPORT FUNCTIONS / MODULES / SUBWORKFLOWS / WORKFLOWS ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ +include { TAXPROFILER } from './workflows/taxprofiler' +include { PIPELINE_INITIALISATION } from './subworkflows/local/utils_nfcore_taxprofiler_pipeline' +include { PIPELINE_COMPLETION } from './subworkflows/local/utils_nfcore_taxprofiler_pipeline' + /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - VALIDATE & PRINT PARAMETER SUMMARY + GENOME PARAMETER VALUES ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ include { validateParameters; paramsHelp } from 'plugin/nf-validation' -// Print help message if needed -if (params.help) { - def logo = NfcoreTemplate.logo(workflow, params.monochrome_logs) - def citation = '\n' + WorkflowMain.citation(workflow) + '\n' - def String command = "nextflow run ${workflow.manifest.name} --input samplesheet.csv --databases databases.csv --outdir results/ -profile docker --run_kraken2" - log.info logo + paramsHelp(command) + citation + NfcoreTemplate.dashedLine(params.monochrome_logs) - System.exit(0) -} - -// Validate input parameters -if (params.validate_params) { - validateParameters() -} - -WorkflowMain.initialise(workflow, params, log, args) - /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - NAMED WORKFLOW FOR PIPELINE + NAMED WORKFLOWS FOR PIPELINE ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -include { TAXPROFILER } from './workflows/taxprofiler' - // -// WORKFLOW: Run main nf-core/taxprofiler analysis pipeline +// WORKFLOW: Run main analysis pipeline depending on type of input // workflow NFCORE_TAXPROFILER { - TAXPROFILER () -} + take: + samplesheet // channel: samplesheet read in from --input + databases // channel: databases in from --databases + + main: + + // + // WORKFLOW: Run pipeline + // + TAXPROFILER ( + samplesheet, + databases, + ) + + emit: + multiqc_report = TAXPROFILER.out.multiqc_report // channel: /path/to/multiqc_report.html + +} /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - RUN ALL WORKFLOWS + RUN MAIN WORKFLOW ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -// -// WORKFLOW: Execute a single named workflow for the pipeline -// See: https://github.com/nf-core/rnaseq/issues/619 -// workflow { - NFCORE_TAXPROFILER () + + main: + + // + // SUBWORKFLOW: Run initialisation tasks + // + PIPELINE_INITIALISATION ( + params.version, + params.help, + params.validate_params, + params.monochrome_logs, + args, + params.outdir, + params.input, + params.databases + ) + + // + // WORKFLOW: Run main workflow + // + NFCORE_TAXPROFILER ( + PIPELINE_INITIALISATION.out.samplesheet, + PIPELINE_INITIALISATION.out.databases, + ) + + // + // SUBWORKFLOW: Run completion tasks + // + PIPELINE_COMPLETION ( + params.email, + params.email_on_fail, + params.plaintext_email, + params.outdir, + params.monochrome_logs, + params.hook_url, + NFCORE_TAXPROFILER.out.multiqc_report + ) } /* diff --git a/modules.json b/modules.json index 7e0ccda3..f8c101e0 100644 --- a/modules.json +++ b/modules.json @@ -50,11 +50,6 @@ "git_sha": "9a07a1293d9b818d1e06d0f7b58152f74d462012", "installed_by": ["modules"] }, - "custom/dumpsoftwareversions": { - "branch": "master", - "git_sha": "8ec825f465b9c17f9d83000022995b4f7de6fe93", - "installed_by": ["modules"] - }, "diamond/blastx": { "branch": "master", "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", @@ -62,18 +57,17 @@ }, "falco": { "branch": "master", - "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", - "installed_by": ["modules"], - "patch": "modules/nf-core/falco/falco.diff" + "git_sha": "a236d2c2ec9e68db9b8501105d804acb359552b5", + "installed_by": ["modules"] }, "fastp": { "branch": "master", - "git_sha": "d497a4868ace3302016ea8ed4b395072d5e833cd", + "git_sha": "451d49b70f1801a9e5835f111c927104af64481e", "installed_by": ["modules"] }, "fastqc": { "branch": "master", - "git_sha": "c9488585ce7bd35ccd2a30faa2371454c8112fb9", + "git_sha": "f4ae1d942bd50c5c0b9bd2de1393ce38315ba57c", "installed_by": ["modules"] }, "filtlong": { @@ -198,7 +192,7 @@ }, "multiqc": { "branch": "master", - "git_sha": "8ec825f465b9c17f9d83000022995b4f7de6fe93", + "git_sha": "b7ebe95761cd389603f9cc0e0dc384c0f663815a", "installed_by": ["modules"] }, "porechop/porechop": { @@ -248,6 +242,25 @@ "installed_by": ["modules"] } } + }, + "subworkflows": { + "nf-core": { + "utils_nextflow_pipeline": { + "branch": "master", + "git_sha": "5caf7640a9ef1d18d765d55339be751bb0969dfa", + "installed_by": ["subworkflows"] + }, + "utils_nfcore_pipeline": { + "branch": "master", + "git_sha": "5caf7640a9ef1d18d765d55339be751bb0969dfa", + "installed_by": ["subworkflows"] + }, + "utils_nfvalidation_plugin": { + "branch": "master", + "git_sha": "5caf7640a9ef1d18d765d55339be751bb0969dfa", + "installed_by": ["subworkflows"] + } + } } } } diff --git a/modules/local/samplesheet_check.nf b/modules/local/samplesheet_check.nf deleted file mode 100644 index 7cd27e39..00000000 --- a/modules/local/samplesheet_check.nf +++ /dev/null @@ -1,31 +0,0 @@ -process SAMPLESHEET_CHECK { - tag "$samplesheet" - label 'process_single' - - conda "conda-forge::python=3.8.3" - container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/python:3.8.3' : - 'biocontainers/python:3.8.3' }" - - input: - path samplesheet - - output: - path '*.csv' , emit: csv - path "versions.yml", emit: versions - - when: - task.ext.when == null || task.ext.when - - script: // This script is bundled with the pipeline, in nf-core/taxprofiler/bin/ - """ - check_samplesheet.py \\ - $samplesheet \\ - samplesheet.valid.csv - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - python: \$(python --version | sed 's/Python //g') - END_VERSIONS - """ -} diff --git a/modules/nf-core/custom/dumpsoftwareversions/main.nf b/modules/nf-core/custom/dumpsoftwareversions/main.nf deleted file mode 100644 index f2187611..00000000 --- a/modules/nf-core/custom/dumpsoftwareversions/main.nf +++ /dev/null @@ -1,24 +0,0 @@ -process CUSTOM_DUMPSOFTWAREVERSIONS { - label 'process_single' - - // Requires `pyyaml` which does not have a dedicated container but is in the MultiQC container - conda "${moduleDir}/environment.yml" - container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/multiqc:1.19--pyhdfd78af_0' : - 'biocontainers/multiqc:1.19--pyhdfd78af_0' }" - - input: - path versions - - output: - path "software_versions.yml" , emit: yml - path "software_versions_mqc.yml", emit: mqc_yml - path "versions.yml" , emit: versions - - when: - task.ext.when == null || task.ext.when - - script: - def args = task.ext.args ?: '' - template 'dumpsoftwareversions.py' -} diff --git a/modules/nf-core/custom/dumpsoftwareversions/meta.yml b/modules/nf-core/custom/dumpsoftwareversions/meta.yml deleted file mode 100644 index 5f15a5fd..00000000 --- a/modules/nf-core/custom/dumpsoftwareversions/meta.yml +++ /dev/null @@ -1,37 +0,0 @@ -# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json -name: custom_dumpsoftwareversions -description: Custom module used to dump software versions within the nf-core pipeline template -keywords: - - custom - - dump - - version -tools: - - custom: - description: Custom module used to dump software versions within the nf-core pipeline template - homepage: https://github.com/nf-core/tools - documentation: https://github.com/nf-core/tools - licence: ["MIT"] -input: - - versions: - type: file - description: YML file containing software versions - pattern: "*.yml" -output: - - yml: - type: file - description: Standard YML file containing software versions - pattern: "software_versions.yml" - - mqc_yml: - type: file - description: MultiQC custom content YML file containing software versions - pattern: "software_versions_mqc.yml" - - versions: - type: file - description: File containing software versions - pattern: "versions.yml" -authors: - - "@drpatelh" - - "@grst" -maintainers: - - "@drpatelh" - - "@grst" diff --git a/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py b/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py deleted file mode 100755 index da033408..00000000 --- a/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py +++ /dev/null @@ -1,101 +0,0 @@ -#!/usr/bin/env python - - -"""Provide functions to merge multiple versions.yml files.""" - - -import yaml -import platform -from textwrap import dedent - - -def _make_versions_html(versions): - """Generate a tabular HTML output of all versions for MultiQC.""" - html = [ - dedent( - """\\ - - - - - - - - - - """ - ) - ] - for process, tmp_versions in sorted(versions.items()): - html.append("") - for i, (tool, version) in enumerate(sorted(tmp_versions.items())): - html.append( - dedent( - f"""\\ - - - - - - """ - ) - ) - html.append("") - html.append("
    Process Name Software Version
    {process if (i == 0) else ''}{tool}{version}
    ") - return "\\n".join(html) - - -def main(): - """Load all version files and generate merged output.""" - versions_this_module = {} - versions_this_module["${task.process}"] = { - "python": platform.python_version(), - "yaml": yaml.__version__, - } - - with open("$versions") as f: - versions_by_process = yaml.load(f, Loader=yaml.BaseLoader) | versions_this_module - - # aggregate versions by the module name (derived from fully-qualified process name) - versions_by_module = {} - for process, process_versions in versions_by_process.items(): - module = process.split(":")[-1] - try: - if versions_by_module[module] != process_versions: - raise AssertionError( - "We assume that software versions are the same between all modules. " - "If you see this error-message it means you discovered an edge-case " - "and should open an issue in nf-core/tools. " - ) - except KeyError: - versions_by_module[module] = process_versions - - versions_by_module["Workflow"] = { - "Nextflow": "$workflow.nextflow.version", - "$workflow.manifest.name": "$workflow.manifest.version", - } - - versions_mqc = { - "id": "software_versions", - "section_name": "${workflow.manifest.name} Software Versions", - "section_href": "https://github.com/${workflow.manifest.name}", - "plot_type": "html", - "description": "are collected at run time from the software output.", - "data": _make_versions_html(versions_by_module), - } - - with open("software_versions.yml", "w") as f: - yaml.dump(versions_by_module, f, default_flow_style=False) - with open("software_versions_mqc.yml", "w") as f: - yaml.dump(versions_mqc, f, default_flow_style=False) - - with open("versions.yml", "w") as f: - yaml.dump(versions_this_module, f, default_flow_style=False) - - -if __name__ == "__main__": - main() diff --git a/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test b/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test deleted file mode 100644 index b1e1630b..00000000 --- a/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test +++ /dev/null @@ -1,43 +0,0 @@ -nextflow_process { - - name "Test Process CUSTOM_DUMPSOFTWAREVERSIONS" - script "../main.nf" - process "CUSTOM_DUMPSOFTWAREVERSIONS" - tag "modules" - tag "modules_nfcore" - tag "custom" - tag "dumpsoftwareversions" - tag "custom/dumpsoftwareversions" - - test("Should run without failures") { - when { - process { - """ - def tool1_version = ''' - TOOL1: - tool1: 0.11.9 - '''.stripIndent() - - def tool2_version = ''' - TOOL2: - tool2: 1.9 - '''.stripIndent() - - input[0] = Channel.of(tool1_version, tool2_version).collectFile() - """ - } - } - - then { - assertAll( - { assert process.success }, - { assert snapshot( - process.out.versions, - file(process.out.mqc_yml[0]).readLines()[0..10], - file(process.out.yml[0]).readLines()[0..7] - ).match() - } - ) - } - } -} diff --git a/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test.snap b/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test.snap deleted file mode 100644 index 5f59a936..00000000 --- a/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test.snap +++ /dev/null @@ -1,33 +0,0 @@ -{ - "Should run without failures": { - "content": [ - [ - "versions.yml:md5,76d454d92244589d32455833f7c1ba6d" - ], - [ - "data: \"\\n\\n \\n \\n \\n \\n \\n \\n \\n\\", - " \\n\\n\\n \\n \\n\\", - " \\ \\n\\n\\n\\n \\n \\", - " \\ \\n \\n\\n\\n\\n\\", - " \\n\\n \\n \\n\\", - " \\ \\n\\n\\n\\n\\n\\n \\n\\", - " \\ \\n \\n\\n\\n\\n\\", - " \\n\\n \\n \\n\\" - ], - [ - "CUSTOM_DUMPSOFTWAREVERSIONS:", - " python: 3.11.7", - " yaml: 5.4.1", - "TOOL1:", - " tool1: 0.11.9", - "TOOL2:", - " tool2: '1.9'", - "Workflow:" - ] - ], - "timestamp": "2024-01-09T23:01:18.710682" - } -} \ No newline at end of file diff --git a/modules/nf-core/custom/dumpsoftwareversions/tests/tags.yml b/modules/nf-core/custom/dumpsoftwareversions/tests/tags.yml deleted file mode 100644 index 405aa24a..00000000 --- a/modules/nf-core/custom/dumpsoftwareversions/tests/tags.yml +++ /dev/null @@ -1,2 +0,0 @@ -custom/dumpsoftwareversions: - - modules/nf-core/custom/dumpsoftwareversions/** diff --git a/modules/nf-core/custom/dumpsoftwareversions/environment.yml b/modules/nf-core/falco/environment.yml similarity index 51% rename from modules/nf-core/custom/dumpsoftwareversions/environment.yml rename to modules/nf-core/falco/environment.yml index 9b3272bc..eeedb5b7 100644 --- a/modules/nf-core/custom/dumpsoftwareversions/environment.yml +++ b/modules/nf-core/falco/environment.yml @@ -1,7 +1,7 @@ -name: custom_dumpsoftwareversions +name: falco channels: - conda-forge - bioconda - defaults dependencies: - - bioconda::multiqc=1.19 + - bioconda::falco=1.2.1 diff --git a/modules/nf-core/falco/main.nf b/modules/nf-core/falco/main.nf index 29ccc4bc..a4b343b2 100644 --- a/modules/nf-core/falco/main.nf +++ b/modules/nf-core/falco/main.nf @@ -3,7 +3,7 @@ process FALCO { label 'process_single' - conda "bioconda::falco=1.2.1" + conda "${moduleDir}/environment.yml" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/falco:1.2.1--h867801b_3': 'biocontainers/falco:1.2.1--h867801b_3' }" @@ -24,7 +24,7 @@ process FALCO { def prefix = task.ext.prefix ?: "${meta.id}" if ( reads.toList().size() == 1 ) { """ - falco $args --threads $task.cpus ${reads} -D ${prefix}_data.txt -S ${prefix}_summary.txt -R ${prefix}_report.html + falco $args --threads $task.cpus ${reads} -D ${prefix}_fastqc_data.txt -S ${prefix}_summary.txt -R ${prefix}_report.html cat <<-END_VERSIONS > versions.yml "${task.process}": @@ -33,9 +33,7 @@ process FALCO { """ } 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 - falco $args --threads $task.cpus ${prefix}_1.fastq.gz ${prefix}_2.fastq.gz + falco $args --threads $task.cpus ${reads} cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/nf-core/falco/meta.yml b/modules/nf-core/falco/meta.yml index 63846491..6201790c 100644 --- a/modules/nf-core/falco/meta.yml +++ b/modules/nf-core/falco/meta.yml @@ -8,12 +8,9 @@ keywords: tools: - fastqc: description: "falco is a drop-in C++ implementation of FastQC to assess the quality of sequence reads." - homepage: "https://falco.readthedocs.io/" documentation: "https://falco.readthedocs.io/" - - licence: "['GPL v3']" - + licence: ["GPL v3"] input: - meta: type: map @@ -49,3 +46,5 @@ output: pattern: "versions.yml" authors: - "@lucacozzuto" +maintainers: + - "@lucacozzuto" diff --git a/modules/nf-core/falco/tests/main.nf.test b/modules/nf-core/falco/tests/main.nf.test new file mode 100644 index 00000000..816c72ba --- /dev/null +++ b/modules/nf-core/falco/tests/main.nf.test @@ -0,0 +1,108 @@ +nextflow_process { + + name "Test Process FALCO" + script "../main.nf" + process "FALCO" + + tag "modules" + tag "modules_nfcore" + tag "falco" + + test("sarscov2 - fastq - single end") { + + when { + process { + """ + input[0] = [ + [ id: 'test', single_end:true ], + [ + file( + params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], + checkIfExists: true + ), + ], + ] + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot( + process.out.txt, + file(process.out.html.get(0).get(1)).list(), + ).match() + }, + ) + } + + } + + test("sarscov2 - fastq - paired end") { + + when { + process { + """ + input[0] = [ + [ id: 'test', single_end:false ], + [ + file( + params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], + checkIfExists: true + ), + file( + params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], + checkIfExists: true + ), + ], + ] + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot( + process.out.txt, + process.out.html.get(0).get(1).collect{ it.split("/")[-1] }.sort(), + ).match() + }, + ) + } + + } + + test("sarscov2 - fastq - interleaved") { + + when { + process { + """ + input[0] = [ + [ id: 'test', single_end:false ], + [ + file( + params.test_data['sarscov2']['illumina']['test_interleaved_fastq_gz'], + checkIfExists: true + ), + ], + ] + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot( + process.out.txt, + file(process.out.html.get(0).get(1)).list(), + ).match() + }, + ) + } + + } + +} diff --git a/modules/nf-core/falco/tests/main.nf.test.snap b/modules/nf-core/falco/tests/main.nf.test.snap new file mode 100644 index 00000000..34ac64e3 --- /dev/null +++ b/modules/nf-core/falco/tests/main.nf.test.snap @@ -0,0 +1,61 @@ +{ + "sarscov2 - fastq - single end": { + "content": [ + [ + [ + { + "id": "test", + "single_end": true + }, + [ + "test_fastqc_data.txt:md5,36d989bb9e2d5a632e19452f4e6c2a4e", + "test_summary.txt:md5,a925aec214a83d2f6252847166f2ef3a" + ] + ] + ], + null + ], + "timestamp": "2024-02-02T16:28:17.756764" + }, + "sarscov2 - fastq - paired end": { + "content": [ + [ + [ + { + "id": "test", + "single_end": false + }, + [ + "test_1.fastq.gz_fastqc_data.txt:md5,36d989bb9e2d5a632e19452f4e6c2a4e", + "test_1.fastq.gz_summary.txt:md5,a925aec214a83d2f6252847166f2ef3a", + "test_2.fastq.gz_fastqc_data.txt:md5,ad5c45dfc8f79754dd5d8029456b715b", + "test_2.fastq.gz_summary.txt:md5,d0cb642adefb5635a25e808f1f38780a" + ] + ] + ], + [ + "test_1.fastq.gz_fastqc_report.html", + "test_2.fastq.gz_fastqc_report.html" + ] + ], + "timestamp": "2024-02-02T16:22:11.757473" + }, + "sarscov2 - fastq - interleaved": { + "content": [ + [ + [ + { + "id": "test", + "single_end": false + }, + [ + "test_fastqc_data.txt:md5,b5e593f140fe578bdd25ceb84e98fd37", + "test_summary.txt:md5,ca52f458b1223d89db69e2d5e73cf867" + ] + ] + ], + null + ], + "timestamp": "2024-02-02T16:28:36.035899" + } +} \ No newline at end of file diff --git a/modules/nf-core/falco/tests/tags.yml b/modules/nf-core/falco/tests/tags.yml new file mode 100644 index 00000000..bf5610e2 --- /dev/null +++ b/modules/nf-core/falco/tests/tags.yml @@ -0,0 +1,2 @@ +falco: + - "modules/nf-core/falco/**" diff --git a/modules/nf-core/fastqc/tests/main.nf.test b/modules/nf-core/fastqc/tests/main.nf.test index c061650b..83586e4a 100644 --- a/modules/nf-core/fastqc/tests/main.nf.test +++ b/modules/nf-core/fastqc/tests/main.nf.test @@ -33,7 +33,7 @@ nextflow_process { { assert process.out.zip[0][1] ==~ ".*/test_fastqc.zip" }, { assert path(process.out.html[0][1]).text.contains("") }, - { assert snapshot(process.out.versions).match("versions") } + { assert snapshot(process.out.versions).match("fastqc_versions_single") } ) } } @@ -63,7 +63,7 @@ nextflow_process { { assert path(process.out.html[0][1][0]).text.contains("") }, { assert path(process.out.html[0][1][1]).text.contains("") }, - { assert snapshot(process.out.versions).match("versions") } + { assert snapshot(process.out.versions).match("fastqc_versions_paired") } ) } } @@ -89,7 +89,7 @@ nextflow_process { { assert process.out.zip[0][1] ==~ ".*/test_fastqc.zip" }, { assert path(process.out.html[0][1]).text.contains("") }, - { assert snapshot(process.out.versions).match("versions") } + { assert snapshot(process.out.versions).match("fastqc_versions_interleaved") } ) } } @@ -141,7 +141,7 @@ nextflow_process { { assert process.out.zip[0][1] ==~ ".*/test_fastqc.zip" }, { assert path(process.out.html[0][1]).text.contains("") }, - { assert snapshot(process.out.versions).match("versions") } + { assert snapshot(process.out.versions).match("fastqc_versions_bam") } ) } } @@ -179,7 +179,7 @@ nextflow_process { { assert path(process.out.html[0][1][2]).text.contains("") }, { assert path(process.out.html[0][1][3]).text.contains("") }, - { assert snapshot(process.out.versions).match("versions") } + { assert snapshot(process.out.versions).match("fastqc_versions_multiple") } ) } } @@ -205,7 +205,7 @@ nextflow_process { { assert process.out.zip[0][1] ==~ ".*/mysample_fastqc.zip" }, { assert path(process.out.html[0][1]).text.contains("") }, - { assert snapshot(process.out.versions).match("versions") } + { assert snapshot(process.out.versions).match("fastqc_versions_custom_prefix") } ) } } @@ -230,7 +230,7 @@ nextflow_process { { assert process.success }, { assert snapshot(process.out.html.collect { file(it[1]).getName() } + process.out.zip.collect { file(it[1]).getName() } + - process.out.versions ).match() } + process.out.versions ).match("fastqc_stub") } ) } } diff --git a/modules/nf-core/fastqc/tests/main.nf.test.snap b/modules/nf-core/fastqc/tests/main.nf.test.snap index 5d624bb8..86f7c311 100644 --- a/modules/nf-core/fastqc/tests/main.nf.test.snap +++ b/modules/nf-core/fastqc/tests/main.nf.test.snap @@ -1,5 +1,17 @@ { - "sarscov2 single-end [fastq] - stub": { + "fastqc_versions_interleaved": { + "content": [ + [ + "versions.yml:md5,e1cc25ca8af856014824abd842e93978" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-01-31T17:40:07.293713" + }, + "fastqc_stub": { "content": [ [ "test.html", @@ -7,14 +19,70 @@ "versions.yml:md5,e1cc25ca8af856014824abd842e93978" ] ], - "timestamp": "2024-01-17T18:40:57.254299" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-01-31T17:31:01.425198" + }, + "fastqc_versions_multiple": { + "content": [ + [ + "versions.yml:md5,e1cc25ca8af856014824abd842e93978" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-01-31T17:40:55.797907" + }, + "fastqc_versions_bam": { + "content": [ + [ + "versions.yml:md5,e1cc25ca8af856014824abd842e93978" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-01-31T17:40:26.795862" + }, + "fastqc_versions_single": { + "content": [ + [ + "versions.yml:md5,e1cc25ca8af856014824abd842e93978" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-01-31T17:39:27.043675" + }, + "fastqc_versions_paired": { + "content": [ + [ + "versions.yml:md5,e1cc25ca8af856014824abd842e93978" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-01-31T17:39:47.584191" }, - "versions": { + "fastqc_versions_custom_prefix": { "content": [ [ "versions.yml:md5,e1cc25ca8af856014824abd842e93978" ] ], - "timestamp": "2024-01-17T18:36:50.033627" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-01-31T17:41:14.576531" } } \ No newline at end of file diff --git a/modules/nf-core/multiqc/environment.yml b/modules/nf-core/multiqc/environment.yml index 7625b752..ca39fb67 100644 --- a/modules/nf-core/multiqc/environment.yml +++ b/modules/nf-core/multiqc/environment.yml @@ -4,4 +4,4 @@ channels: - bioconda - defaults dependencies: - - bioconda::multiqc=1.19 + - bioconda::multiqc=1.21 diff --git a/modules/nf-core/multiqc/main.nf b/modules/nf-core/multiqc/main.nf index 1b9f7c43..47ac352f 100644 --- a/modules/nf-core/multiqc/main.nf +++ b/modules/nf-core/multiqc/main.nf @@ -3,8 +3,8 @@ process MULTIQC { conda "${moduleDir}/environment.yml" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/multiqc:1.19--pyhdfd78af_0' : - 'biocontainers/multiqc:1.19--pyhdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/multiqc:1.21--pyhdfd78af_0' : + 'biocontainers/multiqc:1.21--pyhdfd78af_0' }" input: path multiqc_files, stageAs: "?/*" diff --git a/modules/nf-core/multiqc/tests/main.nf.test b/modules/nf-core/multiqc/tests/main.nf.test index d0438eda..f1c4242e 100644 --- a/modules/nf-core/multiqc/tests/main.nf.test +++ b/modules/nf-core/multiqc/tests/main.nf.test @@ -3,6 +3,7 @@ nextflow_process { name "Test Process MULTIQC" script "../main.nf" process "MULTIQC" + tag "modules" tag "modules_nfcore" tag "multiqc" @@ -12,7 +13,7 @@ nextflow_process { when { process { """ - input[0] = Channel.of([file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz_fastqc_zip'], checkIfExists: true)]) + input[0] = Channel.of(file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastqc/test_fastqc.zip', checkIfExists: true)) input[1] = [] input[2] = [] input[3] = [] @@ -25,7 +26,7 @@ nextflow_process { { assert process.success }, { assert process.out.report[0] ==~ ".*/multiqc_report.html" }, { assert process.out.data[0] ==~ ".*/multiqc_data" }, - { assert snapshot(process.out.versions).match("versions") } + { assert snapshot(process.out.versions).match("multiqc_versions_single") } ) } @@ -36,7 +37,7 @@ nextflow_process { when { process { """ - input[0] = Channel.of([file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz_fastqc_zip'], checkIfExists: true)]) + input[0] = Channel.of(file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastqc/test_fastqc.zip', checkIfExists: true)) input[1] = Channel.of(file("https://github.com/nf-core/tools/raw/dev/nf_core/pipeline-template/assets/multiqc_config.yml", checkIfExists: true)) input[2] = [] input[3] = [] @@ -49,7 +50,7 @@ nextflow_process { { assert process.success }, { assert process.out.report[0] ==~ ".*/multiqc_report.html" }, { assert process.out.data[0] ==~ ".*/multiqc_data" }, - { assert snapshot(process.out.versions).match("versions") } + { assert snapshot(process.out.versions).match("multiqc_versions_config") } ) } } @@ -61,7 +62,7 @@ nextflow_process { when { process { """ - input[0] = Channel.of([file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz_fastqc_zip'], checkIfExists: true)]) + input[0] = Channel.of(file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastqc/test_fastqc.zip', checkIfExists: true)) input[1] = [] input[2] = [] input[3] = [] @@ -75,7 +76,7 @@ nextflow_process { { assert snapshot(process.out.report.collect { file(it).getName() } + process.out.data.collect { file(it).getName() } + process.out.plots.collect { file(it).getName() } + - process.out.versions ).match() } + process.out.versions ).match("multiqc_stub") } ) } diff --git a/modules/nf-core/multiqc/tests/main.nf.test.snap b/modules/nf-core/multiqc/tests/main.nf.test.snap index d37e7304..bfebd802 100644 --- a/modules/nf-core/multiqc/tests/main.nf.test.snap +++ b/modules/nf-core/multiqc/tests/main.nf.test.snap @@ -1,21 +1,41 @@ { - "versions": { + "multiqc_versions_single": { "content": [ [ - "versions.yml:md5,14e9a2661241abd828f4f06a7b5c222d" + "versions.yml:md5,21f35ee29416b9b3073c28733efe4b7d" ] ], - "timestamp": "2024-01-09T23:02:49.911994" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-29T08:48:55.657331" }, - "sarscov2 single-end [fastqc] - stub": { + "multiqc_stub": { "content": [ [ "multiqc_report.html", "multiqc_data", "multiqc_plots", - "versions.yml:md5,14e9a2661241abd828f4f06a7b5c222d" + "versions.yml:md5,21f35ee29416b9b3073c28733efe4b7d" ] ], - "timestamp": "2024-01-09T23:03:14.524346" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-29T08:49:49.071937" + }, + "multiqc_versions_config": { + "content": [ + [ + "versions.yml:md5,21f35ee29416b9b3073c28733efe4b7d" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-29T08:49:25.457567" } } \ No newline at end of file diff --git a/nextflow.config b/nextflow.config index 35aff8fe..3e178ef7 100644 --- a/nextflow.config +++ b/nextflow.config @@ -6,6 +6,8 @@ ---------------------------------------------------------------------------------------- */ +nextflow.enable.strict = true + // Global default params, used in configs params { @@ -30,6 +32,7 @@ params { email_on_fail = null plaintext_email = false monochrome_logs = false + monochromeLogs = false // required so nf-validation nextflow.enabled.strict works nicely together hook_url = null help = false version = false @@ -51,12 +54,13 @@ params { // Schema validation default options validationFailUnrecognisedParams = false validationLenientMode = false - validationSchemaIgnoreParams = 'genomes,igenomes_base,fasta' + validationSchemaIgnoreParams = 'genomes,igenomes_base,fasta,monochromeLogs' validationShowHiddenParams = false validate_params = true // Databases - databases = null + databases = null + save_untarred_databases = false // FASTQ preprocessing skip_preprocessing_qc = false @@ -374,8 +378,9 @@ manifest { description = """Taxonomic classification and profiling of shotgun short- and long-read metagenomic data""" mainScript = 'main.nf' nextflowVersion = '!>=23.04.0' - version = '1.1.5' + version = '1.1.6' doi = '10.1101/2023.10.20.563221' + } // Load modules.config for DSL2 module specific options diff --git a/nextflow_schema.json b/nextflow_schema.json index 0f921833..1ce1ee54 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -16,6 +16,7 @@ "type": "string", "format": "file-path", "exists": true, + "schema": "assets/schema_input.json", "mimetype": "text/csv", "pattern": "^\\S+\\.csv$", "description": "Path to comma-separated file containing information about the samples and libraries/runs.", @@ -26,10 +27,19 @@ "type": "string", "mimetype": "text/csv", "format": "file-path", + "exists": true, + "schema": "assets/schema_database.json", + "pattern": "^\\S+\\.csv$", "fa_icon": "fas fa-database", "description": "Path to comma-separated file containing information about databases and profiling parameters for each taxonomic profiler", "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/taxprofiler/dev/usage#full-database-sheet).\n\nProfilers will only be executed if a corresponding database are supplied. \n\nWe recommend storing this database sheet somewhere centrally and accessible by others members of your lab/institutions, as this file will likely be regularly reused." }, + "save_untarred_databases": { + "type": "boolean", + "fa_icon": "fas fa-database", + "description": "Specify to save decompressed user-supplied TAR archives of databases", + "help_text": "If input databases are supplied as gzipped TAR archives, in some cases you may want to move and re-use these for future runs. Specifying this parameter will save these to `--outdir results/` under a directory called `untar`." + }, "outdir": { "type": "string", "format": "directory-path", diff --git a/pyproject.toml b/pyproject.toml index 7d08e1c8..56110621 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -3,11 +3,13 @@ [tool.ruff] line-length = 120 target-version = "py38" -select = ["I", "E1", "E4", "E7", "E9", "F", "UP", "N"] cache-dir = "~/.cache/ruff" -[tool.ruff.isort] +[tool.ruff.lint] +select = ["I", "E1", "E4", "E7", "E9", "F", "UP", "N"] + +[tool.ruff.lint.isort] known-first-party = ["nf_core"] -[tool.ruff.per-file-ignores] +[tool.ruff.lint.per-file-ignores] "__init__.py" = ["E402", "F401"] diff --git a/subworkflows/local/db_check.nf b/subworkflows/local/db_check.nf deleted file mode 100644 index b4ba3cf6..00000000 --- a/subworkflows/local/db_check.nf +++ /dev/null @@ -1,97 +0,0 @@ -// -// Check input samplesheet and get read channels -// - -include { UNTAR } from '../../modules/nf-core/untar/main' - -workflow DB_CHECK { - take: - dbsheet // file: /path/to/dbsheet.csv - - main: - ch_versions = Channel.empty() - ch_dbs_for_untar = Channel.empty() - ch_final_dbs = Channel.empty() - - /* - Validation - */ - - // Special check to header exists - Channel.fromPath(dbsheet) - .splitCsv ( header:false, sep:',' ) - .first() - .map { - if ( it[0] != 'tool' && it[1] != 'db_name' && it[2] != 'db_params' && it[2] != 'db_path' ) error ("[nf-core/taxprofiler] ERROR: database sheet is missing header. Please see nf-core/taxprofiler documentation for database sheet specifications.") - } - - // Normal checks for within-row validity, so can be moved to separate functions - parsed_samplesheet = Channel.fromPath(dbsheet) - .splitCsv ( header:true, sep:',' ) - .map { row -> - validate_db_rows(row) - return [ row.subMap(['tool', 'db_name', 'db_params']), file(row.db_path) ] - } - - // Special check to check _between_ rows, for which we must group rows together - // Note: this will run in parallel to within-row validity, but we can assume this will run faster thus will fail first - Channel.fromPath(dbsheet) - .splitCsv ( header:true, sep:',' ) - .map {[it.tool, it.db_name] } - .groupTuple() - .map { - tool, db_name -> - def unique_names = db_name.unique(false) - if ( unique_names.size() < db_name.size() ) error("[nf-core/taxprofiler] ERROR: Each database for a tool must have a unique name, duplicated detected. Tool: ${tool}, Database name: ${unique_names}") - } - - /* - Preparation - */ - - // Decompress - ch_dbs_for_untar = parsed_samplesheet - .branch { db_meta, db -> - untar: db.name.endsWith(".tar.gz") - skip: true - } - - // Filter the channel to untar only those databases for tools that are selected to be run by the user. - ch_input_untar = ch_dbs_for_untar.untar - .filter { db_meta, db -> params["run_${db_meta.tool}"] } - - UNTAR (ch_input_untar) - ch_versions = ch_versions.mix(UNTAR.out.versions.first()) - ch_final_dbs = ch_dbs_for_untar.skip.mix( UNTAR.out.untar ) - - emit: - dbs = ch_final_dbs // channel: [ val(meta), [ db ] ] - versions = ch_versions // channel: [ versions.yml ] -} - -def validate_db_rows(LinkedHashMap row) { - - // check minimum number of columns - if (row.size() < 4) error("[nf-core/taxprofiler] ERROR: Invalid database input sheet - malformed row (e.g. missing column). See documentation for more information. Error in: ${row}") - - // all columns there - def expected_headers = ['tool', 'db_name', 'db_params', 'db_path'] - if ( !row.keySet().containsAll(expected_headers) ) error("[nf-core/taxprofiler] ERROR: Invalid database input sheet - malformed column names. Please check input TSV. Column names should be: ${expected_headers.join(", ")}") - - // valid tools specified - def expected_tools = [ "bracken", "centrifuge", "diamond", "ganon", "kaiju", "kmcp", "kraken2", "krakenuniq", "malt", "metaphlan", "motus" ] - - if ( !expected_tools.contains(row.tool) ) error("[nf-core/taxprofiler] ERROR: Invalid tool name. Please see documentation for all supported profilers. Error in: ${row}") - - // detect quotes in params - if ( row.db_params.contains('"') ) error("[nf-core/taxprofiler] ERROR: Invalid database db_params entry. No quotes allowed. Error in: ${row}") - if ( row.db_params.contains("'") ) error("[nf-core/taxprofiler] ERROR: Invalid database db_params entry. No quotes allowed. Error in: ${row}") - - // check if any form of bracken params, that it must have `;` - if ( row.tool == 'bracken' && row.db_params && !row.db_params.contains(";") ) error("[nf-core/taxprofiler] ERROR: Invalid database db_params entry. Bracken requires a semi-colon if passing parameter. Error in: ${row}") - if ( row.tool == 'kmcp' && row.db_params && row.db_params.matches(".*;\$")) error ("[nf-core/taxprofiler] ERROR: Invalid database db_params entry. KMCP only requires a semi-colon if passing arguments to KMCP profile, in cases of which the arguments should go after the semi-colon. Error in: ${row}") - - // ensure that the database directory exists - if (!file(row.db_path, type: 'dir').exists()) error("ERROR: Please check input samplesheet -> database path could not be found!\n${row.db_path}") - -} diff --git a/subworkflows/local/input_check.nf b/subworkflows/local/input_check.nf deleted file mode 100644 index 1274c398..00000000 --- a/subworkflows/local/input_check.nf +++ /dev/null @@ -1,103 +0,0 @@ -// -// Check input samplesheet and get read channels -// - -include { SAMPLESHEET_CHECK } from '../../modules/local/samplesheet_check' - -workflow INPUT_CHECK { - take: - samplesheet // file: /path/to/samplesheet.csv - - main: - - // Table to list, group per sample, detect if sample has multi-run, - // then spread back to per-run rows but with multi-run info added to meta - ch_split_samplesheet = SAMPLESHEET_CHECK ( samplesheet ) - .csv - .splitCsv ( header:true, sep:',' ) - .map{ - row -> - [ [ row.sample.toString() ], row ] - } - .groupTuple() - .map { - sample, rows -> - def is_multirun = rows.size() > 1 - [ rows, is_multirun ] - } - .transpose(by: 0) - .map { - row, is_multirun -> - row['is_multirun'] = is_multirun - return row - } - - // Split for context-dependent channel generation - ch_parsed_samplesheet = ch_split_samplesheet - .branch { row -> - fasta: row.fasta != '' - nanopore: row.instrument_platform == 'OXFORD_NANOPORE' - fastq: true - } - - // Channel generation - ch_fastq = ch_parsed_samplesheet.fastq - .map { create_fastq_channel(it) } - - ch_nanopore = ch_parsed_samplesheet.nanopore - .map { create_fastq_channel(it) } - - ch_fasta = ch_parsed_samplesheet.fasta - .map { create_fasta_channel(it) } - - emit: - fastq = ch_fastq ?: [] // channel: [ val(meta), [ reads ] ] - nanopore = ch_nanopore ?: [] // channel: [ val(meta), [ reads ] ] - fasta = ch_fasta ?: [] // channel: [ val(meta), fasta ] - versions = SAMPLESHEET_CHECK.out.versions // channel: [ versions.yml ] -} - -// Function to get list of [ meta, [ fastq_1, fastq_2 ] ] -def create_fastq_channel(LinkedHashMap row) { - // create meta map - def meta = row.subMap(['sample', 'run_accession', 'instrument_platform', 'is_multirun']) - meta.id = meta.sample - meta.single_end = row.single_end.toBoolean() - meta.is_fasta = false - - // add path(s) of the fastq file(s) to the meta map - if (!file(row.fastq_1).exists()) { - error("ERROR: Please check input samplesheet -> Read 1 FastQ file does not exist!\n${row.fastq_1}") - } - - if (meta.single_end) { - return [ meta, [ file(row.fastq_1) ] ] - } else { - if (meta.instrument_platform == 'OXFORD_NANOPORE') { - if (row.fastq_2 != '') { - error("ERROR: Please check input samplesheet -> For Oxford Nanopore reads Read 2 FastQ should be empty!\n${row.fastq_2}") - } - return [ meta, [ file(row.fastq_1) ] ] - } else { - if (!file(row.fastq_2).exists()) { - error("ERROR: Please check input samplesheet -> Read 2 FastQ file does not exist!\n${row.fastq_2}") - } - return [ meta, [ file(row.fastq_1), file(row.fastq_2) ] ] - } - } -} - -// Function to get list of [ meta, fasta ] -def create_fasta_channel(LinkedHashMap row) { - - // don't include multi-run information as we don't do FASTA run merging - def meta = row.subMap(['sample', 'run_accession', 'instrument_platform' ]) - meta.id = meta.sample - meta.single_end = true - meta.is_fasta = true - - if (!file(row.fasta).exists()) { - error("ERROR: Please check input samplesheet -> FastA file does not exist!\n${row.fasta}") - } - return [ meta, [ file(row.fasta) ] ] -} diff --git a/subworkflows/local/standardisation_profiles.nf b/subworkflows/local/standardisation_profiles.nf index 4592e9de..95cd9d3f 100644 --- a/subworkflows/local/standardisation_profiles.nf +++ b/subworkflows/local/standardisation_profiles.nf @@ -15,25 +15,43 @@ include { GANON_TABLE // Custom Functions /** -* Combine profiles with their original database, then separate into two channels. +* Group all profiles per reference database. * -* The channel elements are assumed to be tuples one of [ meta, profile ], and the -* database to be of [db_key, meta, database_file]. +* @param ch_profiles A channel containing pairs of a meta map and the report of +* a given profiler, where meta must contain a key `db_name`. +* @return A channel with one element per reference database. Each element is a +* pair of a meta map with an `id` key and all corresponding profiles. +*/ +def groupProfiles(ch_profiles, groupTupleOptions = [:]) { + return ch_profiles + .map { meta, profile -> [meta.db_name, profile] } + .groupTuple(groupTupleOptions) + .map { db_name, profiles -> [[id: db_name], profiles] } +} + +/** +* Combine profiles with their corresponding reference database, then separate into two channels. * -* @param ch_profile A channel containing a meta and the profilign report of a given profiler -* @param ch_database A channel containing a key, the database meta, and the database file/folders itself -* @return A multiMap'ed output channel with two sub channels, one with the profile and the other with the db +* The combined results are returned on multiple channels, where the element +* position for the profiles in one channel is the same as the position of the +* corresponding database element in the other channel. +* +* @param ch_profiles A channel containing pairs of a meta map with an `id` key +* for a reference database, and all the corresponding profiling reports. +* @param ch_database A channel containing pairs of a database meta map and the +* database itself. +* @return A multiMap'ed output channel with two sub channels, one with the +* profiles (`profile`) and the other with the corresponding database (`db`). */ -def combineProfilesWithDatabase(ch_profile, ch_database) { - -return ch_profile - .map { meta, profile -> [meta.db_name, meta, profile] } - .combine(ch_database, by: 0) - .multiMap { - key, meta, profile, db_meta, db -> - profile: [meta, profile] - db: db - } +def combineProfilesWithDatabase(ch_profiles, ch_database) { + return ch_profiles + .map { meta, profile -> [meta.id, meta, profile] } + .combine(ch_database.map { db_meta, db -> [db_meta.db_name, db] }, by: 0) + .multiMap { + key, meta, profile, db -> + profile: [meta, profile] + db: db + } } workflow STANDARDISATION_PROFILES { @@ -117,12 +135,7 @@ workflow STANDARDISATION_PROFILES { // Bracken - ch_profiles_for_bracken = ch_input_profiles.bracken - .map { [it[0]['db_name'], it[1]] } - .groupTuple() - .map { - [[id:it[0]], it[1]] - } + ch_profiles_for_bracken = groupProfiles(ch_input_profiles.bracken) BRACKEN_COMBINEBRACKENOUTPUTS ( ch_profiles_for_bracken ) @@ -131,13 +144,10 @@ workflow STANDARDISATION_PROFILES { // Collect and replace id for db_name for prefix // Have to sort by size to ensure first file actually has hits otherwise // the script fails - ch_profiles_for_centrifuge = ch_input_profiles.centrifuge - .map { [it[0]['db_name'], it[1]] } - .groupTuple(sort: {-it.size()} ) - .map { - [[id:it[0]], it[1]] - } - + ch_profiles_for_centrifuge = groupProfiles( + ch_input_profiles.centrifuge, + [sort: { -it.size() }] + ) KRAKENTOOLS_COMBINEKREPORTS_CENTRIFUGE ( ch_profiles_for_centrifuge ) ch_multiqc_files = ch_multiqc_files.mix( KRAKENTOOLS_COMBINEKREPORTS_CENTRIFUGE.out.txt ) @@ -146,12 +156,7 @@ workflow STANDARDISATION_PROFILES { // Kaiju // Collect and replace id for db_name for prefix - ch_profiles_for_kaiju = ch_input_classifications.kaiju - .map { [it[0]['db_name'], it[1]] } - .groupTuple() - .map { - [[id:it[0]], it[1]] - } + ch_profiles_for_kaiju = groupProfiles(ch_input_classifications.kaiju) ch_input_for_kaiju2tablecombine = combineProfilesWithDatabase(ch_profiles_for_kaiju, ch_input_databases.kaiju) @@ -164,16 +169,15 @@ workflow STANDARDISATION_PROFILES { // Collect and replace id for db_name for prefix // Have to sort by size to ensure first file actually has hits otherwise // the script fails - ch_profiles_for_kraken2 = ch_input_profiles.kraken2 - .map { - meta, profiles -> - def new_meta = [:] - new_meta.tool = meta.tool == 'kraken2-bracken' ? 'kraken2' : meta.tool // replace to get the right output-format description - new_meta.id = meta.tool // append so to disambiguate when we have same databases for kraken2 step of bracken, with normal bracken - new_meta.db_name = meta.tool == 'kraken2-bracken' ? "${meta.db_name}-bracken" : "${meta.db_name}" // append so to disambiguate when we have same databases for kraken2 step of bracken, with normal bracken - [ new_meta, profiles ] - } - .groupTuple(sort: {-it.size()}) + ch_profiles_for_kraken2 = groupProfiles( + ch_input_profiles.kraken2 + .map { meta, profile -> + // Replace database name, to get the right output description. + def db_name = meta.tool == 'kraken2-bracken' ? "${meta.db_name}-bracken" : "${meta.db_name}" + return [meta + [db_name: db_name], profile] + }, + [sort: { -it.size() }] + ) KRAKENTOOLS_COMBINEKREPORTS_KRAKEN ( ch_profiles_for_kraken2 ) ch_multiqc_files = ch_multiqc_files.mix( KRAKENTOOLS_COMBINEKREPORTS_KRAKEN.out.txt ) @@ -181,12 +185,7 @@ workflow STANDARDISATION_PROFILES { // MetaPhlAn - ch_profiles_for_metaphlan = ch_input_profiles.metaphlan - .map { [it[0]['db_name'], it[1]] } - .groupTuple() - .map { - [[id:it[0]], it[1]] - } + ch_profiles_for_metaphlan = groupProfiles(ch_input_profiles.metaphlan) METAPHLAN_MERGEMETAPHLANTABLES ( ch_profiles_for_metaphlan ) ch_multiqc_files = ch_multiqc_files.mix( METAPHLAN_MERGEMETAPHLANTABLES.out.txt ) @@ -198,12 +197,7 @@ workflow STANDARDISATION_PROFILES { // Therefore removing db info here, and publish merged at root mOTUs results // directory - ch_profiles_for_motus = ch_input_profiles.motus - .map { [it[0]['db_name'], it[1]] } - .groupTuple() - .map { - [[id:it[0]], it[1]] - } + ch_profiles_for_motus = groupProfiles(ch_input_profiles.motus) ch_input_for_motusmerge = combineProfilesWithDatabase(ch_profiles_for_motus, ch_input_databases.motus) @@ -212,12 +206,7 @@ workflow STANDARDISATION_PROFILES { // Ganon - ch_profiles_for_ganon = ch_input_profiles.ganon - .map { [it[0]['db_name'], it[1]] } - .groupTuple() - .map { - [[id:it[0]], it[1]] - } + ch_profiles_for_ganon = groupProfiles(ch_input_profiles.ganon) GANON_TABLE ( ch_profiles_for_ganon ) ch_multiqc_files = ch_multiqc_files.mix( GANON_TABLE.out.txt ) diff --git a/subworkflows/local/utils_nfcore_taxprofiler_pipeline/main.nf b/subworkflows/local/utils_nfcore_taxprofiler_pipeline/main.nf new file mode 100644 index 00000000..822672e2 --- /dev/null +++ b/subworkflows/local/utils_nfcore_taxprofiler_pipeline/main.nf @@ -0,0 +1,368 @@ +// +// Subworkflow with functionality specific to the nf-core/pipeline pipeline +// + +/* +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + IMPORT FUNCTIONS / MODULES / SUBWORKFLOWS +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +*/ + +include { UTILS_NFVALIDATION_PLUGIN } from '../../nf-core/utils_nfvalidation_plugin' +include { paramsSummaryMap } from 'plugin/nf-validation' +include { fromSamplesheet } from 'plugin/nf-validation' +include { UTILS_NEXTFLOW_PIPELINE } from '../../nf-core/utils_nextflow_pipeline' +include { completionEmail } from '../../nf-core/utils_nfcore_pipeline' +include { completionSummary } from '../../nf-core/utils_nfcore_pipeline' +include { dashedLine } from '../../nf-core/utils_nfcore_pipeline' +include { nfCoreLogo } from '../../nf-core/utils_nfcore_pipeline' +include { imNotification } from '../../nf-core/utils_nfcore_pipeline' +include { UTILS_NFCORE_PIPELINE } from '../../nf-core/utils_nfcore_pipeline' +include { workflowCitation } from '../../nf-core/utils_nfcore_pipeline' + +/* +======================================================================================== + SUBWORKFLOW TO INITIALISE PIPELINE +======================================================================================== +*/ + +workflow PIPELINE_INITIALISATION { + + take: + version // boolean: Display version and exit + help // boolean: Display help text + validate_params // boolean: Boolean whether to validate parameters against the schema at runtime + monochrome_logs // boolean: Do not use coloured log outputs + nextflow_cli_args // array: List of positional nextflow CLI args + outdir // string: The output directory where the results will be saved + input // string: Path to input samplesheet + databases // string: Path to databases + + main: + + ch_versions = Channel.empty() + + // + // Print version and exit if required and dump pipeline parameters to JSON file + // + UTILS_NEXTFLOW_PIPELINE ( + version, + true, + outdir, + workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1 + ) + + // + // Validate parameters and generate parameter summary to stdout + // + pre_help_text = nfCoreLogo(monochrome_logs) + post_help_text = '\n' + workflowCitation() + '\n' + dashedLine(monochrome_logs) + def String workflow_command = "nextflow run ${workflow.manifest.name} -profile --input samplesheet.csv --databases databases.csv --outdir --run_kraken2" + UTILS_NFVALIDATION_PLUGIN ( + help, + workflow_command, + pre_help_text, + post_help_text, + validate_params, + "nextflow_schema.json" + ) + + // + // Check config provided to the pipeline + // + UTILS_NFCORE_PIPELINE ( + nextflow_cli_args + ) + // + // Custom validation for pipeline parameters + // + validateInputParameters() + + // + // Create channel from input file provided through params.input + // + Channel + .fromSamplesheet("input") + .set { ch_samplesheet } + + emit: + samplesheet = ch_samplesheet + versions = ch_versions + +// Create channel from databases file provided through params.databases + Channel + .fromSamplesheet("databases") + .set {ch_databases} + + emit: + databases = ch_databases + versions = ch_versions +} + +/* +======================================================================================== + SUBWORKFLOW FOR PIPELINE COMPLETION +======================================================================================== +*/ + +workflow PIPELINE_COMPLETION { + + take: + email // string: email address + email_on_fail // string: email address sent on pipeline failure + plaintext_email // boolean: Send plain-text email instead of HTML + outdir // path: Path to output directory where results will be published + monochrome_logs // boolean: Disable ANSI colour codes in log output + hook_url // string: hook URL for notifications + multiqc_report // string: Path to MultiQC report + + main: + + summary_params = paramsSummaryMap(workflow, parameters_schema: "nextflow_schema.json") + + // + // Completion email and summary + // + workflow.onComplete { + if (email || email_on_fail) { + completionEmail(summary_params, email, email_on_fail, plaintext_email, outdir, monochrome_logs, multiqc_report.toList()) + } + + completionSummary(monochrome_logs) + + if (hook_url) { + imNotification(summary_params, hook_url) + } + } +} + +/* +======================================================================================== + FUNCTIONS +======================================================================================== +*/ +// +// Check and validate pipeline parameters +// +def validateInputParameters() { + genomeExistsError() +}// +// Validate channels from input samplesheet +// +def validateInputSamplesheet(input) { + def (metas, fastqs, fasta) = input[1..3] + + // Check that multiple runs of the same sample are of the same datatype i.e. single-end / paired-end + def endedness_ok = metas.collect{ it.single_end }.unique().size == 1 + if (!endedness_ok) { + error("Please check input samplesheet -> Multiple runs of a sample must be of the same datatype i.e. single-end or paired-end: ${metas[0].id}") + } + + return [ metas[0], fastqs, fasta ] +} +// +// Get attribute from genome config file e.g. fasta +// +def getGenomeAttribute(attribute) { + if (params.genomes && params.genome && params.genomes.containsKey(params.genome)) { + if (params.genomes[ params.genome ].containsKey(attribute)) { + return params.genomes[ params.genome ][ attribute ] + } + } + return null +} + +// +// Exit pipeline if incorrect --genome key provided +// +def genomeExistsError() { + if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) { + def error_string = "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" + + " Genome '${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" + + "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~" + error(error_string) + } +}// +// Generate methods description for MultiQC +// +def toolCitationText() { + def text_seq_qc = [ + "Sequencing quality control was carried out with:", + params.preprocessing_qc_tool == "falco" ? "Falco (de Sena Brandine and Smith 2021)." : "FastQC (Andrews 2010)." + ].join(' ').trim() + + def text_shortread_qc = [ + "Short read preprocessing was performed with:", + params.shortread_qc_tool == "adapterremoval" ? "AdapterRemoval (Schubert et al. 2016)." : "", + params.shortread_qc_tool == "fastp" ? "fastp (Chen et al. 2018)." : "", + ].join(' ').trim() + + def text_longread_qc = [ + "Long read preprocessing was performed with:", + !params.longread_qc_skipadaptertrim ? "Porechop (Wick et al. 2017)," : "", + !params.longread_qc_skipqualityfilter ? "Filtlong (Wick 2021)," : "", + "." + ].join(' ').trim() + + def text_shortreadcomplexity = [ + "Low-complexity sequence filtering was carried out with:", + params.shortread_complexityfilter_tool == "bbduk" ? "BBDuk (Bushnell 2022)." : "", + params.shortread_complexityfilter_tool == "prinseqplusplus" ? "PRINSEQ++ (Cantu et al. 2019)." : "", + params.shortread_complexityfilter_tool == "fastp" ? "fastp (Chen et al. 2018)." : "", + ].join(' ').trim() + + def text_shortreadhostremoval = [ + "Host read removal was performed for short reads with Bowtie2 (Langmead and Salzberg 2012) and SAMtools (Danecek et al. 2021)." + ].join(' ').trim() + + def text_longreadhostremoval = [ + "Host read removal was performed for long reads with minimap2 (Li et al. 2018) and SAMtools (Danecek et al. 2021)." + ].join(' ').trim() + + + def text_classification = [ + "Taxonomic classification or profiling was carried out with:", + params.run_bracken ? "Bracken (Lu et al. 2017)," : "", + params.run_kraken2 ? "Kraken2 (Wood et al. 2019)," : "", + params.run_krakenuniq ? "KrakenUniq (Breitwieser et al. 2018)," : "", + params.run_metaphlan ? "MetaPhlAn (Blanco-Míguez et al. 2023)," : "", + params.run_malt ? "MALT (Vågene et al. 2018) and MEGAN6 CE (Huson et al. 2016)," : "", + params.run_diamond ? "DIAMOND (Buchfink et al. 2015)," : "", + params.run_centrifuge ? "Centrifuge (Kim et al. 2016)," : "", + params.run_kaiju ? "Kaiju (Menzel et al. 2016)," : "", + params.run_motus ? "mOTUs (Ruscheweyh et al. 2022)," : "", + params.run_ganon ? "ganon (Piro et al. 2020)" : "", + params.run_kmcp ? "KMCP (Shen et al. 2023)" : "", + "." + ].join(' ').trim() + + def text_visualisation = [ + "Visualisation of results, where supported, was performed with Krona (Ondov et al. 2011)." + ].join(' ').trim() + + def text_postprocessing = [ + "Standardisation of taxonomic profiles was carried out with TAXPASTA (Beber et al. 2023).", + ].join(' ').trim() + + def citation_text = [ + "Tools used in the workflow included:", + text_seq_qc, + params.perform_shortread_qc ? text_shortread_qc : "", + params.perform_longread_qc ? text_longread_qc : "", + params.perform_shortread_complexityfilter ? text_shortreadcomplexity : "", + params.perform_shortread_hostremoval ? text_shortreadhostremoval : "", + params.perform_longread_hostremoval ? text_longreadhostremoval : "", + text_classification, + params.run_krona ? text_visualisation : "", + params.run_profile_standardisation ? text_postprocessing : "", + "Pipeline results statistics were summarised with MultiQC (Ewels et al. 2016)." + ].join(' ').trim().replaceAll("[,|.] +\\.", ".") + + return citation_text +} + +def toolBibliographyText() { + def text_seq_qc = [ + params.preprocessing_qc_tool == "falco" ? "
  • de Sena Brandine, G., & Smith, A. D. (2021). Falco: high-speed FastQC emulation for quality control of sequencing data. F1000Research, 8(1874), 1874. 10.12688/f1000research.21142.2
    • " : "", + params.preprocessing_qc_tool == "fastqc" ? "
  • Andrews S. (2010) FastQC: A Quality Control Tool for High Throughput Sequence Data, URL: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/
    • " : "", + ].join(' ').trim() + + + def text_shortread_qc = [ + params.shortread_qc_tool == "adapterremoval" ? "
  • Schubert, M., Lindgreen, S., & Orlando, L. (2016). AdapterRemoval v2: rapid adapter trimming, identification, and read merging. BMC Research Notes, 9, 88. 10.1186/s13104-016-1900-2
    • " : "", + ].join(' ').trim() + + def text_longread_qc = [ + !params.longread_qc_skipadaptertrim ? "
  • Wick, R. R., Judd, L. M., Gorrie, C. L., & Holt, K. E. (2017). Completing bacterial genome assemblies with multiplex MinION sequencing. Microbial Genomics, 3(10), e000132. 10.1099/mgen.0.000132
    • " : "", + !params.longread_qc_skipqualityfilter ? "
  • Wick R. (2021) Filtlong, URL: https://github.com/rrwick/Filtlong
    • " : "" + ].join(' ').trim() + + def text_shortreadcomplexity = [ + params.shortread_complexityfilter_tool == "bbduk" ? "
  • Bushnell B. (2022) BBMap, URL: http://sourceforge.net/projects/bbmap/
    • " : "", + params.shortread_complexityfilter_tool == "prinseqplusplus" ? "
  • Cantu, V. A., Sadural, J., & Edwards, R. (2019). PRINSEQ++, a multi-threaded tool for fast and efficient quality control and preprocessing of sequencing datasets (e27553v1). PeerJ Preprints. 10.7287/peerj.preprints.27553v1
    • " : "", + ].join(' ').trim() + + def text_shortreadhostremoval = [ + "
  • Langmead, B., & Salzberg, S. L. (2012). Fast gapped-read alignment with Bowtie 2. Nature Methods, 9(4), 357–359. 10.1038/nmeth.1923
    • ", + ].join(' ').trim() + + def text_longreadhostremoval = [ + "
  • Li, H. (2018). Minimap2: pairwise alignment for nucleotide sequences. Bioinformatics , 34(18), 3094–3100. 10.1093/bioinformatics/bty191
    • ", + ].join(' ').trim() + + + def text_classification = [ + params.run_bracken ? "
  • Lu, J., Breitwieser, F. P., Thielen, P., & Salzberg, S. L. (2017). Bracken: estimating species abundance in metagenomics data. PeerJ. Computer Science, 3(e104), e104. 10.7717/peerj-cs.104
    • " : "", + params.run_kraken2 ? "
  • Wood, D. E., Lu, J., & Langmead, B. (2019). Improved metagenomic analysis with Kraken 2. Genome Biology, 20(1), 257. 10.1186/s13059-019-1891-0
    • " : "", + params.run_krakenuniq ? "
  • Breitwieser, F. P., Baker, D. N., & Salzberg, S. L. (2018). KrakenUniq: confident and fast metagenomics classification using unique k-mer counts. Genome Biology, 19(1), 198. 10.1186/s13059-018-1568-0
    • " : "", + params.run_metaphlan ? "
  • Blanco-Míguez, A., Beghini, F., Cumbo, F., McIver, L. J., Thompson, K. N., Zolfo, M., Manghi, P., Dubois, L., Huang, K. D., Thomas, A. M., Nickols, W. A., Piccinno, G., Piperni, E., Punčochář, M., Valles-Colomer, M., Tett, A., Giordano, F., Davies, R., Wolf, J., … Segata, N. (2023). Extending and improving metagenomic taxonomic profiling with uncharacterized species using MetaPhlAn 4. Nature Biotechnology, 1–12. 10.1038/s41587-023-01688-w
    • " : "", + params.run_malt ? "
  • Vågene, Å. J., Herbig, A., Campana, M. G., Robles García, N. M., Warinner, C., Sabin, S., Spyrou, M. A., Andrades Valtueña, A., Huson, D., Tuross, N., Bos, K. I., & Krause, J. (2018). Salmonella enterica genomes from victims of a major sixteenth-century epidemic in Mexico. Nature Ecology & Evolution, 2(3), 520–528. 10.1038/s41559-017-0446-6
    • " : "", + params.run_malt ? "
  • Huson, D. H., Beier, S., Flade, I., Górska, A., El-Hadidi, M., Mitra, S., Ruscheweyh, H.-J., & Tappu, R. (2016). MEGAN Community Edition - Interactive Exploration and Analysis of Large-Scale Microbiome Sequencing Data. PLoS Computational Biology, 12(6), e1004957. 10.1371/journal.pcbi.1004957
    • " : "", + params.run_diamond ? "
  • Buchfink, B., Xie, C., & Huson, D. H. (2015). Fast and sensitive protein alignment using DIAMOND. Nature Methods, 12(1), 59–60. 10.1038/nmeth.3176
    • " : "", + params.run_centrifuge ? "
  • Kim, D., Song, L., Breitwieser, F. P., & Salzberg, S. L. (2016). Centrifuge: rapid and sensitive classification of metagenomic sequences. Genome Research, 26(12), 1721–1729. 10.1101/gr.210641.116
    • " : "", + params.run_kaiju ? "
  • Menzel, P., Ng, K. L., & Krogh, A. (2016). Fast and sensitive taxonomic classification for metagenomics with Kaiju. Nature Communications, 7, 11257. 10.1038/ncomms11257
    • " : "", + params.run_motus ? "
  • Ruscheweyh, H.-J., Milanese, A., Paoli, L., Karcher, N., Clayssen, Q., Keller, M. I., Wirbel, J., Bork, P., Mende, D. R., Zeller, G., & Sunagawa, S. (2022). Cultivation-independent genomes greatly expand taxonomic-profiling capabilities of mOTUs across various environments. Microbiome, 10(1), 212. 10.1186/s40168-022-01410-z
    • " : "", + params.run_ganon ? "
  • Piro, V. C., Dadi, T. H., Seiler, E., Reinert, K., & Renard, B. Y. (2020). Ganon: Precise metagenomics classification against large and up-to-date sets of reference sequences. Bioinformatics (Oxford, England), 36(Suppl_1), i12–i20. 10.1093/bioinformatics/btaa458
    • " : "", + params.run_kmcp ? "
  • Shen, W., Xiang, H., Huang, T., Tang, H., Peng, M., Cai, D., Hu, P., & Ren, H. (2023). KMCP: accurate metagenomic profiling of both prokaryotic and viral populations by pseudo-mapping. Bioinformatics (Oxford, England), 39(1). 10.1093/bioinformatics/btac845
    • " : "", + ].join(' ').trim() + + def text_visualisation = [ + "
  • Ondov, B. D., Bergman, N. H., & Phillippy, A. M. (2011). Interactive metagenomic visualization in a Web browser. BMC Bioinformatics, 12(1), 385. 10.1186/1471-2105-12-385
    • " + ].join(' ').trim() + + def text_postprocessing = [ + "
  • Beber, M. E., Borry, M., Stamouli, S., & Fellows Yates, J. A. (2023). TAXPASTA: TAXonomic Profile Aggregation and STAndardisation. Journal of Open Source Software, 8(87), 5627. 10.21105/joss.05627
    • ", + ].join(' ').trim() + + def text_extras = [ + // fastp shortread qc / complexity filtering + ( params.perform_shortread_qc && params.shortread_qc_tool == "fastp" ) || ( params.perform_shortread_complexityfilter && params.shortread_complexityfilter_tool == "fastp" ) ? "
  • Chen, S., Zhou, Y., Chen, Y., & Gu, J. (2018). fastp: an ultra-fast all-in-one FASTQ preprocessor. Bioinformatics , 34(17), i884–i890. 10.1093/bioinformatics/bty560
    • " : "", + // samtools long / short hostremoval + params.perform_shortread_hostremoval || params.perform_longread_hostremoval ? "
  • Danecek, P., Bonfield, J. K., Liddle, J., Marshall, J., Ohan, V., Pollard, M. O., Whitwham, A., Keane, T., McCarthy, S. A., Davies, R. M., & Li, H. (2021). Twelve years of SAMtools and BCFtools. GigaScience, 10(2). 10.1093/gigascience/giab008
    • " : "", + ].join(' ').trim() + + def reference_text = [ + text_seq_qc, + params.perform_shortread_qc ? text_shortread_qc : "", + params.perform_longread_qc ? text_longread_qc : "", + params.perform_shortread_complexityfilter ? text_shortreadcomplexity : "", + params.perform_shortread_hostremoval ? text_shortreadhostremoval : "", + params.perform_longread_hostremoval ? text_longreadhostremoval : "", + text_extras, + text_classification, + params.run_krona ? text_visualisation : "", + params.run_profile_standardisation ? text_postprocessing : "", + "
  • Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics , 32(19), 3047–3048. 10.1093/bioinformatics/btw354.
    • " + ].join(' ').trim().replaceAll("[,|.] +\\.", ".") + + return reference_text +} + +def methodsDescriptionText( mqc_methods_yaml ) { + + def meta = [:] + + meta.workflow = workflow.toMap() + meta["manifest_map"] = workflow.manifest.toMap() + + // Pipeline DOI + meta["doi_text"] = meta.manifest_map.doi ? "(doi: Stamouli et al. 2023)" : "" + meta["nodoi_text"] = meta.manifest_map.doi ? "": "
  • If available, make sure to update the text to include the Zenodo DOI of version of the pipeline used.
    • " + + meta["tool_citations"] = "" + meta["tool_bibliography"] = "" + + // TODO nf-core: Only uncomment below if logic in toolCitationText/toolBibliographyText has been filled! + // meta["tool_citations"] = toolCitationText().replaceAll(", \\.", ".").replaceAll("\\. \\.", ".").replaceAll(", \\.", ".") + // meta["tool_bibliography"] = toolBibliographyText() + + + def methods_text = mqc_methods_yaml.text + + def engine = new groovy.text.SimpleTemplateEngine() + def description_html = engine.createTemplate(methods_text).make(meta) + + return description_html.toString() +} diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/main.nf b/subworkflows/nf-core/utils_nextflow_pipeline/main.nf new file mode 100644 index 00000000..ac31f28f --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/main.nf @@ -0,0 +1,126 @@ +// +// Subworkflow with functionality that may be useful for any Nextflow pipeline +// + +import org.yaml.snakeyaml.Yaml +import groovy.json.JsonOutput +import nextflow.extension.FilesEx + +/* +======================================================================================== + SUBWORKFLOW DEFINITION +======================================================================================== +*/ + +workflow UTILS_NEXTFLOW_PIPELINE { + + take: + print_version // boolean: print version + dump_parameters // boolean: dump parameters + outdir // path: base directory used to publish pipeline results + check_conda_channels // boolean: check conda channels + + main: + + // + // Print workflow version and exit on --version + // + if (print_version) { + log.info "${workflow.manifest.name} ${getWorkflowVersion()}" + System.exit(0) + } + + // + // Dump pipeline parameters to a JSON file + // + if (dump_parameters && outdir) { + dumpParametersToJSON(outdir) + } + + // + // When running with Conda, warn if channels have not been set-up appropriately + // + if (check_conda_channels) { + checkCondaChannels() + } + + emit: + dummy_emit = true +} + +/* +======================================================================================== + FUNCTIONS +======================================================================================== +*/ + +// +// Generate version string +// +def getWorkflowVersion() { + String version_string = "" + if (workflow.manifest.version) { + def prefix_v = workflow.manifest.version[0] != 'v' ? 'v' : '' + version_string += "${prefix_v}${workflow.manifest.version}" + } + + if (workflow.commitId) { + def git_shortsha = workflow.commitId.substring(0, 7) + version_string += "-g${git_shortsha}" + } + + return version_string +} + +// +// Dump pipeline parameters to a JSON file +// +def dumpParametersToJSON(outdir) { + def timestamp = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss') + def filename = "params_${timestamp}.json" + def temp_pf = new File(workflow.launchDir.toString(), ".${filename}") + def jsonStr = JsonOutput.toJson(params) + temp_pf.text = JsonOutput.prettyPrint(jsonStr) + + FilesEx.copyTo(temp_pf.toPath(), "${outdir}/pipeline_info/params_${timestamp}.json") + temp_pf.delete() +} + +// +// When running with -profile conda, warn if channels have not been set-up appropriately +// +def checkCondaChannels() { + 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 + // This channel list is ordered by required channel priority. + def required_channels_in_order = ['conda-forge', 'bioconda', 'defaults'] + def channels_missing = ((required_channels_in_order as Set) - (channels as Set)) as Boolean + + // Check that they are in the right order + def channel_priority_violation = false + def n = required_channels_in_order.size() + for (int i = 0; i < n - 1; i++) { + channel_priority_violation |= !(channels.indexOf(required_channels_in_order[i]) < channels.indexOf(required_channels_in_order[i+1])) + } + + if (channels_missing | channel_priority_violation) { + 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/\n" + + " The observed channel order is \n" + + " ${channels}\n" + + " but the following channel order is required:\n" + + " ${required_channels_in_order}\n" + + "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~" + } +} diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/meta.yml b/subworkflows/nf-core/utils_nextflow_pipeline/meta.yml new file mode 100644 index 00000000..e5c3a0a8 --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/meta.yml @@ -0,0 +1,38 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json +name: "UTILS_NEXTFLOW_PIPELINE" +description: Subworkflow with functionality that may be useful for any Nextflow pipeline +keywords: + - utility + - pipeline + - initialise + - version +components: [] +input: + - print_version: + type: boolean + description: | + Print the version of the pipeline and exit + - dump_parameters: + type: boolean + description: | + Dump the parameters of the pipeline to a JSON file + - output_directory: + type: directory + description: Path to output dir to write JSON file to. + pattern: "results/" + - check_conda_channel: + type: boolean + description: | + Check if the conda channel priority is correct. +output: + - dummy_emit: + type: boolean + description: | + Dummy emit to make nf-core subworkflows lint happy +authors: + - "@adamrtalbot" + - "@drpatelh" +maintainers: + - "@adamrtalbot" + - "@drpatelh" + - "@maxulysse" diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test new file mode 100644 index 00000000..68718e4f --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test @@ -0,0 +1,54 @@ + +nextflow_function { + + name "Test Functions" + script "subworkflows/nf-core/utils_nextflow_pipeline/main.nf" + config "subworkflows/nf-core/utils_nextflow_pipeline/tests/nextflow.config" + tag 'subworkflows' + tag 'utils_nextflow_pipeline' + tag 'subworkflows/utils_nextflow_pipeline' + + test("Test Function getWorkflowVersion") { + + function "getWorkflowVersion" + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } + + test("Test Function dumpParametersToJSON") { + + function "dumpParametersToJSON" + + when { + function { + """ + // define inputs of the function here. Example: + input[0] = "$outputDir" + """.stripIndent() + } + } + + then { + assertAll( + { assert function.success } + ) + } + } + + test("Test Function checkCondaChannels") { + + function "checkCondaChannels" + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } +} diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test.snap b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test.snap new file mode 100644 index 00000000..e3f0baf4 --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test.snap @@ -0,0 +1,20 @@ +{ + "Test Function getWorkflowVersion": { + "content": [ + "v9.9.9" + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:02:05.308243" + }, + "Test Function checkCondaChannels": { + "content": null, + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:02:12.425833" + } +} \ No newline at end of file diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test new file mode 100644 index 00000000..ca964ce8 --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test @@ -0,0 +1,111 @@ +nextflow_workflow { + + name "Test Workflow UTILS_NEXTFLOW_PIPELINE" + script "../main.nf" + config "subworkflows/nf-core/utils_nextflow_pipeline/tests/nextflow.config" + workflow "UTILS_NEXTFLOW_PIPELINE" + tag 'subworkflows' + tag 'utils_nextflow_pipeline' + tag 'subworkflows/utils_nextflow_pipeline' + + test("Should run no inputs") { + + when { + workflow { + """ + print_version = false + dump_parameters = false + outdir = null + check_conda_channels = false + + input[0] = print_version + input[1] = dump_parameters + input[2] = outdir + input[3] = check_conda_channels + """ + } + } + + then { + assertAll( + { assert workflow.success } + ) + } + } + + test("Should print version") { + + when { + workflow { + """ + print_version = true + dump_parameters = false + outdir = null + check_conda_channels = false + + input[0] = print_version + input[1] = dump_parameters + input[2] = outdir + input[3] = check_conda_channels + """ + } + } + + then { + assertAll( + { assert workflow.success }, + { assert workflow.stdout.contains("nextflow_workflow v9.9.9") } + ) + } + } + + test("Should dump params") { + + when { + workflow { + """ + print_version = false + dump_parameters = true + outdir = 'results' + check_conda_channels = false + + input[0] = false + input[1] = true + input[2] = outdir + input[3] = false + """ + } + } + + then { + assertAll( + { assert workflow.success } + ) + } + } + + test("Should not create params JSON if no output directory") { + + when { + workflow { + """ + print_version = false + dump_parameters = true + outdir = null + check_conda_channels = false + + input[0] = false + input[1] = true + input[2] = outdir + input[3] = false + """ + } + } + + then { + assertAll( + { assert workflow.success } + ) + } + } +} diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/nextflow.config b/subworkflows/nf-core/utils_nextflow_pipeline/tests/nextflow.config new file mode 100644 index 00000000..d0a926bf --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/nextflow.config @@ -0,0 +1,9 @@ +manifest { + name = 'nextflow_workflow' + author = """nf-core""" + homePage = 'https://127.0.0.1' + description = """Dummy pipeline""" + nextflowVersion = '!>=23.04.0' + version = '9.9.9' + doi = 'https://doi.org/10.5281/zenodo.5070524' +} diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/tags.yml b/subworkflows/nf-core/utils_nextflow_pipeline/tests/tags.yml new file mode 100644 index 00000000..f8476112 --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/tags.yml @@ -0,0 +1,2 @@ +subworkflows/utils_nextflow_pipeline: + - subworkflows/nf-core/utils_nextflow_pipeline/** diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/main.nf b/subworkflows/nf-core/utils_nfcore_pipeline/main.nf new file mode 100644 index 00000000..a8b55d6f --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/main.nf @@ -0,0 +1,440 @@ +// +// Subworkflow with utility functions specific to the nf-core pipeline template +// + +import org.yaml.snakeyaml.Yaml +import nextflow.extension.FilesEx + +/* +======================================================================================== + SUBWORKFLOW DEFINITION +======================================================================================== +*/ + +workflow UTILS_NFCORE_PIPELINE { + + take: + nextflow_cli_args + + main: + valid_config = checkConfigProvided() + checkProfileProvided(nextflow_cli_args) + + emit: + valid_config +} + +/* +======================================================================================== + FUNCTIONS +======================================================================================== +*/ + +// +// Warn if a -profile or Nextflow config has not been provided to run the pipeline +// +def checkConfigProvided() { + valid_config = true + if (workflow.profile == 'standard' && workflow.configFiles.size() <= 1) { + log.warn "[$workflow.manifest.name] You are attempting to run the pipeline without any custom configuration!\n\n" + + "This will be dependent on your local compute environment but can be achieved via one or more of the following:\n" + + " (1) Using an existing pipeline profile e.g. `-profile docker` or `-profile singularity`\n" + + " (2) Using an existing nf-core/configs for your Institution e.g. `-profile crick` or `-profile uppmax`\n" + + " (3) Using your own local custom config e.g. `-c /path/to/your/custom.config`\n\n" + + "Please refer to the quick start section and usage docs for the pipeline.\n " + valid_config = false + } + return valid_config +} + +// +// Exit pipeline if --profile contains spaces +// +def checkProfileProvided(nextflow_cli_args) { + if (workflow.profile.endsWith(',')) { + error "The `-profile` option cannot end with a trailing comma, please remove it and re-run the pipeline!\n" + + "HINT: A common mistake is to provide multiple values separated by spaces e.g. `-profile test, docker`.\n" + } + if (nextflow_cli_args[0]) { + log.warn "nf-core pipelines do not accept positional arguments. The positional argument `${nextflow_cli_args[0]}` has been detected.\n" + + "HINT: A common mistake is to provide multiple values separated by spaces e.g. `-profile test, docker`.\n" + } +} + +// +// Citation string for pipeline +// +def workflowCitation() { + return "If you use ${workflow.manifest.name} for your analysis please cite:\n\n" + + "* The pipeline\n" + + " ${workflow.manifest.doi}\n\n" + + "* The nf-core framework\n" + + " https://doi.org/10.1038/s41587-020-0439-x\n\n" + + "* Software dependencies\n" + + " https://github.com/${workflow.manifest.name}/blob/master/CITATIONS.md" +} + +// +// Generate workflow version string +// +def getWorkflowVersion() { + String version_string = "" + if (workflow.manifest.version) { + def prefix_v = workflow.manifest.version[0] != 'v' ? 'v' : '' + version_string += "${prefix_v}${workflow.manifest.version}" + } + + if (workflow.commitId) { + def git_shortsha = workflow.commitId.substring(0, 7) + version_string += "-g${git_shortsha}" + } + + return version_string +} + +// +// Get software versions for pipeline +// +def processVersionsFromYAML(yaml_file) { + Yaml yaml = new Yaml() + versions = yaml.load(yaml_file).collectEntries { k, v -> [ k.tokenize(':')[-1], v ] } + return yaml.dumpAsMap(versions).trim() +} + +// +// Get workflow version for pipeline +// +def workflowVersionToYAML() { + return """ + Workflow: + $workflow.manifest.name: ${getWorkflowVersion()} + Nextflow: $workflow.nextflow.version + """.stripIndent().trim() +} + +// +// Get channel of software versions used in pipeline in YAML format +// +def softwareVersionsToYAML(ch_versions) { + return ch_versions + .unique() + .map { processVersionsFromYAML(it) } + .unique() + .mix(Channel.of(workflowVersionToYAML())) +} + +// +// Get workflow summary for MultiQC +// +def paramsSummaryMultiqc(summary_params) { + def summary_section = '' + for (group in summary_params.keySet()) { + def group_params = summary_params.get(group) // This gets the parameters of that particular group + if (group_params) { + summary_section += "

    $group

    \n" + summary_section += "
    \n" + for (param in group_params.keySet()) { + summary_section += "
    $param
    ${group_params.get(param) ?: 'N/A'}
    \n" + } + summary_section += "
    \n" + } + } + + String yaml_file_text = "id: '${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 +} + +// +// nf-core logo +// +def nfCoreLogo(monochrome_logs=true) { + 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} ${getWorkflowVersion()}${colors.reset} + ${dashedLine(monochrome_logs)} + """.stripIndent() + ) +} + +// +// Return dashed line +// +def dashedLine(monochrome_logs=true) { + Map colors = logColours(monochrome_logs) + return "-${colors.dim}----------------------------------------------------${colors.reset}-" +} + +// +// ANSII colours used for terminal logging +// +def logColours(monochrome_logs=true) { + 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 +} + +// +// Attach the multiqc report to email +// +def attachMultiqcReport(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 "[$workflow.manifest.name] Could not attach MultiQC report to summary email" + } + } + return mqc_report +} + +// +// Construct and send completion email +// +def completionEmail(summary_params, email, email_on_fail, plaintext_email, outdir, monochrome_logs=true, multiqc_report=null) { + + // Set up the e-mail variables + def subject = "[$workflow.manifest.name] Successful: $workflow.runName" + if (!workflow.success) { + subject = "[$workflow.manifest.name] FAILED: $workflow.runName" + } + + def summary = [:] + for (group in summary_params.keySet()) { + summary << summary_params[group] + } + + def misc_fields = [:] + misc_fields['Date Started'] = workflow.start + misc_fields['Date Completed'] = workflow.complete + misc_fields['Pipeline script file path'] = workflow.scriptFile + misc_fields['Pipeline script hash ID'] = workflow.scriptId + if (workflow.repository) misc_fields['Pipeline repository Git URL'] = workflow.repository + if (workflow.commitId) misc_fields['Pipeline repository Git Commit'] = workflow.commitId + if (workflow.revision) misc_fields['Pipeline Git branch/tag'] = workflow.revision + misc_fields['Nextflow Version'] = workflow.nextflow.version + misc_fields['Nextflow Build'] = workflow.nextflow.build + misc_fields['Nextflow Compile Timestamp'] = workflow.nextflow.timestamp + + def email_fields = [:] + email_fields['version'] = getWorkflowVersion() + email_fields['runName'] = workflow.runName + email_fields['success'] = workflow.success + email_fields['dateComplete'] = workflow.complete + email_fields['duration'] = workflow.duration + email_fields['exitStatus'] = workflow.exitStatus + email_fields['errorMessage'] = (workflow.errorMessage ?: 'None') + email_fields['errorReport'] = (workflow.errorReport ?: 'None') + email_fields['commandLine'] = workflow.commandLine + email_fields['projectDir'] = workflow.projectDir + email_fields['summary'] = summary << misc_fields + + // On success try attach the multiqc report + def mqc_report = attachMultiqcReport(multiqc_report) + + // Check if we are only sending emails on failure + def email_address = email + if (!email && email_on_fail && !workflow.success) { + email_address = email_on_fail + } + + // Render the TXT template + def engine = new groovy.text.GStringTemplateEngine() + def tf = new File("${workflow.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("${workflow.projectDir}/assets/email_template.html") + def html_template = engine.createTemplate(hf).make(email_fields) + def email_html = html_template.toString() + + // Render the sendmail template + def max_multiqc_email_size = (params.containsKey('max_multiqc_email_size') ? params.max_multiqc_email_size : 0) as nextflow.util.MemoryUnit + def smail_fields = [ email: email_address, subject: subject, email_txt: email_txt, email_html: email_html, projectDir: "${workflow.projectDir}", mqcFile: mqc_report, mqcMaxSize: max_multiqc_email_size.toBytes() ] + def sf = new File("${workflow.projectDir}/assets/sendmail_template.txt") + def sendmail_template = engine.createTemplate(sf).make(smail_fields) + def sendmail_html = sendmail_template.toString() + + // Send the HTML e-mail + Map colors = logColours(monochrome_logs) + if (email_address) { + try { + if (plaintext_email) { throw GroovyException('Send plaintext e-mail, not HTML') } + // Try to send HTML e-mail using sendmail + def sendmail_tf = new File(workflow.launchDir.toString(), ".sendmail_tmp.html") + sendmail_tf.withWriter { w -> w << sendmail_html } + [ 'sendmail', '-t' ].execute() << sendmail_html + log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Sent summary e-mail to $email_address (sendmail)-" + } catch (all) { + // Catch failures and try with plaintext + def mail_cmd = [ 'mail', '-s', subject, '--content-type=text/html', email_address ] + mail_cmd.execute() << email_html + log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Sent summary e-mail to $email_address (mail)-" + } + } + + // Write summary e-mail HTML to a file + def output_hf = new File(workflow.launchDir.toString(), ".pipeline_report.html") + output_hf.withWriter { w -> w << email_html } + FilesEx.copyTo(output_hf.toPath(), "${outdir}/pipeline_info/pipeline_report.html"); + output_hf.delete() + + // Write summary e-mail TXT to a file + def output_tf = new File(workflow.launchDir.toString(), ".pipeline_report.txt") + output_tf.withWriter { w -> w << email_txt } + FilesEx.copyTo(output_tf.toPath(), "${outdir}/pipeline_info/pipeline_report.txt"); + output_tf.delete() +} + +// +// Print pipeline summary on completion +// +def completionSummary(monochrome_logs=true) { + Map colors = logColours(monochrome_logs) + if (workflow.success) { + if (workflow.stats.ignoredCount == 0) { + log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Pipeline completed successfully${colors.reset}-" + } else { + log.info "-${colors.purple}[$workflow.manifest.name]${colors.yellow} Pipeline completed successfully, but with errored process(es) ${colors.reset}-" + } + } else { + log.info "-${colors.purple}[$workflow.manifest.name]${colors.red} Pipeline completed with errors${colors.reset}-" + } +} + +// +// Construct and send a notification to a web server as JSON e.g. Microsoft Teams and Slack +// +def imNotification(summary_params, hook_url) { + def summary = [:] + for (group in summary_params.keySet()) { + summary << summary_params[group] + } + + def misc_fields = [:] + misc_fields['start'] = workflow.start + misc_fields['complete'] = workflow.complete + misc_fields['scriptfile'] = workflow.scriptFile + misc_fields['scriptid'] = workflow.scriptId + if (workflow.repository) misc_fields['repository'] = workflow.repository + if (workflow.commitId) misc_fields['commitid'] = workflow.commitId + if (workflow.revision) misc_fields['revision'] = workflow.revision + misc_fields['nxf_version'] = workflow.nextflow.version + misc_fields['nxf_build'] = workflow.nextflow.build + misc_fields['nxf_timestamp'] = workflow.nextflow.timestamp + + def msg_fields = [:] + msg_fields['version'] = getWorkflowVersion() + msg_fields['runName'] = workflow.runName + msg_fields['success'] = workflow.success + msg_fields['dateComplete'] = workflow.complete + msg_fields['duration'] = workflow.duration + msg_fields['exitStatus'] = workflow.exitStatus + msg_fields['errorMessage'] = (workflow.errorMessage ?: 'None') + msg_fields['errorReport'] = (workflow.errorReport ?: 'None') + msg_fields['commandLine'] = workflow.commandLine.replaceFirst(/ +--hook_url +[^ ]+/, "") + msg_fields['projectDir'] = workflow.projectDir + msg_fields['summary'] = summary << misc_fields + + // Render the JSON template + def engine = new groovy.text.GStringTemplateEngine() + // Different JSON depending on the service provider + // Defaults to "Adaptive Cards" (https://adaptivecards.io), except Slack which has its own format + def json_path = hook_url.contains("hooks.slack.com") ? "slackreport.json" : "adaptivecard.json" + def hf = new File("${workflow.projectDir}/assets/${json_path}") + def json_template = engine.createTemplate(hf).make(msg_fields) + def json_message = json_template.toString() + + // POST + def post = new URL(hook_url).openConnection(); + post.setRequestMethod("POST") + post.setDoOutput(true) + post.setRequestProperty("Content-Type", "application/json") + post.getOutputStream().write(json_message.getBytes("UTF-8")); + def postRC = post.getResponseCode(); + if (! postRC.equals(200)) { + log.warn(post.getErrorStream().getText()); + } +} diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/meta.yml b/subworkflows/nf-core/utils_nfcore_pipeline/meta.yml new file mode 100644 index 00000000..d08d2434 --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/meta.yml @@ -0,0 +1,24 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json +name: "UTILS_NFCORE_PIPELINE" +description: Subworkflow with utility functions specific to the nf-core pipeline template +keywords: + - utility + - pipeline + - initialise + - version +components: [] +input: + - nextflow_cli_args: + type: list + description: | + Nextflow CLI positional arguments +output: + - success: + type: boolean + description: | + Dummy output to indicate success +authors: + - "@adamrtalbot" +maintainers: + - "@adamrtalbot" + - "@maxulysse" diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test new file mode 100644 index 00000000..1dc317f8 --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test @@ -0,0 +1,134 @@ + +nextflow_function { + + name "Test Functions" + script "../main.nf" + config "subworkflows/nf-core/utils_nfcore_pipeline/tests/nextflow.config" + tag "subworkflows" + tag "subworkflows_nfcore" + tag "utils_nfcore_pipeline" + tag "subworkflows/utils_nfcore_pipeline" + + test("Test Function checkConfigProvided") { + + function "checkConfigProvided" + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } + + test("Test Function checkProfileProvided") { + + function "checkProfileProvided" + + when { + function { + """ + input[0] = [] + """ + } + } + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } + + test("Test Function workflowCitation") { + + function "workflowCitation" + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } + + test("Test Function nfCoreLogo") { + + function "nfCoreLogo" + + when { + function { + """ + input[0] = false + """ + } + } + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } + + test("Test Function dashedLine") { + + function "dashedLine" + + when { + function { + """ + input[0] = false + """ + } + } + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } + + test("Test Function without logColours") { + + function "logColours" + + when { + function { + """ + input[0] = true + """ + } + } + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } + + test("Test Function with logColours") { + function "logColours" + + when { + function { + """ + input[0] = false + """ + } + } + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } +} diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test.snap b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test.snap new file mode 100644 index 00000000..1037232c --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test.snap @@ -0,0 +1,166 @@ +{ + "Test Function checkProfileProvided": { + "content": null, + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:03:03.360873" + }, + "Test Function checkConfigProvided": { + "content": [ + true + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:02:59.729647" + }, + "Test Function nfCoreLogo": { + "content": [ + "\n\n-\u001b[2m----------------------------------------------------\u001b[0m-\n \u001b[0;32m,--.\u001b[0;30m/\u001b[0;32m,-.\u001b[0m\n\u001b[0;34m ___ __ __ __ ___ \u001b[0;32m/,-._.--~'\u001b[0m\n\u001b[0;34m |\\ | |__ __ / ` / \\ |__) |__ \u001b[0;33m} {\u001b[0m\n\u001b[0;34m | \\| | \\__, \\__/ | \\ |___ \u001b[0;32m\\`-._,-`-,\u001b[0m\n \u001b[0;32m`._,._,'\u001b[0m\n\u001b[0;35m nextflow_workflow v9.9.9\u001b[0m\n-\u001b[2m----------------------------------------------------\u001b[0m-\n" + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:03:10.562934" + }, + "Test Function workflowCitation": { + "content": [ + "If you use nextflow_workflow for your analysis please cite:\n\n* The pipeline\n https://doi.org/10.5281/zenodo.5070524\n\n* The nf-core framework\n https://doi.org/10.1038/s41587-020-0439-x\n\n* Software dependencies\n https://github.com/nextflow_workflow/blob/master/CITATIONS.md" + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:03:07.019761" + }, + "Test Function without logColours": { + "content": [ + { + "reset": "", + "bold": "", + "dim": "", + "underlined": "", + "blink": "", + "reverse": "", + "hidden": "", + "black": "", + "red": "", + "green": "", + "yellow": "", + "blue": "", + "purple": "", + "cyan": "", + "white": "", + "bblack": "", + "bred": "", + "bgreen": "", + "byellow": "", + "bblue": "", + "bpurple": "", + "bcyan": "", + "bwhite": "", + "ublack": "", + "ured": "", + "ugreen": "", + "uyellow": "", + "ublue": "", + "upurple": "", + "ucyan": "", + "uwhite": "", + "iblack": "", + "ired": "", + "igreen": "", + "iyellow": "", + "iblue": "", + "ipurple": "", + "icyan": "", + "iwhite": "", + "biblack": "", + "bired": "", + "bigreen": "", + "biyellow": "", + "biblue": "", + "bipurple": "", + "bicyan": "", + "biwhite": "" + } + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:03:17.969323" + }, + "Test Function dashedLine": { + "content": [ + "-\u001b[2m----------------------------------------------------\u001b[0m-" + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:03:14.366181" + }, + "Test Function with logColours": { + "content": [ + { + "reset": "\u001b[0m", + "bold": "\u001b[1m", + "dim": "\u001b[2m", + "underlined": "\u001b[4m", + "blink": "\u001b[5m", + "reverse": "\u001b[7m", + "hidden": "\u001b[8m", + "black": "\u001b[0;30m", + "red": "\u001b[0;31m", + "green": "\u001b[0;32m", + "yellow": "\u001b[0;33m", + "blue": "\u001b[0;34m", + "purple": "\u001b[0;35m", + "cyan": "\u001b[0;36m", + "white": "\u001b[0;37m", + "bblack": "\u001b[1;30m", + "bred": "\u001b[1;31m", + "bgreen": "\u001b[1;32m", + "byellow": "\u001b[1;33m", + "bblue": "\u001b[1;34m", + "bpurple": "\u001b[1;35m", + "bcyan": "\u001b[1;36m", + "bwhite": "\u001b[1;37m", + "ublack": "\u001b[4;30m", + "ured": "\u001b[4;31m", + "ugreen": "\u001b[4;32m", + "uyellow": "\u001b[4;33m", + "ublue": "\u001b[4;34m", + "upurple": "\u001b[4;35m", + "ucyan": "\u001b[4;36m", + "uwhite": "\u001b[4;37m", + "iblack": "\u001b[0;90m", + "ired": "\u001b[0;91m", + "igreen": "\u001b[0;92m", + "iyellow": "\u001b[0;93m", + "iblue": "\u001b[0;94m", + "ipurple": "\u001b[0;95m", + "icyan": "\u001b[0;96m", + "iwhite": "\u001b[0;97m", + "biblack": "\u001b[1;90m", + "bired": "\u001b[1;91m", + "bigreen": "\u001b[1;92m", + "biyellow": "\u001b[1;93m", + "biblue": "\u001b[1;94m", + "bipurple": "\u001b[1;95m", + "bicyan": "\u001b[1;96m", + "biwhite": "\u001b[1;97m" + } + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:03:21.714424" + } +} \ No newline at end of file diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test new file mode 100644 index 00000000..8940d32d --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test @@ -0,0 +1,29 @@ +nextflow_workflow { + + name "Test Workflow UTILS_NFCORE_PIPELINE" + script "../main.nf" + config "subworkflows/nf-core/utils_nfcore_pipeline/tests/nextflow.config" + workflow "UTILS_NFCORE_PIPELINE" + tag "subworkflows" + tag "subworkflows_nfcore" + tag "utils_nfcore_pipeline" + tag "subworkflows/utils_nfcore_pipeline" + + test("Should run without failures") { + + when { + workflow { + """ + input[0] = [] + """ + } + } + + then { + assertAll( + { assert workflow.success }, + { assert snapshot(workflow.out).match() } + ) + } + } +} diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test.snap b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test.snap new file mode 100644 index 00000000..859d1030 --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test.snap @@ -0,0 +1,19 @@ +{ + "Should run without failures": { + "content": [ + { + "0": [ + true + ], + "valid_config": [ + true + ] + } + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:03:25.726491" + } +} \ No newline at end of file diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/tests/nextflow.config b/subworkflows/nf-core/utils_nfcore_pipeline/tests/nextflow.config new file mode 100644 index 00000000..d0a926bf --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/nextflow.config @@ -0,0 +1,9 @@ +manifest { + name = 'nextflow_workflow' + author = """nf-core""" + homePage = 'https://127.0.0.1' + description = """Dummy pipeline""" + nextflowVersion = '!>=23.04.0' + version = '9.9.9' + doi = 'https://doi.org/10.5281/zenodo.5070524' +} diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/tests/tags.yml b/subworkflows/nf-core/utils_nfcore_pipeline/tests/tags.yml new file mode 100644 index 00000000..ac8523c9 --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/tags.yml @@ -0,0 +1,2 @@ +subworkflows/utils_nfcore_pipeline: + - subworkflows/nf-core/utils_nfcore_pipeline/** diff --git a/subworkflows/nf-core/utils_nfvalidation_plugin/main.nf b/subworkflows/nf-core/utils_nfvalidation_plugin/main.nf new file mode 100644 index 00000000..2585b65d --- /dev/null +++ b/subworkflows/nf-core/utils_nfvalidation_plugin/main.nf @@ -0,0 +1,62 @@ +// +// Subworkflow that uses the nf-validation plugin to render help text and parameter summary +// + +/* +======================================================================================== + IMPORT NF-VALIDATION PLUGIN +======================================================================================== +*/ + +include { paramsHelp } from 'plugin/nf-validation' +include { paramsSummaryLog } from 'plugin/nf-validation' +include { validateParameters } from 'plugin/nf-validation' + +/* +======================================================================================== + SUBWORKFLOW DEFINITION +======================================================================================== +*/ + +workflow UTILS_NFVALIDATION_PLUGIN { + + take: + print_help // boolean: print help + workflow_command // string: default commmand used to run pipeline + pre_help_text // string: string to be printed before help text and summary log + post_help_text // string: string to be printed after help text and summary log + validate_params // boolean: validate parameters + schema_filename // path: JSON schema file, null to use default value + + main: + + log.debug "Using schema file: ${schema_filename}" + + // Default values for strings + pre_help_text = pre_help_text ?: '' + post_help_text = post_help_text ?: '' + workflow_command = workflow_command ?: '' + + // + // Print help message if needed + // + if (print_help) { + log.info pre_help_text + paramsHelp(workflow_command, parameters_schema: schema_filename) + post_help_text + System.exit(0) + } + + // + // Print parameter summary to stdout + // + log.info pre_help_text + paramsSummaryLog(workflow, parameters_schema: schema_filename) + post_help_text + + // + // Validate parameters relative to the parameter JSON schema + // + if (validate_params){ + validateParameters(parameters_schema: schema_filename) + } + + emit: + dummy_emit = true +} diff --git a/subworkflows/nf-core/utils_nfvalidation_plugin/meta.yml b/subworkflows/nf-core/utils_nfvalidation_plugin/meta.yml new file mode 100644 index 00000000..3d4a6b04 --- /dev/null +++ b/subworkflows/nf-core/utils_nfvalidation_plugin/meta.yml @@ -0,0 +1,44 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json +name: "UTILS_NFVALIDATION_PLUGIN" +description: Use nf-validation to initiate and validate a pipeline +keywords: + - utility + - pipeline + - initialise + - validation +components: [] +input: + - print_help: + type: boolean + description: | + Print help message and exit + - workflow_command: + type: string + description: | + The command to run the workflow e.g. "nextflow run main.nf" + - pre_help_text: + type: string + description: | + Text to print before the help message + - post_help_text: + type: string + description: | + Text to print after the help message + - validate_params: + type: boolean + description: | + Validate the parameters and error if invalid. + - schema_filename: + type: string + description: | + The filename of the schema to validate against. +output: + - dummy_emit: + type: boolean + description: | + Dummy emit to make nf-core subworkflows lint happy +authors: + - "@adamrtalbot" +maintainers: + - "@adamrtalbot" + - "@maxulysse" diff --git a/subworkflows/nf-core/utils_nfvalidation_plugin/tests/main.nf.test b/subworkflows/nf-core/utils_nfvalidation_plugin/tests/main.nf.test new file mode 100644 index 00000000..5784a33f --- /dev/null +++ b/subworkflows/nf-core/utils_nfvalidation_plugin/tests/main.nf.test @@ -0,0 +1,200 @@ +nextflow_workflow { + + name "Test Workflow UTILS_NFVALIDATION_PLUGIN" + script "../main.nf" + workflow "UTILS_NFVALIDATION_PLUGIN" + tag "subworkflows" + tag "subworkflows_nfcore" + tag "plugin/nf-validation" + tag "'plugin/nf-validation'" + tag "utils_nfvalidation_plugin" + tag "subworkflows/utils_nfvalidation_plugin" + + test("Should run nothing") { + + when { + + params { + monochrome_logs = true + test_data = '' + } + + workflow { + """ + help = false + workflow_command = null + pre_help_text = null + post_help_text = null + validate_params = false + schema_filename = "$moduleTestDir/nextflow_schema.json" + + input[0] = help + input[1] = workflow_command + input[2] = pre_help_text + input[3] = post_help_text + input[4] = validate_params + input[5] = schema_filename + """ + } + } + + then { + assertAll( + { assert workflow.success } + ) + } + } + + test("Should run help") { + + + when { + + params { + monochrome_logs = true + test_data = '' + } + workflow { + """ + help = true + workflow_command = null + pre_help_text = null + post_help_text = null + validate_params = false + schema_filename = "$moduleTestDir/nextflow_schema.json" + + input[0] = help + input[1] = workflow_command + input[2] = pre_help_text + input[3] = post_help_text + input[4] = validate_params + input[5] = schema_filename + """ + } + } + + then { + assertAll( + { assert workflow.success }, + { assert workflow.exitStatus == 0 }, + { assert workflow.stdout.any { it.contains('Input/output options') } }, + { assert workflow.stdout.any { it.contains('--outdir') } } + ) + } + } + + test("Should run help with command") { + + when { + + params { + monochrome_logs = true + test_data = '' + } + workflow { + """ + help = true + workflow_command = "nextflow run noorg/doesntexist" + pre_help_text = null + post_help_text = null + validate_params = false + schema_filename = "$moduleTestDir/nextflow_schema.json" + + input[0] = help + input[1] = workflow_command + input[2] = pre_help_text + input[3] = post_help_text + input[4] = validate_params + input[5] = schema_filename + """ + } + } + + then { + assertAll( + { assert workflow.success }, + { assert workflow.exitStatus == 0 }, + { assert workflow.stdout.any { it.contains('nextflow run noorg/doesntexist') } }, + { assert workflow.stdout.any { it.contains('Input/output options') } }, + { assert workflow.stdout.any { it.contains('--outdir') } } + ) + } + } + + test("Should run help with extra text") { + + + when { + + params { + monochrome_logs = true + test_data = '' + } + workflow { + """ + help = true + workflow_command = "nextflow run noorg/doesntexist" + pre_help_text = "pre-help-text" + post_help_text = "post-help-text" + validate_params = false + schema_filename = "$moduleTestDir/nextflow_schema.json" + + input[0] = help + input[1] = workflow_command + input[2] = pre_help_text + input[3] = post_help_text + input[4] = validate_params + input[5] = schema_filename + """ + } + } + + then { + assertAll( + { assert workflow.success }, + { assert workflow.exitStatus == 0 }, + { assert workflow.stdout.any { it.contains('pre-help-text') } }, + { assert workflow.stdout.any { it.contains('nextflow run noorg/doesntexist') } }, + { assert workflow.stdout.any { it.contains('Input/output options') } }, + { assert workflow.stdout.any { it.contains('--outdir') } }, + { assert workflow.stdout.any { it.contains('post-help-text') } } + ) + } + } + + test("Should validate params") { + + when { + + params { + monochrome_logs = true + test_data = '' + outdir = 1 + } + workflow { + """ + help = false + workflow_command = null + pre_help_text = null + post_help_text = null + validate_params = true + schema_filename = "$moduleTestDir/nextflow_schema.json" + + input[0] = help + input[1] = workflow_command + input[2] = pre_help_text + input[3] = post_help_text + input[4] = validate_params + input[5] = schema_filename + """ + } + } + + then { + assertAll( + { assert workflow.failed }, + { assert workflow.stdout.any { it.contains('ERROR ~ ERROR: Validation of pipeline parameters failed!') } } + ) + } + } +} diff --git a/subworkflows/nf-core/utils_nfvalidation_plugin/tests/nextflow_schema.json b/subworkflows/nf-core/utils_nfvalidation_plugin/tests/nextflow_schema.json new file mode 100644 index 00000000..7626c1c9 --- /dev/null +++ b/subworkflows/nf-core/utils_nfvalidation_plugin/tests/nextflow_schema.json @@ -0,0 +1,96 @@ +{ + "$schema": "http://json-schema.org/draft-07/schema", + "$id": "https://raw.githubusercontent.com/./master/nextflow_schema.json", + "title": ". pipeline parameters", + "description": "", + "type": "object", + "definitions": { + "input_output_options": { + "title": "Input/output options", + "type": "object", + "fa_icon": "fas fa-terminal", + "description": "Define where the pipeline should find input data and save output data.", + "required": ["outdir"], + "properties": { + "validate_params": { + "type": "boolean", + "description": "Validate parameters?", + "default": true, + "hidden": true + }, + "outdir": { + "type": "string", + "format": "directory-path", + "description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.", + "fa_icon": "fas fa-folder-open" + }, + "test_data_base": { + "type": "string", + "default": "https://raw.githubusercontent.com/nf-core/test-datasets/modules", + "description": "Base for test data directory", + "hidden": true + }, + "test_data": { + "type": "string", + "description": "Fake test data param", + "hidden": true + } + } + }, + "generic_options": { + "title": "Generic 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`.", + "properties": { + "help": { + "type": "boolean", + "description": "Display help text.", + "fa_icon": "fas fa-question-circle", + "hidden": true + }, + "version": { + "type": "boolean", + "description": "Display version and exit.", + "fa_icon": "fas fa-question-circle", + "hidden": true + }, + "logo": { + "type": "boolean", + "default": true, + "description": "Display nf-core logo in console output.", + "fa_icon": "fas fa-image", + "hidden": true + }, + "singularity_pull_docker_container": { + "type": "boolean", + "description": "Pull Singularity container from Docker?", + "hidden": true + }, + "publish_dir_mode": { + "type": "string", + "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 + }, + "monochrome_logs": { + "type": "boolean", + "description": "Use monochrome_logs", + "hidden": true + } + } + } + }, + "allOf": [ + { + "$ref": "#/definitions/input_output_options" + }, + { + "$ref": "#/definitions/generic_options" + } + ] +} diff --git a/subworkflows/nf-core/utils_nfvalidation_plugin/tests/tags.yml b/subworkflows/nf-core/utils_nfvalidation_plugin/tests/tags.yml new file mode 100644 index 00000000..60b1cfff --- /dev/null +++ b/subworkflows/nf-core/utils_nfvalidation_plugin/tests/tags.yml @@ -0,0 +1,2 @@ +subworkflows/utils_nfvalidation_plugin: + - subworkflows/nf-core/utils_nfvalidation_plugin/** diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf index a83b54c4..6e079164 100644 --- a/workflows/taxprofiler.nf +++ b/workflows/taxprofiler.nf @@ -1,19 +1,16 @@ /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - PRINT PARAMS SUMMARY + IMPORT MODULES / SUBWORKFLOWS / FUNCTIONS ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -include { paramsSummaryLog; paramsSummaryMap } from 'plugin/nf-validation' - -def logo = NfcoreTemplate.logo(workflow, params.monochrome_logs) -def citation = '\n' + WorkflowMain.citation(workflow) + '\n' -def summary_params = paramsSummaryMap(workflow) - -// Print parameter summary log to screen -log.info logo + paramsSummaryLog(workflow) + citation - -WorkflowTaxprofiler.initialise(params, log) +include { FASTQC } from '../modules/nf-core/fastqc/main' +include { MULTIQC } from '../modules/nf-core/multiqc/main' +include { paramsSummaryMap } from 'plugin/nf-validation' +include { paramsSummaryMultiqc } from '../subworkflows/nf-core/utils_nfcore_pipeline' +include { softwareVersionsToYAML } from '../subworkflows/nf-core/utils_nfcore_pipeline' +include { methodsDescriptionText } from '../subworkflows/local/utils_nfcore_taxprofiler_pipeline' +include { validateParameters; paramsHelp; paramsSummaryLog; fromSamplesheet } from 'plugin/nf-validation' // Check input path parameters to see if they exist def checkPathParamList = [ params.input, params.genome, params.databases, @@ -55,16 +52,6 @@ if (params.run_bracken && !params.run_kraken2) error('ERROR: [nf-core/taxprofile if ( [params.taxpasta_add_name, params.taxpasta_add_rank, params.taxpasta_add_lineage, params.taxpasta_add_lineage, params.taxpasta_add_idlineage, params.taxpasta_add_ranklineage].any() && !params.taxpasta_taxonomy_dir ) error('ERROR: [nf-core/taxprofiler] All --taxpasta_add_* parameters require a taxonomy supplied to --taxpasta_taxonomy_dir. However the latter parameter was not detected. Please check input.') -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - CONFIG FILES -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -*/ - -ch_multiqc_config = Channel.fromPath("$projectDir/assets/multiqc_config.yml", checkIfExists: true) -ch_multiqc_custom_config = params.multiqc_config ? Channel.fromPath( params.multiqc_config, checkIfExists: true ) : Channel.empty() -ch_multiqc_logo = params.multiqc_logo ? Channel.fromPath( params.multiqc_logo, checkIfExists: true ) : Channel.empty() -ch_multiqc_custom_methods_description = params.multiqc_methods_description ? file(params.multiqc_methods_description, checkIfExists: true) : file("$projectDir/assets/methods_description_template.yml", checkIfExists: true) /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -75,9 +62,7 @@ ch_multiqc_custom_methods_description = params.multiqc_methods_description ? fil // // SUBWORKFLOW: Consisting of a mix of local and nf-core/modules // -include { INPUT_CHECK } from '../subworkflows/local/input_check' -include { DB_CHECK } from '../subworkflows/local/db_check' include { SHORTREAD_PREPROCESSING } from '../subworkflows/local/shortread_preprocessing' include { LONGREAD_PREPROCESSING } from '../subworkflows/local/longread_preprocessing' include { SHORTREAD_HOSTREMOVAL } from '../subworkflows/local/shortread_hostremoval' @@ -96,10 +81,8 @@ include { STANDARDISATION_PROFILES } from '../subworkflows/local/standardis // // MODULE: Installed directly from nf-core/modules // -include { FASTQC } from '../modules/nf-core/fastqc/main' +include { UNTAR } from '../modules/nf-core/untar/main' include { FALCO } from '../modules/nf-core/falco/main' -include { MULTIQC } from '../modules/nf-core/multiqc/main' -include { CUSTOM_DUMPSOFTWAREVERSIONS } from '../modules/nf-core/custom/dumpsoftwareversions/main' include { CAT_FASTQ as MERGE_RUNS } from '../modules/nf-core/cat/fastq/main' /* @@ -108,13 +91,8 @@ include { CAT_FASTQ as MERGE_RUNS } from '../modules/nf-core/cat/fastq/main' ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -// Info required for completion email and summary -def multiqc_report = [] - workflow TAXPROFILER { - ch_versions = Channel.empty() - ch_multiqc_logo= Channel.fromPath("$projectDir/docs/images/nf-core-taxprofiler_logo_custom_light.png") adapterlist = params.shortread_qc_adapterlist ? file(params.shortread_qc_adapterlist) : [] if ( params.shortread_qc_adapterlist ) { @@ -122,29 +100,94 @@ workflow TAXPROFILER { if ( params.shortread_qc_tool == 'fastp' && !adapterlist.extension.matches(".*(fa|fasta|fna|fas)") ) error "[nf-core/taxprofiler] ERROR: fastp adapter list requires a `.fasta` format and extension (or fa, fas, fna). Check input: --shortread_qc_adapterlist ${params.shortread_qc_adapterlist}" } - /* - SUBWORKFLOW: Read in samplesheet, validate and stage input files - */ - INPUT_CHECK ( - file(params.input) - ) - ch_versions = ch_versions.mix(INPUT_CHECK.out.versions) - // TODO: OPTIONAL, you can use nf-validation plugin to create an input channel from the samplesheet with Channel.fromSamplesheet("input") - // See the documentation https://nextflow-io.github.io/nf-validation/samplesheets/fromSamplesheet/ - // ! There is currently no tooling to help you write a sample sheet schema + take: + samplesheet // channel: samplesheet read in from --input + databases // channel: databases from --databases - // Save final FASTA reads if requested, as otherwise no processing occurs on FASTA + main: + ch_versions = Channel.empty() + ch_multiqc_files = Channel.empty() - DB_CHECK ( - ch_databases - ) - ch_versions = ch_versions.mix(DB_CHECK.out.versions) + // Validate input files and create separate channels for FASTQ, FASTA, and Nanopore data + ch_input = samplesheet + .map { meta, run_accession, instrument_platform, fastq_1, fastq_2, fasta -> + meta.run_accession = run_accession + meta.instrument_platform = instrument_platform + + // Define single_end based on the conditions + meta.single_end = ( fastq_1 && !fastq_2 && instrument_platform != 'OXFORD_NANOPORE' ) + + // Define is_fasta based on the presence of fasta + meta.is_fasta = fasta ? true : false + + if ( !meta.is_fasta && !fastq_1 ) { + error("ERROR: Please check input samplesheet: entry `fastq_1` doesn't exist!") + } + if ( meta.instrument_platform == 'OXFORD_NANOPORE' && fastq_2 ) { + error("Error: Please check input samplesheet: for Oxford Nanopore reads entry `fastq_2` should be empty!") + } + if ( meta.single_end && fastq_2 ) { + error("Error: Please check input samplesheet: for single-end reads entry `fastq_2` should be empty") + } + return [ meta, run_accession, instrument_platform, fastq_1, fastq_2, fasta ] + } + .branch { meta, run_accession, instrument_platform, fastq_1, fastq_2, fasta -> + fastq: meta.single_end || fastq_2 + return [ meta, fastq_2 ? [ fastq_1, fastq_2 ] : [ fastq_1 ] ] + nanopore: instrument_platform == 'OXFORD_NANOPORE' + meta.single_end = true + return [ meta, [ fastq_1 ] ] + fasta: meta.is_fasta + meta.single_end = true + return [ meta, [ fasta ] ] + } + + // Merge ch_input.fastq and ch_input.nanopore into a single channel + def ch_input_for_fastqc = ch_input.fastq.mix( ch_input.nanopore ) + + // Validate and decompress databases + ch_dbs_for_untar = databases + .branch { db_meta, db_path -> + untar: db_path.name.endsWith( ".tar.gz" ) + skip: true + } + // Filter the channel to untar only those databases for tools that are selected to be run by the user. + // Also, to ensure only untar once per file, group together all databases of one file + ch_inputdb_untar = ch_dbs_for_untar.untar + .filter { db_meta, db_path -> + params[ "run_${db_meta.tool}" ] + } + .groupTuple(by: 1) + .map { + meta, dbfile -> + def new_meta = [ 'id': dbfile.baseName ] + [ 'meta': meta ] + [new_meta , dbfile ] + } + + // Untar the databases + UNTAR ( ch_inputdb_untar ) + ch_versions = ch_versions.mix( UNTAR.out.versions.first() ) + + // Spread out the untarred and shared databases + ch_outputdb_from_untar = UNTAR.out.untar + .map { + meta, db -> + [meta.meta, db] + } + .transpose(by: 0) + + ch_final_dbs = ch_dbs_for_untar.skip + .mix( ch_outputdb_from_untar ) + .map { db_meta, db -> + def corrected_db_params = db_meta.db_params ? [ db_params: db_meta.db_params ] : [ db_params: '' ] + [ db_meta + corrected_db_params, db ] + } /* MODULE: Run FastQC */ - ch_input_for_fastqc = INPUT_CHECK.out.fastq.mix( INPUT_CHECK.out.nanopore ) + if ( !params.skip_preprocessing_qc ) { if ( params.preprocessing_qc_tool == 'falco' ) { @@ -161,18 +204,18 @@ workflow TAXPROFILER { */ if ( params.perform_shortread_qc ) { - ch_shortreads_preprocessed = SHORTREAD_PREPROCESSING ( INPUT_CHECK.out.fastq, adapterlist ).reads + ch_shortreads_preprocessed = SHORTREAD_PREPROCESSING ( ch_input.fastq, adapterlist ).reads ch_versions = ch_versions.mix( SHORTREAD_PREPROCESSING.out.versions ) } else { - ch_shortreads_preprocessed = INPUT_CHECK.out.fastq + ch_shortreads_preprocessed = ch_input.fastq } if ( params.perform_longread_qc ) { - ch_longreads_preprocessed = LONGREAD_PREPROCESSING ( INPUT_CHECK.out.nanopore ).reads + ch_longreads_preprocessed = LONGREAD_PREPROCESSING ( ch_input.nanopore ).reads .map { it -> [ it[0], [it[1]] ] } ch_versions = ch_versions.mix( LONGREAD_PREPROCESSING.out.versions ) } else { - ch_longreads_preprocessed = INPUT_CHECK.out.nanopore + ch_longreads_preprocessed = ch_input.nanopore } /* @@ -233,27 +276,27 @@ workflow TAXPROFILER { meta, reads -> [ meta, [ reads ].flatten() ] } - .mix( INPUT_CHECK.out.fasta ) + .mix( ch_input.fasta ) ch_versions = ch_versions.mix(MERGE_RUNS.out.versions) } else { ch_reads_runmerged = ch_shortreads_hostremoved - .mix( ch_longreads_hostremoved, INPUT_CHECK.out.fasta ) + .mix( ch_longreads_hostremoved, ch_input.fasta ) } /* SUBWORKFLOW: PROFILING */ - PROFILING ( ch_reads_runmerged, DB_CHECK.out.dbs ) + PROFILING ( ch_reads_runmerged, ch_final_dbs ) ch_versions = ch_versions.mix( PROFILING.out.versions ) /* SUBWORKFLOW: VISUALIZATION_KRONA */ if ( params.run_krona ) { - VISUALIZATION_KRONA ( PROFILING.out.classifications, PROFILING.out.profiles, DB_CHECK.out.dbs ) + VISUALIZATION_KRONA ( PROFILING.out.classifications, PROFILING.out.profiles, ch_final_dbs ) ch_versions = ch_versions.mix( VISUALIZATION_KRONA.out.versions ) } @@ -261,7 +304,7 @@ workflow TAXPROFILER { SUBWORKFLOW: PROFILING STANDARDISATION */ if ( params.run_profile_standardisation ) { - STANDARDISATION_PROFILES ( PROFILING.out.classifications, PROFILING.out.profiles, DB_CHECK.out.dbs, PROFILING.out.motus_version ) + STANDARDISATION_PROFILES ( PROFILING.out.classifications, PROFILING.out.profiles, ch_final_dbs, PROFILING.out.motus_version ) ch_versions = ch_versions.mix( STANDARDISATION_PROFILES.out.versions ) } @@ -269,21 +312,26 @@ workflow TAXPROFILER { MODULE: MultiQC */ - CUSTOM_DUMPSOFTWAREVERSIONS ( - ch_versions.unique().collectFile(name: 'collated_versions.yml') - ) - - - workflow_summary = WorkflowTaxprofiler.paramsSummaryMultiqc(workflow, summary_params) - ch_workflow_summary = Channel.value(workflow_summary) - - methods_description = WorkflowTaxprofiler.methodsDescriptionText(workflow, ch_multiqc_custom_methods_description, params) - ch_methods_description = Channel.value(methods_description) - - ch_multiqc_files = Channel.empty() - ch_multiqc_files = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml')) - ch_multiqc_files = ch_multiqc_files.mix(ch_methods_description.collectFile(name: 'methods_description_mqc.yaml')) - ch_multiqc_files = ch_multiqc_files.mix(CUSTOM_DUMPSOFTWAREVERSIONS.out.mqc_yml.collect()) + // + // Collate and save software versions + // + softwareVersionsToYAML(ch_versions) + .collectFile(storeDir: "${params.outdir}/pipeline_info", name: 'nf_core_pipeline_software_mqc_versions.yml', sort: true, newLine: true) + .set { ch_collated_versions } + + // + // MODULE: MultiQC + // + ch_multiqc_config = Channel.fromPath("$projectDir/assets/multiqc_config.yml", checkIfExists: true) + ch_multiqc_custom_config = params.multiqc_config ? Channel.fromPath(params.multiqc_config, checkIfExists: true) : Channel.empty() + ch_multiqc_logo = params.multiqc_logo ? Channel.fromPath(params.multiqc_logo, checkIfExists: true) : Channel.empty() + summary_params = paramsSummaryMap(workflow, parameters_schema: "nextflow_schema.json") + ch_workflow_summary = Channel.value(paramsSummaryMultiqc(summary_params)) + ch_multiqc_custom_methods_description = params.multiqc_methods_description ? file(params.multiqc_methods_description, checkIfExists: true) : file("$projectDir/assets/methods_description_template.yml", checkIfExists: true) + ch_methods_description = Channel.value(methodsDescriptionText(ch_multiqc_custom_methods_description)) + ch_multiqc_files = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml')) + ch_multiqc_files = ch_multiqc_files.mix(ch_collated_versions) + ch_multiqc_files = ch_multiqc_files.mix(ch_methods_description.collectFile(name: 'methods_description_mqc.yaml', sort: false)) if ( !params.skip_preprocessing_qc ) { if ( params.preprocessing_qc_tool == 'falco' ) { @@ -330,31 +378,10 @@ workflow TAXPROFILER { ch_multiqc_custom_config.toList(), ch_multiqc_logo.toList() ) - multiqc_report = MULTIQC.out.report.toList() -} - -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - COMPLETION EMAIL AND SUMMARY -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -*/ - -workflow.onComplete { - if (params.email || params.email_on_fail) { - NfcoreTemplate.email(workflow, params, summary_params, projectDir, log, multiqc_report) - } - NfcoreTemplate.dump_parameters(workflow, params) - NfcoreTemplate.summary(workflow, params, log) - if (params.hook_url) { - NfcoreTemplate.IM_notification(workflow, params, summary_params, projectDir, log) - } -} -workflow.onError { - if (workflow.errorReport.contains("Process requirement exceeds available memory")) { - println("🛑 Default resources exceed availability 🛑 ") - println("💡 See here on how to configure pipeline: https://nf-co.re/docs/usage/configuration#tuning-workflow-resources 💡") - } + emit: + multiqc_report = MULTIQC.out.report.toList() // channel: /path/to/multiqc_report.html + versions = ch_versions // channel: [ path(versions.yml) ] } /*
    Process Name \\", - " \\ Software Version
    CUSTOM_DUMPSOFTWAREVERSIONSpython3.11.7
    yaml5.4.1
    TOOL1tool10.11.9
    TOOL2tool21.9
    WorkflowNextflow
    File typeConventional base calls
    File typeConventional base calls
    File typeConventional base calls
    File typeConventional base calls
    File typeConventional base calls
    File typeConventional base calls
    File typeConventional base calls
    File typeConventional base calls