Merge pull request #46 from mskcc/release/candidate-1.0.0

Release candidate for 1.0.0
mskcc · Jul 31, 2024 · 18769d6 · 18769d6
2 parents 0dc5c68 + 53eedf9
commit 18769d6
Show file tree

Hide file tree

Showing 142 changed files with 9,127 additions and 713 deletions.
diff --git a/.editorconfig b/.editorconfig
@@ -24,13 +24,31 @@ end_of_line = unset
 insert_final_newline = unset
 trim_trailing_whitespace = unset
 indent_style = unset
+[/modules/msk/**]
+charset = unset
+end_of_line = unset
+insert_final_newline = unset
+trim_trailing_whitespace = unset
+indent_style = unset
+[/subworkflows/msk/**]
+charset = unset
+end_of_line = unset
+insert_final_newline = unset
+trim_trailing_whitespace = unset
+indent_style = unset
+
 
 [/assets/email*]
 indent_size = unset
 
 # ignore Readme
 [README.md]
 indent_style = unset
+trim_trailing_whitespace = unset
+
+[/docs/usage.md]
+indent_style = unset
+trim_trailing_whitespace = unset
 
 # ignore python
 [*.{py,md}]

diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml
@@ -2,53 +2,53 @@ name: Bug report
 description: Report something that is broken or incorrect
 labels: bug
 body:
-- type: textarea
-  id: description
-  attributes:
-    label: Description of the bug
-    description: A clear and concise description of what the bug is.
-  validations:
-    required: true
-- type: textarea
-  id: command_used
-  attributes:
-    label: Command used and terminal output
-    description: Steps to reproduce the behaviour. Please paste the command you used
-      to launch the pipeline and the output from your terminal.
-    render: console
-    placeholder: '$ nextflow run ...
-
-
-      Some output where something broke
-
-      '
-- type: textarea
-  id: files
-  attributes:
-    label: Relevant files
-    description: 'Please drag and drop the relevant files here. Create a `.zip` archive
-      if the extension is not allowed.
-
-      Your verbose log file `.nextflow.log` is often useful _(this is a hidden file
-      in the directory where you launched the pipeline)_ as well as custom Nextflow
-      configuration files.
-
-      '
-- type: textarea
-  id: system
-  attributes:
-    label: System information
-    description: '* Nextflow version _(eg. 23.04.0)_
-
-      * Hardware _(eg. HPC, Desktop, Cloud)_
-
-      * Executor _(eg. slurm, local, awsbatch)_
-
-      * Container engine: _(e.g. Docker, Singularity, Conda, Podman, Shifter, Charliecloud,
-      or Apptainer)_
-
-      * OS _(eg. CentOS Linux, macOS, Linux Mint)_
-
-      * Version of mskcc/neoantigenpipeline _(eg. 1.1, 1.5, 1.8.2)_
-
-      '
+  - type: textarea
+    id: description
+    attributes:
+      label: Description of the bug
+      description: A clear and concise description of what the bug is.
+    validations:
+      required: true
+  - type: textarea
+    id: command_used
+    attributes:
+      label: Command used and terminal output
+      description: Steps to reproduce the behaviour. Please paste the command you used
+        to launch the pipeline and the output from your terminal.
+      render: console
+      placeholder: "$ nextflow run ...
+
+
+        Some output where something broke
+
+        "
+  - type: textarea
+    id: files
+    attributes:
+      label: Relevant files
+      description: "Please drag and drop the relevant files here. Create a `.zip` archive
+        if the extension is not allowed.
+
+        Your verbose log file `.nextflow.log` is often useful _(this is a hidden file
+        in the directory where you launched the pipeline)_ as well as custom Nextflow
+        configuration files.
+
+        "
+  - type: textarea
+    id: system
+    attributes:
+      label: System information
+      description: "* Nextflow version _(eg. 23.04.0)_
+
+        * Hardware _(eg. HPC, Desktop, Cloud)_
+
+        * Executor _(eg. slurm, local, awsbatch)_
+
+        * Container engine: _(e.g. Docker, Singularity, Conda, Podman, Shifter, Charliecloud,
+        or Apptainer)_
+
+        * OS _(eg. CentOS Linux, macOS, Linux Mint)_
+
+        * Version of mskcc/neoantigenpipeline _(eg. 1.1, 1.5, 1.8.2)_
+
+        "
diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
@@ -17,7 +17,7 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/mskcc/neoant
 - [ ] If you've fixed a bug or added code that should be tested, add tests!
 - [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/mskcc/neoantigenpipeline/tree/master/.github/CONTRIBUTING.md)
 - [ ] Make sure your code lints (`nf-core lint`).
-- [ ] Ensure the test suite passes (`nf-test test main.nf.test -profile test,docker`).
+- [ ] Ensure the test suite passes (`nextflow run . -profile test,docker --outdir <OUTDIR>`).
 - [ ] Check for unexpected warnings in debug mode (`nextflow run . -profile debug,test,docker --outdir <OUTDIR>`).
 - [ ] Usage Documentation in `docs/usage.md` is updated.
 - [ ] Output Documentation in `docs/output.md` is updated.

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -5,6 +5,7 @@ on:
     branches:
       - dev
   pull_request:
+    branches: ["dev", "main", "master"]
   release:
     types: [published]
 

diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml
@@ -14,13 +14,12 @@ jobs:
   pre-commit:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4
+      - uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
 
-      - name: Set up Python 3.11
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5
+      - name: Set up Python 3.12
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5
         with:
-          python-version: 3.11
-          cache: "pip"
+          python-version: "3.12"
 
       - name: Install pre-commit
         run: pip install pre-commit
@@ -32,14 +31,14 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check out pipeline code
-        uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4
+        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
 
       - name: Install Nextflow
-        uses: nf-core/setup-nextflow@v1
+        uses: nf-core/setup-nextflow@v2
 
-      - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5
+      - uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5
         with:
-          python-version: "3.11"
+          python-version: "3.12"
           architecture: "x64"
 
       - name: Install dependencies
@@ -60,7 +59,7 @@ jobs:
 
       - name: Upload linting log file artifact
         if: ${{ always() }}
-        uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4
+        uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4
         with:
           name: linting-logs
           path: |

diff --git 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@f6b0bace624032e30a85a8fd9c1a7f8f611f5737 # v3
+        uses: dawidd6/action-download-artifact@09f2f74827fd3a8607589e5ad7f9398816f540fe # v3
         with:
           workflow: linting.yml
           workflow_conclusion: completed

diff --git a/.nf-core.yml b/.nf-core.yml
@@ -1,23 +1,24 @@
+nf_core_version: 2.14.1
 lint:
   files_exist:
-  - CODE_OF_CONDUCT.md
-  - assets/nf-core-neoantigenpipeline_logo_light.png
-  - docs/images/nf-core-neoantigenpipeline_logo_light.png
-  - docs/images/nf-core-neoantigenpipeline_logo_dark.png
-  - .github/ISSUE_TEMPLATE/config.yml
-  - .github/workflows/awstest.yml
-  - .github/workflows/awsfulltest.yml
+    - CODE_OF_CONDUCT.md
+    - assets/nf-core-neoantigenpipeline_logo_light.png
+    - docs/images/nf-core-neoantigenpipeline_logo_light.png
+    - docs/images/nf-core-neoantigenpipeline_logo_dark.png
+    - .github/ISSUE_TEMPLATE/config.yml
+    - .github/workflows/awstest.yml
+    - .github/workflows/awsfulltest.yml
   files_unchanged:
-  - CODE_OF_CONDUCT.md
-  - assets/nf-core-neoantigenpipeline_logo_light.png
-  - docs/images/nf-core-neoantigenpipeline_logo_light.png
-  - docs/images/nf-core-neoantigenpipeline_logo_dark.png
-  - .github/ISSUE_TEMPLATE/bug_report.yml
+    - CODE_OF_CONDUCT.md
+    - assets/nf-core-neoantigenpipeline_logo_light.png
+    - docs/images/nf-core-neoantigenpipeline_logo_light.png
+    - docs/images/nf-core-neoantigenpipeline_logo_dark.png
+    - .github/ISSUE_TEMPLATE/bug_report.yml
   multiqc_config:
-  - report_comment
+    - report_comment
   nextflow_config:
-  - manifest.name
-  - manifest.homePage
+    - manifest.name
+    - manifest.homePage
 repository_type: pipeline
 template:
   prefix: mskcc

diff --git a/.prettierignore b/.prettierignore
@@ -10,3 +10,4 @@ testing/
 testing*
 *.pyc
 bin/
+README.md
diff --git a/CITATIONS.md b/CITATIONS.md
@@ -10,13 +10,20 @@
 
 ## Pipeline tools
 
-- [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
+- [Phylowgs](https://github.com/morrislab/phylowgs)
 
-  > Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
+  > Deshwar, A. G., Vembu, S., Yung, C. K., Jang, G. H., Stein, L., & Morris, Q. (2015). PhyloWGS: reconstructing subclonal composition and evolution from whole-genome sequencing of tumors. Genome biology, 16(1), 35. https://doi.org/10.1186/s13059-015-0602-8
 
-- [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
+- [NetMHCPan-4](https://services.healthtech.dtu.dk/services/NetMHCpan-4.1/)
 
-  > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
+  > Jurtz, V., Paul, S., Andreatta, M., Marcatili, P., Peters, B., & Nielsen, M. (2017). NetMHCpan-4.0: Improved Peptide-MHC Class I Interaction Predictions Integrating Eluted Ligand and Peptide Binding Affinity Data. Journal of immunology (Baltimore, Md. : 1950), 199(9), 3360–3368. https://doi.org/10.4049/jimmunol.1700893
+
+- [NeoantigenEditing](https://github.com/LukszaLab/NeoantigenEditing)
+
+  > Łuksza, M., Sethna, Z.M., Rojas, L.A. et al. Neoantigen quality predicts immunoediting in survivors of pancreatic cancer. Nature 606, 389–395 (2022). https://doi.org/10.1038/s41586-022-04735-9
+
+- [NetMHCPanStab](https://services.healthtech.dtu.dk/services/NetMHCstabpan-1.0/)
+  > Rasmussen, M., Fenoy, E., Harndahl, M., Kristensen, A. B., Nielsen, I. K., Nielsen, M., & Buus, S. (2016). Pan-Specific Prediction of Peptide-MHC Class I Complex Stability, a Correlate of T Cell Immunogenicity. Journal of immunology (Baltimore, Md. : 1950), 197(4), 1517–1524. https://doi.org/10.4049/jimmunol.1600582
 
 ## Software packaging/containerisation tools
 

diff --git a/README.md b/README.md
@@ -1,29 +1,22 @@
-[![GitHub Actions CI Status](https://github.com/mskcc/neoantigenpipeline/actions/workflows/ci.yml/badge.svg)](https://github.com/mskcc/neoantigenpipeline/actions/workflows/ci.yml)
-[![GitHub Actions Linting Status](https://github.com/mskcc/neoantigenpipeline/actions/workflows/linting.yml/badge.svg)](https://github.com/mskcc/neoantigenpipeline/actions/workflows/linting.yml)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX)
-[![nf-test](https://img.shields.io/badge/unit_tests-nf--test-337ab7.svg)](https://www.nf-test.com)
+> [![GitHub Actions CI Status](https://github.com/mskcc/neoantigen-pipeline/actions/workflows/ci.yml/badge.svg)](https://github.com/mskcc/neoantigen-pipeline/actions/workflows/ci.yml) > [![GitHub Actions Linting Status](https://github.com/mskcc/neoantigen-pipeline/actions/workflows/linting.yml/badge.svg)](https://github.com/mskcc/neoantigen-pipeline/actions/workflows/linting.yml) > [![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 Seqera Platform](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Seqera%20Platform-%234256e7)](https://tower.nf/launch?pipeline=https://github.com/mskcc/neoantigenpipeline)
+[![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/mskcc/neoantigen-pipeline)
 
 ## Introduction
 
-**mskcc/neoantigenpipeline** is a bioinformatics pipeline that ...
+**mskcc/neoantigenpipeline** is a bioinformatics pipeline that adapts Luksza et al.'s neoantigenEditing and fitness pipeline for usage by investigators in MSK. The pipeline curently supports working with TEMPO output mafs, Facets gene-level copy number calls, and Polysolver outputs. It outputs a json representation of the clonal structure of the tumor annotated with neoantigen burden, driver burden, and fitness of the clone. Also individual neoantigens are labeled with the quality of the neoantigen as described by Luksza et al.
 
-<!-- TODO nf-core:
-   Complete this sentence with a 2-3 sentence summary of what types of data the pipeline ingests, a brief overview of the
-   major pipeline sections and the types of output it produces. You're giving an overview to someone new
-   to nf-core here, in 15-20 seconds. For an example, see https://github.com/nf-core/rnaseq/blob/master/README.md#introduction
--->
+![Workflow Diagram](assets/workflow_diagram.png)
 
-<!-- TODO nf-core: Include a figure that guides the user through the major workflow steps. Many nf-core
-     workflows use the "tube map" design for that. See https://nf-co.re/docs/contributing/design_guidelines#examples for examples.   -->
-<!-- TODO nf-core: Fill in short bullet-pointed list of the default steps in the pipeline -->
 
-1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
-2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
+1. Create phylogenetic trees using [PhyloWGS](https://genomebiology.biomedcentral.com/articles/10.1186/s13059-015-0602-8)
+2. Use [netMHCpan-4](https://services.healthtech.dtu.dk/services/NetMHCpan-4.1/) to calculate binding affinities 
+3. Use [netMHCpanStab](https://services.healthtech.dtu.dk/services/NetMHCstabpan-1.0/) to calculate stability scores 
+4. Use Luksza et al.'s neoantigen quality and fitness computations tool ([NeoantigenEditing](https://github.com/LukszaLab/NeoantigenEditing)) to evaluate peptides
 
 ## Usage
 
@@ -38,12 +31,10 @@ First, prepare a samplesheet with your input data that looks as follows:
 `samplesheet.csv`:
 
 ```csv
-sample,fastq_1,fastq_2
-CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz
+sample,maf,facets_hisens_cncf,hla_file
+tumor_normal,temp_test_somatic_unfiltered.maf,facets_hisens.cncf.txt,winners.hla.txt
+tumor_normal2,temp_test_somatic_unfiltered.maf,facets_hisens.cncf.txt,winners.hla.txt
 ```
-
-Each row represents a fastq file (single-end) or a pair of fastq files (paired end).
-
 -->
 
 Now, you can run the pipeline using:
@@ -52,7 +43,7 @@ Now, you can run the pipeline using:
 
 ```bash
 nextflow run mskcc/neoantigenpipeline \
-   -profile <docker/singularity/.../institute> \
+   -profile prod,<docker/singularity> \
    --input samplesheet.csv \
    --outdir <OUTDIR>
 ```
@@ -63,22 +54,27 @@ nextflow run mskcc/neoantigenpipeline \
 
 ## Credits
 
-mskcc/neoantigenpipeline was originally written by Nikhil Kumar.
-
 We thank the following people for their extensive assistance in the development of this pipeline:
 
-<!-- TODO nf-core: If applicable, make list of people who have also contributed -->
+ - Nikhil ([@nikhil](https://github.com/nikhil))
+ - John ([@johnoooh](https://github.com/johnoooh))
+ - Alex ([@pintoa1-mskcc](https://github.com/pintoa1-mskcc))
+ - Martina ([@BradicM](https://github.com/BradicM))
+ - Allison ([@arichards2564](https://github.com/arichards2564))
+
 
 ## Contributions and Support
 
 If you would like to contribute to this pipeline, please see the [contributing guidelines](.github/CONTRIBUTING.md).
 
 ## Citations
 
-<!-- TODO nf-core: Add citation for pipeline after first release. Uncomment lines below and update Zenodo doi and badge at the top of this file. -->
-<!-- If you use mskcc/neoantigenpipeline for your analysis, please cite it using the following doi: [10.5281/zenodo.XXXXXX](https://doi.org/10.5281/zenodo.XXXXXX) -->
 
-<!-- TODO nf-core: Add bibliography of tools and data used in your pipeline -->
+- Deshwar, A. G., Vembu, S., Yung, C. K., Jang, G. H., Stein, L., & Morris, Q. (2015). PhyloWGS: reconstructing subclonal composition and evolution from whole-genome sequencing of tumors. Genome biology, 16(1), 35. https://doi.org/10.1186/s13059-015-0602-8
+- Jurtz, V., Paul, S., Andreatta, M., Marcatili, P., Peters, B., & Nielsen, M. (2017). NetMHCpan-4.0: Improved Peptide-MHC Class I Interaction Predictions Integrating Eluted Ligand and Peptide Binding Affinity Data. Journal of immunology (Baltimore, Md. : 1950), 199(9), 3360–3368. https://doi.org/10.4049/jimmunol.1700893
+- Łuksza, M., Sethna, Z.M., Rojas, L.A. et al. Neoantigen quality predicts immunoediting in survivors of pancreatic cancer. Nature 606, 389–395 (2022). https://doi.org/10.1038/s41586-022-04735-9
+- Rasmussen, M., Fenoy, E., Harndahl, M., Kristensen, A. B., Nielsen, I. K., Nielsen, M., & Buus, S. (2016). Pan-Specific Prediction of Peptide-MHC Class I Complex Stability, a Correlate of T Cell Immunogenicity. Journal of immunology (Baltimore, Md. : 1950), 197(4), 1517–1524. https://doi.org/10.4049/jimmunol.1600582
+
 
 An extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.
 

diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml
@@ -1,8 +1,8 @@
 report_comment: >
-  
+
   This report has been generated by the <a href="https://github.com/mskcc/neoantigenpipeline/releases/tag/1.0.0" target="_blank">mskcc/neoantigenpipeline</a>
   analysis pipeline.
-  
+
 report_section_order:
   "mskcc-neoantigenpipeline-methods-description":
     order: -1000

diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv
@@ -1,3 +1,3 @@
-sample,fastq_1,fastq_2
-SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,
+sample,maf,facets_hisens_cncf,hla_file
+tumor_normal,https://raw.githubusercontent.com/mskcc-omics-workflows/test-datasets/neoantigen/neoantigen/temp_test_somatic_unfiltered.maf,https://raw.githubusercontent.com/mskcc-omics-workflows/test-datasets/neoantigen/neoantigen/facets_hisens.cncf.txt,https://raw.githubusercontent.com/mskcc-omics-workflows/test-datasets/neoantigen/neoantigen/winners.hla.txt
+tumor_normal2,https://raw.githubusercontent.com/mskcc-omics-workflows/test-datasets/neoantigen/neoantigen/temp_test_somatic_unfiltered.maf,https://raw.githubusercontent.com/mskcc-omics-workflows/test-datasets/neoantigen/neoantigen/facets_hisens.cncf.txt,https://raw.githubusercontent.com/mskcc-omics-workflows/test-datasets/neoantigen/neoantigen/winners.hla.txt