[Do not merge!] Pseudo PR for first release

.github/workflows/ci.yml

@@ -1,5 +1,5 @@
-name: nf-core CI
 # This workflow runs the pipeline with the minimal test dataset to check that it completes without any syntax errors
+name: nf-core CI
 on:
   push:
     branches:
@@ -11,6 +11,7 @@ on:
 
 env:
   NXF_ANSI_LOG: false
+  NFT_VER: "0.9.0"
   NXF_SINGULARITY_CACHEDIR: ${{ github.workspace }}/.singularity
   NXF_SINGULARITY_LIBRARYDIR: ${{ github.workspace }}/.singularity
 
@@ -19,28 +20,125 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  test:
-    name: "Run pipeline with test data (${{ matrix.NXF_VER }} | ${{ matrix.test_name }} | ${{ matrix.profile }})"
+  test_profile_standard:
+    name: nf-test with standard profiles
     # Only run on push if this is the nf-core dev branch (merged PRs)
     if: "${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/metapep') }}"
     runs-on: ubuntu-latest
     strategy:
+      fail-fast: false
       matrix:
         NXF_VER:
           - "24.04.2"
           - "latest-everything"
         profile:
-          - "conda"
+          # - "conda"
           - "docker"
           - "singularity"
         test_name:
           - "test"
+          - "test_model_information"
+          - "test_mouse_all_pep_lengths"
+          - "test_assembly_only"
+          - "test_bins_only"
+          - "test_coassembly"
+          - "test_mhcflurry"
+          - "test_mhcnuggets_1"
+          - "test_mhcnuggets_2"
         isMaster:
           - ${{ github.base_ref == 'master' }}
         # Exclude conda and singularity on dev
         exclude:
+          # - isMaster: false
+          #  profile: "conda"
           - isMaster: false
-            profile: "conda"
+            profile: "singularity"
+
+    steps:
+      - name: Check out pipeline code
+        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
+
+      - name: Set up Nextflow
+        uses: nf-core/setup-nextflow@v2
+        with:
+          version: "${{ matrix.NXF_VER }}"
+
+      - name: Set up Apptainer
+        if: matrix.profile == 'singularity'
+        uses: eWaterCycle/setup-apptainer@main
+
+      - name: Set up Singularity
+        if: matrix.profile == 'singularity'
+        run: |
+          mkdir -p $NXF_SINGULARITY_CACHEDIR
+          mkdir -p $NXF_SINGULARITY_LIBRARYDIR
+
+      - name: Set up Miniconda
+        if: matrix.profile == 'conda'
+        uses: conda-incubator/setup-miniconda@a4260408e20b96e80095f42ff7f1a15b27dd94ca # v3
+        with:
+          miniconda-version: "latest"
+          auto-update-conda: true
+          conda-solver: libmamba
+          channels: conda-forge,bioconda
+
+      - name: Set up Conda
+        if: matrix.profile == 'conda'
+        run: |
+          echo $(realpath $CONDA)/condabin >> $GITHUB_PATH
+          echo $(realpath python) >> $GITHUB_PATH
+
+      - name: Clean up Disk space
+        uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
+
+      - name: Install nf-test
+        uses: nf-core/setup-nf-test@v1
+        with:
+          version: ${{ env.NFT_VER }}
+
+      - name: Run nf-test
+        run: |
+          nf-test test --tag ${{ matrix.test_name }} --profile ${{ matrix.test_name }},${{ matrix.profile }} --junitxml=test.xml --verbose
+
+      - name: Output log on failure
+        if: failure()
+        run: |
+          sudo apt install bat > /dev/null
+          batcat --decorations=always --color=always ${{ github.workspace }}/.nf-test/tests/*/output/pipeline_info/software_versions.yml
+
+      - name: Publish Test Report
+        uses: mikepenz/action-junit-report@v3
+        if: always() # always run even if the previous step fails
+        with:
+          report_paths: "*.xml"
+
+  test_profile_download:
+    name: nf-test with profiles needing entrez downloads
+    # Only run on PRs from branches of nf-core/metapep repository or on push if this is the nf-core dev branch (merged PRs)
+    # (GitHub secrets are not accessible for workflows from forks)
+    if: "${{ github.event.pull_request.head.repo.full_name == 'nf-core/metapep' || (github.event_name == 'push' && github.repository == 'nf-core/metapep') }}"
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        NXF_VER:
+          - "24.04.2"
+          - "latest-everything"
+        profile:
+          # - "conda"
+          - "docker"
+          - "singularity"
+        test_name:
+          - "test_all"
+          - "test_mouse"
+          - "test_taxa_only"
+          - "test_taxa_specific_assembly"
+        isMaster:
+          - ${{ github.base_ref == 'master' }}
+        # Exclude conda and singularity on dev
+        exclude:
+          # - isMaster: false
+          #   profile: "conda"
           - isMaster: false
             profile: "singularity"
     steps:
@@ -80,6 +178,28 @@ jobs:
       - name: Clean up Disk space
         uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
 
-      - name: "Run pipeline with test data ${{ matrix.NXF_VER }} | ${{ matrix.test_name }} | ${{ matrix.profile }}"
+      - name: Install nf-test
+        uses: nf-core/setup-nf-test@v1
+        with:
+          version: ${{ env.NFT_VER }}
+
+      - name: Run nf-test
+        env:
+          NCBI_EMAIL: ${{ secrets.NCBI_EMAIL }}
+          NCBI_KEY: ${{ secrets.NCBI_KEY }}
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.test_name }},${{ matrix.profile }} --outdir ./results
+          nextflow secrets set NCBI_EMAIL ${{ secrets.NCBI_EMAIL }}
+          nextflow secrets set NCBI_KEY ${{ secrets.NCBI_KEY }}
+          nf-test test --tag ${{ matrix.test_name }} --profile ${{ matrix.test_name }},${{ matrix.profile }} --junitxml=test.xml --verbose
+
+      - name: Output log on failure
+        if: failure()
+        run: |
+          sudo apt install bat > /dev/null
+          batcat --decorations=always --color=always ${{ github.workspace }}/.nf-test/tests/*/output/pipeline_info/software_versions.yml
+
+      - name: Publish Test Report
+        uses: mikepenz/action-junit-report@v3
+        if: always() # always run even if the previous step fails
+        with:
+          report_paths: "*.xml"

.gitignore

@@ -6,4 +6,7 @@ results/
 testing/
 testing*
 *.pyc
+.nf-test/
+results_test/*
+.nf-test*
 null/

.nf-core.yml

@@ -3,6 +3,8 @@ lint:
   actions_ci: false
   files_exist:
     - conf/igenomes.config
+  files_unchanged:
+    - .gitignore
 nf_core_version: 3.0.2
 org_path: null
 repository_type: pipeline
@@ -14,6 +16,8 @@ template:
   name: metapep
   org: nf-core
   outdir: .
-  skip_features: null
+  skip_features:
+    - fastqc
+    - igenomes
   version: 1.0.0
 update: null

CHANGELOG.md

@@ -3,14 +3,38 @@
 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).
 
-## v1.0.0 - [date]
+## v1.0.0 - nf-core/metapep "Golden Megalodon" - [2022-01-20]
 
-Initial release of nf-core/metapep, created with the [nf-core](https://nf-co.re/) template.
+First release of [nf-core/metapep](https://nf-co.re/metapep), based on [nf-core](https://nf-co.re) standards and [nf-core/tools](https://nf-co.re/tools) template version 1.14.1.
 
 ### `Added`
 
-### `Fixed`
+- Download proteins for input type taxa from [Entrez](https://www.ncbi.nlm.nih.gov/Web/Search/entrezfs.html).
+- Predict proteins for input type assembly or bins using [Prodigal](https://github.com/hyattpd/Prodigal).
+- Generate peptides from proteins.
+- Split peptide files into chunks for parallel prediction and report stats.
+- Predict epitopes for given alleles and peptides using [SYFPEITHI](http://www.syfpeithi.de), [MHCflurry](https://github.com/openvax/mhcflurry) or [MHCnuggets](https://github.com/KarchinLab/mhcnuggets).
+- Downstream visualizations between conditions (different microbiomes assemblies, bins, taxids or same input class with different weights) given within samplesheet
+  - binding affinities
+  - entity binding ratios
+- Summarize workflow using MultiQC
 
-### `Dependencies`
+- Relational datamodel to handle large amounts of data
+  Tables defined within model:
 
-### `Deprecated`
+  - `alleles.tsv`
+  - `condition_alleles.tsv`
+  - `conditions.tsv`
+  - `entities_proteins.tsv`
+  - `entities.tsv`
+  - `microbiomes_entities.no_weights.tsv`
+  - `microbiome_entities.nucl.tsv`
+  - `microbiomes_entities.tsv`
+  - `microbiomes.tsv`
+  - `preptides.tsv.gz`
+  - `predictions.tsv.gz`
+  - `proteins_peptides.tsv`
+  - `proteins.tsv.gz`
+  - `stats.txt`
+
+- Additional subworkflow to fetch possible model and peptide lengths for the prediction tools

CITATIONS.md

@@ -8,15 +8,89 @@
 
 > Di Tommaso P, Chatzou M, Floden EW, Barja PP, Palumbo E, Notredame C. Nextflow enables reproducible computational workflows. Nat Biotechnol. 2017 Apr 11;35(4):316-319. doi: 10.1038/nbt.3820. PubMed PMID: 28398311.
 
+## [nf-test](https://www.biorxiv.org/content/10.1101/2024.05.25.595877v1)
+
+> L. Forer, S. Schönherr Improving the Reliability and Quality of Nextflow Pipelines with nf-test. bioRxiv 2024.05.25.595877; doi: 10.1101/2024.05.25.595877
+
 ## Pipeline tools
 
-- [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
+- [Entrez](https://pubmed.ncbi.nlm.nih.gov/15608257/)
+
+  > Maglott D, Ostell J, Pruitt KD, Tatusova T. Entrez Gene: gene-centered information at NCBI. Nucleic Acids Res. 2005 Jan 1;33(Database issue):D54-8. doi: 10.1093/nar/gki031. Update in: Nucleic Acids Res. 2007 Jan;35(Database issue):D26-31. PMID: 15608257; PMCID: PMC539985.
+
+- [Epytope](https://academic.oup.com/bioinformatics/article/32/13/2044/1743767)
+
+  > Schubert, B., Walzer, M., Brachvogel, H-P., Sozolek, A., Mohr, C., and Kohlbacher, O. (2016). FRED 2 - An Immunoinformatics Framework for Python. Bioinformatics 2016; doi: 10.1093/bioinformatics/btw113
 
-> Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
+- [MHCflurry](https://dx.doi.org/10.1016/j.cels.2018.05.014)
+
+  > Timothy J. O’Donnell, Alex Rubinsteyn, Maria Bonsack, Angelika B. Riemer, Uri Laserson, Jeff Hammerbacher. MHC flurry: open-source class I MHC binding affinity prediction. Cell systems 7(1), 129-132 (2018). doi: 10.1016/j.cels.2018.05.014.
+
+- [MHCnuggets](https://dx.doi.org/10.1158/2326-6066.CIR-19-0464)
+
+  > Xiaoshan M. Shao, Rohit Bhattacharya, Justin Huang, I.K. Ashok Sivakumar, Collin Tokheim, Lily Zheng, Dylan Hirsch, Benjamin Kaminow, Ashton Omdahl, Maria Bonsack, Angelika B. Riemer, Victor E. Velculescu, Valsamo Anagnostou, Kymberleigh A. Pagel and Rachel Karchin. High-throughput prediction of MHC class i and ii neoantigens with MHCnuggets. Cancer Immunology Research 8(3), 396-408 (2020). doi: 10.1158/2326-6066.CIR-19-0464.
 
 - [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
 
-> Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
+  > 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.
+
+- [pigz](https://zlib.net/pigz/)
+
+- [Prodigal](https://pubmed.ncbi.nlm.nih.gov/20211023/)
+
+  > Hyatt D, Chen GL, Locascio PF, Land ML, Larimer FW, Hauser LJ. Prodigal: prokaryotic gene recognition and translation initiation site identification. BMC Bioinformatics. 2010 Mar 8;11:119. doi: 10.1186/1471-2105-11-119. PMID: 20211023; PMCID: PMC2848648.
+
+- [SYFPEITHI](https://pubmed.ncbi.nlm.nih.gov/10602881/)
+
+  > Hans-Georg Rammensee, Jutta Bachmann, Niels Nikolaus Emmerich, Oskar Alexander Bachor, Stefan Stevanovic: SYFPEITHI: database for MHC ligands and peptide motifs. Immunogenetics (1999) 50: 213-219
+
+## Python Packages
+
+- [Python](https://www.python.org/)
+
+  > Python Core Team (2022). Python: A dynamic, open source programming language. Python Software Foundation. https://www.python.org/.
+
+- [biopython](https://academic.oup.com/bioinformatics/article/25/11/1422/330687)
+
+  > Cock PA, Antao T, Chang JT, Chapman BA, Cox CJ, Dalke A, Friedberg I, Hamelryck T, Kauff F, Wilczynski B and de Hoon MJL (2009) Biopython: freely available Python tools for computational molecular biology and bioinformatics. Bioinformatics, 25, 1422-1423. https://doi.org/10.1093/bioinformatics/btp163.
+
+- [numpy](https://www.nature.com/articles/s41586-020-2649-2)
+
+  > Harris, C.R., Millman, K.J., van der Walt, S.J. et al. Array programming with NumPy. Nature 585, 357–362 (2020). DOI: 10.1038/s41586-020-2649-2. https://www.nature.com/articles/s41586-020-2649-2.
+
+- [pandas](https://doi.org/10.5281/zenodo.3509134)
+
+  > The pandas development team. (2023). pandas-dev/pandas: Pandas (v2.0.3). Zenodo. https://doi.org/10.5281/zenodo.8092754
+
+## R Packages
+
+- [R](https://www.R-project.org/)
+
+  > R Core Team (2022). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. https://www.R-project.org/.
+
+- [data.table](https://cran.r-project.org/package=data.table)
+
+  > Dowle Matt (2022). data.table: Extension of 'data.frame'.
+
+- [dplyr](https://dplyr.tidyverse.org)
+
+  > Wickham H, François R, Henry L, Müller K, Vaughan D (2023). dplyr: A Grammar of Data Manipulation. https://dplyr.tidyverse.org, https://github.com/tidyverse/dplyr.
+
+- [ggplot2](https://cran.r-project.org/package=ggplot2)
+
+  > H. Wickham (2016). ggplot2: Elegant Graphics for Data Analysis. Springer-Verlag New York.
+
+- [ggpubr](https://cran.r-project.org/package=ggpubr)
+
+  > Kassambara Alboukadel (2023). ggpubr: 'ggplot2' Based Publication Ready Plots.
+
+- [optparse](https://CRAN.R-project.org/package=optparse)
+
+  > Trevor L Davis (2022). optparse: Command Line Option Parser.
+
+- [stringr](https://stringr.tidyverse.org)
+
+  > Wickham H (2022). stringr: Simple, Consistent Wrappers for Common String Operations. https://stringr.tidyverse.org, https://github.com/tidyverse/stringr.
 
 ## Software packaging/containerisation tools