diff --git a/.devcontainer/devcontainer.json b/.devcontainer/devcontainer.json index ea27a58..4ecfbfe 100644 --- a/.devcontainer/devcontainer.json +++ b/.devcontainer/devcontainer.json @@ -2,6 +2,7 @@ "name": "nfcore", "image": "nfcore/gitpod:latest", "remoteUser": "gitpod", + "runArgs": ["--privileged"], // Configure tool-specific properties. "customizations": { diff --git a/.editorconfig b/.editorconfig index b78de6e..dd9ffa5 100644 --- a/.editorconfig +++ b/.editorconfig @@ -8,7 +8,7 @@ trim_trailing_whitespace = true indent_size = 4 indent_style = space -[*.{md,yml,yaml,html,css,scss,js,cff}] +[*.{md,yml,yaml,html,css,scss,js}] indent_size = 2 # These files are edited and tested upstream in nf-core/modules @@ -18,7 +18,20 @@ 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 + +# ignore Readme +[README.md] +indent_style = unset + +# ignore python +[*.{py,md}] +indent_style = unset diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md index efea5c1..98cc2fc 100644 --- a/.github/CONTRIBUTING.md +++ b/.github/CONTRIBUTING.md @@ -9,7 +9,9 @@ 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 ;) -> If you need help using or modifying nf-core/epitopeprediction then the best place to ask is on the nf-core Slack [#epitopeprediction](https://nfcore.slack.com/channels/epitopeprediction) channel ([join our Slack here](https://nf-co.re/join/slack)). +:::info +If you need help using or modifying nf-core/epitopeprediction then the best place to ask is on the nf-core Slack [#epitopeprediction](https://nfcore.slack.com/channels/epitopeprediction) channel ([join our Slack here](https://nf-co.re/join/slack)). +::: ## Contribution workflow @@ -25,6 +27,9 @@ 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 `. + 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. @@ -116,4 +121,3 @@ To get started: Devcontainer specs: - [DevContainer config](.devcontainer/devcontainer.json) -- [Dockerfile](.devcontainer/Dockerfile) diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml index 046680a..ad03c10 100644 --- a/.github/ISSUE_TEMPLATE/bug_report.yml +++ b/.github/ISSUE_TEMPLATE/bug_report.yml @@ -42,9 +42,9 @@ body: attributes: label: System information description: | - * Nextflow version _(eg. 22.10.1)_ + * 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 or Charliecloud)_ + * Container engine: _(e.g. Docker, Singularity, Conda, Podman, Shifter, Charliecloud, or Apptainer)_ * OS _(eg. CentOS Linux, macOS, Linux Mint)_ * Version of nf-core/epitopeprediction _(eg. 1.1, 1.5, 1.8.2)_ diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index e530977..754539c 100644 --- a/.github/PULL_REQUEST_TEMPLATE.md +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -15,9 +15,11 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/epit - [ ] This comment contains a description of changes (with reason). - [ ] If you've fixed a bug or added code that should be tested, add tests! -- [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/epitopeprediction/tree/master/.github/CONTRIBUTING.md)- [ ] If necessary, also make a PR on the nf-core/epitopeprediction _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository. +- [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/epitopeprediction/tree/master/.github/CONTRIBUTING.md) +- [ ] If necessary, also make a PR on the nf-core/epitopeprediction _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 `). +- [ ] 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. - [ ] `CHANGELOG.md` is updated. diff --git a/.github/workflows/awsfulltest.yml b/.github/workflows/awsfulltest.yml index 6b2e17e..6fc0856 100644 --- a/.github/workflows/awsfulltest.yml +++ b/.github/workflows/awsfulltest.yml @@ -14,18 +14,23 @@ jobs: runs-on: ubuntu-latest steps: - name: Launch workflow via tower - uses: nf-core/tower-action@v3 + uses: seqeralabs/action-tower-launch@922e5c8d5ac4e918107ec311d2ebbd65e5982b3d # v2 with: workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} access_token: ${{ secrets.TOWER_ACCESS_TOKEN }} compute_env: ${{ secrets.TOWER_COMPUTE_ENV }} + revision: ${{ github.sha }} workdir: s3://${{ secrets.AWS_S3_BUCKET }}/work/epitopeprediction/work-${{ github.sha }} parameters: | { + "hook_url": "${{ secrets.MEGATESTS_ALERTS_SLACK_HOOK_URL }}", "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/epitopeprediction/results-${{ github.sha }}" } - profiles: test_full,aws_tower - - uses: actions/upload-artifact@v3 + profiles: test_full + + - uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4 with: name: Tower debug log file - path: tower_action_*.log + path: | + tower_action_*.log + tower_action_*.json diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml index 3d1d8b9..6e4dc60 100644 --- a/.github/workflows/awstest.yml +++ b/.github/workflows/awstest.yml @@ -12,18 +12,22 @@ jobs: steps: # Launch workflow using Tower CLI tool action - name: Launch workflow via tower - uses: nf-core/tower-action@v3 + uses: seqeralabs/action-tower-launch@922e5c8d5ac4e918107ec311d2ebbd65e5982b3d # v2 with: workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} access_token: ${{ secrets.TOWER_ACCESS_TOKEN }} compute_env: ${{ secrets.TOWER_COMPUTE_ENV }} + revision: ${{ github.sha }} workdir: s3://${{ secrets.AWS_S3_BUCKET }}/work/epitopeprediction/work-${{ github.sha }} parameters: | { "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/epitopeprediction/results-test-${{ github.sha }}" } - profiles: test,aws_tower - - uses: actions/upload-artifact@v3 + profiles: test + + - uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4 with: name: Tower debug log file - path: tower_action_*.log + path: | + tower_action_*.log + tower_action_*.json diff --git a/.github/workflows/branch.yml b/.github/workflows/branch.yml index 28af178..a468112 100644 --- a/.github/workflows/branch.yml +++ b/.github/workflows/branch.yml @@ -13,13 +13,13 @@ jobs: - name: Check PRs if: github.repository == 'nf-core/epitopeprediction' run: | - { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/epitopeprediction ]] && [[ $GITHUB_HEAD_REF = "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]] + { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/epitopeprediction ]] && [[ $GITHUB_HEAD_REF == "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]] # If the above check failed, post a comment on the PR explaining the failure # NOTE - this doesn't currently work if the PR is coming from a fork, due to limitations in GitHub actions secrets - name: Post PR comment if: failure() - uses: mshick/add-pr-comment@v1 + uses: mshick/add-pr-comment@b8f338c590a895d50bcbfa6c5859251edc8952fc # v2 with: message: | ## This PR is against the `master` branch :x: diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 0da72f1..6859253 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -24,17 +24,20 @@ jobs: strategy: matrix: NXF_VER: - - "22.10.1" + - "23.04.0" - "latest-everything" steps: - name: Check out pipeline code - uses: actions/checkout@v3 + uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4 - name: Install Nextflow - uses: nf-core/setup-nextflow@v1 + uses: nf-core/setup-nextflow@b9f764e8ba5c76b712ace14ecbfcef0e40ae2dd8 # v1 with: version: "${{ matrix.NXF_VER }}" + - name: Disk space cleanup + uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1 + - name: Run pipeline with test data run: | nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results @@ -42,40 +45,22 @@ jobs: name: Run profile tests if: ${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/epitopeprediction') }} runs-on: ubuntu-latest - env: - NXF_VER: ${{ matrix.nxf_ver }} - NXF_ANSI_LOG: false strategy: matrix: - include: - # Test pipeline minimum Nextflow version - - NXF_VER: "22.10.1" - NXF_EDGE: "" - # Test latest edge release of Nextflow - - NXF_VER: "" - NXF_EDGE: "1" + NXF_VER: + - "23.04.0" + - "latest-everything" tests: - [ - "test_variant_tsv", - "test_grch38_variant_tsv", - "test_peptides", - "test_peptides_h2", - "test_proteins", - "test_mhcnuggets", - "test_mhcflurry", - ] + ["test_grch38", "test_peptides", "test_peptides_h2", "test_proteins", "test_mhcnuggets", "test_mhcflurry"] steps: - name: Check out pipeline code - uses: actions/checkout@v2 + uses: actions/checkout@v3 + - name: Install Nextflow - env: - NXF_VER: ${{ matrix.NXF_VER }} - # Uncomment only if the edge release is more recent than the latest stable release - # See https://github.com/nextflow-io/nextflow/issues/2467 - # NXF_EDGE: ${{ matrix.NXF_EDGE }} - run: | - wget -qO- get.nextflow.io | bash - sudo mv nextflow /usr/local/bin/ + uses: nf-core/setup-nextflow@v1 + with: + version: "${{ matrix.NXF_VER }}" + - name: Run pipeline with profile ${{ matrix.tests }} run: | nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.tests }},docker --outdir ./results @@ -84,20 +69,14 @@ jobs: name: Run NetMHC tool family tests if: ${{ ( github.event_name == 'push' && github.repository == 'nf-core/epitopeprediction' ) || github.event.pull_request.head.repo.full_name == 'nf-core/epitopeprediction' }} runs-on: ubuntu-latest - env: - NXF_VER: ${{ matrix.nxf_ver }} strategy: matrix: - include: - # Test pipeline minimum Nextflow version - - NXF_VER: "22.10.1" - NXF_EDGE: "" - # Test latest edge release of Nextflow - - NXF_VER: "" - NXF_EDGE: "1" + NXF_VER: + - "23.04.0" + - "latest-everything" steps: - name: Check out pipeline code - uses: actions/checkout@v2 + uses: actions/checkout@v3 - name: Install non-free software env: @@ -107,14 +86,10 @@ jobs: curl -L https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/software/non-free-software.tar.gpg | ${GITHUB_WORKSPACE}/bin/decrypt | tar -C non-free -v -x - name: Install Nextflow - env: - NXF_VER: ${{ matrix.NXF_VER }} - # Uncomment only if the edge release is more recent than the latest stable release - # See https://github.com/nextflow-io/nextflow/issues/2467 - # NXF_EDGE: ${{ matrix.NXF_EDGE }} - run: | - wget -qO- get.nextflow.io | bash - sudo mv nextflow /usr/local/bin/ + uses: nf-core/setup-nextflow@v1 + with: + version: "${{ matrix.NXF_VER }}" + - name: Run pipeline with NetMHC run: | nextflow run ${GITHUB_WORKSPACE} -profile test_netmhc,docker --outdir ./results diff --git a/.github/workflows/clean-up.yml b/.github/workflows/clean-up.yml new file mode 100644 index 0000000..0b6b1f2 --- /dev/null +++ b/.github/workflows/clean-up.yml @@ -0,0 +1,24 @@ +name: "Close user-tagged issues and PRs" +on: + schedule: + - cron: "0 0 * * 0" # Once a week + +jobs: + clean-up: + runs-on: ubuntu-latest + permissions: + issues: write + pull-requests: write + steps: + - uses: actions/stale@28ca1036281a5e5922ead5184a1bbf96e5fc984e # v9 + with: + stale-issue-message: "This issue has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor. Remove stale label or add a comment otherwise this issue will be closed in 20 days." + stale-pr-message: "This PR has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor. Remove stale label or add a comment if it is still useful." + close-issue-message: "This issue was closed because it has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor and then staled for 20 days with no activity." + days-before-stale: 30 + days-before-close: 20 + days-before-pr-close: -1 + any-of-labels: "awaiting-changes,awaiting-feedback" + exempt-issue-labels: "WIP" + exempt-pr-labels: "WIP" + repo-token: "${{ secrets.GITHUB_TOKEN }}" diff --git a/.github/workflows/download_pipeline.yml b/.github/workflows/download_pipeline.yml new file mode 100644 index 0000000..f823210 --- /dev/null +++ b/.github/workflows/download_pipeline.yml @@ -0,0 +1,72 @@ +name: Test successful pipeline download with 'nf-core download' + +# Run the workflow when: +# - dispatched manually +# - when a PR is opened or reopened to master branch +# - 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 + branches: + - master + pull_request_target: + branches: + - master + +env: + NXF_ANSI_LOG: false + +jobs: + download: + runs-on: ubuntu-latest + steps: + - name: Install Nextflow + uses: nf-core/setup-nextflow@b9f764e8ba5c76b712ace14ecbfcef0e40ae2dd8 # v1 + + - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 + with: + python-version: "3.11" + architecture: "x64" + - uses: eWaterCycle/setup-singularity@931d4e31109e875b13309ae1d07c70ca8fbc8537 # v7 + with: + singularity-version: 3.8.3 + + - name: Install dependencies + run: | + python -m pip install --upgrade pip + pip install git+https://github.com/nf-core/tools.git@dev + + - name: Get the repository name and current branch set as environment variable + run: | + echo "REPO_LOWERCASE=${GITHUB_REPOSITORY,,}" >> ${GITHUB_ENV} + echo "REPOTITLE_LOWERCASE=$(basename ${GITHUB_REPOSITORY,,})" >> ${GITHUB_ENV} + echo "REPO_BRANCH=${{ github.event.inputs.testbranch || 'dev' }}" >> ${GITHUB_ENV} + + - name: Download the pipeline + env: + NXF_SINGULARITY_CACHEDIR: ./ + run: | + nf-core download ${{ env.REPO_LOWERCASE }} \ + --revision ${{ env.REPO_BRANCH }} \ + --outdir ./${{ env.REPOTITLE_LOWERCASE }} \ + --compress "none" \ + --container-system 'singularity' \ + --container-library "quay.io" -l "docker.io" -l "ghcr.io" \ + --container-cache-utilisation 'amend' \ + --download-configuration + + - name: Inspect download + run: tree ./${{ env.REPOTITLE_LOWERCASE }} + + - name: Run the downloaded pipeline + env: + NXF_SINGULARITY_CACHEDIR: ./ + NXF_SINGULARITY_HOME_MOUNT: true + run: nextflow run ./${{ env.REPOTITLE_LOWERCASE }}/$( sed 's/\W/_/g' <<< ${{ env.REPO_BRANCH }}) -stub -profile test,singularity --outdir ./results diff --git a/.github/workflows/fix-linting.yml b/.github/workflows/fix-linting.yml index 9ebf496..5b20cfe 100644 --- a/.github/workflows/fix-linting.yml +++ b/.github/workflows/fix-linting.yml @@ -4,7 +4,7 @@ on: types: [created] jobs: - deploy: + fix-linting: # Only run if comment is on a PR with the main repo, and if it contains the magic keywords if: > contains(github.event.comment.html_url, '/pull/') && @@ -13,10 +13,17 @@ jobs: runs-on: ubuntu-latest steps: # Use the @nf-core-bot token to check out so we can push later - - uses: actions/checkout@v3 + - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4 with: token: ${{ secrets.nf_core_bot_auth_token }} + # indication that the linting is being fixed + - name: React on comment + uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043 # v4 + with: + comment-id: ${{ github.event.comment.id }} + reactions: eyes + # Action runs on the issue comment, so we don't get the PR by default # Use the gh cli to check out the PR - name: Checkout Pull Request @@ -24,32 +31,59 @@ jobs: env: GITHUB_TOKEN: ${{ secrets.nf_core_bot_auth_token }} - - uses: actions/setup-node@v3 + # Install and run pre-commit + - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 + with: + python-version: 3.11 - - name: Install Prettier - run: npm install -g prettier @prettier/plugin-php + - name: Install pre-commit + run: pip install pre-commit - # Check that we actually need to fix something - - name: Run 'prettier --check' - id: prettier_status - run: | - if prettier --check ${GITHUB_WORKSPACE}; then - echo "result=pass" >> $GITHUB_OUTPUT - else - echo "result=fail" >> $GITHUB_OUTPUT - fi + - name: Run pre-commit + id: pre-commit + run: pre-commit run --all-files + continue-on-error: true - - name: Run 'prettier --write' - if: steps.prettier_status.outputs.result == 'fail' - run: prettier --write ${GITHUB_WORKSPACE} + # indication that the linting has finished + - name: react if linting finished succesfully + if: steps.pre-commit.outcome == 'success' + uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043 # v4 + with: + comment-id: ${{ github.event.comment.id }} + reactions: "+1" - name: Commit & push changes - if: steps.prettier_status.outputs.result == 'fail' + id: commit-and-push + if: steps.pre-commit.outcome == 'failure' run: | git config user.email "core@nf-co.re" git config user.name "nf-core-bot" git config push.default upstream git add . git status - git commit -m "[automated] Fix linting with Prettier" + git commit -m "[automated] Fix code linting" git push + + - name: react if linting errors were fixed + id: react-if-fixed + if: steps.commit-and-push.outcome == 'success' + uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043 # v4 + with: + comment-id: ${{ github.event.comment.id }} + reactions: hooray + + - name: react if linting errors were not fixed + if: steps.commit-and-push.outcome == 'failure' + uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043 # v4 + with: + comment-id: ${{ github.event.comment.id }} + reactions: confused + + - name: react if linting errors were not fixed + if: steps.commit-and-push.outcome == 'failure' + uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043 # v4 + with: + issue-number: ${{ github.event.issue.number }} + body: | + @${{ github.actor }} I tried to fix the linting errors, but it didn't work. Please fix them manually. + See [CI log](https://github.com/nf-core/epitopeprediction/actions/runs/${{ github.run_id }}) for more details. diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index 858d622..748b431 100644 --- a/.github/workflows/linting.yml +++ b/.github/workflows/linting.yml @@ -11,74 +11,35 @@ on: types: [published] jobs: - EditorConfig: + pre-commit: runs-on: ubuntu-latest steps: - - uses: actions/checkout@v3 + - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4 - - uses: actions/setup-node@v3 - - - name: Install editorconfig-checker - run: npm install -g editorconfig-checker - - - name: Run ECLint check - run: editorconfig-checker -exclude README.md $(find .* -type f | grep -v '.git\|.py\|.md\|json\|yml\|yaml\|html\|css\|work\|.nextflow\|build\|nf_core.egg-info\|log.txt\|Makefile') - - Prettier: - runs-on: ubuntu-latest - steps: - - uses: actions/checkout@v3 - - - uses: actions/setup-node@v3 - - - name: Install Prettier - run: npm install -g prettier - - - name: Run Prettier --check - run: prettier --check ${GITHUB_WORKSPACE} - - PythonBlack: - runs-on: ubuntu-latest - steps: - - uses: actions/checkout@v3 - - - name: Check code lints with Black - uses: psf/black@stable - - # If the above check failed, post a comment on the PR explaining the failure - - name: Post PR comment - if: failure() - uses: mshick/add-pr-comment@v1 + - name: Set up Python 3.11 + uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 with: - message: | - ## Python linting (`black`) is failing - - To keep the code consistent with lots of contributors, we run automated code consistency checks. - To fix this CI test, please run: - - * Install [`black`](https://black.readthedocs.io/en/stable/): `pip install black` - * Fix formatting errors in your pipeline: `black .` - - Once you push these changes the test should pass, and you can hide this comment :+1: + python-version: 3.11 + cache: "pip" - We highly recommend setting up Black in your code editor so that this formatting is done automatically on save. Ask about it on Slack for help! + - name: Install pre-commit + run: pip install pre-commit - Thanks again for your contribution! - repo-token: ${{ secrets.GITHUB_TOKEN }} - allow-repeats: false + - name: Run pre-commit + run: pre-commit run --all-files nf-core: runs-on: ubuntu-latest steps: - name: Check out pipeline code - uses: actions/checkout@v3 + uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4 - name: Install Nextflow - uses: nf-core/setup-nextflow@v1 + uses: nf-core/setup-nextflow@b9f764e8ba5c76b712ace14ecbfcef0e40ae2dd8 # v1 - - uses: actions/setup-python@v4 + - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 with: - python-version: "3.7" + python-version: "3.11" architecture: "x64" - name: Install dependencies @@ -99,7 +60,7 @@ jobs: - name: Upload linting log file artifact if: ${{ always() }} - uses: actions/upload-artifact@v3 + uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4 with: name: linting-logs path: | diff --git a/.github/workflows/linting_comment.yml b/.github/workflows/linting_comment.yml index 0bbcd30..b706875 100644 --- a/.github/workflows/linting_comment.yml +++ b/.github/workflows/linting_comment.yml @@ -11,7 +11,7 @@ jobs: runs-on: ubuntu-latest steps: - name: Download lint results - uses: dawidd6/action-download-artifact@v2 + uses: dawidd6/action-download-artifact@f6b0bace624032e30a85a8fd9c1a7f8f611f5737 # v3 with: workflow: linting.yml workflow_conclusion: completed @@ -21,7 +21,7 @@ jobs: run: echo "pr_number=$(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: ${{ steps.pr_number.outputs.pr_number }} diff --git a/.github/workflows/release-announcements.yml b/.github/workflows/release-announcements.yml new file mode 100644 index 0000000..c3674af --- /dev/null +++ b/.github/workflows/release-announcements.yml @@ -0,0 +1,75 @@ +name: release-announcements +# Automatic release toot and tweet anouncements +on: + release: + types: [published] + workflow_dispatch: + +jobs: + toot: + runs-on: ubuntu-latest + steps: + - name: get topics and convert to hashtags + id: get_topics + run: | + curl -s https://nf-co.re/pipelines.json | jq -r '.remote_workflows[] | select(.name == "${{ github.repository }}") | .topics[]' | awk '{print "#"$0}' | tr '\n' ' ' > $GITHUB_OUTPUT + + - uses: rzr/fediverse-action@master + with: + access-token: ${{ secrets.MASTODON_ACCESS_TOKEN }} + host: "mstdn.science" # custom host if not "mastodon.social" (default) + # GitHub event payload + # https://docs.github.com/en/developers/webhooks-and-events/webhooks/webhook-events-and-payloads#release + message: | + Pipeline release! ${{ github.repository }} v${{ github.event.release.tag_name }} - ${{ github.event.release.name }}! + + 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@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 + with: + python-version: "3.10" + - name: Install dependencies + run: pip install tweepy==4.14.0 + - name: Send tweet + shell: python + run: | + import os + import tweepy + + client = tweepy.Client( + access_token=os.getenv("TWITTER_ACCESS_TOKEN"), + access_token_secret=os.getenv("TWITTER_ACCESS_TOKEN_SECRET"), + consumer_key=os.getenv("TWITTER_CONSUMER_KEY"), + consumer_secret=os.getenv("TWITTER_CONSUMER_SECRET"), + ) + tweet = os.getenv("TWEET") + client.create_tweet(text=tweet) + env: + TWEET: | + Pipeline release! ${{ github.repository }} v${{ github.event.release.tag_name }} - ${{ github.event.release.name }}! + + Please see the changelog: ${{ github.event.release.html_url }} + TWITTER_CONSUMER_KEY: ${{ secrets.TWITTER_CONSUMER_KEY }} + TWITTER_CONSUMER_SECRET: ${{ secrets.TWITTER_CONSUMER_SECRET }} + TWITTER_ACCESS_TOKEN: ${{ secrets.TWITTER_ACCESS_TOKEN }} + TWITTER_ACCESS_TOKEN_SECRET: ${{ secrets.TWITTER_ACCESS_TOKEN_SECRET }} + + bsky-post: + runs-on: ubuntu-latest + steps: + - 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 }}! + + Please see the changelog: ${{ github.event.release.html_url }} + env: + BSKY_IDENTIFIER: ${{ secrets.BSKY_IDENTIFIER }} + BSKY_PASSWORD: ${{ secrets.BSKY_PASSWORD }} + # diff --git a/.gitpod.yml b/.gitpod.yml index 85d95ec..363d5b1 100644 --- a/.gitpod.yml +++ b/.gitpod.yml @@ -1,4 +1,12 @@ image: nfcore/gitpod:latest +tasks: + - name: Update Nextflow and setup pre-commit + command: | + pre-commit install --install-hooks + nextflow self-update + - name: unset JAVA_TOOL_OPTIONS + command: | + unset JAVA_TOOL_OPTIONS vscode: extensions: # based on nf-core.nf-core-extensionpack diff --git a/.nf-core.yml b/.nf-core.yml index 3805dc8..8b4d3e7 100644 --- a/.nf-core.yml +++ b/.nf-core.yml @@ -1 +1,6 @@ repository_type: pipeline +lint: + files_unchanged: + - assets/nf-core-epitopeprediction_logo_light.png + - docs/images/nf-core-epitopeprediction_logo_light.png + - docs/images/nf-core-epitopeprediction_logo_dark.png diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml new file mode 100644 index 0000000..af57081 --- /dev/null +++ b/.pre-commit-config.yaml @@ -0,0 +1,10 @@ +repos: + - repo: https://github.com/pre-commit/mirrors-prettier + rev: "v3.1.0" + hooks: + - id: prettier + - repo: https://github.com/editorconfig-checker/editorconfig-checker.python + rev: "2.7.3" + hooks: + - id: editorconfig-checker + alias: ec diff --git a/CHANGELOG.md b/CHANGELOG.md index e898808..0e33d11 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,6 +3,27 @@ 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). +## v2.3.0 - Oesterberg - 2024-02-26 + +### `Changed` + +- [#233](https://github.com/nf-core/epitopeprediction/pull/233) - Update to nf-core template `2.13` +- [#228](https://github.com/nf-core/epitopeprediction/pull/228) - Update to nf-core template `2.12` +- [#227](https://github.com/nf-core/epitopeprediction/pull/227) Prevent crash if no transcript is found (in splitted vcf) +- [#220](https://github.com/nf-core/epitopeprediction/pull/220) - Switch to nf-validation to parse samplesheet +- [#213](https://github.com/nf-core/epitopeprediction/pull/213) - Update epytope and Ensembl reference handling and update to nf-core template `2.10` +- [#206](https://github.com/nf-core/epitopeprediction/issues/206) - Update the row checker class. +- [#203](https://github.com/nf-core/epitopeprediction/pull/203) - Update to nf-core template `2.9`, rename param `genome_version` to `genome_reference`, add functionality to handle BioMart archive urls + +### `Fixed` + +- [#219](https://github.com/nf-core/epitopeprediction/pull/219) - Fix `EXTERNAL_TOOLS_IMPORT`` container registry and bump version +- [#227](https://github.com/nf-core/epitopeprediction/pull/227) - Prevent crash if no transcript is found (in splitted vcf) + +### `Removed` + +- [#221](https://github.com/nf-core/epitopeprediction/pull/221) - Remove support of `GSvar` and variant `tsv` input files + ## v2.2.1 - WaldhaeuserOst Hotfix - 2023-03-16 ### `Fixed` diff --git a/CITATIONS.md b/CITATIONS.md index 76d1cf6..5466f3b 100644 --- a/CITATIONS.md +++ b/CITATIONS.md @@ -10,8 +10,6 @@ ## Pipeline tools -- [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/) - - [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. @@ -71,5 +69,8 @@ - [Docker](https://dl.acm.org/doi/10.5555/2600239.2600241) + > Merkel, D. (2014). Docker: lightweight linux containers for consistent development and deployment. Linux Journal, 2014(239), 2. doi: 10.5555/2600239.2600241. + - [Singularity](https://pubmed.ncbi.nlm.nih.gov/28494014/) + > Kurtzer GM, Sochat V, Bauer MW. Singularity: Scientific containers for mobility of compute. PLoS One. 2017 May 11;12(5):e0177459. doi: 10.1371/journal.pone.0177459. eCollection 2017. PubMed PMID: 28494014; PubMed Central PMCID: PMC5426675. diff --git a/CODE_OF_CONDUCT.md b/CODE_OF_CONDUCT.md index f4fd052..c089ec7 100644 --- a/CODE_OF_CONDUCT.md +++ b/CODE_OF_CONDUCT.md @@ -1,18 +1,20 @@ -# Code of Conduct at nf-core (v1.0) +# Code of Conduct at nf-core (v1.4) ## Our Pledge -In the interest of fostering an open, collaborative, and welcoming environment, we as contributors and maintainers of nf-core, pledge to making participation in our projects and community a harassment-free experience for everyone, regardless of: +In the interest of fostering an open, collaborative, and welcoming environment, we as contributors and maintainers of nf-core pledge to making participation in our projects and community a harassment-free experience for everyone, regardless of: - Age +- Ability - Body size +- Caste - Familial status - Gender identity and expression - Geographical location - Level of experience - Nationality and national origins - Native language -- Physical and neurological ability +- Neurodiversity - Race or ethnicity - Religion - Sexual identity and orientation @@ -22,80 +24,133 @@ Please note that the list above is alphabetised and is therefore not ranked in a ## Preamble -> Note: This Code of Conduct (CoC) has been drafted by the nf-core Safety Officer and been edited after input from members of the nf-core team and others. "We", in this document, refers to the Safety Officer and members of the nf-core core team, both of whom are deemed to be members of the nf-core community and are therefore required to abide by this Code of Conduct. This document will amended periodically to keep it up-to-date, and in case of any dispute, the most current version will apply. +:::note +This Code of Conduct (CoC) has been drafted by Renuka Kudva, Cris Tuñí, and Michael Heuer, with input from the nf-core Core Team and Susanna Marquez from the nf-core community. "We", in this document, refers to the Safety Officers and members of the nf-core Core Team, both of whom are deemed to be members of the nf-core community and are therefore required to abide by this Code of Conduct. This document will be amended periodically to keep it up-to-date. In case of any dispute, the most current version will apply. +::: -An up-to-date list of members of the nf-core core team can be found [here](https://nf-co.re/about). Our current safety officer is Renuka Kudva. +An up-to-date list of members of the nf-core core team can be found [here](https://nf-co.re/about). + +Our Safety Officers are Saba Nafees, Cris Tuñí, and Michael Heuer. nf-core is a young and growing community that welcomes contributions from anyone with a shared vision for [Open Science Policies](https://www.fosteropenscience.eu/taxonomy/term/8). Open science policies encompass inclusive behaviours and we strive to build and maintain a safe and inclusive environment for all individuals. -We have therefore adopted this code of conduct (CoC), which we require all members of our community and attendees in nf-core events to adhere to in all our workspaces at all times. Workspaces include but are not limited to Slack, meetings on Zoom, Jitsi, YouTube live etc. +We have therefore adopted this CoC, which we require all members of our community and attendees of nf-core events to adhere to in all our workspaces at all times. Workspaces include, but are not limited to, Slack, meetings on Zoom, gather.town, YouTube live etc. -Our CoC will be strictly enforced and the nf-core team reserve the right to exclude participants who do not comply with our guidelines from our workspaces and future nf-core activities. +Our CoC will be strictly enforced and the nf-core team reserves the right to exclude participants who do not comply with our guidelines from our workspaces and future nf-core activities. -We ask all members of our community to help maintain a supportive and productive workspace and to avoid behaviours that can make individuals feel unsafe or unwelcome. Please help us maintain and uphold this CoC. +We ask all members of our community to help maintain supportive and productive workspaces and to avoid behaviours that can make individuals feel unsafe or unwelcome. Please help us maintain and uphold this CoC. -Questions, concerns or ideas on what we can include? Contact safety [at] nf-co [dot] re +Questions, concerns, or ideas on what we can include? Contact members of the Safety Team on Slack or email safety [at] nf-co [dot] re. ## Our Responsibilities -The safety officer is responsible for clarifying the standards of acceptable behavior and are expected to take appropriate and fair corrective action in response to any instances of unacceptable behaviour. +Members of the Safety Team (the Safety Officers) are responsible for clarifying the standards of acceptable behavior and are expected to take appropriate and fair corrective action in response to any instances of unacceptable behaviour. -The safety officer in consultation with the nf-core core team have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct, or to ban temporarily or permanently any contributor for other behaviors that they deem inappropriate, threatening, offensive, or harmful. +The Safety Team, in consultation with the nf-core core team, have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this CoC, or to ban temporarily or permanently any contributor for other behaviors that they deem inappropriate, threatening, offensive, or harmful. -Members of the core team or the safety officer who violate the CoC will be required to recuse themselves pending investigation. They will not have access to any reports of the violations and be subject to the same actions as others in violation of the CoC. +Members of the core team or the Safety Team who violate the CoC will be required to recuse themselves pending investigation. They will not have access to any reports of the violations and will be subject to the same actions as others in violation of the CoC. -## When are where does this Code of Conduct apply? +## When and where does this Code of Conduct apply? -Participation in the nf-core community is contingent on following these guidelines in all our workspaces and events. This includes but is not limited to the following listed alphabetically and therefore in no order of preference: +Participation in the nf-core community is contingent on following these guidelines in all our workspaces and events, such as hackathons, workshops, bytesize, and collaborative workspaces on gather.town. These guidelines include, but are not limited to, the following (listed alphabetically and therefore in no order of preference): - Communicating with an official project email address. - Communicating with community members within the nf-core Slack channel. - Participating in hackathons organised by nf-core (both online and in-person events). -- Participating in collaborative work on GitHub, Google Suite, community calls, mentorship meetings, email correspondence. -- Participating in workshops, training, and seminar series organised by nf-core (both online and in-person events). This applies to events hosted on web-based platforms such as Zoom, Jitsi, YouTube live etc. +- Participating in collaborative work on GitHub, Google Suite, community calls, mentorship meetings, email correspondence, and on the nf-core gather.town workspace. +- Participating in workshops, training, and seminar series organised by nf-core (both online and in-person events). This applies to events hosted on web-based platforms such as Zoom, gather.town, Jitsi, YouTube live etc. - Representing nf-core on social media. This includes both official and personal accounts. ## nf-core cares 😊 -nf-core's CoC and expectations of respectful behaviours for all participants (including organisers and the nf-core team) include but are not limited to the following (listed in alphabetical order): +nf-core's CoC and expectations of respectful behaviours for all participants (including organisers and the nf-core team) include, but are not limited to, the following (listed in alphabetical order): - Ask for consent before sharing another community member’s personal information (including photographs) on social media. - Be respectful of differing viewpoints and experiences. We are all here to learn from one another and a difference in opinion can present a good learning opportunity. -- Celebrate your accomplishments at events! (Get creative with your use of emojis 🎉 🥳 💯 🙌 !) +- Celebrate your accomplishments! (Get creative with your use of emojis 🎉 🥳 💯 🙌 !) - Demonstrate empathy towards other community members. (We don’t all have the same amount of time to dedicate to nf-core. If tasks are pending, don’t hesitate to gently remind members of your team. If you are leading a task, ask for help if you feel overwhelmed.) - Engage with and enquire after others. (This is especially important given the geographically remote nature of the nf-core community, so let’s do this the best we can) - Focus on what is best for the team and the community. (When in doubt, ask) -- Graciously accept constructive criticism, yet be unafraid to question, deliberate, and learn. +- Accept feedback, yet be unafraid to question, deliberate, and learn. - Introduce yourself to members of the community. (We’ve all been outsiders and we know that talking to strangers can be hard for some, but remember we’re interested in getting to know you and your visions for open science!) -- Show appreciation and **provide clear feedback**. (This is especially important because we don’t see each other in person and it can be harder to interpret subtleties. Also remember that not everyone understands a certain language to the same extent as you do, so **be clear in your communications to be kind.**) +- Show appreciation and **provide clear feedback**. (This is especially important because we don’t see each other in person and it can be harder to interpret subtleties. Also remember that not everyone understands a certain language to the same extent as you do, so **be clear in your communication to be kind.**) - Take breaks when you feel like you need them. -- Using welcoming and inclusive language. (Participants are encouraged to display their chosen pronouns on Zoom or in communication on Slack.) +- Use welcoming and inclusive language. (Participants are encouraged to display their chosen pronouns on Zoom or in communication on Slack) ## nf-core frowns on 😕 -The following behaviours from any participants within the nf-core community (including the organisers) will be considered unacceptable under this code of conduct. Engaging or advocating for any of the following could result in expulsion from nf-core workspaces. +The following behaviours from any participants within the nf-core community (including the organisers) will be considered unacceptable under this CoC. Engaging or advocating for any of the following could result in expulsion from nf-core workspaces: - Deliberate intimidation, stalking or following and sustained disruption of communication among participants of the community. This includes hijacking shared screens through actions such as using the annotate tool in conferencing software such as Zoom. - “Doxing” i.e. posting (or threatening to post) another person’s personal identifying information online. - Spamming or trolling of individuals on social media. -- Use of sexual or discriminatory imagery, comments, or jokes and unwelcome sexual attention. -- Verbal and text comments that reinforce social structures of domination related to gender, gender identity and expression, sexual orientation, ability, physical appearance, body size, race, age, religion or work experience. +- Use of sexual or discriminatory imagery, comments, jokes, or unwelcome sexual attention. +- Verbal and text comments that reinforce social structures of domination related to gender, gender identity and expression, sexual orientation, ability, physical appearance, body size, race, age, religion, or work experience. ### Online Trolling -The majority of nf-core interactions and events are held online. Unfortunately, holding events online comes with the added issue of online trolling. This is unacceptable, reports of such behaviour will be taken very seriously, and perpetrators will be excluded from activities immediately. +The majority of nf-core interactions and events are held online. Unfortunately, holding events online comes with the risk of online trolling. This is unacceptable — reports of such behaviour will be taken very seriously and perpetrators will be excluded from activities immediately. -All community members are required to ask members of the group they are working within for explicit consent prior to taking screenshots of individuals during video calls. +All community members are **required** to ask members of the group they are working with for explicit consent prior to taking screenshots of individuals during video calls. -## Procedures for Reporting CoC violations +## Procedures for reporting CoC violations If someone makes you feel uncomfortable through their behaviours or actions, report it as soon as possible. -You can reach out to members of the [nf-core core team](https://nf-co.re/about) and they will forward your concerns to the safety officer(s). +You can reach out to members of the Safety Team (Saba Nafees, Cris Tuñí, and Michael Heuer) on Slack. Alternatively, contact a member of the nf-core core team [nf-core core team](https://nf-co.re/about), and they will forward your concerns to the Safety Team. + +Issues directly concerning members of the Core Team or the Safety Team will be dealt with by other members of the core team and the safety manager — possible conflicts of interest will be taken into account. nf-core is also in discussions about having an ombudsperson and details will be shared in due course. + +All reports will be handled with the utmost discretion and confidentiality. + +You can also report any CoC violations to safety [at] nf-co [dot] re. In your email report, please do your best to include: + +- Your contact information. +- Identifying information (e.g. names, nicknames, pseudonyms) of the participant who has violated the Code of Conduct. +- The behaviour that was in violation and the circumstances surrounding the incident. +- The approximate time of the behaviour (if different than the time the report was made). +- Other people involved in the incident, if applicable. +- If you believe the incident is ongoing. +- If there is a publicly available record (e.g. mailing list record, a screenshot). +- Any additional information. + +After you file a report, one or more members of our Safety Team will contact you to follow up on your report. + +## Who will read and handle reports + +All reports will be read and handled by the members of the Safety Team at nf-core. + +If members of the Safety Team are deemed to have a conflict of interest with a report, they will be required to recuse themselves as per our Code of Conduct and will not have access to any follow-ups. + +To keep this first report confidential from any of the Safety Team members, please submit your first report by direct messaging on Slack/direct email to any of the nf-core members you are comfortable disclosing the information to, and be explicit about which member(s) you do not consent to sharing the information with. + +## Reviewing reports + +After receiving the report, members of the Safety Team will review the incident report to determine whether immediate action is required, for example, whether there is immediate threat to participants’ safety. + +The Safety Team, in consultation with members of the nf-core core team, will assess the information to determine whether the report constitutes a Code of Conduct violation, for them to decide on a course of action. + +In the case of insufficient information, one or more members of the Safety Team may contact the reporter, the reportee, or any other attendees to obtain more information. -Issues directly concerning members of the core team will be dealt with by other members of the core team and the safety manager, and possible conflicts of interest will be taken into account. nf-core is also in discussions about having an ombudsperson, and details will be shared in due course. +Once additional information is gathered, the Safety Team will collectively review and decide on the best course of action to take, if any. The Safety Team reserves the right to not act on a report. -All reports will be handled with utmost discretion and confidentially. +## Confidentiality + +All reports, and any additional information included, are only shared with the team of safety officers (and possibly members of the core team, in case the safety officer is in violation of the CoC). We will respect confidentiality requests for the purpose of protecting victims of abuse. + +We will not name harassment victims, beyond discussions between the safety officer and members of the nf-core team, without the explicit consent of the individuals involved. + +## Enforcement + +Actions taken by the nf-core’s Safety Team may include, but are not limited to: + +- Asking anyone to stop a behaviour. +- Asking anyone to leave the event and online spaces either temporarily, for the remainder of the event, or permanently. +- Removing access to the gather.town and Slack, either temporarily or permanently. +- Communicating to all participants to reinforce our expectations for conduct and remind what is unacceptable behaviour; this may be public for practical reasons. +- Communicating to all participants that an incident has taken place and how we will act or have acted — this may be for the purpose of letting event participants know we are aware of and dealing with the incident. +- Banning anyone from participating in nf-core-managed spaces, future events, and activities, either temporarily or permanently. +- No action. ## Attribution and Acknowledgements @@ -106,6 +161,22 @@ All reports will be handled with utmost discretion and confidentially. ## Changelog -### v1.0 - March 12th, 2021 +### v1.4 - February 8th, 2022 + +- Included a new member of the Safety Team. Corrected a typographical error in the text. + +### v1.3 - December 10th, 2021 + +- Added a statement that the CoC applies to nf-core gather.town workspaces. Corrected typographical errors in the text. + +### v1.2 - November 12th, 2021 + +- Removed information specific to reporting CoC violations at the Hackathon in October 2021. + +### v1.1 - October 14th, 2021 + +- Updated with names of new Safety Officers and specific information for the hackathon in October 2021. + +### v1.0 - March 15th, 2021 - Complete rewrite from original [Contributor Covenant](http://contributor-covenant.org/) CoC. diff --git a/README.md b/README.md index 44af412..8fe7ad9 100644 --- a/README.md +++ b/README.md @@ -1,25 +1,37 @@ -# ![nf-core/epitopeprediction](docs/images/nf-core-epitopeprediction_logo_light.png#gh-light-mode-only) ![nf-core/epitopeprediction](docs/images/nf-core-epitopeprediction_logo_dark.png#gh-dark-mode-only) +

+ + + nf-core/epitopeprediction + +

[![GitHub Actions CI Status](https://github.com/nf-core/epitopeprediction/workflows/nf-core%20CI/badge.svg)](https://github.com/nf-core/epitopeprediction/actions?query=workflow%3A%22nf-core+CI%22) -[![GitHub Actions Linting Status](https://github.com/nf-core/epitopeprediction/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/epitopeprediction/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/epitopeprediction/results) -[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.3564666-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.3564666) +[![GitHub Actions Linting Status](https://github.com/nf-core/epitopeprediction/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/epitopeprediction/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/epitopeprediction/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.3564666-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.3564666) -[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A522.10.1-23aa62.svg)](https://www.nextflow.io/) +[![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?labelColor=000000)](https://tower.nf/launch?pipeline=https://github.com/nf-core/epitopeprediction) -[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23epitopeprediction-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/epitopeprediction) -[![Follow on Twitter](http://img.shields.io/badge/twitter-%40nf__core-1DA1F2?labelColor=000000&logo=twitter)](https://twitter.com/nf_core) -[![Watch on YouTube](http://img.shields.io/badge/youtube-nf--core-FF0000?labelColor=000000&logo=youtube)](https://www.youtube.com/c/nf-core) +[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23epitopeprediction-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/epitopeprediction)[![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) ## Introduction **nf-core/epitopeprediction** is a bioinformatics best-practice analysis pipeline for epitope prediction and annotation. The pipeline performs epitope predictions for a given set of variants or peptides directly using state of the art prediction tools. Additionally, resulting prediction results can be annotated with metadata. +Supported prediction tools: + +- `syfpeithi` +- `mhcflurry` +- `mhcnuggets-class-1` +- `mhcnuggets-class-2` +- `netmhcpan-4.0` +- `netmhcpan-4.1` +- `netmhc-4.0` +- `netmhciipan-4.1` + The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. It uses Docker/Singularity containers making installation trivial and results highly reproducible. The [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html) implementation of this pipeline uses one container per process which makes it easier to maintain and update software dependencies. Where possible, these processes have been submitted to and installed from [nf-core/modules](https://github.com/nf-core/modules) in order to make them available to all nf-core pipelines, and to everyone within the Nextflow community! On release, automated continuous integration tests run the pipeline on a full-sized dataset on the AWS cloud infrastructure. This ensures that the pipeline runs on AWS, has sensible resource allocation defaults set to run on real-world datasets, and permits the persistent storage of results to benchmark between pipeline releases and other analysis sources.The results obtained from the full-sized test can be viewed on the [nf-core website](https://nf-co.re/epitopeprediction/results). @@ -30,40 +42,45 @@ On release, automated continuous integration tests run the pipeline on a full-si 2. Generate peptides from variants or proteins or use peptides directly 3. Predict HLA-binding peptides for the given set of HLA alleles -## Quick Start - -1. Install [`Nextflow`](https://www.nextflow.io/docs/latest/getstarted.html#installation) (`>=22.10.1`) +> [!NOTE] +> If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline) with `-profile test` before running the workflow on actual data. -2. Install any of [`Docker`](https://docs.docker.com/engine/installation/), [`Singularity`](https://www.sylabs.io/guides/3.0/user-guide/) (you can follow [this tutorial](https://singularity-tutorial.github.io/01-installation/)), [`Podman`](https://podman.io/), [`Shifter`](https://nersc.gitlab.io/development/shifter/how-to-use/) or [`Charliecloud`](https://hpc.github.io/charliecloud/) for full pipeline reproducibility _(you can use [`Conda`](https://conda.io/miniconda.html) both to install Nextflow itself and also to manage software within pipelines. Please only use it within pipelines as a last resort; see [docs](https://nf-co.re/usage/configuration#basic-configuration-profiles))_. +First, prepare a samplesheet with your input data that looks as follows: -3. Download the pipeline and test it on a minimal dataset with a single command: +`samplesheet.csv`: - ```bash - nextflow run nf-core/epitopeprediction -profile test,YOURPROFILE --outdir - ``` +```csv +sample,alleles,mhc_class,filename +GBM_1,A*01:01;A*02:01;B*07:02;B*24:02;C*03:01;C*04:01,I,gbm_1_variants.vcf +GBM_1,A*02:01;A*24:01;B*07:02;B*08:01;C*04:01;C*07:01,I,gbm_1_peptides.vcf +``` - Note that some form of configuration will be needed so that Nextflow knows how to fetch the required software. This is usually done in the form of a config profile (`YOURPROFILE` in the example command above). You can chain multiple config profiles in a comma-separated string. +Each row represents a sample with associated HLA alleles and input data (variants/peptides/proteins). - > - The pipeline comes with config profiles called `docker`, `singularity`, `podman`, `shifter`, `charliecloud` and `conda` which instruct the pipeline to use the named tool for software management. For example, `-profile test,docker`. - > - Please check [nf-core/configs](https://github.com/nf-core/configs#documentation) to see if a custom config file to run nf-core pipelines already exists for your Institute. If so, you can simply use `-profile ` in your command. This will enable either `docker` or `singularity` and set the appropriate execution settings for your local compute environment. - > - If you are using `singularity`, please use the [`nf-core download`](https://nf-co.re/tools/#downloading-pipelines-for-offline-use) command to download images first, before running the pipeline. Setting the [`NXF_SINGULARITY_CACHEDIR` or `singularity.cacheDir`](https://www.nextflow.io/docs/latest/singularity.html?#singularity-docker-hub) Nextflow options enables you to store and re-use the images from a central location for future pipeline runs. - > - If you are using `conda`, it is highly recommended to use the [`NXF_CONDA_CACHEDIR` or `conda.cacheDir`](https://www.nextflow.io/docs/latest/conda.html) settings to store the environments in a central location for future pipeline runs. +Now, you can run the pipeline using: -4. Start running your own analysis! +```bash +nextflow run nf-core/epitopeprediction \ + -profile \ + --input samplesheet.csv \ + --outdir +``` - ```bash - nextflow run nf-core/epitopeprediction --input samplesheet.csv --outdir -profile - ``` +> [!WARNING] +> Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_; +> see [docs](https://nf-co.re/usage/configuration#custom-configuration-files). -See [usage docs](https://nf-co.re/epitopeprediction/usage) for all of the available options when running the pipeline. +For more details and further functionality, please refer to the [usage documentation](https://nf-co.re/epitopeprediction/usage) and the [parameter documentation](https://nf-co.re/epitopeprediction/parameters). -## Documentation +## Pipeline output -The nf-core/epitopeprediction pipeline comes with documentation about the pipeline [usage](https://nf-co.re/epitopeprediction/usage), [parameters](https://nf-co.re/epitopeprediction/parameters), and [output](https://nf-co.re/epitopeprediction/output). +To see the results of an example test run with a full size dataset refer to the [results](https://nf-co.re/epitopeprediction/results) tab on the nf-core website pipeline page. +For more details about the output files and reports, please refer to the +[output documentation](https://nf-co.re/epitopeprediction/output). ## Credits -nf-core/epitopeprediction was originally written by [Christopher Mohr](https://github.com/christopher-mohr) from [Medical Data Integration Center](https://www.medizin.uni-tuebingen.de/de/das-klinikum/einrichtungen/institute/informationstechnologie-und-medizininformatik/medic) and [Quantitative Biology Center](https://uni-tuebingen.de/forschung/forschungsinfrastruktur/zentrum-fuer-quantitative-biologie-qbic/) and [Alexander Peltzer](https://github.com/apeltzer) from [Böhringer Ingelheim](https://www.boehringer-ingelheim.de). Further contributions were made by [Sabrina Krakau](https://github.com/skrakau) from [Quantitative Biology Center](https://uni-tuebingen.de/forschung/forschungsinfrastruktur/zentrum-fuer-quantitative-biologie-qbic/) and [Leon Kuchenbecker](https://github.com/lkuchenb) from the [Kohlbacher Lab](https://kohlbacherlab.org/). +nf-core/epitopeprediction was originally written by [Christopher Mohr](https://github.com/christopher-mohr) from [Boehringer Ingelheim](https://www.boehringer-ingelheim.de) and [Alexander Peltzer](https://github.com/apeltzer) from [Boehringer Ingelheim](https://www.boehringer-ingelheim.de). Further contributions were made by [Sabrina Krakau](https://github.com/skrakau) from [Quantitative Biology Center](https://uni-tuebingen.de/forschung/forschungsinfrastruktur/zentrum-fuer-quantitative-biologie-qbic/) and [Leon Kuchenbecker](https://github.com/lkuchenb) from the [Kohlbacher Lab](https://kohlbacherlab.org/). The pipeline was converted to Nextflow DSL2 by [Christopher Mohr](https://github.com/christopher-mohr), [Marissa Dubbelaar](https://github.com/marissaDubbelaar) from [Clinical Collaboration Unit Translational Immunology](https://www.medizin.uni-tuebingen.de/en-de/das-klinikum/einrichtungen/kliniken/medizinische-klinik/kke-translationale-immunologie) and [Quantitative Biology Center](https://uni-tuebingen.de/forschung/forschungsinfrastruktur/zentrum-fuer-quantitative-biologie-qbic/), [Gisela Gabernet](https://github.com/ggabernet) from [Quantitative Biology Center](https://uni-tuebingen.de/forschung/forschungsinfrastruktur/zentrum-fuer-quantitative-biologie-qbic/), and [Jonas Scheid](https://github.com/jonasscheid) from [Quantitative Biology Center](https://uni-tuebingen.de/forschung/forschungsinfrastruktur/zentrum-fuer-quantitative-biologie-qbic/) diff --git a/assets/email_template.html b/assets/email_template.html index 08d9a41..251ba8c 100644 --- a/assets/email_template.html +++ b/assets/email_template.html @@ -12,7 +12,7 @@ -

nf-core/epitopeprediction v${version}

+

nf-core/epitopeprediction ${version}

Run Name: $runName

<% if (!success){ diff --git a/assets/email_template.txt b/assets/email_template.txt index 8b39053..9d39536 100644 --- a/assets/email_template.txt +++ b/assets/email_template.txt @@ -4,7 +4,7 @@ |\\ | |__ __ / ` / \\ |__) |__ } { | \\| | \\__, \\__/ | \\ |___ \\`-._,-`-, `._,._,' - nf-core/epitopeprediction v${version} + nf-core/epitopeprediction ${version} ---------------------------------------------------- Run Name: $runName diff --git a/assets/methods_description_template.yml b/assets/methods_description_template.yml index 1c54d0f..751c833 100644 --- a/assets/methods_description_template.yml +++ b/assets/methods_description_template.yml @@ -3,17 +3,19 @@ description: "Suggested text and references to use when describing pipeline usag section_name: "nf-core/epitopeprediction Methods Description" section_href: "https://github.com/nf-core/epitopeprediction" plot_type: "html" -## TODO nf-core: Update the HTML below to your prefered methods description, e.g. add publication citation for this pipeline -## You inject any metadata in the Nextflow '${workflow}' object data: |

Methods

-

Data was processed using nf-core/epitopeprediction v${workflow.manifest.version} ${doi_text} of the nf-core collection of workflows (Ewels et al., 2020).

+

Data was processed using nf-core/epitopeprediction v${workflow.manifest.version} ${doi_text} of the nf-core collection of workflows (Ewels et al., 2020), utilising reproducible software environments from the Bioconda (Grüning et al., 2018) and Biocontainers (da Veiga Leprevost et al., 2017) projects.

The pipeline was executed with Nextflow v${workflow.nextflow.version} (Di Tommaso et al., 2017) with the following command:

${workflow.commandLine}
+

${tool_citations}

References

    -
  • Di Tommaso, P., Chatzou, M., Floden, E. W., Barja, P. P., Palumbo, E., & Notredame, C. (2017). Nextflow enables reproducible computational workflows. Nature Biotechnology, 35(4), 316-319. https://doi.org/10.1038/nbt.3820
    • -
  • Ewels, P. A., Peltzer, A., Fillinger, S., Patel, H., Alneberg, J., Wilm, A., Garcia, M. U., Di Tommaso, P., & Nahnsen, S. (2020). The nf-core framework for community-curated bioinformatics pipelines. Nature Biotechnology, 38(3), 276-278. https://doi.org/10.1038/s41587-020-0439-x
    • +
  • Di Tommaso, P., Chatzou, M., Floden, E. W., Barja, P. P., Palumbo, E., & Notredame, C. (2017). Nextflow enables reproducible computational workflows. Nature Biotechnology, 35(4), 316-319. doi: 10.1038/nbt.3820
    • +
  • Ewels, P. A., Peltzer, A., Fillinger, S., Patel, H., Alneberg, J., Wilm, A., Garcia, M. U., Di Tommaso, P., & Nahnsen, S. (2020). The nf-core framework for community-curated bioinformatics pipelines. Nature Biotechnology, 38(3), 276-278. doi: 10.1038/s41587-020-0439-x
    • +
  • Grüning, B., Dale, R., Sjödin, A., Chapman, B. A., Rowe, J., Tomkins-Tinch, C. H., Valieris, R., Köster, J., & Bioconda Team. (2018). Bioconda: sustainable and comprehensive software distribution for the life sciences. Nature Methods, 15(7), 475–476. doi: 10.1038/s41592-018-0046-7
    • +
  • da Veiga Leprevost, F., Grüning, B. A., Alves Aflitos, S., Röst, H. L., Uszkoreit, J., Barsnes, H., Vaudel, M., Moreno, P., Gatto, L., Weber, J., Bai, M., Jimenez, R. C., Sachsenberg, T., Pfeuffer, J., Vera Alvarez, R., Griss, J., Nesvizhskii, A. I., & Perez-Riverol, Y. (2017). BioContainers: an open-source and community-driven framework for software standardization. Bioinformatics (Oxford, England), 33(16), 2580–2582. doi: 10.1093/bioinformatics/btx192
    • + ${tool_bibliography}
Notes:
diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml index 7be32f7..00ebcf7 100644 --- a/assets/multiqc_config.yml +++ b/assets/multiqc_config.yml @@ -1,11 +1,9 @@ -custom_logo: "nf-core-epitopeprediction_logo_light.png" -custom_logo_url: https://github.com/nf-core/epitopeprediction/ -custom_logo_title: "nf-core/epitopeprediction" - report_comment: > - This report has been generated by the nf-core/epitopeprediction + + This report has been generated by the nf-core/epitopeprediction analysis pipeline. For information about how to interpret these results, please see the - documentation. + documentation. + report_section_order: "nf-core-epitopeprediction-methods-description": order: -1000 @@ -15,3 +13,5 @@ report_section_order: order: -1002 export_plots: true + +disable_version_detection: true diff --git a/assets/nf-core-epitopeprediction_logo_light.png b/assets/nf-core-epitopeprediction_logo_light.png index 07da76c..998876a 100644 Binary files a/assets/nf-core-epitopeprediction_logo_light.png and b/assets/nf-core-epitopeprediction_logo_light.png differ diff --git a/assets/schema_input.json b/assets/schema_input.json index b564a5c..95d5bb4 100644 --- a/assets/schema_input.json +++ b/assets/schema_input.json @@ -10,7 +10,8 @@ "sample": { "type": "string", "pattern": "^\\S+$", - "errorMessage": "Sample name must be provided and cannot contain spaces" + "errorMessage": "Sample name must be provided and cannot contain spaces", + "meta": ["id"] }, "alleles": { "anyOf": [ @@ -20,20 +21,32 @@ }, { "type": "string", - "pattern": "(^[A-Z][*][0-9][0-9][:][0-9][0-9])$" + "pattern": "^([A-E]{1}[*][0-9]{2}[:][0-9]{2})(;[A-E]{1}[*][0-9]{2}[:][0-9]{2})*$" + }, + { + "type": "string", + "pattern": "^((DR|DP|DQ)[AB][0-9][*][0-9]{2}[:][0-9]{2})(;(DR|DP|DQ)[AB][0-9][*][0-9]{2}[:][0-9]{2})*$" + }, + { + "type": "string", + "pattern": "^((DR|DP|DQ)[AB][0-9][*][0-9]{2}[:][0-9]{2}[-](DR|DP|DQ)[AB][0-9][*][0-9]{2}[:][0-9]{2})(;((DR|DP|DQ)[AB][0-9][*][0-9]{2}[:][0-9]{2}[-](DR|DP|DQ)[AB][0-9][*][0-9]{2}[:][0-9]{2}))*$" + }, + { + "type": "string", + "pattern": "^[H][-][2][-][A-Za-z]{2,3}$" } ], - "errorMessage": "Alleles must be provided as string or file with extension '.txt''" + "errorMessage": "Alleles must be provided as string or file with extension '.txt'. Please check the documentation for more information." }, "mhc_class": { "type": "string", "pattern": "^(I|II|H-2)$", - "errorMessage": "The MHC class must be provided. Valid values: " + "errorMessage": "The MHC class must be provided. Valid values: 'I', 'II' or 'H-2'" }, "filename": { "type": "string", - "pattern": "^\\S+\\.(vcf|tsv|fasta|fa|txt)$", - "errorMessage": "Variants/proteins/peptides for sample must be provided and have one of the following extensions: '.vcf', '.tsv', '.fasta', '.fa', '.txt'" + "pattern": "^\\S+\\.(vcf|vcf.gz|tsv|fasta|fa)$", + "errorMessage": "Variants/proteins/peptides of a sample must be provided and have one of the following extensions: '.vcf', '.vcf.gz', '.tsv', '.fasta', '.fa'" } }, "required": ["sample", "alleles", "mhc_class", "filename"] diff --git a/assets/slackreport.json b/assets/slackreport.json index 043d02f..f27f64a 100644 --- a/assets/slackreport.json +++ b/assets/slackreport.json @@ -3,7 +3,7 @@ { "fallback": "Plain-text summary of the attachment.", "color": "<% if (success) { %>good<% } else { %>danger<%} %>", - "author_name": "sanger-tol/readmapping v${version} - ${runName}", + "author_name": "nf-core/epitopeprediction ${version} - ${runName}", "author_icon": "https://www.nextflow.io/docs/latest/_static/favicon.ico", "text": "<% if (success) { %>Pipeline completed successfully!<% } else { %>Pipeline completed with errors<% } %>", "fields": [ diff --git a/bin/check_requested_models.py b/bin/check_requested_models.py index 2a509e0..845666d 100755 --- a/bin/check_requested_models.py +++ b/bin/check_requested_models.py @@ -2,14 +2,14 @@ # Written by Sabrina Krakau, Christopher Mohr and released under the MIT license. -import sys -import csv import argparse +import csv import logging +import sys +import urllib.request from epytope.Core.Allele import Allele from epytope.Core.Peptide import Peptide -from epytope.IO import FileReader from epytope.EpitopePrediction import EpitopePredictorFactory # instantiate global logger object @@ -24,7 +24,7 @@ def read_peptide_input(filename): peptides = [] """expected columns (min required): id sequence""" - with open(filename, "r") as peptide_input: + with open(filename) as peptide_input: # enable listing of protein names for each peptide csv.field_size_limit(600000) reader = csv.DictReader(peptide_input, delimiter="\t") @@ -53,7 +53,7 @@ def __main__(): "Write out information about supported models by epytope for installed predictor tool versions." ) parser.add_argument("-p", "--peptides", help="File with one peptide per line") - parser.add_argument("-c", "--mhcclass", default=1, help="MHC class I or II") + parser.add_argument("-c", "--mhc_class", default=1, help="MHC class I or II") parser.add_argument("-l", "--max_length", help="Maximum peptide length", type=int) parser.add_argument("-ml", "--min_length", help="Minimum peptide length", type=int) parser.add_argument("-a", "--alleles", help=" MHC Alleles", required=True, type=str) @@ -61,7 +61,7 @@ def __main__(): parser.add_argument("-v", "--versions", help=" File with used software versions.", required=True) args = parser.parse_args() selected_methods = [item.split("-")[0] if "mhcnuggets" not in item else item for item in args.tools.split(",")] - with open(args.versions, "r") as versions_file: + with open(args.versions) as versions_file: tool_version = [(row[0].split()[0], str(row[1])) for row in csv.reader(versions_file, delimiter=":")] # NOTE this needs to be updated, if a newer version will be available via epytope and should be used in the future tool_version.append(("syfpeithi", "1.0")) # how to handle this? diff --git a/bin/check_samplesheet.py b/bin/check_samplesheet.py deleted file mode 100755 index a8a9284..0000000 --- a/bin/check_samplesheet.py +++ /dev/null @@ -1,332 +0,0 @@ -#!/usr/bin/env python - - -import argparse -import logging -import os -import re -import sys -import errno -import re -from pathlib import Path - -logger = logging.getLogger() - - -class RowChecker: - """ - Define a service that can validate and transform each given row. - - Attributes: - modified (list): A list of dicts, where each dict corresponds to a previously - validated and transformed row. The order of rows is maintained. - - """ - - VALID_FORMATS = ( - ".fq.gz", - ".fastq.gz", - ) - - def __init__( - self, - sample_col="sample", - first_col="fastq_1", - second_col="fastq_2", - single_col="single_end", - **kwargs, - ): - """ - Initialize the row checker with the expected column names. - - Args: - sample_col (str): The name of the column that contains the sample name - (default "sample"). - first_col (str): The name of the column that contains the first (or only) - FASTQ file path (default "fastq_1"). - second_col (str): The name of the column that contains the second (if any) - FASTQ file path (default "fastq_2"). - single_col (str): The name of the new column that will be inserted and - records whether the sample contains single- or paired-end sequencing - reads (default "single_end"). - - """ - super().__init__(**kwargs) - self._sample_col = sample_col - self._first_col = first_col - self._second_col = second_col - self._single_col = single_col - self._seen = set() - self.modified = [] - - def validate_and_transform(self, row): - """ - Perform all validations on the given row and insert the read pairing status. - - Args: - row (dict): A mapping from column headers (keys) to elements of that row - (values). - - """ - self._validate_sample(row) - self._validate_first(row) - self._validate_second(row) - self._validate_pair(row) - self._seen.add((row[self._sample_col], row[self._first_col])) - self.modified.append(row) - - def _validate_sample(self, row): - """Assert that the sample name exists and convert spaces to underscores.""" - if len(row[self._sample_col]) <= 0: - raise AssertionError("Sample input is required.") - # Sanitize samples slightly. - row[self._sample_col] = row[self._sample_col].replace(" ", "_") - - def _validate_first(self, row): - """Assert that the first FASTQ entry is non-empty and has the right format.""" - if len(row[self._first_col]) <= 0: - raise AssertionError("At least the first FASTQ file is required.") - self._validate_fastq_format(row[self._first_col]) - - def _validate_second(self, row): - """Assert that the second FASTQ entry has the right format if it exists.""" - if len(row[self._second_col]) > 0: - self._validate_fastq_format(row[self._second_col]) - - def _validate_pair(self, row): - """Assert that read pairs have the same file extension. Report pair status.""" - if row[self._first_col] and row[self._second_col]: - row[self._single_col] = False - first_col_suffix = Path(row[self._first_col]).suffixes[-2:] - second_col_suffix = Path(row[self._second_col]).suffixes[-2:] - if first_col_suffix != second_col_suffix: - raise AssertionError("FASTQ pairs must have the same file extensions.") - else: - row[self._single_col] = True - - def _validate_fastq_format(self, filename): - """Assert that a given filename has one of the expected FASTQ extensions.""" - if not any(filename.endswith(extension) for extension in self.VALID_FORMATS): - raise AssertionError( - f"The FASTQ file has an unrecognized extension: {filename}\n" - f"It should be one of: {', '.join(self.VALID_FORMATS)}" - ) - - def validate_unique_samples(self): - """ - Assert that the combination of sample name and FASTQ filename is unique. - - In addition to the validation, also rename all samples to have a suffix of _T{n}, where n is the - number of times the same sample exist, but with different FASTQ files, e.g., multiple runs per experiment. - - """ - if len(self._seen) != len(self.modified): - raise AssertionError("The pair of sample name and FASTQ must be unique.") - seen = Counter() - for row in self.modified: - sample = row[self._sample_col] - seen[sample] += 1 - row[self._sample_col] = f"{sample}_T{seen[sample]}" - - -def read_head(handle, num_lines=10): - """Read the specified number of lines from the current position in the file.""" - lines = [] - for idx, line in enumerate(handle): - if idx == num_lines: - break - lines.append(line) - return "".join(lines) - - -def sniff_format(handle): - """ - Detect the tabular format. - - Args: - handle (text file): A handle to a `text file`_ object. The read position is - expected to be at the beginning (index 0). - - Returns: - csv.Dialect: The detected tabular format. - - .. _text file: - https://docs.python.org/3/glossary.html#term-text-file - - """ - peek = read_head(handle) - handle.seek(0) - sniffer = csv.Sniffer() - if not sniffer.has_header(peek): - logger.critical("The given sample sheet does not appear to contain a header.") - sys.exit(1) - dialect = sniffer.sniff(peek) - return dialect - - -def parse_args(argv=None): - """Define and immediately parse command line arguments.""" - parser = argparse.ArgumentParser( - description="Validate and transform a tabular samplesheet.", - epilog="Example: python check_samplesheet.py samplesheet.csv samplesheet.valid.csv", - ) - parser.add_argument( - "file_in", - metavar="FILE_IN", - type=Path, - help="Tabular input samplesheet in CSV or TSV format.", - ) - parser.add_argument( - "file_out", - metavar="FILE_OUT", - type=Path, - help="Transformed output samplesheet in CSV format.", - ) - parser.add_argument( - "-l", - "--log-level", - help="The desired log level (default WARNING).", - choices=("CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG"), - default="WARNING", - ) - return parser.parse_args(argv) - - -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_allele_nomenclature(allele): - pattern = re.compile("(^[A-Z][\*][0-9][0-9][:][0-9][0-9])$") - return pattern.match(allele) is not None - - -def make_dir(path): - if len(path) > 0: - try: - os.makedirs(path) - except OSError as exception: - if exception.errno != errno.EEXIST: - raise exception - - -def check_samplesheet(file_in, file_out): - """ - sample,alleles,mhc_class,filename - GBM_1,A*01:01;A*02:01;B*07:02;B*24:02;C*03:01;C*04:01,I,gbm_1_anno.vcf|gbm_1_peps.tsv|gbm_1_prot.fasta - GBM_2,A*02:01;A*24:01;B*07:02;B*08:01;C*04:01;C*07:01,I,gbm_2_anno.vcf|gbm_2_peps.tsv|gbm_2_prot.fasta - - or - - sample,alleles,mhc_class,filename - GBM_1,gbm_1_alleles.txt,I,gbm_1_anno.vcf|gbm_1_peps.tsv|gbm_1_prot.fasta - GBM_2,gbm_2_alleles.txt,I,gbm_2_anno.vcf|gbm_2_peps.tsv|gbm_2_prot.fasta - - - where the FileName column contains EITHER a vcf/tsv file with genomic variants, a tsv file (peptides), or a fasta file (proteins) - and the Alleles column contains EITHER a string of alleles separated by semicolon or the path to a text file - containing one allele per line (no header) - - Further examples: - - Class2 allele format => https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/testdata/alleles/alleles.DRB1_01_01.txt - - Mouse allele format => https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/testdata/alleles/alleles.H2.txt - - Peptide format => https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/testdata/peptides/peptides.tsv - - Variant TSV format => https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/testdata/variants/variants.tsv - - Variant VCF format => https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/testdata/variants/variants.vcf - """ - - sample_run_dict = {} - with open(file_in, "r") as fin: - ## Check header - COL_NUM = 4 - HEADER = ["sample", "alleles", "mhc_class", "filename"] - header = [x.strip('"') for x in fin.readline().strip().split(",")] - valid_classes = "I,II,H-2" - valid_class1_loci = ["A*", "B*", "C*", "E*", "G*"] - valid_class2_loci = ["DR", "DP", "DQ"] - if header[: len(HEADER)] != HEADER: - print("ERROR: Please check samplesheet header -> {} != {}".format("\t".join(header), "\t".join(HEADER))) - sys.exit(1) - - ## Check sample entries - for line in fin: - lspl = [x.strip('"').replace(" ", "") for x in line.strip().split(",")] - ## Check valid number of columns per row - if len(lspl) != len(HEADER): - print_error( - "Invalid number of columns (valid = {})!".format(len(HEADER)), - "Line", - line, - ) - num_cols = len([x for x in lspl if x]) - if num_cols != COL_NUM: - print_error( - "Invalid number of populated columns (valid = {})!".format(COL_NUM), - "Line", - line, - ) - - ## Check sample name entries - sample, alleles, mhcclass, filename = lspl[: len(HEADER)] - - ## Check given file types - if not filename.lower().endswith((".vcf", ".vcf.gz", ".tsv", ".GSvar", ".fasta", ".txt")): - print_error("Samplesheet contains unsupported file type!", "Line", line) - - # Check given mhc classes - if mhcclass not in valid_classes: - print_error("Samplesheet contains unsupported mhc class!", "Line", line) - - # Check mhc class and allele combintion - if ( - not os.path.isfile(alleles) - and mhcclass == "I" - and any(substring in alleles for substring in valid_class2_loci) - or mhcclass == "II" - and any(substring in alleles for substring in valid_class1_loci) - ): - print_error("Samplesheet contains invalid mhc class and allele combination!", "Line", line) - - sample_info = [sample, alleles, mhcclass, filename] - ## Create sample mapping dictionary - if sample not in sample_run_dict: - sample_run_dict[sample] = [sample_info] - else: - if sample_info in sample_run_dict[sample]: - print_error("Samplesheet contains duplicate rows!", "Line", line) - else: - sample_run_dict[sample].append(sample_info) - - ## Write validated samplesheet with appropriate columns - if len(sample_run_dict) > 0: - out_dir = os.path.dirname(file_out) - make_dir(out_dir) - with open(file_out, "w") as fout: - fout.write(",".join(["sample", "alleles", "mhc_class", "filename"]) + "\n") - - for sample in sorted(sample_run_dict.keys()): - for val in sample_run_dict[sample]: - fout.write(",".join(val) + "\n") - else: - print_error("No entries to process!", context="File", context_str="Samplesheet: {}".format(file_in)) - - -def main(argv=None): - """Coordinate argument parsing and program execution.""" - args = parse_args(argv) - logging.basicConfig(level=args.log_level, format="[%(levelname)s] %(message)s") - if not args.file_in.is_file(): - logger.error(f"The given input file {args.file_in} was not found!") - sys.exit(2) - args.file_out.parent.mkdir(parents=True, exist_ok=True) - check_samplesheet(args.file_in, args.file_out) - - -if __name__ == "__main__": - sys.exit(main()) diff --git a/bin/check_supported_models.py b/bin/check_supported_models.py index 8edc5ba..61c4801 100755 --- a/bin/check_supported_models.py +++ b/bin/check_supported_models.py @@ -2,9 +2,8 @@ # Written by Sabrina Krakau, Christopher Mohr and released under the MIT license. -import sys -import csv import argparse +import csv from epytope.EpitopePrediction import EpitopePredictorFactory @@ -30,7 +29,7 @@ def __main__(): # NOTE this needs to be updated manually, if other methods should be used in the future available_methods = ["syfpeithi", "mhcflurry", "mhcnuggets-class-1", "mhcnuggets-class-2"] - with open(args.versions, "r") as versions_file: + with open(args.versions) as versions_file: tool_version = [(row[0].split()[0], str(row[1])) for row in csv.reader(versions_file, delimiter=":")] # NOTE this needs to be updated, if a newer version will be available via Fred2 and should be used in the future tool_version.append(("syfpeithi", "1.0")) diff --git a/bin/epaa.py b/bin/epaa.py index 3f66b82..65a3151 100755 --- a/bin/epaa.py +++ b/bin/epaa.py @@ -1,30 +1,29 @@ #!/usr/bin/env python # Written by Christopher Mohr and released under the MIT license (2022). -import os -import sys -import logging -import csv -import re -import vcf import argparse -import urllib +import csv import itertools -import pandas as pd -import numpy as np -import epytope.Core.Generator as generator -import math import json +import logging +import math +import os +import re +import sys +from datetime import datetime -from epytope.IO.MartsAdapter import MartsAdapter -from epytope.Core.Variant import Variant, VariationType, MutationSyntax +import epytope.Core.Generator as generator +import numpy as np +import pandas as pd +import vcf +from Bio import SeqUtils +from epytope.Core.Allele import Allele +from epytope.Core.Peptide import Peptide +from epytope.Core.Variant import MutationSyntax, Variant, VariationType from epytope.EpitopePrediction import EpitopePredictorFactory from epytope.IO.ADBAdapter import EIdentifierTypes +from epytope.IO.MartsAdapter import MartsAdapter from epytope.IO.UniProtAdapter import UniProtDB -from epytope.Core.Allele import Allele -from epytope.Core.Peptide import Peptide -from Bio import SeqUtils -from datetime import datetime __author__ = "Christopher Mohr" VERSION = "1.1" @@ -40,7 +39,7 @@ logger.addHandler(handler) ID_SYSTEM_USED = EIdentifierTypes.ENSEMBL -transcriptProteinMap = {} +transcriptProteinTable = {} transcriptSwissProtMap = {} @@ -69,26 +68,6 @@ def get_epytope_annotation(vt, p, r, alt): return position, reference, alternative -def check_min_req_GSvar(row): - """ - checking the presence of mandatory columns - :param row: dictionary of a GSvar row - :return: boolean, True if min req met - """ - if ( - "#chr" in row.keys() - and "start" in row.keys() - and "end" in row.keys() - and "ref" in row.keys() - and "obs" in row.keys() - and ( - "coding_and_splicing_details" in row.keys() or "coding" in row.keys() or "coding_and_splicing" in row.keys() - ) - ): - return True - return False - - def determine_variant_type(record, alternative): vt = VariationType.UNKNOWN if record.is_snp: @@ -128,154 +107,6 @@ def determine_zygosity(record): return isHomozygous -def read_GSvar(filename, pass_only=True): - """ - reads GSvar and tsv files (tab sep files in context of genetic variants), omitting and warning about rows missing - mandatory columns - :param filename: /path/to/file - :return: list epytope variants - """ - global ID_SYSTEM_USED - RE = re.compile("(\w+):([\w.]+):([&\w]+):\w*:exon(\d+)\D*\d*:(c.\D*([_\d]+)\D*):(p.\D*(\d+)\w*)") - - # list of mandatory (meta)data - exclusion_list = [ - "start", - "end", - "#chr", - "ref", - "obs", - "gene", - "tumour_genotype", - "coding_and_splicing_details", - "variant_details", - "variant_type", - "coding_and_splicing", - ] - - list_vars = list() - lines = list() - transcript_ids = [] - dict_vars = {} - - cases = 0 - - with open(filename, "rt") as tsvfile: - tsvreader = csv.DictReader((row for row in tsvfile if not row.startswith("##")), delimiter="\t") - for row in tsvreader: - if not check_min_req_GSvar(row): - logger.warning("read_GSvar: Omitted row! Mandatory columns not present in: \n" + str(row) + ".") - continue - lines.append(row) - - # get list of additional metadata - metadata_list = set(tsvreader.fieldnames) - set(exclusion_list) - - for mut_id, line in enumerate(lines): - if "filter" in line and pass_only and line["filter"].strip(): - continue - genome_start = int(line["start"]) - 1 - genome_stop = int(line["end"]) - 1 - chrom = line["#chr"] - ref = line["ref"] - alt = line["obs"] - gene = line.get("gene", "") - - isHomozygous = ( - True - if ( - ("tumour_genotype" in line) - and (line["tumour_genotype"].split("/")[0] == line["tumour_genotype"].split("/")[1]) - ) - else False - ) - - # old GSvar version - if "coding_and_splicing_details" in line: - mut_type = line.get("variant_details", "") - annots = RE.findall(line["coding_and_splicing_details"]) - else: - mut_type = line.get("variant_type", "") - # Gene, transcript number, type, impact, exon/intron number, HGVS.c, HGVS.p, Pfam - annots = RE.findall(line["coding_and_splicing"]) - isyn = mut_type == "synonymous_variant" - - """ - Enum for variation types: - type.SNP, type.DEL, type.INS, type.FSDEL, type.FSINS, type.UNKNOWN - """ - vt = VariationType.UNKNOWN - if mut_type == "missense_variant" or "missense_variant" in mut_type: - vt = VariationType.SNP - elif mut_type == "frameshift_variant": - if (ref == "-") or (len(ref) < len(alt)): - vt = VariationType.FSINS - else: - vt = VariationType.FSDEL - elif mut_type == "inframe_deletion": - vt = VariationType.DEL - elif mut_type == "inframe_insertion": - vt = VariationType.INS - - coding = dict() - - for annot in annots: - a_gene, transcript_id, a_mut_type, exon, trans_coding, trans_pos, prot_coding, prot_start = annot - if "NM" in transcript_id: - ID_SYSTEM_USED = EIdentifierTypes.REFSEQ - if "stop_gained" not in mut_type: - if not gene: - gene = a_gene - if not mut_type: - mut_type = a_mut_type - - # TODO with the next epytope release we can deal with transcript id version - transcript_id = transcript_id.split(".")[0] - - coding[transcript_id] = MutationSyntax( - transcript_id, int(trans_pos.split("_")[0]) - 1, int(prot_start) - 1, trans_coding, prot_coding - ) - transcript_ids.append(transcript_id) - if coding: - var = Variant( - mut_id, - vt, - chrom.strip("chr"), - int(genome_start), - ref.upper(), - alt.upper(), - coding, - isHomozygous, - isSynonymous=isyn, - ) - var.gene = gene - - # metadata logging - for meta_name in metadata_list: - var.log_metadata(meta_name, line.get(meta_name, "")) - - dict_vars[var] = var - list_vars.append(var) - - transToVar = {} - - # fix because of memory/timing issues due to combinatorial explosion - for variant in list_vars: - for trans_id in variant.coding.keys(): - transToVar.setdefault(trans_id, []).append(variant) - - for tId, vs in transToVar.items(): - if len(vs) > 10: - cases += 1 - for v in vs: - vs_new = Variant(v.id, v.type, v.chrom, v.genomePos, v.ref, v.obs, v.coding, True, v.isSynonymous) - vs_new.gene = v.gene - for m in metadata_list: - vs_new.log_metadata(m, v.get_metadata(m)[0]) - dict_vars[v] = vs_new - return dict_vars.values(), transcript_ids, metadata_list - - def read_vcf(filename, pass_only=True): """ reads vcf files @@ -318,7 +149,7 @@ def read_vcf(filename, pass_only=True): SNPEFF_KEY = "ANN" variants = list() - with open(filename, "rt") as tsvfile: + with open(filename) as tsvfile: vcf_reader = vcf.Reader(tsvfile) variants = [r for r in vcf_reader] @@ -364,8 +195,7 @@ def read_vcf(filename, pass_only=True): SNP => seq[pos] = OBS (replace) INSERTION => seqp[pos:pos] = obs (insert at that position) - DELETION => s = slice(pos, pos+len(ref)) (create slice that will be removed) - del seq[s] (remove) + DELETION => s = slice(pos, pos+len(ref)) (create slice that will be removed) del seq[s] (remove) """ for alt in alternative_list: isHomozygous = determine_zygosity(record) @@ -419,8 +249,7 @@ def read_vcf(filename, pass_only=True): positions = re.findall(r"\d+", prot_coding) tpos = int(positions[0]) - 1 - # TODO with the new epytope release we will support transcript IDs with version - transcript_id = transcript_id.split(".")[0] + # with the latest epytope release (3.3.1), we can now handle full transcript IDs if "NM" in transcript_id: ID_SYSTEM_USED = EIdentifierTypes.REFSEQ @@ -451,7 +280,6 @@ def read_vcf(filename, pass_only=True): split_coding_c[0] if split_coding_c[0] else split_annotation[vep_fields["feature"]] ) transcript_id = transcript_id.split(".")[0] - tpos = int(cds_pos.split("/")[0].split("-")[0]) - 1 if split_annotation[vep_fields["protein_position"]]: ppos = ( @@ -487,12 +315,10 @@ def read_vcf(filename, pass_only=True): for format_key in format_list: if getattr(sample.data, format_key, None) is None: logger.warning( - "FORMAT entry {entry} not defined for {genotype}. Skipping.".format( - entry=format_key, genotype=sample.sample - ) + f"FORMAT entry {format_key} not defined for {sample.sample}. Skipping." ) continue - format_header = "{}.{}".format(sample.sample, format_key) + format_header = f"{sample.sample}.{format_key}" final_metadata_list.append(format_header) if isinstance(sample[format_key], list): format_value = ",".join([str(i) for i in sample[format_key]]) @@ -531,7 +357,7 @@ def read_peptide_input(filename): metadata = [] """expected columns (min required): id sequence""" - with open(filename, "r") as peptide_input: + with open(filename) as peptide_input: # enable listing of protein names for each peptide csv.field_size_limit(600000) reader = csv.DictReader(peptide_input, delimiter="\t") @@ -553,7 +379,7 @@ def read_protein_quant(filename): # protein id: sample1: intensity, sample2: intensity: intensities = {} - with open(filename, "r") as inp: + with open(filename) as inp: inpreader = csv.DictReader(inp, delimiter="\t") for row in inpreader: if "REV" in row["Protein IDs"]: @@ -574,7 +400,7 @@ def read_diff_expression_values(filename): # feature id: log2fold changes fold_changes = {} - with open(filename, "r") as inp: + with open(filename) as inp: inp.readline() for row in inp: values = row.strip().split("\t") @@ -588,7 +414,7 @@ def read_lig_ID_values(filename): # sequence: score median intensity intensities = {} - with open(filename, "r") as inp: + with open(filename) as inp: reader = csv.DictReader(inp, delimiter=",") for row in reader: seq = re.sub("[\(].*?[\)]", "", row["sequence"]) @@ -598,13 +424,17 @@ def read_lig_ID_values(filename): def create_protein_column_value(pep): + # retrieve Ensembl protein ID for given transcript IDs, if we want to provide additional protein ID types, adapt here all_proteins = [ - transcriptProteinMap[transcript.transcript_id.split(":")[0]] for transcript in set(pep.get_all_transcripts()) + # split by : otherwise epytope generator suffix included + transcriptProteinTable.query(f'transcript_id == "{transcript.transcript_id.split(":")[0]}"')["ensembl_id"] + for transcript in set(pep.get_all_transcripts()) ] return ",".join(set([item for sublist in all_proteins for item in sublist])) def create_transcript_column_value(pep): + # split by : otherwise epytope generator suffix included return ",".join(set([transcript.transcript_id.split(":")[0] for transcript in set(pep.get_all_transcripts())])) @@ -629,11 +459,11 @@ def create_gene_column_value(pep, pep_dictionary): def create_variant_pos_column_value(pep, pep_dictionary): - return ",".join(set(["{}".format(variant.genomePos) for variant in set(pep_dictionary[pep])])) + return ",".join(set([f"{variant.genomePos}" for variant in set(pep_dictionary[pep])])) def create_variant_chr_column_value(pep, pep_dictionary): - return ",".join(set(["{}".format(variant.chrom) for variant in set(pep_dictionary[pep])])) + return ",".join(set([f"{variant.chrom}" for variant in set(pep_dictionary[pep])])) def create_variant_type_column_value(pep, pep_dictionary): @@ -661,7 +491,7 @@ def create_metadata_column_value(pep, c, pep_dictionary): if len(variant.get_metadata(c)) != 0 ] ) - if len(meta) is 0: + if len(meta) == 0: return np.nan else: return ",".join(meta) @@ -676,7 +506,7 @@ def create_wt_seq_column_value(pep, wtseqs): if bool(transcript.vars) and "{}_{}".format(str(pep["sequence"]), transcript.transcript_id) in wtseqs ] ) - if len(wild_type) is 0: + if len(wild_type) == 0: return np.nan else: return ",".join(wild_type) @@ -735,13 +565,11 @@ def create_expression_column_value_for_result(row, dict, deseq, gene_id_lengths) ) ) logger.warning( - "FKPM value will be based on transcript length for {gene}. Because gene could not be found in the DB".format( - gene=t - ) + f"FKPM value will be based on transcript length for {t}. Because gene could not be found in the DB" ) else: values.append(np.nan) - values = ["{0:.2f}".format(value) for value in values] + values = [f"{value:.2f}" for value in values] return ",".join(values) @@ -755,7 +583,7 @@ def create_quant_column_value_for_result(row, dict, swissProtDict, key): values.append(math.log(int(dict[p][key]), 2)) else: values.append(int(dict[p][key])) - if len(values) is 0: + if len(values) == 0: return np.nan else: return ",".join(set([str(v) for v in values])) @@ -772,91 +600,6 @@ def create_ligandomics_column_value_for_result(row, lig_id, val, wild_type): return "" -def get_protein_ids_for_transcripts(idtype, transcripts, ensembl_url, reference): - result = {} - result_swissProt = {} - - biomart_url = "{}/biomart/martservice?query=".format(ensembl_url) - biomart_head = """ - - - - - """.strip() - biomart_tail = """ - - - """.strip() - biomart_filter = """""" - biomart_attribute = """""" - - ENSEMBL = False - if idtype == EIdentifierTypes.ENSEMBL: - idname = "ensembl_transcript_id" - ENSEMBL = True - elif idtype == EIdentifierTypes.REFSEQ: - idname = "refseq_mrna" - - input_lists = [] - - # too long requests will fail - if len(transcripts) > 200: - input_lists = [transcripts[i : i + 3] for i in range(0, len(transcripts), 3)] - - else: - input_lists += [transcripts] - - attribut_swissprot = "uniprot_swissprot_accession" if reference == "GRCh37" else "uniprotswissprot" - - tsvselect = [] - for l in input_lists: - rq_n = ( - biomart_head % ("hsapiens_gene_ensembl", "default") - + biomart_filter % (idname, ",".join(l)) - + biomart_attribute % ("ensembl_peptide_id") - + biomart_attribute % (attribut_swissprot) - + biomart_attribute % ("refseq_peptide") - + biomart_attribute % (idname) - + biomart_tail - ) - - # DictReader returns byte object that is transformed into a string by '.decode('utf-8')' - tsvreader = csv.DictReader( - urllib.request.urlopen(biomart_url + urllib.parse.quote(rq_n)).read().decode("utf-8").splitlines(), - dialect="excel-tab", - ) - - tsvselect += [x for x in tsvreader] - - swissProtKey = "UniProt/SwissProt Accession" if reference == "GRCh37" else "UniProtKB/Swiss-Prot ID" - - if ENSEMBL: - key = "Ensembl Transcript ID" if reference == "GRCh37" else "Transcript stable ID" - protein_key = "Ensembl Protein ID" if reference == "GRCh37" else "Protein stable ID" - for dic in tsvselect: - if dic[key] in result: - merged = result[dic[key]] + [dic[protein_key]] - merged_swissProt = result_swissProt[dic[key]] + [dic[swissProtKey]] - result[dic[key]] = merged - result_swissProt[dic[key]] = merged_swissProt - else: - result[dic[key]] = [dic[protein_key]] - result_swissProt[dic[key]] = [dic[swissProtKey]] - else: - key = "RefSeq mRNA [e.g. NM_001195597]" - for dic in tsvselect: - if dic[key] in result: - merged = result[dic[key]] + [dic["RefSeq Protein ID [e.g. NP_001005353]"]] - merged_swissProt = result_swissProt[dic[key]] + [dic[swissProtKey]] - result[dic[key]] = merged - result_swissProt[dic[key]] = merged_swissProt - else: - result[dic[key]] = [dic["RefSeq Protein ID [e.g. NP_001005353]"]] - result_swissProt[dic[key]] = [dic[swissProtKey]] - - return result, result_swissProt - - def get_matrix_max_score(allele, length): allele_model = "%s_%i" % (allele, length) try: @@ -926,9 +669,9 @@ def generate_wt_seqs(peptides): wt = SeqUtils.seq1(m.groups()[0]) mut_seq[key] = wt if not_available: - wt_dict["{}_{}".format(str(x), t.transcript_id)] = np.nan + wt_dict[f"{str(x)}_{t.transcript_id}"] = np.nan elif variant_available: - wt_dict["{}_{}".format(str(x), t.transcript_id)] = "".join(mut_seq) + wt_dict[f"{str(x)}_{t.transcript_id}"] = "".join(mut_seq) return wt_dict @@ -944,25 +687,6 @@ def create_peptide_variant_dictionary(peptides): return pep_to_variants -# TODO replace by epytope function once released -def is_created_by_variant(peptide): - transcript_ids = [x.transcript_id for x in set(peptide.get_all_transcripts())] - for t in transcript_ids: - p = peptide.proteins[t] - varmap = p.vars - for pos, vars in varmap.items(): - for var in vars: - if var.type in [VariationType.FSDEL, VariationType.FSINS]: - if peptide.proteinPos[t][0] + len(peptide) > pos: - return True - else: - for start_pos in peptide.proteinPos[t]: - positions = list(range(start_pos, start_pos + len(peptide))) - if pos in positions: - return True - return False - - def make_predictions_from_variants( variants_all, methods, @@ -975,7 +699,7 @@ def make_predictions_from_variants( protein_db, identifier, metadata, - transcriptProteinMap, + transcriptProteinTable, ): # list for all peptides and filtered peptides all_peptides = [] @@ -987,7 +711,6 @@ def make_predictions_from_variants( # list to hold dataframes for all predictions pred_dataframes = [] - prots = [ p for p in generator.generate_proteins_from_transcripts( @@ -999,7 +722,7 @@ def make_predictions_from_variants( peptide_gen = generator.generate_peptides_from_proteins(prots, peplen) peptides_var = [x for x in peptide_gen] - peptides = [p for p in peptides_var if is_created_by_variant(p)] + peptides = [p for p in peptides_var if p.is_created_by_variant()] # filter out self peptides selfies = [str(p) for p in peptides if protein_db.exists(str(p))] @@ -1265,11 +988,10 @@ def __main__(): parser.add_argument("-a", "--alleles", help=" MHC Alleles", required=True, type=str) parser.add_argument( "-r", - "--reference", + "--genome_reference", help="Reference, retrieved information will be based on this ensembl version", required=False, - default="GRCh37", - choices=["GRCh37", "GRCh38"], + default="https://grch37.ensembl.org/", ) parser.add_argument( "-f", "--filter_self", help="Filter peptides against human proteom", required=False, action="store_true" @@ -1303,7 +1025,7 @@ def __main__(): parser.print_help() sys.exit("Provide at least one argument to epaa.py.") - filehandler = logging.FileHandler("{}_prediction.log".format(args.identifier)) + filehandler = logging.FileHandler(f"{args.identifier}_prediction.log") filehandler.setLevel(logging.DEBUG) filehandler.setFormatter(formatter) logger.addHandler(filehandler) @@ -1313,34 +1035,30 @@ def __main__(): metadata = [] proteins = [] - references = {"GRCh37": "http://feb2014.archive.ensembl.org", "GRCh38": "http://apr2018.archive.ensembl.org"} - global transcriptProteinMap + global transcriptProteinTable global transcriptSwissProtMap + # initialize MartsAdapter + # in previous version, these were the defaults "GRCh37": "http://feb2014.archive.ensembl.org" (broken) + # "GRCh38": "http://apr2018.archive.ensembl.org" (different dataset table scheme, could potentially be fixed on BiomartAdapter level if needed ) + ma = MartsAdapter(biomart=args.genome_reference) + # read in variants or peptides if args.peptides: logger.info("Running epaa for peptides...") peptides, metadata = read_peptide_input(args.peptides) else: - if args.somatic_mutations.endswith(".GSvar") or args.somatic_mutations.endswith(".tsv"): - logger.info("Running epaa for variants...") - variant_list, transcripts, metadata = read_GSvar(args.somatic_mutations) - elif args.somatic_mutations.endswith(".vcf"): + logger.info("Running epaa for variants...") + if args.somatic_mutations.endswith(".vcf"): variant_list, transcripts, metadata = read_vcf(args.somatic_mutations) - - transcripts = list(set(transcripts)) - transcriptProteinMap, transcriptSwissProtMap = get_protein_ids_for_transcripts( - ID_SYSTEM_USED, transcripts, references[args.reference], args.reference - ) + transcripts = list(set(transcripts)) + else: + raise ValueError("File is not in VCF format. Please provide a VCF file.") # get the alleles - # alleles = FileReader.read_lines(args.alleles, in_type=Allele) alleles = [Allele(a) for a in args.alleles.split(";")] - # initialize MartsAdapter, GRCh37 or GRCh38 based - ma = MartsAdapter(biomart=references[args.reference]) - # create protein db instance for filtering self-peptides up_db = UniProtDB("sp") if args.filter_self: @@ -1354,7 +1072,7 @@ def __main__(): up_db.read_seqs(args.reference_proteome) selected_methods = [item.split("-")[0] if "mhcnuggets" not in item else item for item in args.tools.split(",")] - with open(args.versions, "r") as versions_file: + with open(args.versions) as versions_file: tool_version = [(row[0].split()[0], str(row[1])) for row in csv.reader(versions_file, delimiter=":")] # NOTE this needs to be updated, if a newer version will be available via epytope and should be used in the future tool_version.append(("syfpeithi", "1.0")) @@ -1386,7 +1104,7 @@ def __main__(): thresholds.update({"netmhc": 2, "netmhcpan": 2, "netmhcii": 10, "netmhciipan": 5}) if args.tool_thresholds: - with open(args.tool_thresholds, "r") as json_file: + with open(args.tool_thresholds) as json_file: threshold_file = json.load(json_file) for tool, thresh in threshold_file.items(): if tool in thresholds.keys(): @@ -1399,7 +1117,15 @@ def __main__(): pred_dataframes, statistics = make_predictions_from_peptides( peptides, methods, thresholds, args.use_affinity_thresholds, alleles, up_db, args.identifier, metadata ) + elif len(transcripts) == 0: + logger.warning(f"No transcripts found for variants in {args.somatic_mutations}") + pred_dataframes = [] + statistics = {} + all_peptides_filtered = [] + proteins = [] else: + # use function provided by epytope to retrieve protein IDs (different systems) for transcript IDs + transcriptProteinTable = ma.get_protein_ids_from_transcripts(transcripts, type=EIdentifierTypes.ENSEMBL) pred_dataframes, statistics, all_peptides_filtered, proteins = make_predictions_from_variants( variant_list, methods, @@ -1412,7 +1138,7 @@ def __main__(): up_db, args.identifier, metadata, - transcriptProteinMap, + transcriptProteinTable, ) # concat dataframes for all peptide lengths @@ -1491,7 +1217,7 @@ def __main__(): protein_quant = read_protein_quant(args.protein_quantification) first_entry = protein_quant[protein_quant.keys()[0]] for k in first_entry.keys(): - complete_df["{} log2 protein LFQ intensity".format(k)] = complete_df.apply( + complete_df[f"{k} log2 protein LFQ intensity"] = complete_df.apply( lambda row: create_quant_column_value_for_result(row, protein_quant, transcriptSwissProtMap, k), axis=1 ) # parse (differential) expression analysis results, annotate features (genes/transcripts) @@ -1500,7 +1226,7 @@ def __main__(): gene_id_lengths = {} col_name = "RNA expression (RPKM)" - with open(args.gene_reference, "r") as gene_list: + with open(args.gene_reference) as gene_list: for l in gene_list: ids = l.split("\t") gene_id_in_df = complete_df.iloc[1]["gene"] @@ -1543,7 +1269,7 @@ def __main__(): ) # write mutated protein sequences to fasta file if args.fasta_output and predictions_available: - with open("{}_prediction_proteins.fasta".format(args.identifier), "w") as protein_outfile: + with open(f"{args.identifier}_prediction_proteins.fasta", "w") as protein_outfile: for p in proteins: variants = [] for v in p.vars: @@ -1552,15 +1278,15 @@ def __main__(): cf = list(itertools.chain.from_iterable(c)) cds = ",".join([y.cdsMutationSyntax for y in set(cf)]) aas = ",".join([y.aaMutationSyntax for y in set(cf)]) - protein_outfile.write(">{}:{}:{}\n".format(p.transcript_id, aas, cds)) - protein_outfile.write("{}\n".format(str(p))) + protein_outfile.write(f">{p.transcript_id}:{aas}:{cds}\n") + protein_outfile.write(f"{str(p)}\n") complete_df["binder"] = complete_df[[col for col in complete_df.columns if "binder" in col]].any(axis=1) # write dataframe to tsv complete_df.fillna("") if predictions_available: - complete_df.to_csv("{}_prediction_result.tsv".format(args.identifier), "\t", index=False) + complete_df.to_csv(f"{args.identifier}_prediction_result.tsv", "\t", index=False) statistics["tool_thresholds"] = thresholds statistics["number_of_predictions"] = len(complete_df) @@ -1569,7 +1295,7 @@ def __main__(): statistics["number_of_unique_binders"] = list(set(binders)) statistics["number_of_unique_nonbinders"] = list(set(non_binders) - set(binders)) - with open("{}_report.json".format(args.identifier), "w") as json_out: + with open(f"{args.identifier}_report.json", "w") as json_out: json.dump(statistics, json_out) logger.info("Finished predictions at " + str(datetime.now().strftime("%Y-%m-%d %H:%M:%S"))) diff --git a/bin/gen_peptides.py b/bin/gen_peptides.py index 50613a0..d962ed3 100755 --- a/bin/gen_peptides.py +++ b/bin/gen_peptides.py @@ -1,13 +1,11 @@ #!/usr/bin/env python # Written by Sabrina Krakau, Christopher Mohr and released under the MIT license (2022). -import sys import argparse -import pandas as pd +import pandas as pd from Bio.SeqIO.FastaIO import SimpleFastaParser -from epytope.Core import Allele, Peptide, Protein, generate_peptides_from_proteins - +from epytope.Core import Protein, generate_peptides_from_proteins parser = argparse.ArgumentParser("Generating peptides from protein sequences.") parser.add_argument( diff --git a/bin/merge_jsons.py b/bin/merge_jsons.py index 75330ce..f6ebd34 100755 --- a/bin/merge_jsons.py +++ b/bin/merge_jsons.py @@ -2,10 +2,10 @@ # Written by Sabrina Krakau, Christopher Mohr, Gisela Gabernet and released under the MIT license (2022). +import argparse +import json import os import sys -import json -import argparse def __main__(): @@ -43,14 +43,14 @@ def combine_dicts(a, b): # read in json reports data = dict() if args.single_input: - with open(args.single_input, "r") as infile: + with open(args.single_input) as infile: json_content = json.load(infile) data = combine_dicts(data, json_content) else: for file in os.listdir(args.input): if file.endswith(".json"): - with open(os.path.join(args.input, file), "r") as infile: + with open(os.path.join(args.input, file)) as infile: json_content = json.load(infile) data = combine_dicts(data, json_content) @@ -69,7 +69,7 @@ def combine_dicts(a, b): data["number_of_predictions"] = sum(list(flatten(data["number_of_predictions"]))) data["number_of_variants"] = sum(list(flatten(data["number_of_variants"]))) - with open("{}_prediction_report.json".format(args.prefix), "w") as outfile: + with open(f"{args.prefix}_prediction_report.json", "w") as outfile: json.dump(data, outfile) diff --git a/bin/split_peptides.py b/bin/split_peptides.py index 5c96dad..4e31134 100755 --- a/bin/split_peptides.py +++ b/bin/split_peptides.py @@ -2,9 +2,8 @@ # Written by Sabrina Krakau, Christopher Mohr and released under the MIT license (2022). -import math import argparse - +import math parser = argparse.ArgumentParser("Split peptides input file.") parser.add_argument("-i", "--input", metavar="FILE", type=str, help="Input file containing peptides.") @@ -17,13 +16,13 @@ ) args = parser.parse_args() -with open(args.input, "r") as infile: +with open(args.input) as infile: tot_size = sum([1 for _ in infile]) - 1 n = int(min(math.ceil(float(tot_size) / args.min_size), args.max_chunks)) h = int(max(args.min_size, math.ceil(float(tot_size) / n))) -with open(args.input, "r") as infile: +with open(args.input) as infile: header = next(infile) for chunk in range(n): with open(args.output_base + ".chunk_" + str(chunk) + ".tsv", "w") as outfile: diff --git a/bin/split_vcf_by_variants.py b/bin/split_vcf_by_variants.py index 5c389f1..fade55e 100755 --- a/bin/split_vcf_by_variants.py +++ b/bin/split_vcf_by_variants.py @@ -2,14 +2,13 @@ # Written by Christopher Mohr and released under the MIT license (2022). import argparse -import logging import csv +import logging import os -from typing import Optional def determine_split_size(input_file, size): - with open(input_file, "r") as variants: + with open(input_file) as variants: input_lines = variants.readlines() num_variants = sum(1 for i in input_lines if not i.startswith("#")) if not size: @@ -57,7 +56,7 @@ def main(): metadata = "" var_group = "" - with open(args.input, "r") as input_file: + with open(args.input) as input_file: vcf_file = csv.reader(input_file, delimiter="\t") for line in vcf_file: diff --git a/conf/base.config b/conf/base.config index 8f7d465..80b52ab 100644 --- a/conf/base.config +++ b/conf/base.config @@ -15,9 +15,9 @@ process { memory = { check_max( 7.GB * task.attempt, 'memory' ) } time = { check_max( 4.h * task.attempt, 'time' ) } - errorStrategy = { task.exitStatus in [143,137,104,134,139] ? 'retry' : 'finish' } - maxRetries = 3 - maxErrors = '-1' + errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' } + maxRetries = 3 + maxErrors = '-1' // Process-specific resource requirements withLabel:process_single { diff --git a/conf/igenomes.config b/conf/igenomes.config index 7a1b3ac..3f11437 100644 --- a/conf/igenomes.config +++ b/conf/igenomes.config @@ -36,6 +36,14 @@ params { macs_gsize = "2.7e9" blacklist = "${projectDir}/assets/blacklists/hg38-blacklist.bed" } + 'CHM13' { + fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/BWAIndex/" + bwamem2 = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/BWAmem2Index/" + gtf = "${params.igenomes_base}/Homo_sapiens/NCBI/CHM13/Annotation/Genes/genes.gtf" + gff = "ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/914/755/GCF_009914755.1_T2T-CHM13v2.0/GCF_009914755.1_T2T-CHM13v2.0_genomic.gff.gz" + mito_name = "chrM" + } 'GRCm38' { fasta = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.fa" bwa = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BWAIndex/version0.6.0/" diff --git a/conf/modules.config b/conf/modules.config index 8886348..6ee473f 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -10,6 +10,8 @@ ---------------------------------------------------------------------------------------- */ +def genome_reference = params.genome_reference.toLowerCase() + process { publishDir = [ @@ -18,23 +20,20 @@ process { saveAs: { filename -> filename.equals('versions.yml') ? null : filename } ] - withName: MULTIQC { - ext.args = '' - } - - withName: SAMPLESHEET_CHECK { + withName: CUSTOM_DUMPSOFTWAREVERSIONS { publishDir = [ path: { "${params.outdir}/pipeline_info" }, mode: params.publish_dir_mode, - saveAs: { filename -> filename.equals('versions.yml') ? null : filename } + pattern: '*_versions.yml' ] } - withName: CUSTOM_DUMPSOFTWAREVERSIONS { + withName: 'MULTIQC' { + ext.args = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' } publishDir = [ - path: { "${params.outdir}/pipeline_info" }, + path: { "${params.outdir}/multiqc" }, mode: params.publish_dir_mode, - pattern: '*_versions.yml' + saveAs: { filename -> filename.equals('versions.yml') ? null : filename } ] } @@ -71,30 +70,45 @@ process { } withName: EPYTOPE_PEPTIDE_PREDICTION_PROTEIN { + // Argument list needs to end with --peptides + ext.args = [ + genome_reference != 'grch37' & genome_reference != 'grch38' ? "--genome_reference '${genome_reference}'" : '', + genome_reference == 'grch37' ? "--genome_reference 'https://grch37.ensembl.org/'" : '', + genome_reference == 'grch38' ? "--genome_reference 'https://www.ensembl.org'" : '', + '--peptides' + ].join(' ').trim() publishDir = [ path: { "${params.outdir}/split_predictions/${meta.sample}" }, mode: params.publish_dir_mode ] - // Argument list needs to end with --peptides - ext.args = "--reference ${params.genome_version} --peptides" } withName: EPYTOPE_PEPTIDE_PREDICTION_PEP { + // Argument list needs to end with --peptides + ext.args = [ + genome_reference != 'grch37' & genome_reference != 'grch38' ? "--genome_reference '${genome_reference}'" : '', + genome_reference == 'grch37' ? "--genome_reference 'https://grch37.ensembl.org/'" : '', + genome_reference == 'grch38' ? "--genome_reference 'https://www.ensembl.org'" : '', + '--peptides' + ].join(' ').trim() publishDir = [ path: { "${params.outdir}/split_predictions/${meta.sample}" }, mode: params.publish_dir_mode ] - // Argument list needs to end with --peptides - ext.args = "--reference ${params.genome_version} --peptides" } withName: EPYTOPE_PEPTIDE_PREDICTION_VAR { + // Argument list needs to end with --somatic_mutation + ext.args = [ + genome_reference != 'grch37' & genome_reference != 'grch38' ? "--genome_reference '${genome_reference}'" : '', + genome_reference == 'grch37' ? "--genome_reference 'https://grch37.ensembl.org/'" : '', + genome_reference == 'grch38' ? "--genome_reference 'https://www.ensembl.org'" : '', + '--somatic_mutation' + ].join(' ').trim() publishDir = [ path: { "${params.outdir}/split_predictions/${meta.sample}" }, mode: params.publish_dir_mode ] - // Argument list needs to end with --somatic_mutation - ext.args = "--reference ${params.genome_version} --somatic_mutation" } withName: MERGE_JSON_SINGLE { @@ -126,13 +140,6 @@ process { ] } - withName: CSVTK_SPLIT { - publishDir = [ - path: { "${params.outdir}/split_input/${meta.sample}" }, - mode: params.publish_dir_mode - ] - } - withName: GET_PREDICTION_VERSIONS { publishDir = [ path: { "${params.outdir}/reports" }, @@ -180,4 +187,5 @@ process { mode: params.publish_dir_mode ] } + } diff --git a/conf/test.config b/conf/test.config index 681012d..749c8e3 100644 --- a/conf/test.config +++ b/conf/test.config @@ -17,7 +17,6 @@ params { // Input data input = 'https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/testdata/sample_sheets/sample_sheet_variants.csv' - schema_ignore_params = 'genomes,input_paths' // Limit resources so that this can run on GitHub Actions max_cpus = 2 diff --git a/conf/test_full.config b/conf/test_full.config index f1fa9ef..b21c2b3 100644 --- a/conf/test_full.config +++ b/conf/test_full.config @@ -16,6 +16,5 @@ params { // Input data for full size test input = 'https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/testdata/sample_sheets/sample_sheet_full_test.csv' - schema_ignore_params = 'genomes,input_paths' tools = 'syfpeithi,mhcflurry,mhcnuggets-class-1,mhcnuggets-class-2' } diff --git a/conf/test_grch38_variant_tsv.config b/conf/test_grch38.config similarity index 85% rename from conf/test_grch38_variant_tsv.config rename to conf/test_grch38.config index 61d804a..0c2bbd0 100644 --- a/conf/test_grch38_variant_tsv.config +++ b/conf/test_grch38.config @@ -4,7 +4,7 @@ * ------------------------------------------------- * Defines bundled input files and everything required * to run a fast and simple test. Use as follows: - * nextflow run nf-core/epitopeprediction -profile test_grch38_variant_tsv, --outdir + * nextflow run nf-core/epitopeprediction -profile test_grch38, --outdir */ params { @@ -13,6 +13,6 @@ params { max_time = 48.h // Input data - input = 'https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/testdata/sample_sheets/sample_sheet_variants_tab.csv' - genome_version = 'GRCh38' + input = 'https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/testdata/sample_sheets/sample_sheet_variants.csv' + genome_reference = 'grch38' } diff --git a/conf/test_variant_tsv.config b/conf/test_variant_tsv.config deleted file mode 100644 index f54d1bc..0000000 --- a/conf/test_variant_tsv.config +++ /dev/null @@ -1,17 +0,0 @@ -/* - * ------------------------------------------------- - * Nextflow config file for running tests - * ------------------------------------------------- - * Defines bundled input files and everything required - * to run a fast and simple test. Use as follows: - * nextflow run nf-core/epitopeprediction -profile test_variant_tsv, --outdir - */ - -params { - max_cpus = 2 - max_memory = 6.GB - max_time = 48.h - - // Input data - input = 'https://raw.githubusercontent.com/nf-core/test-datasets/epitopeprediction/testdata/sample_sheets/sample_sheet_variants_tab.csv' -} diff --git a/docs/images/nf-core-epitopeprediction_logo_dark.png b/docs/images/nf-core-epitopeprediction_logo_dark.png index 7c16270..42629eb 100644 Binary files a/docs/images/nf-core-epitopeprediction_logo_dark.png and b/docs/images/nf-core-epitopeprediction_logo_dark.png differ diff --git a/docs/images/nf-core-epitopeprediction_logo_light.png b/docs/images/nf-core-epitopeprediction_logo_light.png index 40ba75d..bbaf60a 100644 Binary files a/docs/images/nf-core-epitopeprediction_logo_light.png and b/docs/images/nf-core-epitopeprediction_logo_light.png differ diff --git a/docs/output.md b/docs/output.md index ebb2f96..bda154a 100644 --- a/docs/output.md +++ b/docs/output.md @@ -97,6 +97,7 @@ When running the pipeline using the `--show_supported_models` parameter, informa - Reports generated by Nextflow: `execution_report.html`, `execution_timeline.html`, `execution_trace.txt` and `pipeline_dag.dot`/`pipeline_dag.svg`. - Reports generated by the pipeline: `pipeline_report.html`, `pipeline_report.txt` and `software_versions.yml`. The `pipeline_report*` files will only be present if the `--email` / `--email_on_fail` parameter's are used when running the pipeline. - Reformatted samplesheet files used as input to the pipeline: `samplesheet.valid.csv`. + - Parameters used by the pipeline run: `params.json`. diff --git a/docs/usage.md b/docs/usage.md index 825ec22..08ff5e3 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -16,12 +16,15 @@ You will need to create a samplesheet with information about the samples you wou ### Input Formats -The pipeline currently accepts three different types of input that are genomic variants, peptides and proteins. The supported file formats for genomic variants are `.vcf`, `.vcf.gz` and `tsv`. - -:warning: Please note that genomic variants have to be annotated. Currently, we support variants that have been annotated using [SnpEff](http://pcingola.github.io/SnpEff/). Support for [VEP](https://www.ensembl.org/info/docs/tools/vep/index.html) will be available with one of the upcoming versions. +The pipeline currently accepts three different types of input that are genomic variants, peptides and proteins. #### Genomic variants +The supported file formats for genomic variants are `.vcf`, `.vcf.gz`. + +> [!IMPORTANT] +> Please note that genomic variants have to be annotated. Currently, we support variants that have been annotated using [SnpEff](http://pcingola.> github.io/SnpEff/) and [VEP](https://www.ensembl.org/info/docs/tools/vep/index.html). + `tsv` files with genomic variants have to provide the following columns: ```console @@ -32,6 +35,13 @@ chr1 12954870 12954870 C T . 0 NORMAL:414,TUMOR:8 . missense_variant 0.5 transcr ``` +For genomic variants, reference information from `Ensembl BioMart` is used. The default database version is the most recent `GRCh37` version. If you want to do the predictions based on `GRCh38` as the reference genome, please specify `--genome_reference grch38` in your pipeline call. + +You can also specify valid `Ensembl BioMart` archive version urls as `--genome_reference` value, e.g. [the archive version of December 2021](http://dec2021.archive.ensembl.org/). + +> [!IMPORTANT] +> Please note that old archive versions are regularly retired, therefore it might be possible that a used version is not available anymore at a later point. + #### Peptide sequences Peptide sequences have to be provided in `tsv` format with two mandatory columns `id` and `sequence`. Additional columns will be added as metadata to results. @@ -72,7 +82,7 @@ GBM_2,alleles.txt,I,gbm_2_variants.vcf | `sample` | Custom sample name. This entry will be identical for multiple sequencing libraries/runs from the same sample. Spaces in sample names are automatically converted to underscores (`_`). | | `alleles` | A string that consists of the patient's alleles (separated by ";"), or a full path to a allele ".txt" file where each allele is saved on a row. | | `mhc_class` | Specifies the MHC class for which the prediction should be performed. Valid values are: `I`, `II` and `H-2` (mouse). | -| `filename` | Full path to a variant/peptide or protein file (".vcf", ".vcf.gz", "tsv", "fasta", or "GSvar"). | +| `filename` | Full path to a variant/peptide or protein file (".vcf", ".vcf.gz", "tsv" or "fasta"). | An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline. @@ -80,8 +90,8 @@ An [example samplesheet](../assets/samplesheet.csv) has been provided with the p The typical command for running the pipeline is as follows: -```console -nextflow run nf-core/epitopeprediction --input samplesheet.csv -profile docker --genome GRCh37 --outdir +```bash +nextflow run nf-core/epitopeprediction --input ./samplesheet.csv --outdir ./results -profile docker ``` This will launch the pipeline with the `docker` configuration profile and default options (`syfpeithi` by default). See below for more information about profiles. @@ -95,6 +105,29 @@ work # Directory containing the nextflow working files # Other nextflow hidden files, eg. history of pipeline runs and old logs. ``` +If you wish to repeatedly use the same parameters for multiple runs, rather than specifying each flag in the command, you can specify these in a params file. + +Pipeline settings can be provided in a `yaml` or `json` file via `-params-file `. + +> [!WARNING] +> Do not use `-c ` to specify parameters as this will result in errors. Custom config files specified with `-c` must only be used for [tuning process resource specifications](https://nf-co.re/docs/usage/configuration#tuning-workflow-resources), other infrastructural tweaks (such as output directories), or module arguments (args). + +The above pipeline run specified with a params file in yaml format: + +```bash +nextflow run nf-core/epitopeprediction -profile docker -params-file params.yaml +``` + +with `params.yaml` containing: + +```yaml +input: './samplesheet.csv' +outdir: './results/' +<...> +``` + +You can also generate such `YAML`/`JSON` files via [nf-core/launch](https://nf-co.re/launch). + ### Running the pipeline with external prediction tools The pipeline can be used with external prediction tools that cannot be provided with the pipeline due to license restrictions. @@ -124,17 +157,26 @@ First, go to the [nf-core/epitopeprediction releases page](https://github.com/nf This version number will be logged in reports when you run the pipeline, so that you'll know what you used when you look back in the future. For example, at the bottom of the MultiQC reports. +To further assist in reproducibility, you can use share and re-use [parameter files](#running-the-pipeline) to repeat pipeline runs with the same settings without having to write out a command with every single parameter. + +:::tip +If you wish to share such profile (such as upload as supplementary material for academic publications), make sure to NOT include cluster specific paths to files, nor institutional specific profiles. +::: + ## Core Nextflow arguments -> **NB:** These options are part of Nextflow and use a _single_ hyphen (pipeline parameters use a double-hyphen). +> [!NOTE] +> These options are part of Nextflow and use a _single_ hyphen (pipeline parameters use a double-hyphen). ### `-profile` Use this parameter to choose a configuration profile. Profiles can give configuration presets for different compute environments. -Several generic profiles are bundled with the pipeline which instruct the pipeline to use software packaged using different methods (Docker, Singularity, Podman, Shifter, Charliecloud, Conda) - see below. +Several generic profiles are bundled with the pipeline which instruct the pipeline to use software packaged using different methods (Docker, Singularity, Podman, Shifter, Charliecloud, Apptainer, Conda) - see below. -> We highly recommend the use of Docker or Singularity containers for full pipeline reproducibility, however, Conda is also supported as an alternative. +:::info +We highly recommend the use of Docker or Singularity containers for full pipeline reproducibility, however when this is not possible, Conda is also supported. +::: The pipeline dynamically loads configurations from [https://github.com/nf-core/configs](https://github.com/nf-core/configs) when it runs, making multiple config profiles for various institutional clusters available at run time. For more information, and to see if your system is available in these configs, please see the [nf-core/configs documentation](https://github.com/nf-core/configs#documentation). @@ -156,8 +198,10 @@ If `-profile` is not specified, the pipeline will run locally and expect all sof - A generic configuration profile to be used with [Shifter](https://nersc.gitlab.io/development/shifter/how-to-use/) - `charliecloud` - A generic configuration profile to be used with [Charliecloud](https://hpc.github.io/charliecloud/) +- `apptainer` + - A generic configuration profile to be used with [Apptainer](https://apptainer.org/) - `conda` - - A generic configuration profile to be used with [Conda](https://conda.io/docs/). Please only use Conda as a last resort i.e. when it's not possible to run the pipeline with Docker, Singularity, Podman, Shifter or Charliecloud. + - A generic configuration profile to be used with [Conda](https://conda.io/docs/). Please only use Conda as a last resort i.e. when it's not possible to run the pipeline with Docker, Singularity, Podman, Shifter, Charliecloud, or Apptainer. ### `-resume` @@ -175,102 +219,19 @@ Specify the path to a specific config file (this is a core Nextflow command). Se Whilst the default requirements, set within the pipeline, will hopefully work for most people and input data, you may find that you want to customize the compute resources that the pipeline requests. Each step in the pipeline has a default set of requirements for number of CPUs, memory and time. For most of the steps in the pipeline, if the job exits with any of the error codes specified [here](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/conf/base.config#L18) it will automatically be resubmitted with higher requests (2 x original, then 3 x original). If it still fails after the third attempt then the pipeline execution is stopped. -For example, if the nf-core/rnaseq pipeline is failing after multiple re-submissions of the `STAR_ALIGN` process due to an exit code of `137` this would indicate that there is an out of memory issue: - -```console -[62/149eb0] NOTE: Process `NFCORE_RNASEQ:RNASEQ:ALIGN_STAR:STAR_ALIGN (WT_REP1)` terminated with an error exit status (137) -- Execution is retried (1) -Error executing process > 'NFCORE_RNASEQ:RNASEQ:ALIGN_STAR:STAR_ALIGN (WT_REP1)' - -Caused by: - Process `NFCORE_RNASEQ:RNASEQ:ALIGN_STAR:STAR_ALIGN (WT_REP1)` terminated with an error exit status (137) - -Command executed: - STAR \ - --genomeDir star \ - --readFilesIn WT_REP1_trimmed.fq.gz \ - --runThreadN 2 \ - --outFileNamePrefix WT_REP1. \ - - -Command exit status: - 137 - -Command output: - (empty) - -Command error: - .command.sh: line 9: 30 Killed STAR --genomeDir star --readFilesIn WT_REP1_trimmed.fq.gz --runThreadN 2 --outFileNamePrefix WT_REP1. -Work dir: - /home/pipelinetest/work/9d/172ca5881234073e8d76f2a19c88fb - -Tip: you can replicate the issue by changing to the process work dir and entering the command `bash .command.run` -``` - -#### For beginners - -A first step to bypass this error, you could try to increase the amount of CPUs, memory, and time for the whole pipeline. Therefor you can try to increase the resource for the parameters `--max_cpus`, `--max_memory`, and `--max_time`. Based on the error above, you have to increase the amount of memory. Therefore you can go to the [parameter documentation of rnaseq](https://nf-co.re/rnaseq/3.9/parameters) and scroll down to the `show hidden parameter` button to get the default value for `--max_memory`. In this case 128GB, you than can try to run your pipeline again with `--max_memory 200GB -resume` to skip all process, that were already calculated. If you can not increase the resource of the complete pipeline, you can try to adapt the resource for a single process as mentioned below. - -#### Advanced option on process level - -To bypass this error you would need to find exactly which resources are set by the `STAR_ALIGN` process. The quickest way is to search for `process STAR_ALIGN` in the [nf-core/rnaseq Github repo](https://github.com/nf-core/rnaseq/search?q=process+STAR_ALIGN). -We have standardised the structure of Nextflow DSL2 pipelines such that all module files will be present in the `modules/` directory and so, based on the search results, the file we want is `modules/nf-core/star/align/main.nf`. -If you click on the link to that file you will notice that there is a `label` directive at the top of the module that is set to [`label process_high`](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/modules/nf-core/software/star/align/main.nf#L9). -The [Nextflow `label`](https://www.nextflow.io/docs/latest/process.html#label) directive allows us to organise workflow processes in separate groups which can be referenced in a configuration file to select and configure subset of processes having similar computing requirements. -The default values for the `process_high` label are set in the pipeline's [`base.config`](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/conf/base.config#L33-L37) which in this case is defined as 72GB. -Providing you haven't set any other standard nf-core parameters to **cap** the [maximum resources](https://nf-co.re/usage/configuration#max-resources) used by the pipeline then we can try and bypass the `STAR_ALIGN` process failure by creating a custom config file that sets at least 72GB of memory, in this case increased to 100GB. -The custom config below can then be provided to the pipeline via the [`-c`](#-c) parameter as highlighted in previous sections. - -```nextflow -process { - withName: 'NFCORE_RNASEQ:RNASEQ:ALIGN_STAR:STAR_ALIGN' { - memory = 100.GB - } -} -``` - -> **NB:** We specify the full process name i.e. `NFCORE_RNASEQ:RNASEQ:ALIGN_STAR:STAR_ALIGN` in the config file because this takes priority over the short name (`STAR_ALIGN`) and allows existing configuration using the full process name to be correctly overridden. -> -> If you get a warning suggesting that the process selector isn't recognised check that the process name has been specified correctly. - -### Updating containers (advanced users) - -The [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html) implementation of this pipeline uses one container per process, which makes easier to maintain and update software dependencies. If for some reason, you need to use a different version of a particular tool with the pipeline then you just need to identify the `process` name and override the Nextflow `container` definition for that process using the `withName` declaration. For example, in the [nf-core/viralrecon](https://nf-co.re/viralrecon) pipeline a tool called [Pangolin](https://github.com/cov-lineages/pangolin) has been used during the COVID-19 pandemic to assign lineages to SARS-CoV-2 genome sequenced samples. Given that the lineage assignments change quite frequently, it doesn't make sense to re-release the nf-core/viralrecon every time a new version of Pangolin has been released. However, you can override the default container used by the pipeline by creating a custom config file and passing it as a command-line argument via `-c custom.config`. - -1. Check the default version used by the pipeline in the module file for [Pangolin](https://github.com/nf-core/viralrecon/blob/a85d5969f9025409e3618d6c280ef15ce417df65/modules/nf-core/software/pangolin/main.nf#L14-L19) -2. Find the latest version of the Biocontainer available on [Quay.io](https://quay.io/repository/biocontainers/pangolin?tag=latest&tab=tags) -3. Create the custom config accordingly: - - - For Docker: +To change the resource requests, please see the [max resources](https://nf-co.re/docs/usage/configuration#max-resources) and [tuning workflow resources](https://nf-co.re/docs/usage/configuration#tuning-workflow-resources) section of the nf-core website. - ```nextflow - process { - withName: PANGOLIN { - container = 'quay.io/biocontainers/pangolin:3.0.5--pyhdfd78af_0' - } - } - ``` +### Custom Containers - - For Singularity: +In some cases you may wish to change which container or conda environment a step of the pipeline uses for a particular tool. By default nf-core pipelines use containers and software from the [biocontainers](https://biocontainers.pro/) or [bioconda](https://bioconda.github.io/) projects. However in some cases the pipeline specified version maybe out of date. - ```nextflow - process { - withName: PANGOLIN { - container = 'https://depot.galaxyproject.org/singularity/pangolin:3.0.5--pyhdfd78af_0' - } - } - ``` +To use a different container from the default container or conda environment specified in a pipeline, please see the [updating tool versions](https://nf-co.re/docs/usage/configuration#updating-tool-versions) section of the nf-core website. - - For Conda: +### Custom Tool Arguments - ```nextflow - process { - withName: PANGOLIN { - conda = 'bioconda::pangolin=3.0.5' - } - } - ``` +A pipeline might not always support every possible argument or option of a particular tool used in pipeline. Fortunately, nf-core pipelines provide some freedom to users to insert additional parameters that the pipeline does not include by default. -> **NB:** If you wish to periodically update individual tool-specific results (e.g. Pangolin), generated by the pipeline, then you must ensure to keep the `work/` directory. Otherwise the `-resume` ability of the pipeline will be compromised and it will restart from scratch. +To learn how to provide additional arguments to a particular tool of the pipeline, please see the [customising tool arguments](https://nf-co.re/docs/usage/configuration#customising-tool-arguments) section of the nf-core website. ### nf-core/configs diff --git a/lib/NfcoreSchema.groovy b/lib/NfcoreSchema.groovy deleted file mode 100755 index 33cd4f6..0000000 --- a/lib/NfcoreSchema.groovy +++ /dev/null @@ -1,528 +0,0 @@ -// -// This file holds several functions used to perform JSON parameter validation, help and summary rendering for the nf-core pipeline template. -// - -import org.everit.json.schema.Schema -import org.everit.json.schema.loader.SchemaLoader -import org.everit.json.schema.ValidationException -import org.json.JSONObject -import org.json.JSONTokener -import org.json.JSONArray -import groovy.json.JsonSlurper -import groovy.json.JsonBuilder - -class NfcoreSchema { - - // - // Resolve Schema path relative to main workflow directory - // - public static String getSchemaPath(workflow, schema_filename='nextflow_schema.json') { - return "${workflow.projectDir}/${schema_filename}" - } - - // - // Function to loop over all parameters defined in schema and check - // whether the given parameters adhere to the specifications - // - /* groovylint-disable-next-line UnusedPrivateMethodParameter */ - public static void validateParameters(workflow, params, log, schema_filename='nextflow_schema.json') { - def has_error = false - //~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~// - // Check for nextflow core params and unexpected params - def json = new File(getSchemaPath(workflow, schema_filename=schema_filename)).text - def Map schemaParams = (Map) new JsonSlurper().parseText(json).get('definitions') - def nf_params = [ - // Options for base `nextflow` command - 'bg', - 'c', - 'C', - 'config', - 'd', - 'D', - 'dockerize', - 'h', - 'log', - 'q', - 'quiet', - 'syslog', - 'v', - - // Options for `nextflow run` command - 'ansi', - 'ansi-log', - 'bg', - 'bucket-dir', - 'c', - 'cache', - 'config', - 'dsl2', - 'dump-channels', - 'dump-hashes', - 'E', - 'entry', - 'latest', - 'lib', - 'main-script', - 'N', - 'name', - 'offline', - 'params-file', - 'pi', - 'plugins', - 'poll-interval', - 'pool-size', - 'profile', - 'ps', - 'qs', - 'queue-size', - 'r', - 'resume', - 'revision', - 'stdin', - 'stub', - 'stub-run', - 'test', - 'w', - 'with-charliecloud', - 'with-conda', - 'with-dag', - 'with-docker', - 'with-mpi', - 'with-notification', - 'with-podman', - 'with-report', - 'with-singularity', - 'with-timeline', - 'with-tower', - 'with-trace', - 'with-weblog', - 'without-docker', - 'without-podman', - 'work-dir' - ] - def unexpectedParams = [] - - // Collect expected parameters from the schema - def expectedParams = [] - def enums = [:] - for (group in schemaParams) { - for (p in group.value['properties']) { - expectedParams.push(p.key) - if (group.value['properties'][p.key].containsKey('enum')) { - enums[p.key] = group.value['properties'][p.key]['enum'] - } - } - } - - for (specifiedParam in params.keySet()) { - // nextflow params - if (nf_params.contains(specifiedParam)) { - log.error "ERROR: You used a core Nextflow option with two hyphens: '--${specifiedParam}'. Please resubmit with '-${specifiedParam}'" - has_error = true - } - // unexpected params - def params_ignore = params.schema_ignore_params.split(',') + 'schema_ignore_params' - def expectedParamsLowerCase = expectedParams.collect{ it.replace("-", "").toLowerCase() } - def specifiedParamLowerCase = specifiedParam.replace("-", "").toLowerCase() - def isCamelCaseBug = (specifiedParam.contains("-") && !expectedParams.contains(specifiedParam) && expectedParamsLowerCase.contains(specifiedParamLowerCase)) - if (!expectedParams.contains(specifiedParam) && !params_ignore.contains(specifiedParam) && !isCamelCaseBug) { - // Temporarily remove camelCase/camel-case params #1035 - def unexpectedParamsLowerCase = unexpectedParams.collect{ it.replace("-", "").toLowerCase()} - if (!unexpectedParamsLowerCase.contains(specifiedParamLowerCase)){ - unexpectedParams.push(specifiedParam) - } - } - } - - //~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~// - // Validate parameters against the schema - InputStream input_stream = new File(getSchemaPath(workflow, schema_filename=schema_filename)).newInputStream() - JSONObject raw_schema = new JSONObject(new JSONTokener(input_stream)) - - // Remove anything that's in params.schema_ignore_params - raw_schema = removeIgnoredParams(raw_schema, params) - - Schema schema = SchemaLoader.load(raw_schema) - - // Clean the parameters - def cleanedParams = cleanParameters(params) - - // Convert to JSONObject - def jsonParams = new JsonBuilder(cleanedParams) - JSONObject params_json = new JSONObject(jsonParams.toString()) - - // Validate - try { - schema.validate(params_json) - } catch (ValidationException e) { - println '' - log.error 'ERROR: Validation of pipeline parameters failed!' - JSONObject exceptionJSON = e.toJSON() - printExceptions(exceptionJSON, params_json, log, enums) - println '' - has_error = true - } - - // Check for unexpected parameters - if (unexpectedParams.size() > 0) { - Map colors = NfcoreTemplate.logColours(params.monochrome_logs) - println '' - def warn_msg = 'Found unexpected parameters:' - for (unexpectedParam in unexpectedParams) { - warn_msg = warn_msg + "\n* --${unexpectedParam}: ${params[unexpectedParam].toString()}" - } - log.warn warn_msg - log.info "- ${colors.dim}Ignore this warning: params.schema_ignore_params = \"${unexpectedParams.join(',')}\" ${colors.reset}" - println '' - } - - if (has_error) { - System.exit(1) - } - } - - // - // Beautify parameters for --help - // - public static String paramsHelp(workflow, params, command, schema_filename='nextflow_schema.json') { - Map colors = NfcoreTemplate.logColours(params.monochrome_logs) - Integer num_hidden = 0 - String output = '' - output += 'Typical pipeline command:\n\n' - output += " ${colors.cyan}${command}${colors.reset}\n\n" - Map params_map = paramsLoad(getSchemaPath(workflow, schema_filename=schema_filename)) - Integer max_chars = paramsMaxChars(params_map) + 1 - Integer desc_indent = max_chars + 14 - Integer dec_linewidth = 160 - desc_indent - for (group in params_map.keySet()) { - Integer num_params = 0 - String group_output = colors.underlined + colors.bold + group + colors.reset + '\n' - def group_params = params_map.get(group) // This gets the parameters of that particular group - for (param in group_params.keySet()) { - if (group_params.get(param).hidden && !params.show_hidden_params) { - num_hidden += 1 - continue; - } - def type = '[' + group_params.get(param).type + ']' - def description = group_params.get(param).description - def defaultValue = group_params.get(param).default != null ? " [default: " + group_params.get(param).default.toString() + "]" : '' - def description_default = description + colors.dim + defaultValue + colors.reset - // Wrap long description texts - // Loosely based on https://dzone.com/articles/groovy-plain-text-word-wrap - if (description_default.length() > dec_linewidth){ - List olines = [] - String oline = "" // " " * indent - description_default.split(" ").each() { wrd -> - if ((oline.size() + wrd.size()) <= dec_linewidth) { - oline += wrd + " " - } else { - olines += oline - oline = wrd + " " - } - } - olines += oline - description_default = olines.join("\n" + " " * desc_indent) - } - group_output += " --" + param.padRight(max_chars) + colors.dim + type.padRight(10) + colors.reset + description_default + '\n' - num_params += 1 - } - group_output += '\n' - if (num_params > 0){ - output += group_output - } - } - if (num_hidden > 0){ - output += colors.dim + "!! Hiding $num_hidden params, use --show_hidden_params to show them !!\n" + colors.reset - } - output += NfcoreTemplate.dashedLine(params.monochrome_logs) - return output - } - - // - // Groovy Map summarising parameters/workflow options used by the pipeline - // - public static LinkedHashMap paramsSummaryMap(workflow, params, schema_filename='nextflow_schema.json') { - // Get a selection of core Nextflow workflow options - def Map workflow_summary = [:] - if (workflow.revision) { - workflow_summary['revision'] = workflow.revision - } - workflow_summary['runName'] = workflow.runName - if (workflow.containerEngine) { - workflow_summary['containerEngine'] = workflow.containerEngine - } - if (workflow.container) { - workflow_summary['container'] = workflow.container - } - workflow_summary['launchDir'] = workflow.launchDir - workflow_summary['workDir'] = workflow.workDir - workflow_summary['projectDir'] = workflow.projectDir - workflow_summary['userName'] = workflow.userName - workflow_summary['profile'] = workflow.profile - workflow_summary['configFiles'] = workflow.configFiles.join(', ') - - // Get pipeline parameters defined in JSON Schema - def Map params_summary = [:] - def params_map = paramsLoad(getSchemaPath(workflow, schema_filename=schema_filename)) - for (group in params_map.keySet()) { - def sub_params = new LinkedHashMap() - def group_params = params_map.get(group) // This gets the parameters of that particular group - for (param in group_params.keySet()) { - if (params.containsKey(param)) { - def params_value = params.get(param) - def schema_value = group_params.get(param).default - def param_type = group_params.get(param).type - if (schema_value != null) { - if (param_type == 'string') { - if (schema_value.contains('$projectDir') || schema_value.contains('${projectDir}')) { - def sub_string = schema_value.replace('\$projectDir', '') - sub_string = sub_string.replace('\${projectDir}', '') - if (params_value.contains(sub_string)) { - schema_value = params_value - } - } - if (schema_value.contains('$params.outdir') || schema_value.contains('${params.outdir}')) { - def sub_string = schema_value.replace('\$params.outdir', '') - sub_string = sub_string.replace('\${params.outdir}', '') - if ("${params.outdir}${sub_string}" == params_value) { - schema_value = params_value - } - } - } - } - - // We have a default in the schema, and this isn't it - if (schema_value != null && params_value != schema_value) { - sub_params.put(param, params_value) - } - // No default in the schema, and this isn't empty - else if (schema_value == null && params_value != "" && params_value != null && params_value != false) { - sub_params.put(param, params_value) - } - } - } - params_summary.put(group, sub_params) - } - return [ 'Core Nextflow options' : workflow_summary ] << params_summary - } - - // - // Beautify parameters for summary and return as string - // - public static String paramsSummaryLog(workflow, params) { - Map colors = NfcoreTemplate.logColours(params.monochrome_logs) - String output = '' - def params_map = paramsSummaryMap(workflow, params) - def max_chars = paramsMaxChars(params_map) - for (group in params_map.keySet()) { - def group_params = params_map.get(group) // This gets the parameters of that particular group - if (group_params) { - output += colors.bold + group + colors.reset + '\n' - for (param in group_params.keySet()) { - output += " " + colors.blue + param.padRight(max_chars) + ": " + colors.green + group_params.get(param) + colors.reset + '\n' - } - output += '\n' - } - } - output += "!! Only displaying parameters that differ from the pipeline defaults !!\n" - output += NfcoreTemplate.dashedLine(params.monochrome_logs) - return output - } - - // - // Loop over nested exceptions and print the causingException - // - private static void printExceptions(ex_json, params_json, log, enums, limit=5) { - def causingExceptions = ex_json['causingExceptions'] - if (causingExceptions.length() == 0) { - def m = ex_json['message'] =~ /required key \[([^\]]+)\] not found/ - // Missing required param - if (m.matches()) { - log.error "* Missing required parameter: --${m[0][1]}" - } - // Other base-level error - else if (ex_json['pointerToViolation'] == '#') { - log.error "* ${ex_json['message']}" - } - // Error with specific param - else { - def param = ex_json['pointerToViolation'] - ~/^#\// - def param_val = params_json[param].toString() - if (enums.containsKey(param)) { - def error_msg = "* --${param}: '${param_val}' is not a valid choice (Available choices" - if (enums[param].size() > limit) { - log.error "${error_msg} (${limit} of ${enums[param].size()}): ${enums[param][0..limit-1].join(', ')}, ... )" - } else { - log.error "${error_msg}: ${enums[param].join(', ')})" - } - } else { - log.error "* --${param}: ${ex_json['message']} (${param_val})" - } - } - } - for (ex in causingExceptions) { - printExceptions(ex, params_json, log, enums) - } - } - - // - // Remove an element from a JSONArray - // - private static JSONArray removeElement(json_array, element) { - def list = [] - int len = json_array.length() - for (int i=0;i - if(raw_schema.keySet().contains('definitions')){ - raw_schema.definitions.each { definition -> - for (key in definition.keySet()){ - if (definition[key].get("properties").keySet().contains(ignore_param)){ - // Remove the param to ignore - definition[key].get("properties").remove(ignore_param) - // If the param was required, change this - if (definition[key].has("required")) { - def cleaned_required = removeElement(definition[key].required, ignore_param) - definition[key].put("required", cleaned_required) - } - } - } - } - } - if(raw_schema.keySet().contains('properties') && raw_schema.get('properties').keySet().contains(ignore_param)) { - raw_schema.get("properties").remove(ignore_param) - } - if(raw_schema.keySet().contains('required') && raw_schema.required.contains(ignore_param)) { - def cleaned_required = removeElement(raw_schema.required, ignore_param) - raw_schema.put("required", cleaned_required) - } - } - return raw_schema - } - - // - // Clean and check parameters relative to Nextflow native classes - // - private static Map cleanParameters(params) { - def new_params = params.getClass().newInstance(params) - for (p in params) { - // remove anything evaluating to false - if (!p['value']) { - new_params.remove(p.key) - } - // Cast MemoryUnit to String - if (p['value'].getClass() == nextflow.util.MemoryUnit) { - new_params.replace(p.key, p['value'].toString()) - } - // Cast Duration to String - if (p['value'].getClass() == nextflow.util.Duration) { - new_params.replace(p.key, p['value'].toString().replaceFirst(/d(?!\S)/, "day")) - } - // Cast LinkedHashMap to String - if (p['value'].getClass() == LinkedHashMap) { - new_params.replace(p.key, p['value'].toString()) - } - } - return new_params - } - - // - // This function tries to read a JSON params file - // - private static LinkedHashMap paramsLoad(String json_schema) { - def params_map = new LinkedHashMap() - try { - params_map = paramsRead(json_schema) - } catch (Exception e) { - println "Could not read parameters settings from JSON. $e" - params_map = new LinkedHashMap() - } - return params_map - } - - // - // Method to actually read in JSON file using Groovy. - // Group (as Key), values are all parameters - // - Parameter1 as Key, Description as Value - // - Parameter2 as Key, Description as Value - // .... - // Group - // - - private static LinkedHashMap paramsRead(String json_schema) throws Exception { - def json = new File(json_schema).text - def Map schema_definitions = (Map) new JsonSlurper().parseText(json).get('definitions') - def Map schema_properties = (Map) new JsonSlurper().parseText(json).get('properties') - /* Tree looks like this in nf-core schema - * definitions <- this is what the first get('definitions') gets us - group 1 - title - description - properties - parameter 1 - type - description - parameter 2 - type - description - group 2 - title - description - properties - parameter 1 - type - description - * properties <- parameters can also be ungrouped, outside of definitions - parameter 1 - type - description - */ - - // Grouped params - def params_map = new LinkedHashMap() - schema_definitions.each { key, val -> - def Map group = schema_definitions."$key".properties // Gets the property object of the group - def title = schema_definitions."$key".title - def sub_params = new LinkedHashMap() - group.each { innerkey, value -> - sub_params.put(innerkey, value) - } - params_map.put(title, sub_params) - } - - // Ungrouped params - def ungrouped_params = new LinkedHashMap() - schema_properties.each { innerkey, value -> - ungrouped_params.put(innerkey, value) - } - params_map.put("Other parameters", ungrouped_params) - - return params_map - } - - // - // Get maximum number of characters across all parameter names - // - private static Integer paramsMaxChars(params_map) { - Integer max_chars = 0 - for (group in params_map.keySet()) { - def group_params = params_map.get(group) // This gets the parameters of that particular group - for (param in group_params.keySet()) { - if (param.size() > max_chars) { - max_chars = param.size() - } - } - } - return max_chars - } -} diff --git a/lib/NfcoreTemplate.groovy b/lib/NfcoreTemplate.groovy deleted file mode 100755 index 25a0a74..0000000 --- a/lib/NfcoreTemplate.groovy +++ /dev/null @@ -1,336 +0,0 @@ -// -// This file holds several functions used within the nf-core pipeline template. -// - -import org.yaml.snakeyaml.Yaml - -class NfcoreTemplate { - - // - // Check AWS Batch related parameters have been specified correctly - // - public static void awsBatch(workflow, params) { - if (workflow.profile.contains('awsbatch')) { - // Check params.awsqueue and params.awsregion have been set if running on AWSBatch - assert (params.awsqueue && params.awsregion) : "Specify correct --awsqueue and --awsregion parameters on AWSBatch!" - // Check outdir paths to be S3 buckets if running on AWSBatch - assert params.outdir.startsWith('s3:') : "Outdir not on S3 - specify S3 Bucket to run on AWSBatch!" - } - } - - // - // Warn if a -profile or Nextflow config has not been provided to run the pipeline - // - public static void checkConfigProvided(workflow, log) { - if (workflow.profile == 'standard' && workflow.configFiles.size() <= 1) { - log.warn "[$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("$projectDir/assets/email_template.html") - def html_template = engine.createTemplate(hf).make(email_fields) - def email_html = html_template.toString() - - // Render the sendmail template - def max_multiqc_email_size = params.max_multiqc_email_size as nextflow.util.MemoryUnit - def smail_fields = [ email: email_address, subject: subject, email_txt: email_txt, email_html: email_html, projectDir: "$projectDir", mqcFile: mqc_report, mqcMaxSize: max_multiqc_email_size.toBytes() ] - def sf = new File("$projectDir/assets/sendmail_template.txt") - def sendmail_template = engine.createTemplate(sf).make(smail_fields) - def sendmail_html = sendmail_template.toString() - - // Send the HTML e-mail - Map colors = logColours(params.monochrome_logs) - if (email_address) { - try { - if (params.plaintext_email) { throw GroovyException('Send plaintext e-mail, not HTML') } - // Try to send HTML e-mail using sendmail - [ 'sendmail', '-t' ].execute() << sendmail_html - log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Sent summary e-mail to $email_address (sendmail)-" - } catch (all) { - // Catch failures and try with plaintext - def mail_cmd = [ 'mail', '-s', subject, '--content-type=text/html', email_address ] - if ( mqc_report.size() <= max_multiqc_email_size.toBytes() ) { - mail_cmd += [ '-A', mqc_report ] - } - mail_cmd.execute() << email_html - log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Sent summary e-mail to $email_address (mail)-" - } - } - - // Write summary e-mail HTML to a file - def output_d = new File("${params.outdir}/pipeline_info/") - if (!output_d.exists()) { - output_d.mkdirs() - } - def output_hf = new File(output_d, "pipeline_report.html") - output_hf.withWriter { w -> w << email_html } - def output_tf = new File(output_d, "pipeline_report.txt") - output_tf.withWriter { w -> w << email_txt } - } - - // - // 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()); - } - } - - // - // 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 8d030f4..0000000 --- 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/WorkflowEpitopeprediction.groovy b/lib/WorkflowEpitopeprediction.groovy deleted file mode 100755 index 0912c55..0000000 --- a/lib/WorkflowEpitopeprediction.groovy +++ /dev/null @@ -1,71 +0,0 @@ -// -// This file holds several functions specific to the workflow/epitopeprediction.nf in the nf-core/epitopeprediction pipeline -// - -import groovy.text.SimpleTemplateEngine - -class WorkflowEpitopeprediction { - - // - // Check and validate parameters - // - public static void initialise(params, log) { - } - - // - // 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 - } - - public static String methodsDescriptionText(run_workflow, mqc_methods_yaml) { - // 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() - - meta["doi_text"] = meta.manifest_map.doi ? "(doi: ${meta.manifest_map.doi})" : "" - meta["nodoi_text"] = meta.manifest_map.doi ? "": "
  • If available, make sure to update the text to include the Zenodo DOI of version of the pipeline used.
    • " - - def methods_text = mqc_methods_yaml.text - - def engine = new SimpleTemplateEngine() - def description_html = engine.createTemplate(methods_text).make(meta) - - return description_html - }// - // Exit pipeline if incorrect --genome key provided - // - private static void genomeExistsError(params, log) { - if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) { - log.error "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" + - " Genome '${params.genome}' not found in any config files provided to the pipeline.\n" + - " Currently, the available genome keys are:\n" + - " ${params.genomes.keySet().join(", ")}\n" + - "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~" - System.exit(1) - } - } - -} diff --git a/lib/WorkflowMain.groovy b/lib/WorkflowMain.groovy deleted file mode 100755 index c55c8bd..0000000 --- a/lib/WorkflowMain.groovy +++ /dev/null @@ -1,98 +0,0 @@ -// -// This file holds several functions specific to the main.nf workflow in the nf-core/epitopeprediction pipeline -// - -class WorkflowMain { - - // - // Citation string for pipeline - // - public static String citation(workflow) { - return "If you use ${workflow.manifest.name} for your analysis please cite:\n\n" + - "* The pipeline\n" + - " https://doi.org/10.5281/zenodo.3564666\n\n" + - "* The nf-core framework\n" + - " https://doi.org/10.1038/s41587-020-0439-x\n\n" + - "* Software dependencies\n" + - " https://github.com/${workflow.manifest.name}/blob/master/CITATIONS.md" - } - - // - // Generate help string - // - public static String help(workflow, params, log) { - def command = "nextflow run ${workflow.manifest.name} --input samplesheet.csv --genome GRCh37 -profile docker" - def help_string = '' - help_string += NfcoreTemplate.logo(workflow, params.monochrome_logs) - help_string += NfcoreSchema.paramsHelp(workflow, params, command) - help_string += '\n' + citation(workflow) + '\n' - help_string += NfcoreTemplate.dashedLine(params.monochrome_logs) - return help_string - } - - // - // Generate parameter summary log string - // - public static String paramsSummaryLog(workflow, params, log) { - def summary_log = '' - summary_log += NfcoreTemplate.logo(workflow, params.monochrome_logs) - summary_log += NfcoreSchema.paramsSummaryLog(workflow, params) - summary_log += '\n' + citation(workflow) + '\n' - summary_log += NfcoreTemplate.dashedLine(params.monochrome_logs) - return summary_log - } - - // - // Validate parameters and print summary to screen - // - public static void initialise(workflow, params, log) { - // Print help to screen if required - if (params.help) { - log.info help(workflow, params, log) - System.exit(0) - } - - // Print workflow version and exit on --version - if (params.version) { - String workflow_version = NfcoreTemplate.version(workflow) - log.info "${workflow.manifest.name} ${workflow_version}" - System.exit(0) - } - - // Print parameter summary log to screen - log.info paramsSummaryLog(workflow, params, log) - - // Validate workflow parameters via the JSON schema - if (params.validate_params) { - NfcoreSchema.validateParameters(workflow, params, log) - } - - // Check that a -profile or Nextflow config has been provided to run the pipeline - NfcoreTemplate.checkConfigProvided(workflow, 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) { - log.error "Please provide an input samplesheet to the pipeline e.g. '--input samplesheet.csv'" - System.exit(1) - } - } - // - // Get attribute from genome config file e.g. fasta - // - public static 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 - } -} diff --git a/lib/nfcore_external_java_deps.jar b/lib/nfcore_external_java_deps.jar deleted file mode 100644 index 805c8bb..0000000 Binary files a/lib/nfcore_external_java_deps.jar and /dev/null differ diff --git a/main.nf b/main.nf index 44c34c4..c37b6dd 100644 --- a/main.nf +++ b/main.nf @@ -4,7 +4,6 @@ nf-core/epitopeprediction ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Github : https://github.com/nf-core/epitopeprediction - Website: https://nf-co.re/epitopeprediction Slack : https://nfcore.slack.com/channels/epitopeprediction ---------------------------------------------------------------------------------------- @@ -14,39 +13,92 @@ nextflow.enable.dsl = 2 /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - VALIDATE & PRINT PARAMETER SUMMARY + IMPORT FUNCTIONS / MODULES / SUBWORKFLOWS / WORKFLOWS ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -WorkflowMain.initialise(workflow, params, log) +include { EPITOPEPREDICTION } from './workflows/epitopeprediction' +include { PIPELINE_INITIALISATION } from './subworkflows/local/utils_nfcore_epitopeprediction_pipeline' +include { PIPELINE_COMPLETION } from './subworkflows/local/utils_nfcore_epitopeprediction_pipeline' + +include { getGenomeAttribute } from './subworkflows/local/utils_nfcore_epitopeprediction_pipeline' /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - NAMED WORKFLOW FOR PIPELINE + GENOME PARAMETER VALUES ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -include { EPITOPEPREDICTION } from './workflows/epitopeprediction' + +/* +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + NAMED WORKFLOWS FOR PIPELINE +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +*/ // -// WORKFLOW: Run main nf-core/epitopeprediction analysis pipeline +// WORKFLOW: Run main analysis pipeline depending on type of input // workflow NFCORE_EPITOPEPREDICTION { - EPITOPEPREDICTION () -} + take: + samplesheet // channel: samplesheet read in from --input + + main: + + // + // WORKFLOW: Run pipeline + // + EPITOPEPREDICTION ( + samplesheet + ) + + emit: + multiqc_report = EPITOPEPREDICTION.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_EPITOPEPREDICTION () + + main: + + // + // SUBWORKFLOW: Run initialisation tasks + // + PIPELINE_INITIALISATION ( + params.version, + params.help, + params.validate_params, + params.monochrome_logs, + args, + params.outdir, + params.input + ) + + // + // WORKFLOW: Run main workflow + // + NFCORE_EPITOPEPREDICTION ( + PIPELINE_INITIALISATION.out.samplesheet + ) + + // + // SUBWORKFLOW: Run completion tasks + // + PIPELINE_COMPLETION ( + params.email, + params.email_on_fail, + params.plaintext_email, + params.outdir, + params.monochrome_logs, + params.hook_url, + NFCORE_EPITOPEPREDICTION.out.multiqc_report + ) } /* diff --git a/modules.json b/modules.json index 124d7ba..33101bb 100644 --- a/modules.json +++ b/modules.json @@ -7,20 +7,39 @@ "nf-core": { "custom/dumpsoftwareversions": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "8ec825f465b9c17f9d83000022995b4f7de6fe93", "installed_by": ["modules"] }, "gunzip": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "3a5fef109d113b4997c9822198664ca5f2716208", "installed_by": ["modules"] }, "multiqc": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "ccacf6f5de6df3bc6d73b665c1fd2933d8bbc290", "installed_by": ["modules"] } } + }, + "subworkflows": { + "nf-core": { + "utils_nextflow_pipeline": { + "branch": "master", + "git_sha": "cd08c91373cd00a73255081340e4914485846ba1", + "installed_by": ["subworkflows"] + }, + "utils_nfcore_pipeline": { + "branch": "master", + "git_sha": "262b17ed2aad591039f914951659177e6c39a8d8", + "installed_by": ["subworkflows"] + }, + "utils_nfvalidation_plugin": { + "branch": "master", + "git_sha": "cd08c91373cd00a73255081340e4914485846ba1", + "installed_by": ["subworkflows"] + } + } } } } diff --git a/modules/local/cat_files.nf b/modules/local/cat_files.nf index ee1d20d..20ca1e2 100644 --- a/modules/local/cat_files.nf +++ b/modules/local/cat_files.nf @@ -4,7 +4,7 @@ process CAT_FILES { conda "conda-forge:sed=4.8" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/cat:5.2.3--hdfd78af_1' : - 'quay.io/biocontainers/cat:5.2.3--hdfd78af_1' }" + 'biocontainers/cat:5.2.3--hdfd78af_1' }" input: tuple val(meta), path(input) @@ -13,6 +13,9 @@ process CAT_FILES { tuple val(meta), path("*_prediction{_result,_proteins}*"), emit: output path "versions.yml", emit: versions + when: + task.ext.when == null || task.ext.when + script: def fileExt = input[0].name.tokenize("\\.")[-1] def prefix = task.ext.suffix ? "${meta.sample}_${task.ext.suffix}" : "${meta.sample}" diff --git a/modules/local/csvtk_concat.nf b/modules/local/csvtk_concat.nf index ea88fe2..31a0005 100644 --- a/modules/local/csvtk_concat.nf +++ b/modules/local/csvtk_concat.nf @@ -4,7 +4,7 @@ process CSVTK_CONCAT { conda "bioconda::csvtk=0.23.0" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/csvtk:0.23.0--h9ee0642_0' : - 'quay.io/biocontainers/csvtk:0.23.0--h9ee0642_0' }" + 'biocontainers/csvtk:0.23.0--h9ee0642_0' }" input: tuple val(meta), path(predicted) @@ -13,6 +13,9 @@ process CSVTK_CONCAT { tuple val(meta), path("*prediction_result.tsv"), emit: predicted path "versions.yml", emit: versions + when: + task.ext.when == null || task.ext.when + script: """ csvtk concat -t $predicted > ${meta.sample}_prediction_result_unsorted.tmp diff --git a/modules/local/csvtk_split.nf b/modules/local/csvtk_split.nf deleted file mode 100644 index cdb2db0..0000000 --- a/modules/local/csvtk_split.nf +++ /dev/null @@ -1,27 +0,0 @@ -process CSVTK_SPLIT { - label 'process_low' - - conda "conda-forge::sed=4.7 bioconda::csvtk=0.23.0" - container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/csvtk:0.23.0--h9ee0642_0' : - 'quay.io/biocontainers/csvtk:0.23.0--h9ee0642_0' }" - - input: - tuple val(meta), path(raw) - - output: - tuple val(meta), path("*.tsv"), emit: splitted - path "versions.yml", emit: versions - - script: - """ - sed -i.bak '/^##/d' ${raw} - csvtk split ${raw} -t -C '&' -f '#chr' - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - csvtk: \$(echo \$( csvtk version | sed -e "s/csvtk v//g" )) - END_VERSIONS - """ - -} diff --git a/modules/local/epytope_check_requested_models.nf b/modules/local/epytope_check_requested_models.nf index 7ae5ecd..8438c4d 100644 --- a/modules/local/epytope_check_requested_models.nf +++ b/modules/local/epytope_check_requested_models.nf @@ -1,10 +1,10 @@ process EPYTOPE_CHECK_REQUESTED_MODELS { label 'process_low' - conda "bioconda::epytope=3.1.0" + conda "bioconda::epytope=3.3.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/epytope:3.1.0--pyh5e36f6f_0' : - 'quay.io/biocontainers/epytope:3.1.0--pyh5e36f6f_0' }" + 'https://depot.galaxyproject.org/singularity/epytope:3.3.1--pyh7cba7a3_0' : + 'biocontainers/epytope:3.3.1--pyh7cba7a3_0' }" input: tuple val(meta), path(input_file) @@ -15,6 +15,9 @@ process EPYTOPE_CHECK_REQUESTED_MODELS { path '*.log', emit: log // model_warnings.log path "versions.yml", emit: versions + when: + task.ext.when == null || task.ext.when + script: def argument = task.ext.args @@ -27,8 +30,8 @@ process EPYTOPE_CHECK_REQUESTED_MODELS { } def prefix = task.ext.suffix ? "${meta.sample}_${task.ext.suffix}" : "${meta.sample}_peptides" - def min_length = ("${meta.mhcclass}" == "I") ? params.min_peptide_length : params.min_peptide_length_class2 - def max_length = ("${meta.mhcclass}" == "I") ? params.max_peptide_length : params.max_peptide_length_class2 + def min_length = ("${meta.mhc_class}" == "I") ? params.min_peptide_length : params.min_peptide_length_class2 + def max_length = ("${meta.mhc_class}" == "I") ? params.max_peptide_length : params.max_peptide_length_class2 """ check_requested_models.py ${argument} \ diff --git a/modules/local/epytope_generate_peptides.nf b/modules/local/epytope_generate_peptides.nf index 35acfb9..d79ce4a 100644 --- a/modules/local/epytope_generate_peptides.nf +++ b/modules/local/epytope_generate_peptides.nf @@ -2,10 +2,10 @@ process EPYTOPE_GENERATE_PEPTIDES { label 'process_low' tag "${meta.sample}" - conda "bioconda::epytope=3.1.0" + conda "bioconda::epytope=3.3.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/epytope:3.1.0--pyh5e36f6f_0' : - 'quay.io/biocontainers/epytope:3.1.0--pyh5e36f6f_0' }" + 'https://depot.galaxyproject.org/singularity/epytope:3.3.1--pyh7cba7a3_0' : + 'biocontainers/epytope:3.3.1--pyh7cba7a3_0' }" input: tuple val(meta), path(raw) @@ -14,10 +14,13 @@ process EPYTOPE_GENERATE_PEPTIDES { tuple val(meta), path("*.tsv"), emit: splitted path "versions.yml", emit: versions + when: + task.ext.when == null || task.ext.when + script: def prefix = task.ext.suffix ? "${meta.sample}_${task.ext.suffix}" : "${meta.sample}_peptides" - def min_length = (meta.mhcclass == "I") ? params.min_peptide_length : params.min_peptide_length_class2 - def max_length = (meta.mhcclass == "I") ? params.max_peptide_length : params.max_peptide_length_class2 + def min_length = (meta.mhc_class == "I") ? params.min_peptide_length : params.min_peptide_length_class2 + def max_length = (meta.mhc_class == "I") ? params.max_peptide_length : params.max_peptide_length_class2 """ gen_peptides.py --input ${raw} \\ diff --git a/modules/local/epytope_peptide_prediction.nf b/modules/local/epytope_peptide_prediction.nf index 3b906e5..ef0c07a 100644 --- a/modules/local/epytope_peptide_prediction.nf +++ b/modules/local/epytope_peptide_prediction.nf @@ -2,9 +2,7 @@ process EPYTOPE_PEPTIDE_PREDICTION { label 'process_low' conda "conda-forge::coreutils=9.1 conda-forge::tcsh=6.20.00 bioconda::epytope=3.1.0 conda-forge::gawk=5.1.0 conda-forge::perl=5.32.1" - container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/mulled-v2-11bbf0d242ea96f7b9c08d5b5bc26f2cd5ac5943:3419f320edefe6077631798f50d7bd4f8dc4763f-0' : - 'quay.io/biocontainers/mulled-v2-11bbf0d242ea96f7b9c08d5b5bc26f2cd5ac5943:3419f320edefe6077631798f50d7bd4f8dc4763f-0' }" + container 'ghcr.io/jonasscheid/epitopeprediction-2:0.3.0' input: tuple val(meta), path(splitted), path(software_versions) @@ -16,6 +14,9 @@ process EPYTOPE_PEPTIDE_PREDICTION { tuple val(meta), path("*.fasta"), emit: fasta, optional: true path "versions.yml", emit: versions + when: + task.ext.when == null || task.ext.when + script: // Additions to the argument command need to go to the beginning. // Argument list needs to end with --peptides or --somatic_mutation @@ -46,14 +47,14 @@ process EPYTOPE_PEPTIDE_PREDICTION { def class1_tools = tools_split.findAll { ! it.matches('.*(?i)(class-2|ii).*') } def class2_tools = tools_split.findAll { it.matches('.*(?i)(syf|class-2|ii).*') } - if (((meta.mhcclass == "I") & class1_tools.empty) | ((meta.mhcclass == "II") & class2_tools.empty)) { - exit 1, "No tools specified for mhc class ${meta.mhcclass}" + if (((meta.mhc_class == "I") & class1_tools.empty) | ((meta.mhc_class == "II") & class2_tools.empty)) { + exit 1, "No tools specified for mhc class ${meta.mhc_class}" } - def min_length = (meta.mhcclass == "I") ? params.min_peptide_length : params.min_peptide_length_class2 - def max_length = (meta.mhcclass == "I") ? params.max_peptide_length : params.max_peptide_length_class2 + def min_length = (meta.mhc_class == "I") ? params.min_peptide_length : params.min_peptide_length_class2 + def max_length = (meta.mhc_class == "I") ? params.max_peptide_length : params.max_peptide_length_class2 - def tools_to_use = ((meta.mhcclass == "I") | (meta.mhcclass == "H-2")) ? class1_tools.join(',') : class2_tools.join(',') + def tools_to_use = ((meta.mhc_class == "I") | (meta.mhc_class == "H-2")) ? class1_tools.join(',') : class2_tools.join(',') """ # create folder for MHCflurry downloads to avoid permission problems when running pipeline with docker profile and mhcflurry selected @@ -82,7 +83,7 @@ process EPYTOPE_PEPTIDE_PREDICTION { python: \$(python --version 2>&1 | sed 's/Python //g') epytope: \$(python -c "import pkg_resources; print(pkg_resources.get_distribution('epytope').version)") pandas: \$(python -c "import pkg_resources; print(pkg_resources.get_distribution('pandas').version)") - pyvcf: \$(python -c "import pkg_resources; print(pkg_resources.get_distribution('pyvcf').version)") + pyvcf: \$(python -c "import pkg_resources; print(pkg_resources.get_distribution('PyVCF3').version)") mhcflurry: \$(mhcflurry-predict --version 2>&1 | sed 's/^mhcflurry //; s/ .*\$//') mhcnuggets: \$(python -c "import pkg_resources; print(pkg_resources.get_distribution('mhcnuggets').version)") END_VERSIONS diff --git a/modules/local/epytope_show_supported_models.nf b/modules/local/epytope_show_supported_models.nf index 433ee14..68a8e1b 100644 --- a/modules/local/epytope_show_supported_models.nf +++ b/modules/local/epytope_show_supported_models.nf @@ -1,10 +1,10 @@ process EPYTOPE_SHOW_SUPPORTED_MODELS { label 'process_low' - conda "bioconda::epytope=3.1.0" + conda "bioconda::epytope=3.3.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/epytope:3.1.0--pyh5e36f6f_0' : - 'quay.io/biocontainers/epytope:3.1.0--pyh5e36f6f_0' }" + 'https://depot.galaxyproject.org/singularity/epytope:3.3.1--pyh7cba7a3_0' : + 'biocontainers/epytope:3.3.1--pyh7cba7a3_0' }" input: tuple val(meta), path(raw), path(software_versions) @@ -13,6 +13,9 @@ process EPYTOPE_SHOW_SUPPORTED_MODELS { path '*.txt', emit: txt // model_report.txt path "versions.yml", emit: versions + when: + task.ext.when == null || task.ext.when + script: """ check_supported_models.py --versions ${software_versions} diff --git a/modules/local/external_tools_import.nf b/modules/local/external_tools_import.nf index a9cd0e7..ccf299e 100644 --- a/modules/local/external_tools_import.nf +++ b/modules/local/external_tools_import.nf @@ -7,7 +7,7 @@ process EXTERNAL_TOOLS_IMPORT { conda "conda-forge::coreutils=9.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img' : - 'biocontainers/biocontainers:v1.2.0_cv1' }" + 'docker.io/biocontainers/biocontainers:v1.2.0_cv2' }" input: tuple val(toolname), val(toolversion), val(toolchecksum), path(tooltarball), file(datatarball), val(datachecksum), val(toolbinaryname) @@ -16,6 +16,9 @@ process EXTERNAL_TOOLS_IMPORT { path "${toolname}", emit: nonfree_tools path "versions.yml", emit: versions + when: + task.ext.when == null || task.ext.when + script: """ # @@ -75,7 +78,6 @@ process EXTERNAL_TOOLS_IMPORT { # # CREATE VERSION FILE # - cat <<-END_VERSIONS > versions.yml "${task.process}": ${toolname}: ${toolversion} diff --git a/modules/local/get_prediction_versions.nf b/modules/local/get_prediction_versions.nf index 8538994..939221b 100644 --- a/modules/local/get_prediction_versions.nf +++ b/modules/local/get_prediction_versions.nf @@ -1,10 +1,10 @@ process GET_PREDICTION_VERSIONS { label 'process_low' - conda "bioconda::epytope=3.1.0" + conda "bioconda::epytope=3.3.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/epytope:3.1.0--pyh5e36f6f_0' : - 'quay.io/biocontainers/epytope:3.1.0--pyh5e36f6f_0' }" + 'https://depot.galaxyproject.org/singularity/epytope:3.3.1--pyh7cba7a3_0' : + 'biocontainers/epytope:3.3.1--pyh7cba7a3_0' }" input: val external_tool_versions @@ -12,6 +12,9 @@ process GET_PREDICTION_VERSIONS { output: path "versions.csv", emit: versions // this versions.csv is needed by a downstream process as well. TODO: fix to use versions.yml + when: + task.ext.when == null || task.ext.when + script: def external_tools = external_tool_versions.join(",") diff --git a/modules/local/merge_json.nf b/modules/local/merge_json.nf index 0031ffa..5d66f78 100644 --- a/modules/local/merge_json.nf +++ b/modules/local/merge_json.nf @@ -4,7 +4,7 @@ process MERGE_JSON { conda "conda-forge::python=3.8.3" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/python:3.8.3' : - 'quay.io/biocontainers/python:3.8.3' }" + 'biocontainers/python:3.8.3' }" input: tuple val(meta), path(json) @@ -13,6 +13,9 @@ process MERGE_JSON { tuple val(meta), path("*.json"), emit: json path "versions.yml", emit: versions + when: + task.ext.when == null || task.ext.when + script: def argument = task.ext.args if (argument.contains("single_input") == true) { diff --git a/modules/local/samplesheet_check.nf b/modules/local/samplesheet_check.nf deleted file mode 100644 index 5b2cba0..0000000 --- a/modules/local/samplesheet_check.nf +++ /dev/null @@ -1,31 +0,0 @@ -process SAMPLESHEET_CHECK { - tag "$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' : - 'quay.io/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/epitopeprediction/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/local/snpsift_split.nf b/modules/local/snpsift_split.nf index a3376e7..1e7f218 100644 --- a/modules/local/snpsift_split.nf +++ b/modules/local/snpsift_split.nf @@ -4,7 +4,7 @@ process SNPSIFT_SPLIT { conda "bioconda::snpsift=4.2" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/snpsift:4.2--hdfd78af_5' : - 'quay.io/biocontainers/snpsift:4.2--hdfd78af_5' }" + 'biocontainers/snpsift:4.2--hdfd78af_5' }" input: tuple val(meta), path(input_file) @@ -13,6 +13,9 @@ process SNPSIFT_SPLIT { tuple val(meta), path("*.vcf"), emit: splitted path "versions.yml", emit: versions + when: + task.ext.when == null || task.ext.when + script: """ SnpSift split ${input_file} diff --git a/modules/local/split_peptides.nf b/modules/local/split_peptides.nf index 744c932..3ade5b8 100644 --- a/modules/local/split_peptides.nf +++ b/modules/local/split_peptides.nf @@ -4,7 +4,7 @@ process SPLIT_PEPTIDES { conda "conda-forge::python=3.8.3" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/python:3.8.3' : - 'quay.io/biocontainers/python:3.8.3' }" + 'biocontainers/python:3.8.3' }" input: tuple val(meta), path(peptide) @@ -13,6 +13,9 @@ process SPLIT_PEPTIDES { tuple val(meta), path("*.tsv"), emit: splitted path "versions.yml", emit: versions + when: + task.ext.when == null || task.ext.when + script: def prefix = task.ext.suffix ? "${peptide.baseName}_${task.ext.suffix}" : "${peptide.baseName}" diff --git a/modules/local/variant_split.nf b/modules/local/variant_split.nf index 9f2ca07..e0695c3 100644 --- a/modules/local/variant_split.nf +++ b/modules/local/variant_split.nf @@ -4,7 +4,7 @@ process VARIANT_SPLIT { conda "conda-forge::python=3.8.3" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/python:3.8.3' : - 'quay.io/biocontainers/python:3.8.3' }" + 'biocontainers/python:3.8.3' }" input: tuple val(meta), path(input_file) @@ -13,8 +13,10 @@ process VARIANT_SPLIT { tuple val(meta), path("*.vcf"), emit: splitted path "versions.yml", emit: versions - script: + when: + task.ext.when == null || task.ext.when + script: def size_parameter = params.split_by_variants_size != 0 ? "--size ${params.split_by_variants_size}" : '' def distance_parameter = params.split_by_variants_distance ? "--distance ${params.split_by_variants_distance}" : '' diff --git a/modules/nf-core/custom/dumpsoftwareversions/main.nf b/modules/nf-core/custom/dumpsoftwareversions/main.nf deleted file mode 100644 index 3df2176..0000000 --- a/modules/nf-core/custom/dumpsoftwareversions/main.nf +++ /dev/null @@ -1,24 +0,0 @@ -process CUSTOM_DUMPSOFTWAREVERSIONS { - label 'process_single' - - // Requires `pyyaml` which does not have a dedicated container but is in the MultiQC container - conda "bioconda::multiqc=1.13" - container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/multiqc:1.13--pyhdfd78af_0' : - 'quay.io/biocontainers/multiqc:1.13--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 60b546a..0000000 --- a/modules/nf-core/custom/dumpsoftwareversions/meta.yml +++ /dev/null @@ -1,34 +0,0 @@ -name: custom_dumpsoftwareversions -description: Custom module used to dump software versions within the nf-core pipeline template -keywords: - - custom - - 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" 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 9a493ac..0000000 --- a/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py +++ /dev/null @@ -1,100 +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/${workflow.manifest.name}", - "plot_type": "html", - "description": "are collected at run time from the software output.", - "data": _make_versions_html(versions_by_module), - } - - with open("software_versions.yml", "w") as f: - yaml.dump(versions_by_module, f, default_flow_style=False) - with open("software_versions_mqc.yml", "w") as f: - yaml.dump(versions_mqc, f, default_flow_style=False) - - with open("versions.yml", "w") as f: - yaml.dump(versions_this_module, f, default_flow_style=False) - - -if __name__ == "__main__": - main() diff --git a/modules/nf-core/gunzip/environment.yml b/modules/nf-core/gunzip/environment.yml new file mode 100644 index 0000000..25910b3 --- /dev/null +++ b/modules/nf-core/gunzip/environment.yml @@ -0,0 +1,7 @@ +name: gunzip +channels: + - conda-forge + - bioconda + - defaults +dependencies: + - conda-forge::sed=4.7 diff --git a/modules/nf-core/gunzip/main.nf b/modules/nf-core/gunzip/main.nf index d906034..468a6f2 100644 --- a/modules/nf-core/gunzip/main.nf +++ b/modules/nf-core/gunzip/main.nf @@ -2,10 +2,10 @@ process GUNZIP { tag "$archive" label 'process_single' - conda "conda-forge::sed=4.7" + conda "${moduleDir}/environment.yml" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/ubuntu:20.04' : - 'ubuntu:20.04' }" + 'nf-core/ubuntu:20.04' }" input: tuple val(meta), path(archive) @@ -21,10 +21,14 @@ process GUNZIP { def args = task.ext.args ?: '' gunzip = archive.toString() - '.gz' """ - gunzip \\ - -f \\ + # Not calling gunzip itself because it creates files + # with the original group ownership rather than the + # default one for that user / the work directory + gzip \\ + -cd \\ $args \\ - $archive + $archive \\ + > $gunzip cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/nf-core/gunzip/meta.yml b/modules/nf-core/gunzip/meta.yml index 4d2ebc8..231034f 100644 --- a/modules/nf-core/gunzip/meta.yml +++ b/modules/nf-core/gunzip/meta.yml @@ -3,32 +3,37 @@ description: Compresses and decompresses files. keywords: - gunzip - compression + - decompression tools: - gunzip: - description: | - gzip is a file format and a software application used for file compression and decompression. - documentation: https://www.gnu.org/software/gzip/manual/gzip.html - licence: ["GPL-3.0-or-later"] + description: | + gzip is a file format and a software application used for file compression and decompression. + documentation: https://www.gnu.org/software/gzip/manual/gzip.html + licence: ["GPL-3.0-or-later"] input: - meta: - type: map - description: | - Optional groovy Map containing meta information - e.g. [ id:'test', single_end:false ] + type: map + description: | + Optional groovy Map containing meta information + e.g. [ id:'test', single_end:false ] - archive: - type: file - description: File to be compressed/uncompressed - pattern: "*.*" + type: file + description: File to be compressed/uncompressed + pattern: "*.*" output: - gunzip: - type: file - description: Compressed/uncompressed file - pattern: "*.*" + type: file + description: Compressed/uncompressed file + pattern: "*.*" - versions: - type: file - description: File containing software versions - pattern: "versions.yml" + type: file + description: File containing software versions + pattern: "versions.yml" authors: - "@joseespinosa" - "@drpatelh" - "@jfy133" +maintainers: + - "@joseespinosa" + - "@drpatelh" + - "@jfy133" diff --git a/modules/nf-core/gunzip/tests/main.nf.test b/modules/nf-core/gunzip/tests/main.nf.test new file mode 100644 index 0000000..6406008 --- /dev/null +++ b/modules/nf-core/gunzip/tests/main.nf.test @@ -0,0 +1,36 @@ +nextflow_process { + + name "Test Process GUNZIP" + script "../main.nf" + process "GUNZIP" + tag "gunzip" + tag "modules_nfcore" + tag "modules" + + test("Should run without failures") { + + when { + params { + outdir = "$outputDir" + } + process { + """ + input[0] = Channel.of([ + [], + file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true) + ] + ) + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + + } + +} diff --git a/modules/nf-core/gunzip/tests/main.nf.test.snap b/modules/nf-core/gunzip/tests/main.nf.test.snap new file mode 100644 index 0000000..720fd9f --- /dev/null +++ b/modules/nf-core/gunzip/tests/main.nf.test.snap @@ -0,0 +1,31 @@ +{ + "Should run without failures": { + "content": [ + { + "0": [ + [ + [ + + ], + "test_1.fastq:md5,4161df271f9bfcd25d5845a1e220dbec" + ] + ], + "1": [ + "versions.yml:md5,54376d32aca20e937a4ec26dac228e84" + ], + "gunzip": [ + [ + [ + + ], + "test_1.fastq:md5,4161df271f9bfcd25d5845a1e220dbec" + ] + ], + "versions": [ + "versions.yml:md5,54376d32aca20e937a4ec26dac228e84" + ] + } + ], + "timestamp": "2023-10-17T15:35:37.690477896" + } +} \ No newline at end of file diff --git a/modules/nf-core/gunzip/tests/tags.yml b/modules/nf-core/gunzip/tests/tags.yml new file mode 100644 index 0000000..fd3f691 --- /dev/null +++ b/modules/nf-core/gunzip/tests/tags.yml @@ -0,0 +1,2 @@ +gunzip: + - modules/nf-core/gunzip/** diff --git a/modules/nf-core/multiqc/environment.yml b/modules/nf-core/multiqc/environment.yml new file mode 100644 index 0000000..2212096 --- /dev/null +++ b/modules/nf-core/multiqc/environment.yml @@ -0,0 +1,7 @@ +name: multiqc +channels: + - conda-forge + - bioconda + - defaults +dependencies: + - bioconda::multiqc=1.20 diff --git a/modules/nf-core/multiqc/main.nf b/modules/nf-core/multiqc/main.nf index 68f66be..354f443 100644 --- a/modules/nf-core/multiqc/main.nf +++ b/modules/nf-core/multiqc/main.nf @@ -1,10 +1,10 @@ process MULTIQC { label 'process_single' - conda "bioconda::multiqc=1.13" + conda "${moduleDir}/environment.yml" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/multiqc:1.13--pyhdfd78af_0' : - 'quay.io/biocontainers/multiqc:1.13--pyhdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/multiqc:1.20--pyhdfd78af_0' : + 'biocontainers/multiqc:1.20--pyhdfd78af_0' }" input: path multiqc_files, stageAs: "?/*" @@ -25,12 +25,14 @@ process MULTIQC { def args = task.ext.args ?: '' def config = multiqc_config ? "--config $multiqc_config" : '' def extra_config = extra_multiqc_config ? "--config $extra_multiqc_config" : '' + def logo = multiqc_logo ? /--cl-config 'custom_logo: "${multiqc_logo}"'/ : '' """ multiqc \\ --force \\ $args \\ $config \\ $extra_config \\ + $logo \\ . cat <<-END_VERSIONS > versions.yml @@ -41,7 +43,7 @@ process MULTIQC { stub: """ - touch multiqc_data + mkdir multiqc_data touch multiqc_plots touch multiqc_report.html diff --git a/modules/nf-core/multiqc/meta.yml b/modules/nf-core/multiqc/meta.yml index ebc29b2..45a9bc3 100644 --- a/modules/nf-core/multiqc/meta.yml +++ b/modules/nf-core/multiqc/meta.yml @@ -1,4 +1,4 @@ -name: MultiQC +name: multiqc description: Aggregate results from bioinformatics analyses across many samples into a single report keywords: - QC @@ -12,7 +12,6 @@ tools: homepage: https://multiqc.info/ documentation: https://multiqc.info/docs/ licence: ["GPL-3.0-or-later"] - input: - multiqc_files: type: file @@ -30,14 +29,13 @@ input: type: file description: Optional logo file for MultiQC pattern: "*.{png}" - output: - report: type: file description: MultiQC report file pattern: "multiqc_report.html" - data: - type: dir + type: directory description: MultiQC data dir pattern: "multiqc_data" - plots: @@ -53,3 +51,8 @@ authors: - "@bunop" - "@drpatelh" - "@jfy133" +maintainers: + - "@abhi18av" + - "@bunop" + - "@drpatelh" + - "@jfy133" diff --git a/modules/nf-core/multiqc/tests/main.nf.test b/modules/nf-core/multiqc/tests/main.nf.test new file mode 100644 index 0000000..f1c4242 --- /dev/null +++ b/modules/nf-core/multiqc/tests/main.nf.test @@ -0,0 +1,84 @@ +nextflow_process { + + name "Test Process MULTIQC" + script "../main.nf" + process "MULTIQC" + + tag "modules" + tag "modules_nfcore" + tag "multiqc" + + test("sarscov2 single-end [fastqc]") { + + when { + process { + """ + 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] = [] + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert process.out.report[0] ==~ ".*/multiqc_report.html" }, + { assert process.out.data[0] ==~ ".*/multiqc_data" }, + { assert snapshot(process.out.versions).match("multiqc_versions_single") } + ) + } + + } + + test("sarscov2 single-end [fastqc] [config]") { + + when { + process { + """ + 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] = [] + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert process.out.report[0] ==~ ".*/multiqc_report.html" }, + { assert process.out.data[0] ==~ ".*/multiqc_data" }, + { assert snapshot(process.out.versions).match("multiqc_versions_config") } + ) + } + } + + test("sarscov2 single-end [fastqc] - stub") { + + options "-stub" + + when { + process { + """ + 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] = [] + """ + } + } + + then { + assertAll( + { assert process.success }, + { 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("multiqc_stub") } + ) + } + + } +} diff --git a/modules/nf-core/multiqc/tests/main.nf.test.snap b/modules/nf-core/multiqc/tests/main.nf.test.snap new file mode 100644 index 0000000..c204b48 --- /dev/null +++ b/modules/nf-core/multiqc/tests/main.nf.test.snap @@ -0,0 +1,41 @@ +{ + "multiqc_versions_single": { + "content": [ + [ + "versions.yml:md5,d320d4c37e349c5588e07e7a31cd4186" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-14T09:28:51.744211298" + }, + "multiqc_stub": { + "content": [ + [ + "multiqc_report.html", + "multiqc_data", + "multiqc_plots", + "versions.yml:md5,d320d4c37e349c5588e07e7a31cd4186" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-14T09:29:28.847433492" + }, + "multiqc_versions_config": { + "content": [ + [ + "versions.yml:md5,d320d4c37e349c5588e07e7a31cd4186" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-14T09:29:13.223621555" + } +} \ No newline at end of file diff --git a/modules/nf-core/multiqc/tests/tags.yml b/modules/nf-core/multiqc/tests/tags.yml new file mode 100644 index 0000000..bea6c0d --- /dev/null +++ b/modules/nf-core/multiqc/tests/tags.yml @@ -0,0 +1,2 @@ +multiqc: + - modules/nf-core/multiqc/** diff --git a/nextflow.config b/nextflow.config index 03c191a..8308702 100644 --- a/nextflow.config +++ b/nextflow.config @@ -9,56 +9,55 @@ // Global default params, used in configs params { // Input options - input = null - peptides_split_maxchunks = 100 - peptides_split_minchunksize = 5000 - split_by_variants = false - split_by_variants_size = 0 - split_by_variants_distance = 110000 + input = null + peptides_split_maxchunks = 100 + peptides_split_minchunksize = 5000 + split_by_variants = false + split_by_variants_size = 0 + split_by_variants_distance = 110000 // References - genome_version = 'GRCh37' + genome_reference = 'grch37' // Options: Predictions - tools = 'syfpeithi' - tool_thresholds = null + tools = 'syfpeithi' + tool_thresholds = null use_affinity_thresholds = false // Options: Filtering - filter_self = false + filter_self = false show_supported_models = false // External tools external_tools_meta = "${projectDir}/assets/external_tools_meta.json" - netmhc_system = 'linux' - netmhcpan_path = null - netmhc_path = null - netmhciipan_path = null - netmhcii_path = null + netmhc_system = 'linux' + netmhcpan_path = null + netmhc_path = null + netmhciipan_path = null + netmhcii_path = null // Options: Peptides - max_peptide_length = 11 - min_peptide_length = 8 + max_peptide_length = 11 + min_peptide_length = 8 max_peptide_length_class2 = 16 min_peptide_length_class2 = 15 // Options: Annotation - proteome = null + proteome = null wild_type = false // Options: Output fasta_output = false // MultiQC options - multiqc_config = null - multiqc_title = null - multiqc_logo = "$projectDir/assets/nf-core-epitopeprediction_logo_light.png" - max_multiqc_email_size = '25.MB' + multiqc_config = null + multiqc_title = null + multiqc_logo = "$projectDir/assets/nf-core-epitopeprediction_logo_light.png" + max_multiqc_email_size = '25.MB' multiqc_methods_description = null // Boilerplate options outdir = null - tracedir = "${params.outdir}/pipeline_info" publish_dir_mode = 'copy' email = null email_on_fail = null @@ -69,18 +68,15 @@ params { version = false validate_params = true show_hidden_params = false - schema_ignore_params = 'genomes' igenomes_ignore = true // Config options + config_profile_name = null + config_profile_description = null custom_config_version = 'master' custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}" - config_profile_description = null config_profile_contact = null config_profile_url = null - config_profile_name = null - - conda.enabled = false // Max resource options // Defaults only, expecting to be overwritten @@ -88,6 +84,13 @@ params { max_cpus = 16 max_time = '240.h' + // Schema validation default options + validationFailUnrecognisedParams = false + validationLenientMode = false + validationSchemaIgnoreParams = 'fasta,genome,genomes,igenomes_base' + validationShowHiddenParams = false + validate_params = true + } // Load base.config by default for all pipelines @@ -101,16 +104,19 @@ try { } // Load nf-core/epitopeprediction custom profiles from different institutions. -// Warning: Uncomment only if a pipeline-specific instititutional config already exists on nf-core/configs! +// Warning: Uncomment only if a pipeline-specific institutional config already exists on nf-core/configs! // try { // includeConfig "${params.custom_config_base}/pipeline/epitopeprediction.config" // } catch (Exception e) { // System.err.println("WARNING: Could not load nf-core/config/epitopeprediction profiles: ${params.custom_config_base}/pipeline/epitopeprediction.config") // } - - profiles { - debug { process.beforeScript = 'echo $HOSTNAME' } + debug { + dumpHashes = true + process.beforeScript = 'echo $HOSTNAME' + cleanup = false + nextflow.enable.configProcessNamesValidation = true + } conda { conda.enabled = true docker.enabled = false @@ -118,6 +124,8 @@ profiles { podman.enabled = false shifter.enabled = false charliecloud.enabled = false + channels = ['conda-forge', 'bioconda', 'defaults'] + apptainer.enabled = false } mamba { conda.enabled = true @@ -127,55 +135,75 @@ profiles { podman.enabled = false shifter.enabled = false charliecloud.enabled = false + apptainer.enabled = false } docker { docker.enabled = true - docker.userEmulation = true + conda.enabled = false singularity.enabled = false podman.enabled = false shifter.enabled = false charliecloud.enabled = false + apptainer.enabled = false + docker.runOptions = '-u $(id -u):$(id -g)' } arm { - docker.runOptions = '-u $(id -u):$(id -g) --platform=linux/amd64' + docker.runOptions = '-u $(id -u):$(id -g) --platform=linux/amd64' } singularity { singularity.enabled = true singularity.autoMounts = true + conda.enabled = false docker.enabled = false podman.enabled = false shifter.enabled = false charliecloud.enabled = false + apptainer.enabled = false } podman { podman.enabled = true + conda.enabled = false docker.enabled = false singularity.enabled = false shifter.enabled = false charliecloud.enabled = false + apptainer.enabled = false } shifter { shifter.enabled = true + conda.enabled = false docker.enabled = false singularity.enabled = false podman.enabled = false charliecloud.enabled = false + apptainer.enabled = false } charliecloud { charliecloud.enabled = true + conda.enabled = false + docker.enabled = false + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + apptainer.enabled = false + } + apptainer { + apptainer.enabled = true + apptainer.autoMounts = true + conda.enabled = false docker.enabled = false singularity.enabled = false podman.enabled = false shifter.enabled = false + charliecloud.enabled = false } gitpod { executor.name = 'local' - executor.cpus = 16 - executor.memory = 60.GB + executor.cpus = 4 + executor.memory = 8.GB } test { includeConfig 'conf/test.config' } - test_variant_tsv { includeConfig 'conf/test_variant_tsv.config' } - test_grch38_variant_tsv { includeConfig 'conf/test_grch38_variant_tsv.config' } + test_grch38 { includeConfig 'conf/test_grch38.config' } test_peptides { includeConfig 'conf/test_peptides.config' } test_peptides_h2 { includeConfig 'conf/test_peptides_h2.config' } test_proteins { includeConfig 'conf/test_proteins.config' } @@ -187,6 +215,18 @@ profiles { test_full { includeConfig 'conf/test_full.config' } } +// Set default registry for Apptainer, Docker, Podman and Singularity independent of -profile +// Will not be used unless Apptainer / Docker / Podman / Singularity are enabled +// Set to your registry if you have a mirror of containers +apptainer.registry = 'quay.io' +docker.registry = 'quay.io' +podman.registry = 'quay.io' +singularity.registry = 'quay.io' + +// Nextflow plugins +plugins { + id 'nf-validation@1.1.3' // Validation of pipeline parameters and creation of an input channel from a sample sheet +} // Load igenomes.config if required if (!params.igenomes_ignore) { @@ -194,8 +234,6 @@ if (!params.igenomes_ignore) { } else { params.genomes = [:] } - - // Export these variables to prevent local Python/R libraries from conflicting with those in the container // The JULIA depot path has been adjusted to a fixed path `/usr/local/share/julia` that needs to be used for packages in the container. // See https://apeltzer.github.io/post/03-julia-lang-nextflow/ for details on that. Once we have a common agreement on where to keep Julia packages, this is adjustable. @@ -210,22 +248,25 @@ env { // Capture exit codes from upstream processes when piping process.shell = ['/bin/bash', '-euo', 'pipefail'] +// Disable process selector warnings by default. Use debug profile to enable warnings. +nextflow.enable.configProcessNamesValidation = false + def trace_timestamp = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss') timeline { enabled = true - file = "${params.tracedir}/execution_timeline_${trace_timestamp}.html" + file = "${params.outdir}/pipeline_info/execution_timeline_${trace_timestamp}.html" } report { enabled = true - file = "${params.tracedir}/execution_report_${trace_timestamp}.html" + file = "${params.outdir}/pipeline_info/execution_report_${trace_timestamp}.html" } trace { enabled = true - file = "${params.tracedir}/execution_trace_${trace_timestamp}.txt" + file = "${params.outdir}/pipeline_info/execution_trace_${trace_timestamp}.txt" } dag { enabled = true - file = "${params.tracedir}/pipeline_dag_${trace_timestamp}.html" + file = "${params.outdir}/pipeline_info/pipeline_dag_${trace_timestamp}.html" } // Load modules.config for DSL2 module specific options @@ -237,8 +278,8 @@ manifest { homePage = 'https://github.com/nf-core/epitopeprediction' description = """A fully reproducible and state of the art epitope prediction pipeline.""" mainScript = 'main.nf' - nextflowVersion = '!>=22.10.1' - version = '2.2.1' + nextflowVersion = '!>=23.04.0' + version = '2.3.0' doi = '' } diff --git a/nextflow_schema.json b/nextflow_schema.json index a727277..90ec20f 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -15,8 +15,7 @@ "input": { "type": "string", "format": "file-path", - "mimetype": "text/csv", - "pattern": "^\\S+\\.csv$", + "exists": true, "schema": "assets/schema_input.json", "description": "Path to comma-separated file containing information about the samples in the experiment.", "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row. See [usage docs](https://nf-co.re/epitopeprediction/usage#samplesheet-input).", @@ -48,12 +47,11 @@ "description": "Options for the genome and proteome reference.", "fa_icon": "fas fa-stream", "properties": { - "genome_version": { + "genome_reference": { "type": "string", - "default": "GRCh37", - "help_text": "This defines against which human reference genome the pipeline performs the analysis including the incorporation of genetic variants e.g..", - "enum": ["GRCh37", "GRCh38"], - "description": "Specifies the human reference genome version." + "default": "grch37", + "help_text": "This defines against which human Ensembl genome reference the pipeline performs the analysis including the incorporation of genetic variants. If `grch37` or `grch38` are specified, the most recent Ensembl Biomart version for genome versions will be used. Alternatively, an Ensembl Biomart (archive) version can be specified, e.g. http://jan2020.archive.ensembl.org/.", + "description": "Specifies the Ensembl genome reference version that will be used." }, "proteome": { "type": "string", @@ -113,6 +111,7 @@ "tools": { "type": "string", "default": "syfpeithi", + "pattern": "^(syfpeithi|mhcnuggets-class-1|mhcnuggets-class-2|mhcflurry|netmhc-4.0|netmhcpan-4.0|netmhcpan-4.1|netmhciipan-4.1|netmhc_darwin-4.0|netmhcpan_darwin-4.0|netmhcpan_darwin-4.1|netmhciipan_darwin-4.1)(,(syfpeithi|mhcnuggets-class-1|mhcnuggets-class-2|mhcflurry|netmhc-4.0|netmhcpan-4.0|netmhcpan-4.1|netmhciipan-4.1|netmhc_darwin-4.0|netmhcpan_darwin-4.0|netmhcpan_darwin-4.1|netmhciipan_darwin-4.1))*$", "help_text": "Specifies the tool(s) to use. Multiple tools can be combined in a list separated by comma.\nAvailable are: `syfpeithi`, `mhcflurry`, `mhcnuggets-class-1`, `mhcnuggets-class-2`,`netmhcpan-4.0`,`netmhcpan-4.1`,`netmhc-4.0`,`netmhciipan-4.1`.", "description": "Specifies the prediction tool(s) to use." }, @@ -186,32 +185,40 @@ "properties": { "external_tools_meta": { "type": "string", - "default": "${projectDir}/assets/external_tools_meta.json", "description": "Specifies the path to the JSON file with meta information on external prediction tools." }, "netmhc_system": { "type": "string", "default": "linux", + "enum": ["linux", "darwin"], "description": "Specifies the operating system in use (Linux or Darwin). This is only necessary if conda is used." }, "netmhcpan_path": { "type": "string", - "default": "None", + "format": "file-path", + "exists": true, + "pattern": "^\\S+\\.tar\\.gz$", "description": "To use the 'netmhcpan' tool, specify the path to the original software tarball for NetMHCpan 4.0 here." }, "netmhc_path": { "type": "string", - "default": "None", + "format": "file-path", + "exists": true, + "pattern": "^\\S+\\.tar\\.gz$", "description": "To use the 'netmhc' tool, specify the path to the original software tarball for NetMHC 4.0 here." }, "netmhciipan_path": { "type": "string", - "default": "None", + "format": "file-path", + "exists": true, + "pattern": "^\\S+\\.tar\\.gz$", "description": "To use the 'netmhciipan' tool, specify the path to the original software tarball for NetMHCIIpan 3.1 here." }, "netmhcii_path": { "type": "string", - "default": "None", + "format": "file-path", + "exists": true, + "pattern": "^\\S+\\.tar\\.gz$", "description": "To use the 'netmhcii' tool, specify the path to the original software tarball for NetMHCII 2.2 here." } } @@ -294,7 +301,7 @@ "description": "Maximum amount of time that can be requested for any single job.", "default": "240.h", "fa_icon": "far fa-clock", - "pattern": "^(\\d+\\.?\\s*(s|m|h|day)\\s*)+$", + "pattern": "^(\\d+\\.?\\s*(s|m|h|d|day)\\s*)+$", "hidden": true, "help_text": "Use to set an upper-limit for the time requirement for each process. Should be a string in the format integer-unit e.g. `--max_time '2.h'`" } @@ -365,6 +372,7 @@ }, "multiqc_config": { "type": "string", + "format": "file-path", "description": "Custom config file to supply to MultiQC.", "fa_icon": "fas fa-cog", "hidden": true @@ -380,13 +388,6 @@ "description": "Custom MultiQC yaml file containing HTML including a methods description.", "fa_icon": "fas fa-cog" }, - "tracedir": { - "type": "string", - "description": "Directory to keep pipeline Nextflow logs and reports.", - "default": "${params.outdir}/pipeline_info", - "fa_icon": "fas fa-cogs", - "hidden": true - }, "validate_params": { "type": "boolean", "description": "Boolean whether to validate parameters against the schema at runtime", @@ -394,6 +395,27 @@ "fa_icon": "fas fa-check-square", "hidden": true }, + "validationShowHiddenParams": { + "type": "boolean", + "fa_icon": "far fa-eye-slash", + "description": "Show all params when using `--help`", + "hidden": true, + "help_text": "By default, parameters set as _hidden_ in the schema are not shown on the command line when a user runs with `--help`. Specifying this option will tell the pipeline to show all parameters." + }, + "validationFailUnrecognisedParams": { + "type": "boolean", + "fa_icon": "far fa-check-circle", + "description": "Validation of parameters fails when an unrecognised parameter is found.", + "hidden": true, + "help_text": "By default, when an unrecognised parameter is found, it returns a warinig." + }, + "validationLenientMode": { + "type": "boolean", + "fa_icon": "far fa-check-circle", + "description": "Validation of parameters in lenient more.", + "hidden": true, + "help_text": "Allows string values that are parseable as numbers or booleans. For further information see [JSONSchema docs](https://github.com/everit-org/json-schema#lenient-mode)." + }, "show_hidden_params": { "type": "boolean", "fa_icon": "far fa-eye-slash", diff --git a/pyproject.toml b/pyproject.toml index 0d62beb..5611062 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,10 +1,15 @@ -# Config file for Python. Mostly used to configure linting of bin/check_samplesheet.py with Black. +# Config file for Python. Mostly used to configure linting of bin/*.py with Ruff. # Should be kept the same as nf-core/tools to avoid fighting with template synchronisation. -[tool.black] +[tool.ruff] line-length = 120 -target_version = ["py37", "py38", "py39", "py310"] +target-version = "py38" +cache-dir = "~/.cache/ruff" -[tool.isort] -profile = "black" -known_first_party = ["nf_core"] -multi_line_output = 3 +[tool.ruff.lint] +select = ["I", "E1", "E4", "E7", "E9", "F", "UP", "N"] + +[tool.ruff.lint.isort] +known-first-party = ["nf_core"] + +[tool.ruff.lint.per-file-ignores] +"__init__.py" = ["E402", "F401"] diff --git a/subworkflows/local/input_check.nf b/subworkflows/local/input_check.nf deleted file mode 100644 index 1913eea..0000000 --- a/subworkflows/local/input_check.nf +++ /dev/null @@ -1,85 +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: - SAMPLESHEET_CHECK ( samplesheet ) - .csv - .splitCsv ( header:true, sep:',' ) - .map { get_samplesheet_paths(it) } - .set { reads } - - emit: - reads // channel: [ val(meta), [ reads ] ] - versions = SAMPLESHEET_CHECK.out.versions // channel: [ versions.yml ] -} - -// Function to get list of [ meta, filenames ] -def get_samplesheet_paths(LinkedHashMap row) { - - def allele_string = generate_allele_string(row.alleles, row.mhc_class) - def type = determine_input_type(row.filename) - def meta = [:] - meta.sample = row.sample - meta.alleles = allele_string - meta.mhcclass = row.mhc_class - meta.inputtype = type - - def array = [] - if (!file(row.filename).exists()) { - exit 1, "ERROR: Please check input samplesheet -> file does not exist!\n${row.Filename}" - } else { - array = [ meta, file(row.filename) ] - } - return array -} - -def generate_allele_string(String alleles, String mhcclass) { - // Collect the allele information from the file - def allele_string - valid_class1_loci = ['A*','B*','C*','E*','G*'] - valid_class2_loci = ['DR','DP','DQ'] - if ( alleles.endsWith(".txt") || alleles.endsWith(".alleles") ) { - allele_string = file(alleles).readLines().join(';') - if ((mhcclass == 'I' & valid_class2_loci.any { allele_string.contains(it)}) | - (mhcclass == 'II' & valid_class1_loci.any { allele_string.contains(it)})) { - exit 1, "ERROR: Please check input samplesheet -> invalid mhc class and allele combination found!\n${row.Filename}" - } - } - // or assign the information to a new variable - else { - allele_string = alleles - } - return allele_string -} - -def determine_input_type(String filename) { - def filetype - def input_file = file(filename) - def extension = input_file.extension - - if (filename.endsWith("vcf.gz") ) { - filetype = "variant_compressed" - } - else if (extension == "vcf") { - filetype = "variant" - } - else if ( extension == "tsv" | extension == "GSvar" ) { - // Check if it is a variant annotation file or a peptide file - input_file.withReader { - def first_header_col = it.readLine().split('\t')[0] - if (first_header_col == "id") { filetype = "peptide" } - else if (first_header_col == "#chr") {filetype = "variant"} - } - } - else { - filetype = "protein" - } - return filetype -} diff --git a/subworkflows/local/utils_nfcore_epitopeprediction_pipeline/main.nf b/subworkflows/local/utils_nfcore_epitopeprediction_pipeline/main.nf new file mode 100644 index 0000000..e62cbd1 --- /dev/null +++ b/subworkflows/local/utils_nfcore_epitopeprediction_pipeline/main.nf @@ -0,0 +1,232 @@ +// +// 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 + + 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 --outdir " + 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 +} + +/* +======================================================================================== + 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) = input[1..2] + + // 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: ${metas[0].id}") + } + + return [ metas[0], fastqs ] +} +// +// Get attribute from genome config file e.g. fasta +// +def getGenomeAttribute(attribute) { + if (params.genomes && params.genome && params.genomes.containsKey(params.genome)) { + if (params.genomes[ params.genome ].containsKey(attribute)) { + return params.genomes[ params.genome ][ attribute ] + } + } + return null +} + +// +// Exit pipeline if incorrect --genome key provided +// +def genomeExistsError() { + if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) { + def error_string = "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" + + " Genome '${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 citation_text = [ + "Tools used in the workflow included:", + "Epytope (Schuber et al. 2016)", + "SYFPEITHI (Schuler et al. 2007)", + "NetMHC (Andreatta and Nielsen 2016)", + "NetMHCpan (Reynisson et al. 2020)", + "NetMHCIIpan (Nilsson et al. 2023)", + "MHCnuggets (Shao et al. 2020)", + "MHCflurry (O'Donnell et al. 2020)", + "MultiQC (Ewels et al. 2016)", + "." + ].join(' ').trim() + + return citation_text +} + +def toolBibliographyText() { + def reference_text = [ + "
  • Schubert et al. (2016). FRED 2: an immunoinformatics framework for Python. Bioinformatics , 32(13), 2044–2046. doi: /10.1093/bioinformatics/btw113
    • ", + "
  • Schuler et al. (2007). SYFPEITHI: database for searching and T-cell epitope prediction. Immunoinformatics, 75–93. doi: /10.1007/978-1-60327-118-9_5
    • ", + "
  • Andreatta and Nielsen (2016). Gapped sequence alignment using artificial neural networks: application to the MHC class I system. Bioinformatics, 32(4), 511–517. doi: /10.1093/bioinformatics/btv639
    • ", + "
  • Reynisson et al. (2020). NetMHCpan-4.1 and NetMHCIIpan-4.0: Improved predictions of MHC antigen presentation by concurrent motif deconvolution and integration of MS MHC eluted ligand data. Nucleic Acids Research, Volume 48, Issue W1, Pages W449–W454. doi: /10.1093/nar/gkaa379
    • ", + "
  • Nilsson et al. (2023). Accurate prediction of HLA class II antigen presentation across all loci using tailored data acquisition and refined machine learning. Science Advances, Vol 9, Issue 47. doi: /10.1126/sciadv.adj6367
    • ", + "
  • Shao et al. (2020). High-throughput prediction of MHC class I and II neoantigens with MHCnuggets. Cancer Immunology Research, 8(3), 396–408. doi: /10.1158/2326-6066.CIR-19-0464
    • ", + "
  • O'Donnell et al. (2020). MHCflurry 2.0: improved pan-allele prediction of MHC class I-presented peptides by incorporating antigen processing. Cell Systems, 11, 42–48. doi: /10.1016/j.cels.2020.06.010
    • ", + "
  • Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Science Advances , Vol 9, Issue 47. doi: /10.1126/sciadv.adj6367
    • " + ].join(' ').trim() + + return reference_text +} + +def methodsDescriptionText(mqc_methods_yaml) { + // 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 = workflow.toMap() + meta["manifest_map"] = workflow.manifest.toMap() + + // Pipeline DOI + meta["doi_text"] = meta.manifest_map.doi ? "(doi: ${meta.manifest_map.doi})" : "" + meta["nodoi_text"] = meta.manifest_map.doi ? "": "
  • If available, make sure to update the text to include the Zenodo DOI of version of the pipeline used.
    • " + + meta["tool_citations"] = toolCitationText().replaceAll(", \\.", ".").replaceAll("\\. \\.", ".").replaceAll(", \\.", ".") + meta["tool_bibliography"] = toolBibliographyText() + + + def methods_text = mqc_methods_yaml.text + + def engine = new groovy.text.SimpleTemplateEngine() + def description_html = engine.createTemplate(methods_text).make(meta) + + return description_html.toString() +} diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/main.nf b/subworkflows/nf-core/utils_nextflow_pipeline/main.nf new file mode 100644 index 0000000..ac31f28 --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/main.nf @@ -0,0 +1,126 @@ +// +// Subworkflow with functionality that may be useful for any Nextflow pipeline +// + +import org.yaml.snakeyaml.Yaml +import groovy.json.JsonOutput +import nextflow.extension.FilesEx + +/* +======================================================================================== + SUBWORKFLOW DEFINITION +======================================================================================== +*/ + +workflow UTILS_NEXTFLOW_PIPELINE { + + take: + print_version // boolean: print version + dump_parameters // boolean: dump parameters + outdir // path: base directory used to publish pipeline results + check_conda_channels // boolean: check conda channels + + main: + + // + // Print workflow version and exit on --version + // + if (print_version) { + log.info "${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 0000000..e5c3a0a --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/meta.yml @@ -0,0 +1,38 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json +name: "UTILS_NEXTFLOW_PIPELINE" +description: Subworkflow with functionality that may be useful for any Nextflow pipeline +keywords: + - utility + - pipeline + - initialise + - version +components: [] +input: + - print_version: + type: boolean + description: | + Print the version of the pipeline and exit + - dump_parameters: + type: boolean + description: | + Dump the parameters of the pipeline to a JSON file + - output_directory: + type: directory + description: Path to output dir to write JSON file to. + pattern: "results/" + - check_conda_channel: + type: boolean + description: | + Check if the conda channel priority is correct. +output: + - dummy_emit: + type: boolean + description: | + Dummy emit to make nf-core subworkflows lint happy +authors: + - "@adamrtalbot" + - "@drpatelh" +maintainers: + - "@adamrtalbot" + - "@drpatelh" + - "@maxulysse" diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test new file mode 100644 index 0000000..8ed4310 --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test @@ -0,0 +1,54 @@ + +nextflow_function { + + name "Test Functions" + script "subworkflows/nf-core/utils_nextflow_pipeline/main.nf" + config "subworkflows/nf-core/utils_nextflow_pipeline/tests/nextflow.config" + tag 'subworkflows' + tag 'utils_nextflow_pipeline' + tag 'subworkflows/utils_nextflow_pipeline' + + test("Test Function getWorkflowVersion") { + + function "getWorkflowVersion" + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } + + test("Test Function dumpParametersToJSON") { + + function "dumpParametersToJSON" + + when { + function { + """ + // define inputs of the function here. Example: + input[0] = "$outputDir" + """.stripIndent() + } + } + + then { + assertAll( + { assert function.success } + ) + } + } + + test("Test Function checkCondaChannels") { + + function "checkCondaChannels" + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } +} \ No newline at end of file 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 0000000..db2030f --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test.snap @@ -0,0 +1,12 @@ +{ + "Test Function getWorkflowVersion": { + "content": [ + "v9.9.9" + ], + "timestamp": "2024-01-19T11:32:36.031083" + }, + "Test Function checkCondaChannels": { + "content": null, + "timestamp": "2024-01-19T11:32:50.456" + } +} \ 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 0000000..f7c54bc --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test @@ -0,0 +1,123 @@ +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 { + params { + outdir = "tests/results" + } + 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 { + params { + outdir = "tests/results" + } + 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 { + params { + outdir = "$outputDir" + } + workflow { + """ + print_version = false + dump_parameters = true + outdir = params.outdir + check_conda_channels = false + + input[0] = false + input[1] = true + input[2] = params.outdir + input[3] = false + """ + } + } + + then { + assertAll( + { assert workflow.success } + ) + } + } + + test("Should not create params JSON if no output directory") { + + when { + params { + outdir = "$outputDir" + } + workflow { + """ + print_version = false + dump_parameters = true + outdir = params.outdir + check_conda_channels = false + + input[0] = false + input[1] = true + input[2] = null + 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 0000000..53574ff --- /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' +} \ No newline at end of file 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 0000000..f847611 --- /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 0000000..a8b55d6 --- /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 0000000..d08d243 --- /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 0000000..1dc317f --- /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 0000000..10f948e --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test.snap @@ -0,0 +1,138 @@ +{ + "Test Function checkProfileProvided": { + "content": null, + "timestamp": "2024-02-09T15:43:55.145717" + }, + "Test Function checkConfigProvided": { + "content": [ + true + ], + "timestamp": "2024-01-19T11:34:13.548431224" + }, + "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" + ], + "timestamp": "2024-01-19T11:34:38.840454873" + }, + "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" + ], + "timestamp": "2024-01-19T11:34:22.24352016" + }, + "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": "" + } + ], + "timestamp": "2024-01-19T11:35:04.418416984" + }, + "Test Function dashedLine": { + "content": [ + "-\u001b[2m----------------------------------------------------\u001b[0m-" + ], + "timestamp": "2024-01-19T11:34:55.420000755" + }, + "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" + } + ], + "timestamp": "2024-01-19T11:35:13.436366565" + } +} \ 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 0000000..8940d32 --- /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 0000000..d07ce54 --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test.snap @@ -0,0 +1,15 @@ +{ + "Should run without failures": { + "content": [ + { + "0": [ + true + ], + "valid_config": [ + true + ] + } + ], + "timestamp": "2024-01-19T11:35:22.538940073" + } +} \ 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 0000000..d0a926b --- /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 0000000..ac8523c --- /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 0000000..2585b65 --- /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 0000000..3d4a6b0 --- /dev/null +++ b/subworkflows/nf-core/utils_nfvalidation_plugin/meta.yml @@ -0,0 +1,44 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json +name: "UTILS_NFVALIDATION_PLUGIN" +description: Use nf-validation to initiate and validate a pipeline +keywords: + - utility + - pipeline + - initialise + - validation +components: [] +input: + - print_help: + type: boolean + description: | + Print help message and exit + - workflow_command: + type: string + description: | + The command to run the workflow e.g. "nextflow run main.nf" + - pre_help_text: + type: string + description: | + Text to print before the help message + - post_help_text: + type: string + description: | + Text to print after the help message + - validate_params: + type: boolean + description: | + Validate the parameters and error if invalid. + - schema_filename: + type: string + description: | + The filename of the schema to validate against. +output: + - dummy_emit: + type: boolean + description: | + Dummy emit to make nf-core subworkflows lint happy +authors: + - "@adamrtalbot" +maintainers: + - "@adamrtalbot" + - "@maxulysse" diff --git a/subworkflows/nf-core/utils_nfvalidation_plugin/tests/main.nf.test b/subworkflows/nf-core/utils_nfvalidation_plugin/tests/main.nf.test new file mode 100644 index 0000000..517ee54 --- /dev/null +++ b/subworkflows/nf-core/utils_nfvalidation_plugin/tests/main.nf.test @@ -0,0 +1,200 @@ +nextflow_workflow { + + name "Test Workflow UTILS_NFVALIDATION_PLUGIN" + script "../main.nf" + workflow "UTILS_NFVALIDATION_PLUGIN" + tag "subworkflows" + tag "subworkflows_nfcore" + tag "plugin/nf-validation" + tag "'plugin/nf-validation'" + tag "utils_nfvalidation_plugin" + tag "subworkflows/utils_nfvalidation_plugin" + + test("Should run nothing") { + + when { + + params { + monochrome_logs = true + test_data = '' + } + + workflow { + """ + help = false + workflow_command = null + pre_help_text = null + post_help_text = null + validate_params = false + schema_filename = "$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!') } } + ) + } + } +} \ No newline at end of file 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 0000000..7626c1c --- /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 0000000..60b1cff --- /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/tower.yml b/tower.yml new file mode 100644 index 0000000..787aedf --- /dev/null +++ b/tower.yml @@ -0,0 +1,5 @@ +reports: + multiqc_report.html: + display: "MultiQC HTML report" + samplesheet.csv: + display: "Auto-created samplesheet with collated metadata and FASTQ paths" diff --git a/workflows/epitopeprediction.nf b/workflows/epitopeprediction.nf index 6108cdb..a1060bf 100644 --- a/workflows/epitopeprediction.nf +++ b/workflows/epitopeprediction.nf @@ -1,73 +1,36 @@ -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - VALIDATE INPUTS -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -*/ - -def summary_params = NfcoreSchema.paramsSummaryMap(workflow, params) - -// Validate input parameters -WorkflowEpitopeprediction.initialise(params, log) - -// Check input path parameters to see if they exist -def checkPathParamList = [ params.input, params.multiqc_config ] -for (param in checkPathParamList) { if (param) { file(param, checkIfExists: true) } } - -// Check mandatory parameters -if (params.input) { ch_input = file(params.input) } else { exit 1, 'Input samplesheet not specified!' } - -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - CONFIG FILES -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -*/ - -ch_multiqc_config = 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) - /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ IMPORT LOCAL MODULES/SUBWORKFLOWS ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ - // // MODULE: Local to the pipeline // -include { GET_PREDICTION_VERSIONS } from '../modules/local/get_prediction_versions' - -include { EXTERNAL_TOOLS_IMPORT } from '../modules/local/external_tools_import' - +include { GET_PREDICTION_VERSIONS } from '../modules/local/get_prediction_versions' +include { EXTERNAL_TOOLS_IMPORT } from '../modules/local/external_tools_import' include { EPYTOPE_CHECK_REQUESTED_MODELS as EPYTOPE_CHECK_REQUESTED_MODELS_PROTEIN } from '../modules/local/epytope_check_requested_models' -include { EPYTOPE_CHECK_REQUESTED_MODELS as EPYTOPE_CHECK_REQUESTED_MODELS_PEP } from '../modules/local/epytope_check_requested_models' -include { EPYTOPE_CHECK_REQUESTED_MODELS } from '../modules/local/epytope_check_requested_models' -include { EPYTOPE_SHOW_SUPPORTED_MODELS } from '../modules/local/epytope_show_supported_models' - -include { VARIANT_SPLIT} from '../modules/local/variant_split' -include { SNPSIFT_SPLIT} from '../modules/local/snpsift_split' -include { CSVTK_SPLIT} from '../modules/local/csvtk_split' +include { EPYTOPE_CHECK_REQUESTED_MODELS as EPYTOPE_CHECK_REQUESTED_MODELS_PEP } from '../modules/local/epytope_check_requested_models' +include { EPYTOPE_CHECK_REQUESTED_MODELS } from '../modules/local/epytope_check_requested_models' +include { EPYTOPE_SHOW_SUPPORTED_MODELS } from '../modules/local/epytope_show_supported_models' -include { EPYTOPE_GENERATE_PEPTIDES } from '../modules/local/epytope_generate_peptides' -include { SPLIT_PEPTIDES as SPLIT_PEPTIDES_PEPTIDES } from '../modules/local/split_peptides' -include { SPLIT_PEPTIDES as SPLIT_PEPTIDES_PROTEIN } from '../modules/local/split_peptides' +include { VARIANT_SPLIT } from '../modules/local/variant_split' +include { SNPSIFT_SPLIT } from '../modules/local/snpsift_split' -include { EPYTOPE_PEPTIDE_PREDICTION as EPYTOPE_PEPTIDE_PREDICTION_PROTEIN } from '../modules/local/epytope_peptide_prediction' -include { EPYTOPE_PEPTIDE_PREDICTION as EPYTOPE_PEPTIDE_PREDICTION_PEP } from '../modules/local/epytope_peptide_prediction' -include { EPYTOPE_PEPTIDE_PREDICTION as EPYTOPE_PEPTIDE_PREDICTION_VAR } from '../modules/local/epytope_peptide_prediction' +include { EPYTOPE_GENERATE_PEPTIDES } from '../modules/local/epytope_generate_peptides' +include { SPLIT_PEPTIDES as SPLIT_PEPTIDES_PEPTIDES } from '../modules/local/split_peptides' +include { SPLIT_PEPTIDES as SPLIT_PEPTIDES_PROTEIN } from '../modules/local/split_peptides' -include { CAT_FILES as CAT_TSV } from '../modules/local/cat_files' -include { CAT_FILES as CAT_FASTA } from '../modules/local/cat_files' -include { CSVTK_CONCAT } from '../modules/local/csvtk_concat' +include { EPYTOPE_PEPTIDE_PREDICTION as EPYTOPE_PEPTIDE_PREDICTION_PROTEIN } from '../modules/local/epytope_peptide_prediction' +include { EPYTOPE_PEPTIDE_PREDICTION as EPYTOPE_PEPTIDE_PREDICTION_PEP } from '../modules/local/epytope_peptide_prediction' +include { EPYTOPE_PEPTIDE_PREDICTION as EPYTOPE_PEPTIDE_PREDICTION_VAR } from '../modules/local/epytope_peptide_prediction' -include { MERGE_JSON as MERGE_JSON_SINGLE } from '../modules/local/merge_json' -include { MERGE_JSON as MERGE_JSON_MULTI } from '../modules/local/merge_json' +include { CAT_FILES as CAT_TSV } from '../modules/local/cat_files' +include { CAT_FILES as CAT_FASTA } from '../modules/local/cat_files' +include { CSVTK_CONCAT } from '../modules/local/csvtk_concat' -// -// SUBWORKFLOW: Consisting of a mix of local and nf-core/modules +include { MERGE_JSON as MERGE_JSON_SINGLE } from '../modules/local/merge_json' +include { MERGE_JSON as MERGE_JSON_MULTI } from '../modules/local/merge_json' -include { INPUT_CHECK } from '../subworkflows/local/input_check' /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -79,9 +42,31 @@ include { INPUT_CHECK } from '../subworkflows/local/input_check' // MODULE: Installed directly from nf-core/modules // include { MULTIQC } from '../modules/nf-core/multiqc/main' -include { CUSTOM_DUMPSOFTWAREVERSIONS } from '../modules/nf-core/custom/dumpsoftwareversions/main' include { GUNZIP as GUNZIP_VCF } from '../modules/nf-core/gunzip/main' +include { paramsSummaryLog; paramsSummaryMap; fromSamplesheet; validateParameters } 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_epitopeprediction_pipeline' + +/* +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + FUNCTIONS +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +*/ + +// Function to check if the alleles are valid for the given mhc class +def validate_alleles(String alleles, String mhc_class) { + valid_class1_loci = ['A*','B*','C*','E*','G*'] + valid_class2_loci = ['DR','DP','DQ'] + allele_list = alleles.split(';') + if (( mhc_class == 'I' & allele_list.every { allele -> valid_class2_loci.any { allele.startsWith(it) }}) | + ( mhc_class == 'II' & allele_list.every { allele -> valid_class1_loci.any { allele.startsWith(it) }})) { + exit 1, "Please check input samplesheet -> Invalid mhc class ${mhc_class} and allele combination ${allele_list} found!" + } +} + /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ RUN MAIN WORKFLOW @@ -89,55 +74,64 @@ include { GUNZIP as GUNZIP_VCF } from '../modules/nf-core/gunzip/main' */ // Info required for completion email and summary -def multiqc_report = [] +ch_multiqc_files = Channel.empty() // load meta data of external tools import groovy.json.JsonSlurper def jsonSlurper = new JsonSlurper() def external_tools_meta = jsonSlurper.parse(file(params.external_tools_meta, checkIfExists: true)) + workflow EPITOPEPREDICTION { - ch_versions = Channel.empty() - ch_software_versions = Channel.empty() - // Non-free prediction tools - ch_nonfree_paths = Channel.empty() + take: + samplesheet - // - // SUBWORKFLOW: Read in samplesheet, validate and stage input files - // - INPUT_CHECK ( - ch_input - ) - ch_versions = ch_versions.mix(INPUT_CHECK.out.versions) - - INPUT_CHECK.out.reads - .branch { - meta_data, input_file -> - variant_compressed : meta_data.inputtype == 'variant_compressed' - return [ meta_data, input_file ] - variant_uncompressed : meta_data.inputtype == 'variant' - return [ meta_data, input_file ] - peptide : meta_data.inputtype == 'peptide' - return [ meta_data, input_file ] - protein : meta_data.inputtype == 'protein' - return [ meta_data, input_file ] - } - .set { ch_samples_from_sheet } + main: + ch_versions = Channel.empty() + ch_nonfree_paths = Channel.empty() // Non-free prediction tools + + // Function to read the alleles from a file or use given string + def readAlleles = { input -> + if (input.endsWith(".txt")) { + def file = file(input) + // Alleles are listed in the first line of the file + return file.readLines().get(0) + } else { + // Not a file path, return the original string + return input + } + } + + samplesheet + .branch { + sample, alleles, mhc_class, filename -> + def allele_list = readAlleles(alleles) + validate_alleles(allele_list, mhc_class) + // TODO: Replace sample with id + variant_compressed : filename.endsWith('.vcf.gz') + return [[sample:sample.id, alleles:allele_list, mhc_class:mhc_class, inputtype:'variant_compressed'], filename ] + variant_uncompressed : filename.endsWith('.vcf') + return [[sample:sample.id, alleles:allele_list, mhc_class:mhc_class, inputtype:'variant'], filename ] + peptide : filename.endsWith('.tsv') + return [[sample:sample.id, alleles:allele_list, mhc_class:mhc_class, inputtype:'peptide'], filename ] + protein : filename.endsWith('.fasta') || filename.endsWith('.fa') + return [[sample:sample.id, alleles:allele_list, mhc_class:mhc_class, inputtype:'protein'], filename ]} + .set { ch_samplesheet } + ch_samplesheet.peptide.view() // gunzip variant files GUNZIP_VCF ( - ch_samples_from_sheet.variant_compressed + ch_samplesheet.variant_compressed ) - ch_versions = ch_versions.mix(GUNZIP_VCF.out.versions.ifEmpty(null)) + ch_versions = ch_versions.mix(GUNZIP_VCF.out.versions) ch_variants_uncompressed = GUNZIP_VCF.out.gunzip - .mix(ch_samples_from_sheet.variant_uncompressed) - + .mix(ch_samplesheet.variant_uncompressed) // (re)combine different input file types - ch_samples_uncompressed = ch_samples_from_sheet.protein - .mix(ch_samples_from_sheet.peptide) + ch_samples_uncompressed = ch_samplesheet.protein + .mix(ch_samplesheet.peptide) .mix(ch_variants_uncompressed) .branch { meta_data, input_file -> @@ -150,9 +144,6 @@ workflow EPITOPEPREDICTION { if (tools.isEmpty()) { exit 1, "No valid tools specified." } - if (params.conda.enabled && params.tools.contains("netmhc")) { - log.warn("Please note: if you want to use external prediction tools with conda it might be necessary to set --netmhc_system to darwin depending on your system.") - } c_purple = params.monochrome_logs ? '' : "\033[0;35m"; c_reset = params.monochrome_logs ? '' : "\033[0m"; @@ -166,18 +157,18 @@ workflow EPITOPEPREDICTION { // get versions of all prediction tools GET_PREDICTION_VERSIONS(ch_external_versions.ifEmpty("")) - ch_prediction_tool_versions = GET_PREDICTION_VERSIONS.out.versions.ifEmpty(null) + ch_prediction_tool_versions = GET_PREDICTION_VERSIONS.out.versions // TODO I guess it would be better to have two subworkflows for the if else parts (CM) if (params.show_supported_models) { - SHOW_SUPPORTED_MODELS( + EPYTOPE_SHOW_SUPPORTED_MODELS( ch_samples_uncompressed .protein .mix(ch_samples_uncompressed.variant, ch_samples_uncompressed.peptide) .combine(ch_prediction_tool_versions) .first() ) - ch_versions = ch_versions.mix(SHOW_SUPPORTED_MODELS.out.versions.ifEmpty(null)) + ch_versions = ch_versions.mix(EPYTOPE_SHOW_SUPPORTED_MODELS.out.versions) } else { @@ -193,14 +184,14 @@ workflow EPITOPEPREDICTION { ch_samples_uncompressed.variant, ch_prediction_tool_versions ) - ch_versions = ch_versions.mix(EPYTOPE_CHECK_REQUESTED_MODELS.out.versions.ifEmpty(null)) + ch_versions = ch_versions.mix(EPYTOPE_CHECK_REQUESTED_MODELS.out.versions) // perform the check requested models on the protein files EPYTOPE_CHECK_REQUESTED_MODELS_PROTEIN( ch_samples_uncompressed.protein, ch_prediction_tool_versions ) - ch_versions = ch_versions.mix(EPYTOPE_CHECK_REQUESTED_MODELS_PROTEIN.out.versions.ifEmpty(null)) + ch_versions = ch_versions.mix(EPYTOPE_CHECK_REQUESTED_MODELS_PROTEIN.out.versions) // perform the check requested models on the peptide file where we need the input itself to determine the given peptide lengths EPYTOPE_CHECK_REQUESTED_MODELS_PEP( ch_samples_uncompressed @@ -208,7 +199,7 @@ workflow EPITOPEPREDICTION { .map { meta_data, input_file -> tuple( meta_data, input_file ) }, ch_prediction_tool_versions ) - ch_versions = ch_versions.mix(EPYTOPE_CHECK_REQUESTED_MODELS_PEP.out.versions.ifEmpty(null)) + ch_versions = ch_versions.mix(EPYTOPE_CHECK_REQUESTED_MODELS_PEP.out.versions) // Return a warning if this is raised EPYTOPE_CHECK_REQUESTED_MODELS @@ -271,7 +262,7 @@ workflow EPITOPEPREDICTION { EXTERNAL_TOOLS_IMPORT( ch_nonfree_paths ) - ch_versions = ch_versions.mix(EXTERNAL_TOOLS_IMPORT.out.versions.ifEmpty(null)) + ch_versions = ch_versions.mix(EXTERNAL_TOOLS_IMPORT.out.versions) /* ======================================================================================== @@ -279,58 +270,40 @@ workflow EPITOPEPREDICTION { ======================================================================================== */ - // Make a division for the variant files and process them further accordingly - ch_samples_uncompressed - .variant - .branch { - meta_data, input_file -> - vcf : input_file.extension == 'vcf' || input_file.extension == 'vcf.gz' - return [ meta_data, input_file ] - tab : input_file.extension == 'tsv' || input_file.extension == 'GSvar' - return [ meta_data, input_file ] - } - .set { ch_variants } - - // decide between the split_by_variants and snpsift_split (by chromosome) function (only vcf and vcf.gz variant files) + // decide between the split_by_variants and snpsift_split (by chromosome) function if (params.split_by_variants) { VARIANT_SPLIT( - ch_variants.vcf + ch_samples_uncompressed.variant ) .set { ch_split_variants } - ch_versions = ch_versions.mix( VARIANT_SPLIT.out.versions.ifEmpty(null) ) + ch_versions = ch_versions.mix( VARIANT_SPLIT.out.versions ) } else { SNPSIFT_SPLIT( - ch_variants.vcf + ch_samples_uncompressed.variant ) .set { ch_split_variants } - ch_versions = ch_versions.mix( SNPSIFT_SPLIT.out.versions.ifEmpty(null) ) + ch_versions = ch_versions.mix( SNPSIFT_SPLIT.out.versions ) } - // include the csvtk_split function (only variant files with an tsv and GSvar executable) - CSVTK_SPLIT( - ch_variants.tab - ) - - ch_versions = ch_versions.mix( CSVTK_SPLIT.out.versions.ifEmpty(null) ) // process FASTA file and generated peptides EPYTOPE_GENERATE_PEPTIDES( ch_samples_uncompressed.protein ) - ch_versions = ch_versions.mix(EPYTOPE_GENERATE_PEPTIDES.out.versions.ifEmpty(null)) + ch_versions = ch_versions.mix(EPYTOPE_GENERATE_PEPTIDES.out.versions) SPLIT_PEPTIDES_PROTEIN( EPYTOPE_GENERATE_PEPTIDES.out.splitted ) - ch_versions = ch_versions.mix(SPLIT_PEPTIDES_PROTEIN.out.versions.ifEmpty(null)) + ch_versions = ch_versions.mix(SPLIT_PEPTIDES_PROTEIN.out.versions) // split peptide data SPLIT_PEPTIDES_PEPTIDES( ch_samples_uncompressed.peptide ) - ch_versions = ch_versions.mix( SPLIT_PEPTIDES_PEPTIDES.out.versions.ifEmpty(null) ) + ch_versions = ch_versions.mix( SPLIT_PEPTIDES_PEPTIDES.out.versions ) /* ======================================================================================== @@ -348,7 +321,7 @@ workflow EPITOPEPREDICTION { .transpose(), EXTERNAL_TOOLS_IMPORT.out.nonfree_tools.collect().ifEmpty([]) ) - ch_versions = ch_versions.mix( EPYTOPE_PEPTIDE_PREDICTION_PROTEIN.out.versions.ifEmpty(null) ) + ch_versions = ch_versions.mix( EPYTOPE_PEPTIDE_PREDICTION_PROTEIN.out.versions ) // Run epitope prediction for peptides @@ -360,20 +333,18 @@ workflow EPITOPEPREDICTION { .transpose(), EXTERNAL_TOOLS_IMPORT.out.nonfree_tools.collect().ifEmpty([]) ) - ch_versions = ch_versions.mix( EPYTOPE_PEPTIDE_PREDICTION_PEP.out.versions.ifEmpty(null) ) + ch_versions = ch_versions.mix( EPYTOPE_PEPTIDE_PREDICTION_PEP.out.versions ) // Run epitope prediction for variants EPYTOPE_PEPTIDE_PREDICTION_VAR( - CSVTK_SPLIT - .out + ch_split_variants .splitted - .mix( ch_split_variants.splitted ) .combine( ch_prediction_tool_versions ) .transpose(), EXTERNAL_TOOLS_IMPORT.out.nonfree_tools.collect().ifEmpty([]) ) - ch_versions = ch_versions.mix( EPYTOPE_PEPTIDE_PREDICTION_VAR.out.versions.ifEmpty(null) ) + ch_versions = ch_versions.mix( EPYTOPE_PEPTIDE_PREDICTION_VAR.out.versions ) // Combine the predicted files and save them in a branch to make a distinction between samples with single and multi files EPYTOPE_PEPTIDE_PREDICTION_PEP @@ -395,12 +366,12 @@ workflow EPITOPEPREDICTION { CAT_TSV( ch_predicted_peptides.single ) - ch_versions = ch_versions.mix( CAT_TSV.out.versions.ifEmpty(null) ) + ch_versions = ch_versions.mix( CAT_TSV.out.versions ) CSVTK_CONCAT( ch_predicted_peptides.multi ) - ch_versions = ch_versions.mix( CSVTK_CONCAT.out.versions.ifEmpty(null) ) + ch_versions = ch_versions.mix( CSVTK_CONCAT.out.versions ) // Combine protein sequences CAT_FASTA( @@ -410,7 +381,7 @@ workflow EPITOPEPREDICTION { .mix( EPYTOPE_PEPTIDE_PREDICTION_VAR.out.fasta, EPYTOPE_PEPTIDE_PREDICTION_PROTEIN.out.fasta ) .groupTuple() ) - ch_versions = ch_versions.mix( CAT_FASTA.out.versions.ifEmpty(null) ) + ch_versions = ch_versions.mix( CAT_FASTA.out.versions ) EPYTOPE_PEPTIDE_PREDICTION_PEP .out @@ -432,33 +403,34 @@ workflow EPITOPEPREDICTION { MERGE_JSON_SINGLE( ch_json_reports.single ) - ch_versions = ch_versions.mix( MERGE_JSON_SINGLE.out.versions.ifEmpty(null) ) + ch_versions = ch_versions.mix( MERGE_JSON_SINGLE.out.versions ) MERGE_JSON_MULTI( ch_json_reports.multi ) - ch_versions = ch_versions.mix( MERGE_JSON_MULTI.out.versions.ifEmpty(null) ) + ch_versions = ch_versions.mix( MERGE_JSON_MULTI.out.versions ) + } // - // MODULE: Pipeline reporting + // Collate and save software versions // - CUSTOM_DUMPSOFTWAREVERSIONS ( - ch_versions.unique().collectFile(name: 'collated_versions.yml') - ) + 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 // - workflow_summary = WorkflowEpitopeprediction.paramsSummaryMultiqc( workflow, summary_params ) - ch_workflow_summary = Channel.value( workflow_summary ) - - methods_description = WorkflowEpitopeprediction.methodsDescriptionText(workflow, ch_multiqc_custom_methods_description) - 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()) + 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)) MULTIQC ( ch_multiqc_files.collect(), @@ -466,24 +438,11 @@ workflow EPITOPEPREDICTION { ch_multiqc_custom_config.toList(), ch_multiqc_logo.toList() ) - multiqc_report = MULTIQC.out.report.toList() - } -} -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - COMPLETION EMAIL AND SUMMARY -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -*/ + emit: + multiqc_report = MULTIQC.out.report.toList() // channel: /path/to/multiqc_report.html + versions = ch_versions // channel: [ path(versions.yml) ] -workflow.onComplete { - if (params.email || params.email_on_fail) { - NfcoreTemplate.email(workflow, params, summary_params, projectDir, log, multiqc_report) - } - NfcoreTemplate.summary(workflow, params, log) - if (params.hook_url) { - NfcoreTemplate.IM_notification(workflow, params, summary_params, projectDir, log) - } } /*