From 48b6ef508dbb0d0a35b91aa8e670616f640b36ae Mon Sep 17 00:00:00 2001 From: James Fellows Yates Date: Wed, 23 Mar 2022 10:06:01 +0100 Subject: [PATCH 01/10] Update path to samplesheet --- conf/test.config | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/conf/test.config b/conf/test.config index 42d8de6..2e08499 100644 --- a/conf/test.config +++ b/conf/test.config @@ -24,8 +24,7 @@ params { // TODO nf-core: Give any required params for the test so that command line flags are not needed input = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/samplesheet.csv' outdir = "./results" - // TODO replace with official once ready - databases = 'https://raw.githubusercontent.com/jfy133/nf-core-test-datasets/taxprofiler/database.csv' + databases = 'https://raw.githubusercontent.com/nf-core/nf-core-test-datasets/taxprofiler/database.csv' run_kraken2 = true run_malt = true shortread_clipmerge = true From 038a8d106a3e027d48c781ab15197270ec38e7a5 Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Wed, 23 Mar 2022 11:25:47 +0100 Subject: [PATCH 02/10] Fix test with correct URL --- conf/test.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/test.config b/conf/test.config index 2e08499..5924d7a 100644 --- a/conf/test.config +++ b/conf/test.config @@ -24,7 +24,7 @@ params { // TODO nf-core: Give any required params for the test so that command line flags are not needed input = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/samplesheet.csv' outdir = "./results" - databases = 'https://raw.githubusercontent.com/nf-core/nf-core-test-datasets/taxprofiler/database.csv' + databases = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/database.csv' run_kraken2 = true run_malt = true shortread_clipmerge = true From 6b939e672892474c21ed43283baa85710edb1ddb Mon Sep 17 00:00:00 2001 From: nf-core-bot Date: Wed, 23 Mar 2022 13:57:56 +0000 Subject: [PATCH 03/10] Template update for nf-core/tools version 2.3.1 --- .editorconfig | 5 +- .github/CONTRIBUTING.md | 15 +- .github/ISSUE_TEMPLATE/bug_report.yml | 1 - .github/PULL_REQUEST_TEMPLATE.md | 6 +- .github/workflows/awsfulltest.yml | 1 - .github/workflows/awstest.yml | 2 +- .github/workflows/branch.yml | 5 +- .github/workflows/ci.yml | 12 +- .github/workflows/linting.yml | 85 ++-------- .github/workflows/linting_comment.yml | 3 +- .gitpod.yml | 16 +- .markdownlint.yml | 14 -- .prettierrc.yml | 1 + .yamllint.yml | 6 - CHANGELOG.md | 2 + CITATIONS.md | 27 ++-- README.md | 31 ++-- assets/email_template.html | 146 ++++++++++++------ assets/multiqc_config.yaml | 11 -- assets/multiqc_config.yml | 11 ++ assets/schema_input.json | 5 +- docs/README.md | 8 +- docs/output.md | 28 ++-- docs/usage.md | 99 ++++++------ modules.json | 8 +- .../custom/dumpsoftwareversions/main.nf | 3 + .../custom/dumpsoftwareversions/meta.yml | 2 +- modules/nf-core/modules/fastqc/main.nf | 3 + modules/nf-core/modules/fastqc/meta.yml | 90 +++++------ modules/nf-core/modules/multiqc/main.nf | 9 +- modules/nf-core/modules/multiqc/meta.yml | 66 ++++---- nextflow_schema.json | 14 +- workflows/taxprofiler.nf | 2 +- 33 files changed, 358 insertions(+), 379 deletions(-) delete mode 100644 .markdownlint.yml create mode 100644 .prettierrc.yml delete mode 100644 .yamllint.yml delete mode 100644 assets/multiqc_config.yaml create mode 100644 assets/multiqc_config.yml diff --git a/.editorconfig b/.editorconfig index 9554950..b6b3190 100644 --- a/.editorconfig +++ b/.editorconfig @@ -8,12 +8,9 @@ trim_trailing_whitespace = true indent_size = 4 indent_style = space -[*.{yml,yaml}] +[*.{md,yml,yaml,html,css,scss,js}] indent_size = 2 -[*.json] -insert_final_newline = unset - # These files are edited and tested upstream in nf-core/modules [/modules/nf-core/**] charset = unset diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md index 2347663..08fbbf0 100644 --- a/.github/CONTRIBUTING.md +++ b/.github/CONTRIBUTING.md @@ -15,8 +15,7 @@ Contributions to the code are even more welcome ;) If you'd like to write some code for nf-core/taxprofiler, the standard workflow is as follows: -1. Check that there isn't already an issue about your idea in the [nf-core/taxprofiler issues](https://github.com/nf-core/taxprofiler/issues) to avoid duplicating work - * If there isn't one already, please create one so that others know you're working on this +1. Check that there isn't already an issue about your idea in the [nf-core/taxprofiler issues](https://github.com/nf-core/taxprofiler/issues) to avoid duplicating work. If there isn't one already, please create one so that others know you're working on this 2. [Fork](https://help.github.com/en/github/getting-started-with-github/fork-a-repo) the [nf-core/taxprofiler repository](https://github.com/nf-core/taxprofiler) to your GitHub account 3. Make the necessary changes / additions within your forked repository following [Pipeline conventions](#pipeline-contribution-conventions) 4. Use `nf-core schema build` and add any new parameters to the pipeline JSON schema (requires [nf-core tools](https://github.com/nf-core/tools) >= 1.10). @@ -49,9 +48,9 @@ These tests are run both with the latest available version of `Nextflow` and als :warning: Only in the unlikely and regretful event of a release happening with a bug. -* On your own fork, make a new branch `patch` based on `upstream/master`. -* Fix the bug, and bump version (X.Y.Z+1). -* A PR should be made on `master` from patch to directly this particular bug. +- On your own fork, make a new branch `patch` based on `upstream/master`. +- Fix the bug, and bump version (X.Y.Z+1). +- A PR should be made on `master` from patch to directly this particular bug. ## Getting help @@ -73,7 +72,7 @@ If you wish to contribute a new step, please use the following coding standards: 6. Add sanity checks and validation for all relevant parameters. 7. Perform local tests to validate that the new code works as expected. 8. If applicable, add a new test command in `.github/workflow/ci.yml`. -9. Update MultiQC config `assets/multiqc_config.yaml` so relevant suffixes, file name clean up and module plots are in the appropriate order. If applicable, add a [MultiQC](https://https://multiqc.info/) module. +9. Update MultiQC config `assets/multiqc_config.yml` so relevant suffixes, file name clean up and module plots are in the appropriate order. If applicable, add a [MultiQC](https://https://multiqc.info/) module. 10. Add a description of the output files and if relevant any appropriate images from the MultiQC report to `docs/output.md`. ### Default values @@ -92,8 +91,8 @@ The process resources can be passed on to the tool dynamically within the proces Please use the following naming schemes, to make it easy to understand what is going where. -* initial process channel: `ch_output_from_` -* intermediate and terminal channels: `ch__for_` +- initial process channel: `ch_output_from_` +- intermediate and terminal channels: `ch__for_` ### Nextflow version bumping diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml index fb5dd8d..f0a294c 100644 --- a/.github/ISSUE_TEMPLATE/bug_report.yml +++ b/.github/ISSUE_TEMPLATE/bug_report.yml @@ -2,7 +2,6 @@ name: Bug report description: Report something that is broken or incorrect labels: bug body: - - type: markdown attributes: value: | diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index adb8fde..d9886cf 100644 --- a/.github/PULL_REQUEST_TEMPLATE.md +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -16,10 +16,10 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/taxp - [ ] 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/taxprofiler/tree/master/.github/CONTRIBUTING.md) - - [ ] If necessary, also make a PR on the nf-core/taxprofiler _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository. + - [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/taxprofiler/tree/master/.github/CONTRIBUTING.md) + - [ ] If necessary, also make a PR on the nf-core/taxprofiler _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository. - [ ] Make sure your code lints (`nf-core lint`). -- [ ] Ensure the test suite passes (`nextflow run . -profile test,docker` --outdir `). +- [ ] Ensure the test suite passes (`nextflow run . -profile 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 b4bf919..fe65d56 100644 --- a/.github/workflows/awsfulltest.yml +++ b/.github/workflows/awsfulltest.yml @@ -18,7 +18,6 @@ jobs: # TODO nf-core: You can customise AWS full pipeline tests as required # Add full size test data (but still relatively small datasets for few samples) # on the `test_full.config` test runs with only one set of parameters - with: workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} access_token: ${{ secrets.TOWER_ACCESS_TOKEN }} diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml index b6b30c3..c791946 100644 --- a/.github/workflows/awstest.yml +++ b/.github/workflows/awstest.yml @@ -10,9 +10,9 @@ jobs: if: github.repository == 'nf-core/taxprofiler' runs-on: ubuntu-latest steps: + # Launch workflow using Tower CLI tool action - name: Launch workflow via tower uses: nf-core/tower-action@v3 - with: workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} access_token: ${{ secrets.TOWER_ACCESS_TOKEN }} diff --git a/.github/workflows/branch.yml b/.github/workflows/branch.yml index 2593d19..b8a412e 100644 --- a/.github/workflows/branch.yml +++ b/.github/workflows/branch.yml @@ -13,8 +13,7 @@ jobs: - name: Check PRs if: github.repository == 'nf-core/taxprofiler' run: | - { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/taxprofiler ]] && [[ $GITHUB_HEAD_REF = "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]] - + "{ [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/taxprofiler ]] && [[ $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 @@ -43,4 +42,4 @@ jobs: Thanks again for your contribution! repo-token: ${{ secrets.GITHUB_TOKEN }} allow-repeats: false - +# diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 033eb63..fb6de77 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -16,18 +16,18 @@ jobs: test: name: Run pipeline with test data # Only run on push if this is the nf-core dev branch (merged PRs) - if: ${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/taxprofiler') }} + if: "${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/taxprofiler') }}" runs-on: ubuntu-latest strategy: matrix: # Nextflow versions include: # Test pipeline minimum Nextflow version - - NXF_VER: '21.10.3' - NXF_EDGE: '' + - NXF_VER: "21.10.3" + NXF_EDGE: "" # Test latest edge release of Nextflow - - NXF_VER: '' - NXF_EDGE: '1' + - NXF_VER: "" + NXF_EDGE: "1" steps: - name: Check out pipeline code uses: actions/checkout@v2 @@ -48,3 +48,5 @@ jobs: # Remember that you can parallelise this by using strategy.matrix run: | nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results + +# diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index fda934c..e9cf5de 100644 --- a/.github/workflows/linting.yml +++ b/.github/workflows/linting.yml @@ -1,6 +1,7 @@ name: nf-core linting # This workflow is triggered on pushes and PRs to the repository. -# It runs the `nf-core lint` and markdown lint tests to ensure that the code meets the nf-core guidelines +# It runs the `nf-core lint` and markdown lint tests to ensure +# that the code meets the nf-core guidelines. on: push: pull_request: @@ -8,42 +9,6 @@ on: types: [published] jobs: - Markdown: - runs-on: ubuntu-latest - steps: - - uses: actions/checkout@v2 - - uses: actions/setup-node@v2 - - name: Install markdownlint - run: npm install -g markdownlint-cli - - name: Run Markdownlint - run: markdownlint . - - # 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 - with: - message: | - ## Markdown linting 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 `markdownlint-cli` - * On Mac: `brew install markdownlint-cli` - * Everything else: [Install `npm`](https://www.npmjs.com/get-npm) then [install `markdownlint-cli`](https://www.npmjs.com/package/markdownlint-cli) (`npm install -g markdownlint-cli`) - * Fix the markdown errors - * Automatically: `markdownlint . --fix` - * Manually resolve anything left from `markdownlint .` - - Once you push these changes the test should pass, and you can hide this comment :+1: - - We highly recommend setting up markdownlint in your code editor so that this formatting is done automatically on save. Ask about it on Slack for help! - - Thanks again for your contribution! - repo-token: ${{ secrets.GITHUB_TOKEN }} - allow-repeats: false - EditorConfig: runs-on: ubuntu-latest steps: @@ -55,49 +20,24 @@ jobs: run: npm install -g editorconfig-checker - name: Run ECLint check - run: editorconfig-checker -exclude README.md $(git ls-files | grep -v test) + 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') - YAML: + Prettier: runs-on: ubuntu-latest steps: - - name: Checkout - uses: actions/checkout@master - - name: 'Yamllint' - uses: karancode/yamllint-github-action@master - with: - yamllint_file_or_dir: '.' - yamllint_config_filepath: '.yamllint.yml' + - uses: actions/checkout@v2 - # 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 - with: - message: | - ## YAML linting is failing + - uses: actions/setup-node@v2 - To keep the code consistent with lots of contributors, we run automated code consistency checks. - To fix this CI test, please run: + - name: Install Prettier + run: npm install -g prettier - * Install `yamllint` - * Install `yamllint` following [this](https://yamllint.readthedocs.io/en/stable/quickstart.html#installing-yamllint) - instructions or alternative install it in your [conda environment](https://anaconda.org/conda-forge/yamllint) - * Fix the markdown errors - * Run the test locally: `yamllint $(find . -type f -name "*.yml" -o -name "*.yaml") -c ./.yamllint.yml` - * Fix any reported errors in your YAML files - - Once you push these changes the test should pass, and you can hide this comment :+1: - - We highly recommend setting up yaml-lint in your code editor so that this formatting is done automatically on save. Ask about it on Slack for help! - - Thanks again for your contribution! - repo-token: ${{ secrets.GITHUB_TOKEN }} - allow-repeats: false + - name: Run Prettier --check + run: prettier --check ${GITHUB_WORKSPACE} nf-core: runs-on: ubuntu-latest steps: - - name: Check out pipeline code uses: actions/checkout@v2 @@ -110,8 +50,8 @@ jobs: - uses: actions/setup-python@v1 with: - python-version: '3.6' - architecture: 'x64' + python-version: "3.6" + architecture: "x64" - name: Install dependencies run: | @@ -139,3 +79,4 @@ jobs: lint_results.md PR_number.txt +# diff --git a/.github/workflows/linting_comment.yml b/.github/workflows/linting_comment.yml index 44d7299..91c487a 100644 --- a/.github/workflows/linting_comment.yml +++ b/.github/workflows/linting_comment.yml @@ -1,4 +1,3 @@ - name: nf-core linting comment # This workflow is triggered after the linting action is complete # It posts an automated comment to the PR, even if the PR is coming from a fork @@ -27,4 +26,4 @@ jobs: GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} number: ${{ steps.pr_number.outputs.pr_number }} path: linting-logs/lint_results.md - +# diff --git a/.gitpod.yml b/.gitpod.yml index b7d4cee..c452ee9 100644 --- a/.gitpod.yml +++ b/.gitpod.yml @@ -2,13 +2,13 @@ image: nfcore/gitpod:latest vscode: extensions: # based on nf-core.nf-core-extensionpack - - codezombiech.gitignore # Language support for .gitignore files + - codezombiech.gitignore # Language support for .gitignore files # - cssho.vscode-svgviewer # SVG viewer - - davidanson.vscode-markdownlint # Markdown/CommonMark linting and style checking for Visual Studio Code - - eamodio.gitlens # Quickly glimpse into whom, why, and when a line or code block was changed - - EditorConfig.EditorConfig # override user/workspace settings with settings found in .editorconfig files - - Gruntfuggly.todo-tree # Display TODO and FIXME in a tree view in the activity bar - - mechatroner.rainbow-csv # Highlight columns in csv files in different colors + - davidanson.vscode-markdownlint # Markdown/CommonMark linting and style checking for Visual Studio Code + - eamodio.gitlens # Quickly glimpse into whom, why, and when a line or code block was changed + - EditorConfig.EditorConfig # override user/workspace settings with settings found in .editorconfig files + - Gruntfuggly.todo-tree # Display TODO and FIXME in a tree view in the activity bar + - mechatroner.rainbow-csv # Highlight columns in csv files in different colors # - nextflow.nextflow # Nextflow syntax highlighting - - oderwat.indent-rainbow # Highlight indentation level - - streetsidesoftware.code-spell-checker # Spelling checker for source code + - oderwat.indent-rainbow # Highlight indentation level + - streetsidesoftware.code-spell-checker # Spelling checker for source code diff --git a/.markdownlint.yml b/.markdownlint.yml deleted file mode 100644 index 9e605fc..0000000 --- a/.markdownlint.yml +++ /dev/null @@ -1,14 +0,0 @@ -# Markdownlint configuration file -default: true -line-length: false -ul-indent: - indent: 4 -no-duplicate-header: - siblings_only: true -no-inline-html: - allowed_elements: - - img - - p - - kbd - - details - - summary diff --git a/.prettierrc.yml b/.prettierrc.yml new file mode 100644 index 0000000..c81f9a7 --- /dev/null +++ b/.prettierrc.yml @@ -0,0 +1 @@ +printWidth: 120 diff --git a/.yamllint.yml b/.yamllint.yml deleted file mode 100644 index d466dee..0000000 --- a/.yamllint.yml +++ /dev/null @@ -1,6 +0,0 @@ -extends: default - -rules: - document-start: disable - line-length: disable - truthy: disable diff --git a/CHANGELOG.md b/CHANGELOG.md index ca0928b..bccbb8a 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -11,6 +11,8 @@ Initial release of nf-core/taxprofiler, created with the [nf-core](https://nf-co ### `Fixed` +- Clarified conda usage and added an installation tutorial for Singularity since the one on Syllabs' website uses an outdate version of GO Compiler + ### `Dependencies` ### `Deprecated` diff --git a/CITATIONS.md b/CITATIONS.md index 192b2f4..c5463be 100644 --- a/CITATIONS.md +++ b/CITATIONS.md @@ -10,23 +10,26 @@ ## Pipeline tools -* [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/) +- [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. +- [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. ## Software packaging/containerisation tools -* [Anaconda](https://anaconda.com) - > Anaconda Software Distribution. Computer software. Vers. 2-2.4.0. Anaconda, Nov. 2016. Web. +- [Anaconda](https://anaconda.com) -* [Bioconda](https://pubmed.ncbi.nlm.nih.gov/29967506/) - > Grüning B, Dale R, Sjödin A, Chapman BA, Rowe J, Tomkins-Tinch CH, Valieris R, Köster J; Bioconda Team. Bioconda: sustainable and comprehensive software distribution for the life sciences. Nat Methods. 2018 Jul;15(7):475-476. doi: 10.1038/s41592-018-0046-7. PubMed PMID: 29967506. + > Anaconda Software Distribution. Computer software. Vers. 2-2.4.0. Anaconda, Nov. 2016. Web. -* [BioContainers](https://pubmed.ncbi.nlm.nih.gov/28379341/) - > da Veiga Leprevost F, Grüning B, Aflitos SA, Röst HL, Uszkoreit J, Barsnes H, Vaudel M, Moreno P, Gatto L, Weber J, Bai M, Jimenez RC, Sachsenberg T, Pfeuffer J, Alvarez RV, Griss J, Nesvizhskii AI, Perez-Riverol Y. BioContainers: an open-source and community-driven framework for software standardization. Bioinformatics. 2017 Aug 15;33(16):2580-2582. doi: 10.1093/bioinformatics/btx192. PubMed PMID: 28379341; PubMed Central PMCID: PMC5870671. +- [Bioconda](https://pubmed.ncbi.nlm.nih.gov/29967506/) -* [Docker](https://dl.acm.org/doi/10.5555/2600239.2600241) + > Grüning B, Dale R, Sjödin A, Chapman BA, Rowe J, Tomkins-Tinch CH, Valieris R, Köster J; Bioconda Team. Bioconda: sustainable and comprehensive software distribution for the life sciences. Nat Methods. 2018 Jul;15(7):475-476. doi: 10.1038/s41592-018-0046-7. PubMed PMID: 29967506. -* [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. +- [BioContainers](https://pubmed.ncbi.nlm.nih.gov/28379341/) + + > da Veiga Leprevost F, Grüning B, Aflitos SA, Röst HL, Uszkoreit J, Barsnes H, Vaudel M, Moreno P, Gatto L, Weber J, Bai M, Jimenez RC, Sachsenberg T, Pfeuffer J, Alvarez RV, Griss J, Nesvizhskii AI, Perez-Riverol Y. BioContainers: an open-source and community-driven framework for software standardization. Bioinformatics. 2017 Aug 15;33(16):2580-2582. doi: 10.1093/bioinformatics/btx192. PubMed PMID: 28379341; PubMed Central PMCID: PMC5870671. + +- [Docker](https://dl.acm.org/doi/10.5555/2600239.2600241) + +- [Singularity](https://pubmed.ncbi.nlm.nih.gov/28494014/) + > Kurtzer GM, Sochat V, Bauer MW. Singularity: Scientific containers for mobility of compute. PLoS One. 2017 May 11;12(5):e0177459. doi: 10.1371/journal.pone.0177459. eCollection 2017. PubMed PMID: 28494014; PubMed Central PMCID: PMC5426675. diff --git a/README.md b/README.md index b94fa02..fe8c049 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -# ![nf-core/taxprofiler](docs/images/nf-core-taxprofiler_logo_light.png#gh-light-mode-only) ![nf-core/taxprofiler](docs/images/nf-core-taxprofiler_logo_dark.png#gh-dark-mode-only) +# ![nf-core/taxprofiler](docs/images/nf-core/taxprofiler_logo_light.png#gh-light-mode-only) ![nf-core/taxprofiler](docs/images/nf-core/taxprofiler_logo_dark.png#gh-dark-mode-only) [![GitHub Actions CI Status](https://github.com/nf-core/taxprofiler/workflows/nf-core%20CI/badge.svg)](https://github.com/nf-core/taxprofiler/actions?query=workflow%3A%22nf-core+CI%22) [![GitHub Actions Linting Status](https://github.com/nf-core/taxprofiler/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/taxprofiler/actions?query=workflow%3A%22nf-core+linting%22) @@ -17,11 +17,13 @@ ## Introduction + **nf-core/taxprofiler** is a bioinformatics best-practice analysis pipeline for Taxonomic profiling of shotgun metagenomic data. The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. It uses Docker/Singularity containers making installation trivial and results highly reproducible. The [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html) implementation of this pipeline uses one container per process which makes it much easier to maintain and update software dependencies. Where possible, these processes have been submitted to and installed from [nf-core/modules](https://github.com/nf-core/modules) in order to make them available to all nf-core pipelines, and to everyone within the Nextflow community! + On release, automated continuous integration tests run the pipeline on a full-sized dataset on the AWS cloud infrastructure. This ensures that the pipeline runs on AWS, has sensible resource allocation defaults set to run on real-world datasets, and permits the persistent storage of results to benchmark between pipeline releases and other analysis sources. The results obtained from the full-sized test can be viewed on the [nf-core website](https://nf-co.re/taxprofiler/results). ## Pipeline summary @@ -35,28 +37,28 @@ On release, automated continuous integration tests run the pipeline on a full-si 1. Install [`Nextflow`](https://www.nextflow.io/docs/latest/getstarted.html#installation) (`>=21.10.3`) -2. Install any of [`Docker`](https://docs.docker.com/engine/installation/), [`Singularity`](https://www.sylabs.io/guides/3.0/user-guide/), [`Podman`](https://podman.io/), [`Shifter`](https://nersc.gitlab.io/development/shifter/how-to-use/) or [`Charliecloud`](https://hpc.github.io/charliecloud/) for full pipeline reproducibility _(please only use [`Conda`](https://conda.io/miniconda.html) as a last resort; see [docs](https://nf-co.re/usage/configuration#basic-configuration-profiles))_ +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))_. 3. Download the pipeline and test it on a minimal dataset with a single command: - ```console - nextflow run nf-core/taxprofiler -profile test,YOURPROFILE --outdir - ``` + ```console + nextflow run nf-core/taxprofiler -profile test,YOURPROFILE --outdir + ``` - 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. + 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. - > * 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. + > - 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. 4. Start running your own analysis! - + - ```console - nextflow run nf-core/taxprofiler --input samplesheet.csv --outdir --genome GRCh37 -profile - ``` + ```console + nextflow run nf-core/taxprofiler --input samplesheet.csv --outdir --genome GRCh37 -profile + ``` ## Documentation @@ -82,6 +84,7 @@ For further information or help, don't hesitate to get in touch on the [Slack `# + An extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file. You can cite the `nf-core` publication as follows: diff --git a/assets/email_template.html b/assets/email_template.html index f40addd..c8dce51 100644 --- a/assets/email_template.html +++ b/assets/email_template.html @@ -1,53 +1,111 @@ - - - - + + + + - - nf-core/taxprofiler Pipeline Report - - -
+ + + nf-core/taxprofiler Pipeline Report + + +
+ - +

nf-core/taxprofiler v${version}

+

Run Name: $runName

-

nf-core/taxprofiler v${version}

-

Run Name: $runName

- -<% if (!success){ - out << """ -
-

nf-core/taxprofiler execution completed unsuccessfully!

+ <% if (!success){ out << """ +
+

nf-core/taxprofiler execution completed unsuccessfully!

The exit status of the task that caused the workflow execution to fail was: $exitStatus.

The full error message was:

- 
${errorReport}
-
- """ -} else { - out << """ -
+ 
${errorReport}
+
+ """ } else { out << """ +
nf-core/taxprofiler execution completed successfully! +
+ """ } %> + +

The workflow was completed at $dateComplete (duration: $duration)

+

The command used to launch the workflow was as follows:

+ 
+$commandLine
+ +

Pipeline Configuration:

+ + + <% out << summary.collect{ k,v -> " + + + + + " }.join("\n") %> + +
+ $k + + 
$v
+
+ +

nf-core/taxprofiler

+

https://github.com/nf-core/taxprofiler

- """ -} -%> - -

The workflow was completed at $dateComplete (duration: $duration)

-

The command used to launch the workflow was as follows:

-
$commandLine
- -

Pipeline Configuration:

- - - <% out << summary.collect{ k,v -> "" }.join("\n") %> - -
$k
$v
- -

nf-core/taxprofiler

-

https://github.com/nf-core/taxprofiler

- -
- - + diff --git a/assets/multiqc_config.yaml b/assets/multiqc_config.yaml deleted file mode 100644 index 9a7feaa..0000000 --- a/assets/multiqc_config.yaml +++ /dev/null @@ -1,11 +0,0 @@ -report_comment: > - This report has been generated by the nf-core/taxprofiler - analysis pipeline. For information about how to interpret these results, please see the - documentation. -report_section_order: - software_versions: - order: -1000 - nf-core-taxprofiler-summary: - order: -1001 - -export_plots: true diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml new file mode 100644 index 0000000..b0a0b1c --- /dev/null +++ b/assets/multiqc_config.yml @@ -0,0 +1,11 @@ +report_comment: > + This report has been generated by the nf-core/taxprofiler + analysis pipeline. For information about how to interpret these results, please see the + documentation. +report_section_order: + software_versions: + order: -1000 + "nf-core-taxprofiler-summary": + order: -1001 + +export_plots: true diff --git a/assets/schema_input.json b/assets/schema_input.json index 31d955a..ed098df 100644 --- a/assets/schema_input.json +++ b/assets/schema_input.json @@ -31,9 +31,6 @@ ] } }, - "required": [ - "sample", - "fastq_1" - ] + "required": ["sample", "fastq_1"] } } diff --git a/docs/README.md b/docs/README.md index 9093d04..64e9962 100644 --- a/docs/README.md +++ b/docs/README.md @@ -2,9 +2,9 @@ The nf-core/taxprofiler documentation is split into the following pages: -* [Usage](usage.md) - * An overview of how the pipeline works, how to run it and a description of all of the different command-line flags. -* [Output](output.md) - * An overview of the different results produced by the pipeline and how to interpret them. +- [Usage](usage.md) + - An overview of how the pipeline works, how to run it and a description of all of the different command-line flags. +- [Output](output.md) + - An overview of the different results produced by the pipeline and how to interpret them. You can find a lot more documentation about installing, configuring and running nf-core pipelines on the website: [https://nf-co.re](https://nf-co.re) diff --git a/docs/output.md b/docs/output.md index a1c5ad4..177ca20 100644 --- a/docs/output.md +++ b/docs/output.md @@ -12,18 +12,18 @@ The directories listed below will be created in the results directory after the The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes data using the following steps: -* [FastQC](#fastqc) - Raw read QC -* [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline -* [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution +- [FastQC](#fastqc) - Raw read QC +- [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline +- [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution ### FastQC
Output files -* `fastqc/` - * `*_fastqc.html`: FastQC report containing quality metrics. - * `*_fastqc.zip`: Zip archive containing the FastQC report, tab-delimited data file and plot images. +- `fastqc/` + - `*_fastqc.html`: FastQC report containing quality metrics. + - `*_fastqc.zip`: Zip archive containing the FastQC report, tab-delimited data file and plot images.
@@ -42,10 +42,10 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
Output files -* `multiqc/` - * `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser. - * `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline. - * `multiqc_plots/`: directory containing static images from the report in various formats. +- `multiqc/` + - `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser. + - `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline. + - `multiqc_plots/`: directory containing static images from the report in various formats.
@@ -58,10 +58,10 @@ Results generated by MultiQC collate pipeline QC from supported tools e.g. FastQ
Output files -* `pipeline_info/` - * Reports generated by Nextflow: `execution_report.html`, `execution_timeline.html`, `execution_trace.txt` and `pipeline_dag.dot`/`pipeline_dag.svg`. - * Reports generated by the pipeline: `pipeline_report.html`, `pipeline_report.txt` and `software_versions.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`. +- `pipeline_info/` + - Reports generated by Nextflow: `execution_report.html`, `execution_timeline.html`, `execution_trace.txt` and `pipeline_dag.dot`/`pipeline_dag.svg`. + - Reports generated by the pipeline: `pipeline_report.html`, `pipeline_report.txt` and `software_versions.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`.
diff --git a/docs/usage.md b/docs/usage.md index a8b0448..fbfb5cc 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -44,11 +44,11 @@ TREATMENT_REP3,AEG588A6_S6_L003_R1_001.fastq.gz, TREATMENT_REP3,AEG588A6_S6_L004_R1_001.fastq.gz, ``` -| Column | Description | -|----------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| `sample` | Custom sample name. This entry will be identical for multiple sequencing libraries/runs from the same sample. Spaces in sample names are automatically converted to underscores (`_`). | -| `fastq_1` | Full path to FastQ file for Illumina short reads 1. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz". | -| `fastq_2` | Full path to FastQ file for Illumina short reads 2. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz". | +| Column | Description | +| --------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `sample` | Custom sample name. This entry will be identical for multiple sequencing libraries/runs from the same sample. Spaces in sample names are automatically converted to underscores (`_`). | +| `fastq_1` | Full path to FastQ file for Illumina short reads 1. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz". | +| `fastq_2` | Full path to FastQ file for Illumina short reads 2. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz". | An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline. @@ -57,7 +57,7 @@ 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/taxprofiler --input samplesheet.csv --outdir --genome GRCh37 -profile docker +nextflow run nf-core/taxprofiler --input samplesheet.csv --outdir --genome GRCh37 -profile docker ``` This will launch the pipeline with the `docker` configuration profile. See below for more information about profiles. @@ -65,9 +65,9 @@ This will launch the pipeline with the `docker` configuration profile. See below Note that the pipeline will create the following files in your working directory: ```console -work # Directory containing the nextflow working files -results # Finished results (configurable, see below) -.nextflow_log # Log file from Nextflow +work # Directory containing the nextflow working files + # Finished results in specified location (defined with --outdir) +.nextflow_log # Log file from Nextflow # Other nextflow hidden files, eg. history of pipeline runs and old logs. ``` @@ -106,25 +106,25 @@ They are loaded in sequence, so later profiles can overwrite earlier profiles. If `-profile` is not specified, the pipeline will run locally and expect all software to be installed and available on the `PATH`. This is _not_ recommended. -* `docker` - * A generic configuration profile to be used with [Docker](https://docker.com/) -* `singularity` - * A generic configuration profile to be used with [Singularity](https://sylabs.io/docs/) -* `podman` - * A generic configuration profile to be used with [Podman](https://podman.io/) -* `shifter` - * 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/) -* `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. -* `test` - * A profile with a complete configuration for automated testing - * Includes links to test data so needs no other parameters +- `docker` + - A generic configuration profile to be used with [Docker](https://docker.com/) +- `singularity` + - A generic configuration profile to be used with [Singularity](https://sylabs.io/docs/) +- `podman` + - A generic configuration profile to be used with [Podman](https://podman.io/) +- `shifter` + - A generic configuration profile to be used with [Shifter](https://nersc.gitlab.io/development/shifter/how-to-use/) +- `charliecloud` + - A generic configuration profile to be used with [Charliecloud](https://hpc.github.io/charliecloud/) +- `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. +- `test` + - A profile with a complete configuration for automated testing + - Includes links to test data so needs no other parameters ### `-resume` -Specify this when restarting a pipeline. Nextflow will used cached results from any pipeline steps where the inputs are the same, continuing from where it got to previously. +Specify this when restarting a pipeline. Nextflow will use cached results from any pipeline steps where the inputs are the same, continuing from where it got to previously. For input to be considered the same, not only the names must be identical but the files' contents as well. For more info about this parameter, see [this blog post](https://www.nextflow.io/blog/2019/demystifying-nextflow-resume.html). You can also supply a run name to resume a specific run: `-resume [run-name]`. Use the `nextflow log` command to show previous run names. @@ -186,6 +186,7 @@ process { ``` > **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 @@ -196,35 +197,35 @@ The [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html) implementatio 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: + - For Docker: - ```nextflow - process { - withName: PANGOLIN { - container = 'quay.io/biocontainers/pangolin:3.0.5--pyhdfd78af_0' - } - } - ``` + ```nextflow + process { + withName: PANGOLIN { + container = 'quay.io/biocontainers/pangolin:3.0.5--pyhdfd78af_0' + } + } + ``` - * For Singularity: + - For Singularity: - ```nextflow - process { - withName: PANGOLIN { - container = 'https://depot.galaxyproject.org/singularity/pangolin:3.0.5--pyhdfd78af_0' - } - } - ``` + ```nextflow + process { + withName: PANGOLIN { + container = 'https://depot.galaxyproject.org/singularity/pangolin:3.0.5--pyhdfd78af_0' + } + } + ``` - * For Conda: + - For Conda: - ```nextflow - process { - withName: PANGOLIN { - conda = 'bioconda::pangolin=3.0.5' - } - } - ``` + ```nextflow + process { + withName: PANGOLIN { + conda = 'bioconda::pangolin=3.0.5' + } + } + ``` > **NB:** If you wish to periodically update individual tool-specific results (e.g. Pangolin) generated by the pipeline then you must ensure to keep the `work/` directory otherwise the `-resume` ability of the pipeline will be compromised and it will restart from scratch. diff --git a/modules.json b/modules.json index 939b85f..39ca270 100644 --- a/modules.json +++ b/modules.json @@ -4,14 +4,14 @@ "repos": { "nf-core/modules": { "custom/dumpsoftwareversions": { - "git_sha": "20d8250d9f39ddb05dfb437603aaf99b5c0b2b41" + "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d" }, "fastqc": { - "git_sha": "9d0cad583b9a71a6509b754fdf589cbfbed08961" + "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d" }, "multiqc": { - "git_sha": "20d8250d9f39ddb05dfb437603aaf99b5c0b2b41" + "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d" } } } -} \ No newline at end of file +} diff --git a/modules/nf-core/modules/custom/dumpsoftwareversions/main.nf b/modules/nf-core/modules/custom/dumpsoftwareversions/main.nf index 934bb46..327d510 100644 --- a/modules/nf-core/modules/custom/dumpsoftwareversions/main.nf +++ b/modules/nf-core/modules/custom/dumpsoftwareversions/main.nf @@ -15,6 +15,9 @@ process CUSTOM_DUMPSOFTWAREVERSIONS { 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/modules/custom/dumpsoftwareversions/meta.yml b/modules/nf-core/modules/custom/dumpsoftwareversions/meta.yml index 5b5b8a6..60b546a 100644 --- a/modules/nf-core/modules/custom/dumpsoftwareversions/meta.yml +++ b/modules/nf-core/modules/custom/dumpsoftwareversions/meta.yml @@ -8,7 +8,7 @@ tools: 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'] + licence: ["MIT"] input: - versions: type: file diff --git a/modules/nf-core/modules/fastqc/main.nf b/modules/nf-core/modules/fastqc/main.nf index d250eca..ed6b8c5 100644 --- a/modules/nf-core/modules/fastqc/main.nf +++ b/modules/nf-core/modules/fastqc/main.nf @@ -15,6 +15,9 @@ process FASTQC { tuple val(meta), path("*.zip") , emit: zip path "versions.yml" , emit: versions + when: + task.ext.when == null || task.ext.when + script: def args = task.ext.args ?: '' // Add soft-links to original FastQs for consistent naming in pipeline diff --git a/modules/nf-core/modules/fastqc/meta.yml b/modules/nf-core/modules/fastqc/meta.yml index b09553a..4da5bb5 100644 --- a/modules/nf-core/modules/fastqc/meta.yml +++ b/modules/nf-core/modules/fastqc/meta.yml @@ -1,52 +1,52 @@ name: fastqc description: Run FastQC on sequenced reads keywords: - - quality control - - qc - - adapters - - fastq + - quality control + - qc + - adapters + - fastq tools: - - fastqc: - description: | - FastQC gives general quality metrics about your reads. - It provides information about the quality score distribution - across your reads, the per base sequence content (%A/C/G/T). - You get information about adapter contamination and other - overrepresented sequences. - homepage: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/ - documentation: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/ - licence: ['GPL-2.0-only'] + - fastqc: + description: | + FastQC gives general quality metrics about your reads. + It provides information about the quality score distribution + across your reads, the per base sequence content (%A/C/G/T). + You get information about adapter contamination and other + overrepresented sequences. + homepage: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/ + documentation: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/ + licence: ["GPL-2.0-only"] input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - reads: - type: file - description: | - List of input FastQ files of size 1 and 2 for single-end and paired-end data, - respectively. + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - reads: + type: file + description: | + List of input FastQ files of size 1 and 2 for single-end and paired-end data, + respectively. output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - html: - type: file - description: FastQC report - pattern: "*_{fastqc.html}" - - zip: - type: file - description: FastQC report archive - pattern: "*_{fastqc.zip}" - - versions: - type: file - description: File containing software versions - pattern: "versions.yml" + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - html: + type: file + description: FastQC report + pattern: "*_{fastqc.html}" + - zip: + type: file + description: FastQC report archive + pattern: "*_{fastqc.zip}" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" authors: - - "@drpatelh" - - "@grst" - - "@ewels" - - "@FelixKrueger" + - "@drpatelh" + - "@grst" + - "@ewels" + - "@FelixKrueger" diff --git a/modules/nf-core/modules/multiqc/main.nf b/modules/nf-core/modules/multiqc/main.nf index 3dceb16..1264aac 100644 --- a/modules/nf-core/modules/multiqc/main.nf +++ b/modules/nf-core/modules/multiqc/main.nf @@ -1,10 +1,10 @@ process MULTIQC { label 'process_medium' - conda (params.enable_conda ? 'bioconda::multiqc=1.11' : null) + conda (params.enable_conda ? 'bioconda::multiqc=1.12' : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/multiqc:1.11--pyhdfd78af_0' : - 'quay.io/biocontainers/multiqc:1.11--pyhdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/multiqc:1.12--pyhdfd78af_0' : + 'quay.io/biocontainers/multiqc:1.12--pyhdfd78af_0' }" input: path multiqc_files @@ -15,6 +15,9 @@ process MULTIQC { path "*_plots" , optional:true, emit: plots path "versions.yml" , emit: versions + when: + task.ext.when == null || task.ext.when + script: def args = task.ext.args ?: '' """ diff --git a/modules/nf-core/modules/multiqc/meta.yml b/modules/nf-core/modules/multiqc/meta.yml index 63c75a4..6fa891e 100644 --- a/modules/nf-core/modules/multiqc/meta.yml +++ b/modules/nf-core/modules/multiqc/meta.yml @@ -1,40 +1,40 @@ name: MultiQC description: Aggregate results from bioinformatics analyses across many samples into a single report keywords: - - QC - - bioinformatics tools - - Beautiful stand-alone HTML report + - QC + - bioinformatics tools + - Beautiful stand-alone HTML report tools: - - multiqc: - description: | - MultiQC searches a given directory for analysis logs and compiles a HTML report. - It's a general use tool, perfect for summarising the output from numerous bioinformatics tools. - homepage: https://multiqc.info/ - documentation: https://multiqc.info/docs/ - licence: ['GPL-3.0-or-later'] + - multiqc: + description: | + MultiQC searches a given directory for analysis logs and compiles a HTML report. + It's a general use tool, perfect for summarising the output from numerous bioinformatics tools. + homepage: https://multiqc.info/ + documentation: https://multiqc.info/docs/ + licence: ["GPL-3.0-or-later"] input: - - multiqc_files: - type: file - description: | - List of reports / files recognised by MultiQC, for example the html and zip output of FastQC + - multiqc_files: + type: file + description: | + List of reports / files recognised by MultiQC, for example the html and zip output of FastQC output: - - report: - type: file - description: MultiQC report file - pattern: "multiqc_report.html" - - data: - type: dir - description: MultiQC data dir - pattern: "multiqc_data" - - plots: - type: file - description: Plots created by MultiQC - pattern: "*_data" - - versions: - type: file - description: File containing software versions - pattern: "versions.yml" + - report: + type: file + description: MultiQC report file + pattern: "multiqc_report.html" + - data: + type: dir + description: MultiQC data dir + pattern: "multiqc_data" + - plots: + type: file + description: Plots created by MultiQC + pattern: "*_data" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" authors: - - "@abhi18av" - - "@bunop" - - "@drpatelh" + - "@abhi18av" + - "@bunop" + - "@drpatelh" diff --git a/nextflow_schema.json b/nextflow_schema.json index fa4588a..a8289a8 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -10,10 +10,7 @@ "type": "object", "fa_icon": "fas fa-terminal", "description": "Define where the pipeline should find input data and save output data.", - "required": [ - "input", - "outdir" - ], + "required": ["input", "outdir"], "properties": { "input": { "type": "string", @@ -185,14 +182,7 @@ "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" - ], + "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"], "hidden": true }, "email_on_fail": { diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf index e8cb60a..1e85e7f 100644 --- a/workflows/taxprofiler.nf +++ b/workflows/taxprofiler.nf @@ -23,7 +23,7 @@ if (params.input) { ch_input = file(params.input) } else { exit 1, 'Input sample ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -ch_multiqc_config = file("$projectDir/assets/multiqc_config.yaml", checkIfExists: true) +ch_multiqc_config = file("$projectDir/assets/multiqc_config.yml", checkIfExists: true) ch_multiqc_custom_config = params.multiqc_config ? Channel.fromPath(params.multiqc_config) : Channel.empty() /* From feeb8ba8dd89530ac0b0204b71aa6d5cbf24ba5c Mon Sep 17 00:00:00 2001 From: nf-core-bot Date: Thu, 24 Mar 2022 11:48:43 +0000 Subject: [PATCH 04/10] Template update for nf-core/tools version 2.3.2 --- .github/PULL_REQUEST_TEMPLATE.md | 1 - .github/workflows/awsfulltest.yml | 2 -- .github/workflows/awstest.yml | 2 -- .gitpod.yml | 2 +- CHANGELOG.md | 2 -- 5 files changed, 1 insertion(+), 8 deletions(-) diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index d9886cf..06c0ffe 100644 --- a/.github/PULL_REQUEST_TEMPLATE.md +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -10,7 +10,6 @@ Remember that PRs should be made against the dev branch, unless you're preparing Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/taxprofiler/tree/master/.github/CONTRIBUTING.md) --> - ## PR checklist diff --git a/.github/workflows/awsfulltest.yml b/.github/workflows/awsfulltest.yml index fe65d56..41f5c11 100644 --- a/.github/workflows/awsfulltest.yml +++ b/.github/workflows/awsfulltest.yml @@ -22,8 +22,6 @@ jobs: workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} access_token: ${{ secrets.TOWER_ACCESS_TOKEN }} compute_env: ${{ secrets.TOWER_COMPUTE_ENV }} - pipeline: ${{ github.repository }} - revision: ${{ github.sha }} workdir: s3://${{ secrets.AWS_S3_BUCKET }}/work/taxprofiler/work-${{ github.sha }} parameters: | { diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml index c791946..ebffec6 100644 --- a/.github/workflows/awstest.yml +++ b/.github/workflows/awstest.yml @@ -17,8 +17,6 @@ jobs: workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} access_token: ${{ secrets.TOWER_ACCESS_TOKEN }} compute_env: ${{ secrets.TOWER_COMPUTE_ENV }} - pipeline: ${{ github.repository }} - revision: ${{ github.sha }} workdir: s3://${{ secrets.AWS_S3_BUCKET }}/work/taxprofiler/work-${{ github.sha }} parameters: | { diff --git a/.gitpod.yml b/.gitpod.yml index c452ee9..85d95ec 100644 --- a/.gitpod.yml +++ b/.gitpod.yml @@ -4,7 +4,7 @@ vscode: extensions: # based on nf-core.nf-core-extensionpack - codezombiech.gitignore # Language support for .gitignore files # - cssho.vscode-svgviewer # SVG viewer - - davidanson.vscode-markdownlint # Markdown/CommonMark linting and style checking for Visual Studio Code + - esbenp.prettier-vscode # Markdown/CommonMark linting and style checking for Visual Studio Code - eamodio.gitlens # Quickly glimpse into whom, why, and when a line or code block was changed - EditorConfig.EditorConfig # override user/workspace settings with settings found in .editorconfig files - Gruntfuggly.todo-tree # Display TODO and FIXME in a tree view in the activity bar diff --git a/CHANGELOG.md b/CHANGELOG.md index bccbb8a..ca0928b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -11,8 +11,6 @@ Initial release of nf-core/taxprofiler, created with the [nf-core](https://nf-co ### `Fixed` -- Clarified conda usage and added an installation tutorial for Singularity since the one on Syllabs' website uses an outdate version of GO Compiler - ### `Dependencies` ### `Deprecated` From e3be393f16025f76cb8bc2389ccb2eb841b569f5 Mon Sep 17 00:00:00 2001 From: James Fellows Yates Date: Thu, 24 Mar 2022 14:18:15 +0100 Subject: [PATCH 05/10] Fix broken json --- modules.json | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/modules.json b/modules.json index c24ff6a..b78ba31 100644 --- a/modules.json +++ b/modules.json @@ -26,9 +26,10 @@ }, "untar": { "git_sha": "e080f4c8acf5760039ed12ec1f206170f3f9a918" + }, "porechop": { "git_sha": "e20e57f90b6787ac9a010a980cf6ea98bd990046" } } } -} +} \ No newline at end of file From 203cd2e7d39936dec20d75901fe6afc94b7f8a6f Mon Sep 17 00:00:00 2001 From: James Fellows Yates Date: Thu, 24 Mar 2022 14:31:53 +0100 Subject: [PATCH 06/10] Prettier --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index ea659bb..0c1d3c7 100644 --- a/README.md +++ b/README.md @@ -17,6 +17,7 @@ ## Introduction + **nf-core/taxprofiler** is a bioinformatics best-practice analysis pipeline for taxonomic profiling of shotgun metagenomic data. It allows for in-parallel profiling against multiple profiling tools and databases and produces standardised output tables. The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. It uses Docker/Singularity containers making installation trivial and results highly reproducible. The [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html) implementation of this pipeline uses one container per process which makes it much easier to maintain and update software dependencies. Where possible, these processes have been submitted to and installed from [nf-core/modules](https://github.com/nf-core/modules) in order to make them available to all nf-core pipelines, and to everyone within the Nextflow community! @@ -44,7 +45,7 @@ On release, automated continuous integration tests run the pipeline on a full-si - Kaiju - mOTUs 4. Perform optional post-processing with: - - bracken + - bracken 5. Standardises output tables 6. Present QC for raw reads ([`MultiQC`](http://multiqc.info/)) From cc9368ee527243fc1809f891154ae0eb569887f3 Mon Sep 17 00:00:00 2001 From: James Fellows Yates Date: Thu, 24 Mar 2022 15:35:09 +0100 Subject: [PATCH 07/10] Prettier linting and update schema --- nextflow.config | 2 +- nextflow_schema.json | 48 ++++++++++++++++++++++++++++++++++++---- workflows/taxprofiler.nf | 3 ++- 3 files changed, 47 insertions(+), 6 deletions(-) diff --git a/nextflow.config b/nextflow.config index 5f7aec6..cc77a99 100644 --- a/nextflow.config +++ b/nextflow.config @@ -56,7 +56,7 @@ params { // FASTQ preprocessing shortread_clipmerge = false - shortread_excludeunmerged = true + shortread_excludeunmerged = true longread_clip = false // MALT diff --git a/nextflow_schema.json b/nextflow_schema.json index de1e515..03910e9 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -10,7 +10,10 @@ "type": "object", "fa_icon": "fas fa-terminal", "description": "Define where the pipeline should find input data and save output data.", - "required": ["input", "outdir"], + "required": [ + "input", + "outdir" + ], "properties": { "input": { "type": "string", @@ -173,7 +176,14 @@ "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"], + "enum": [ + "symlink", + "rellink", + "link", + "copy", + "copyNoFollow", + "move" + ], "hidden": true }, "email_on_fail": { @@ -256,5 +266,35 @@ { "$ref": "#/definitions/generic_options" } - ] -} + ], + "properties": { + "databases": { + "type": "string", + "default": null + }, + "shortread_clipmerge": { + "type": "string", + "default": "false" + }, + "shortread_excludeunmerged": { + "type": "string", + "default": "true" + }, + "longread_clip": { + "type": "string", + "default": "false" + }, + "run_malt": { + "type": "string", + "default": "false" + }, + "malt_mode": { + "type": "string", + "default": "BlastN" + }, + "run_kraken2": { + "type": "string", + "default": "false" + } + } +} \ No newline at end of file diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf index 7320922..29058e6 100644 --- a/workflows/taxprofiler.nf +++ b/workflows/taxprofiler.nf @@ -88,8 +88,9 @@ workflow TAXPROFILER { // // MODULE: Run FastQC // + ch_input_for_fastqc = INPUT_CHECK.out.fastq.mix( INPUT_CHECK.out.nanopore ).dump(tag: "input_to_fastq") FASTQC ( - INPUT_CHECK.out.fastq.mix( INPUT_CHECK.out.nanopore ) + ch_input_for_fastqc ) ch_versions = ch_versions.mix(FASTQC.out.versions.first()) From 494c641fb8ade3f6f6e73c537f699df182b16b9d Mon Sep 17 00:00:00 2001 From: James Fellows Yates Date: Thu, 24 Mar 2022 15:37:42 +0100 Subject: [PATCH 08/10] Prettier --- .prettierignore | 2 ++ modules.json | 2 +- nextflow_schema.json | 16 +++------------- 3 files changed, 6 insertions(+), 14 deletions(-) create mode 100644 .prettierignore diff --git a/.prettierignore b/.prettierignore new file mode 100644 index 0000000..c037321 --- /dev/null +++ b/.prettierignore @@ -0,0 +1,2 @@ +testing/ +tests/ diff --git a/modules.json b/modules.json index b78ba31..9e6428a 100644 --- a/modules.json +++ b/modules.json @@ -32,4 +32,4 @@ } } } -} \ No newline at end of file +} diff --git a/nextflow_schema.json b/nextflow_schema.json index 03910e9..7bb03c3 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -10,10 +10,7 @@ "type": "object", "fa_icon": "fas fa-terminal", "description": "Define where the pipeline should find input data and save output data.", - "required": [ - "input", - "outdir" - ], + "required": ["input", "outdir"], "properties": { "input": { "type": "string", @@ -176,14 +173,7 @@ "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" - ], + "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"], "hidden": true }, "email_on_fail": { @@ -297,4 +287,4 @@ "default": "false" } } -} \ No newline at end of file +} From 92a3c8ec8d6e6698f748f154b0dfeaf92fd9d52b Mon Sep 17 00:00:00 2001 From: James Fellows Yates Date: Thu, 24 Mar 2022 15:40:14 +0100 Subject: [PATCH 09/10] Prettier --- nextflow_schema.json | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-) diff --git a/nextflow_schema.json b/nextflow_schema.json index 7bb03c3..9527da4 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -260,31 +260,27 @@ "properties": { "databases": { "type": "string", - "default": null + "default": "None" }, "shortread_clipmerge": { - "type": "string", - "default": "false" + "type": "boolean" }, "shortread_excludeunmerged": { - "type": "string", - "default": "true" + "type": "boolean", + "default": true }, "longread_clip": { - "type": "string", - "default": "false" + "type": "boolean" }, "run_malt": { - "type": "string", - "default": "false" + "type": "boolean" }, "malt_mode": { "type": "string", "default": "BlastN" }, "run_kraken2": { - "type": "string", - "default": "false" + "type": "boolean" } } } From fafb7e0f6fce56a57f6d375976b3cffe37ebe14b Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Thu, 24 Mar 2022 16:59:12 +0100 Subject: [PATCH 10/10] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 0c1d3c7..e976f73 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -# ![nf-core/taxprofiler](docs/images/nf-core/taxprofiler_logo_light.png#gh-light-mode-only) ![nf-core/taxprofiler](docs/images/nf-core/taxprofiler_logo_dark.png#gh-dark-mode-only) +# ![nf-core/taxprofiler](docs/images/nf-core-taxprofiler_logo_light.png#gh-light-mode-only) ![nf-core/taxprofiler](docs/images/nf-core-taxprofiler_logo_dark.png#gh-dark-mode-only) [![GitHub Actions CI Status](https://github.com/nf-core/taxprofiler/workflows/nf-core%20CI/badge.svg)](https://github.com/nf-core/taxprofiler/actions?query=workflow%3A%22nf-core+CI%22) [![GitHub Actions Linting Status](https://github.com/nf-core/taxprofiler/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/taxprofiler/actions?query=workflow%3A%22nf-core+linting%22)