diff --git a/.devcontainer/devcontainer.json b/.devcontainer/devcontainer.json new file mode 100644 index 0000000..ea27a58 --- /dev/null +++ b/.devcontainer/devcontainer.json @@ -0,0 +1,27 @@ +{ + "name": "nfcore", + "image": "nfcore/gitpod:latest", + "remoteUser": "gitpod", + + // Configure tool-specific properties. + "customizations": { + // Configure properties specific to VS Code. + "vscode": { + // Set *default* container specific settings.json values on container create. + "settings": { + "python.defaultInterpreterPath": "/opt/conda/bin/python", + "python.linting.enabled": true, + "python.linting.pylintEnabled": true, + "python.formatting.autopep8Path": "/opt/conda/bin/autopep8", + "python.formatting.yapfPath": "/opt/conda/bin/yapf", + "python.linting.flake8Path": "/opt/conda/bin/flake8", + "python.linting.pycodestylePath": "/opt/conda/bin/pycodestyle", + "python.linting.pydocstylePath": "/opt/conda/bin/pydocstyle", + "python.linting.pylintPath": "/opt/conda/bin/pylint" + }, + + // Add the IDs of extensions you want installed when the container is created. + "extensions": ["ms-python.python", "ms-python.vscode-pylance", "nf-core.nf-core-extensionpack"] + } + } +} diff --git a/.editorconfig b/.editorconfig index b78de6e..b6b3190 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 diff --git a/.gitattributes b/.gitattributes index 050bb12..7a2dabc 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1,3 +1,4 @@ *.config linguist-language=nextflow +*.nf.test linguist-language=nextflow modules/nf-core/** linguist-generated subworkflows/nf-core/** linguist-generated diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md index 951d13a..382f0e2 100644 --- a/.github/CONTRIBUTING.md +++ b/.github/CONTRIBUTING.md @@ -101,3 +101,19 @@ If you are using a new feature from core Nextflow, you may bump the minimum requ ### Images and figures For overview images and other documents we follow the nf-core [style guidelines and examples](https://nf-co.re/developers/design_guidelines). + +## GitHub Codespaces + +This repo includes a devcontainer configuration which will create a GitHub Codespaces for Nextflow development! This is an online developer environment that runs in your browser, complete with VSCode and a terminal. + +To get started: + +- Open the repo in [Codespaces](https://github.com/nf-core/hgtseq/codespaces) +- Tools installed + - nf-core + - Nextflow + +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 17eb04b..19d18fb 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. 21.10.3)_ + * Nextflow version _(eg. 22.10.1)_ * 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/hgtseq _(eg. 1.1, 1.5, 1.8.2)_ diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index 83758ca..7e301f2 100644 --- a/.github/PULL_REQUEST_TEMPLATE.md +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -15,7 +15,8 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/hgts - [ ] 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/hgtseq/tree/master/.github/CONTRIBUTING.md)- [ ] If necessary, also make a PR on the nf-core/hgtseq _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/hgtseq/tree/master/.github/CONTRIBUTING.md) +- [ ] If necessary, also make a PR on the nf-core/hgtseq _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 `). - [ ] Usage Documentation in `docs/usage.md` is updated. diff --git a/.github/workflows/awsfulltest.yml b/.github/workflows/awsfulltest.yml index 4dc4e41..6d9e2dc 100644 --- a/.github/workflows/awsfulltest.yml +++ b/.github/workflows/awsfulltest.yml @@ -14,7 +14,10 @@ jobs: runs-on: ubuntu-latest steps: - name: Launch workflow via tower - uses: nf-core/tower-action@v3 + uses: seqeralabs/action-tower-launch@v1 + # 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: ${{ secrets.TOWER_ACCESS_TOKEN }} @@ -25,3 +28,7 @@ jobs: "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/hgtseq/results-${{ github.sha }}" } profiles: test_full,aws_tower + - uses: actions/upload-artifact@v3 + with: + name: Tower debug log file + path: tower_action_*.log diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml index e9c14b8..9cfa646 100644 --- a/.github/workflows/awstest.yml +++ b/.github/workflows/awstest.yml @@ -12,7 +12,7 @@ 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@v1 with: workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} access_token: ${{ secrets.TOWER_ACCESS_TOKEN }} @@ -23,3 +23,7 @@ jobs: "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/hgtseq/results-test-${{ github.sha }}" } profiles: test,aws_tower + - uses: actions/upload-artifact@v3 + with: + name: Tower debug log file + path: tower_action_*.log diff --git a/.github/workflows/branch.yml b/.github/workflows/branch.yml index c90960b..c14288f 100644 --- a/.github/workflows/branch.yml +++ b/.github/workflows/branch.yml @@ -13,7 +13,7 @@ jobs: - name: Check PRs if: github.repository == 'nf-core/hgtseq' run: | - { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/hgtseq ]] && [[ $GITHUB_HEAD_REF = "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]] + { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/hgtseq ]] && [[ $GITHUB_HEAD_REF == "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]] # If the above check failed, post a comment on the PR explaining the failure # NOTE - this doesn't currently work if the PR is coming from a fork, due to limitations in GitHub actions secrets diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 004b722..0625499 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -11,6 +11,10 @@ on: env: NXF_ANSI_LOG: false +concurrency: + group: "${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}" + cancel-in-progress: true + jobs: test: name: Run pipeline with test data @@ -20,11 +24,11 @@ jobs: strategy: matrix: NXF_VER: - - "21.10.3" + - "22.10.1" - "latest-everything" steps: - name: Check out pipeline code - uses: actions/checkout@v2 + uses: actions/checkout@v3 - name: Install Nextflow uses: nf-core/setup-nextflow@v1 diff --git a/.github/workflows/clean-up.yml b/.github/workflows/clean-up.yml new file mode 100644 index 0000000..694e90e --- /dev/null +++ b/.github/workflows/clean-up.yml @@ -0,0 +1,24 @@ +name: "Close user-tagged issues and PRs" +on: + schedule: + - cron: "0 0 * * 0" # Once a week + +jobs: + clean-up: + runs-on: ubuntu-latest + permissions: + issues: write + pull-requests: write + steps: + - uses: actions/stale@v7 + with: + stale-issue-message: "This issue has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor. Remove stale label or add a comment otherwise this issue will be closed in 20 days." + stale-pr-message: "This PR has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor. Remove stale label or add a comment if it is still useful." + close-issue-message: "This issue was closed because it has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor and then staled for 20 days with no activity." + days-before-stale: 30 + days-before-close: 20 + days-before-pr-close: -1 + any-of-labels: "awaiting-changes,awaiting-feedback" + exempt-issue-labels: "WIP" + exempt-pr-labels: "WIP" + repo-token: "${{ secrets.GITHUB_TOKEN }}" diff --git a/.github/workflows/fix-linting.yml b/.github/workflows/fix-linting.yml index e7f9caa..b60250c 100644 --- a/.github/workflows/fix-linting.yml +++ b/.github/workflows/fix-linting.yml @@ -24,7 +24,7 @@ jobs: env: GITHUB_TOKEN: ${{ secrets.nf_core_bot_auth_token }} - - uses: actions/setup-node@v2 + - uses: actions/setup-node@v3 - name: Install Prettier run: npm install -g prettier @prettier/plugin-php @@ -34,9 +34,9 @@ jobs: id: prettier_status run: | if prettier --check ${GITHUB_WORKSPACE}; then - echo "::set-output name=result::pass" + echo "result=pass" >> $GITHUB_OUTPUT else - echo "::set-output name=result::fail" + echo "result=fail" >> $GITHUB_OUTPUT fi - name: Run 'prettier --write' diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index 8a5ce69..888cb4b 100644 --- a/.github/workflows/linting.yml +++ b/.github/workflows/linting.yml @@ -4,6 +4,8 @@ name: nf-core linting # that the code meets the nf-core guidelines. on: push: + branches: + - dev pull_request: release: types: [published] @@ -12,9 +14,9 @@ jobs: EditorConfig: runs-on: ubuntu-latest steps: - - uses: actions/checkout@v2 + - uses: actions/checkout@v3 - - uses: actions/setup-node@v2 + - uses: actions/setup-node@v3 - name: Install editorconfig-checker run: npm install -g editorconfig-checker @@ -25,9 +27,9 @@ jobs: Prettier: runs-on: ubuntu-latest steps: - - uses: actions/checkout@v2 + - uses: actions/checkout@v3 - - uses: actions/setup-node@v2 + - uses: actions/setup-node@v3 - name: Install Prettier run: npm install -g prettier @@ -38,7 +40,7 @@ jobs: PythonBlack: runs-on: ubuntu-latest steps: - - uses: actions/checkout@v2 + - uses: actions/checkout@v3 - name: Check code lints with Black uses: psf/black@stable @@ -69,14 +71,14 @@ jobs: runs-on: ubuntu-latest steps: - name: Check out pipeline code - uses: actions/checkout@v2 + uses: actions/checkout@v3 - name: Install Nextflow uses: nf-core/setup-nextflow@v1 - - uses: actions/setup-python@v3 + - uses: actions/setup-python@v4 with: - python-version: "3.7" + python-version: "3.8" architecture: "x64" - name: Install dependencies @@ -97,7 +99,7 @@ jobs: - name: Upload linting log file artifact if: ${{ always() }} - uses: actions/upload-artifact@v2 + uses: actions/upload-artifact@v3 with: name: linting-logs path: | diff --git a/.github/workflows/linting_comment.yml b/.github/workflows/linting_comment.yml index 04758f6..0bbcd30 100644 --- a/.github/workflows/linting_comment.yml +++ b/.github/workflows/linting_comment.yml @@ -18,7 +18,7 @@ jobs: - name: Get PR number id: pr_number - run: echo "::set-output name=pr_number::$(cat linting-logs/PR_number.txt)" + run: echo "pr_number=$(cat linting-logs/PR_number.txt)" >> $GITHUB_OUTPUT - name: Post PR comment uses: marocchino/sticky-pull-request-comment@v2 diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml new file mode 100644 index 0000000..0c31cdb --- /dev/null +++ b/.pre-commit-config.yaml @@ -0,0 +1,5 @@ +repos: + - repo: https://github.com/pre-commit/mirrors-prettier + rev: "v2.7.1" + hooks: + - id: prettier diff --git a/.prettierignore b/.prettierignore index eb74a57..437d763 100644 --- a/.prettierignore +++ b/.prettierignore @@ -1,5 +1,6 @@ email_template.html adaptivecard.json +slackreport.json .nextflow* work/ data/ @@ -8,3 +9,4 @@ results/ testing/ testing* *.pyc +bin/ diff --git a/CHANGELOG.md b/CHANGELOG.md index e1d3f93..3f74533 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,14 +3,25 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). -## [1.0.0](https://github.com/nf-core/hgtseq/releases/tag/1.0.0) - Dalmatian Daffodil - -Initial release of nf-core/hgtseq, created with the [nf-core](https://nf-co.re/) template. +## [1.1.0](https://github.com/nf-core/hgtseq/releases/tag/1.1.0) - Beary Rose ### `Added` +- [#31](https://github.com/nf-core/hgtseq/pull/31) - Fixed issue where _single_unmapped_ reads also include _both_unmapped_ reads, by creating a local module with two steps samtools flag filtering + ### `Fixed` +- [#31](https://github.com/nf-core/hgtseq/pull/31) - Sync `TEMPLATE` with `tools 2.8` and all nf-core/modules updated + ### `Dependencies` +| Dependency | Old version | New version | +| ---------- | ----------- | ----------- | +| `samtools` | 1.15.1 | 1.17 | +| `multiqc` | 1.13 | 1.14 | + ### `Deprecated` + +## [1.0.0](https://github.com/nf-core/hgtseq/releases/tag/1.0.0) - Dalmatian Daffodil + +Initial release of nf-core/hgtseq, created with the [nf-core](https://nf-co.re/) template. diff --git a/CITATION.cff b/CITATION.cff deleted file mode 100644 index 4533e2f..0000000 --- a/CITATION.cff +++ /dev/null @@ -1,56 +0,0 @@ -cff-version: 1.2.0 -message: "If you use `nf-core tools` in your work, please cite the `nf-core` publication" -authors: - - family-names: Ewels - given-names: Philip - - family-names: Peltzer - given-names: Alexander - - family-names: Fillinger - given-names: Sven - - family-names: Patel - given-names: Harshil - - family-names: Alneberg - given-names: Johannes - - family-names: Wilm - given-names: Andreas - - family-names: Ulysse Garcia - given-names: Maxime - - family-names: Di Tommaso - given-names: Paolo - - family-names: Nahnsen - given-names: Sven -title: "The nf-core framework for community-curated bioinformatics pipelines." -version: 2.4.1 -doi: 10.1038/s41587-020-0439-x -date-released: 2022-05-16 -url: https://github.com/nf-core/tools -prefered-citation: - type: article - authors: - - family-names: Ewels - given-names: Philip - - family-names: Peltzer - given-names: Alexander - - family-names: Fillinger - given-names: Sven - - family-names: Patel - given-names: Harshil - - family-names: Alneberg - given-names: Johannes - - family-names: Wilm - given-names: Andreas - - family-names: Ulysse Garcia - given-names: Maxime - - family-names: Di Tommaso - given-names: Paolo - - family-names: Nahnsen - given-names: Sven - doi: 10.1038/s41587-020-0439-x - journal: nature biotechnology - start: 276 - end: 278 - title: "The nf-core framework for community-curated bioinformatics pipelines." - issue: 3 - volume: 38 - year: 2020 - url: https://dx.doi.org/10.1038/s41587-020-0439-x diff --git a/CITATIONS.md b/CITATIONS.md index 1decfe5..726aeec 100644 --- a/CITATIONS.md +++ b/CITATIONS.md @@ -1,5 +1,9 @@ # nf-core/hgtseq: Citations +## [hgtseq](https://www.mdpi.com/1422-0067/23/23/14512) + +> Carpanzano S, Santorsola M, Nf-Core Community, Lescai F. hgtseq: A Standard Pipeline to Study Horizontal Gene Transfer. Int J Mol Sci. 2022 Nov 22;23(23):14512. doi: 10.3390/ijms232314512. PMID: 36498841; PMCID: PMC9738810. + ## [nf-core](https://pubmed.ncbi.nlm.nih.gov/32055031/) > Ewels PA, Peltzer A, Fillinger S, Patel H, Alneberg J, Wilm A, Garcia MU, Di Tommaso P, Nahnsen S. The nf-core framework for community-curated bioinformatics pipelines. Nat Biotechnol. 2020 Mar;38(3):276-278. doi: 10.1038/s41587-020-0439-x. PubMed PMID: 32055031. diff --git a/README.md b/README.md index 21aa936..89c0e68 100644 --- a/README.md +++ b/README.md @@ -3,13 +3,13 @@ [![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/hgtseq/results) [![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.7244734-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.7244734) -[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A521.10.3-23aa62.svg)](https://www.nextflow.io/) +[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A522.10.1-23aa62.svg)](https://www.nextflow.io/) [![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/) [![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?labelColor=000000&logo=docker)](https://www.docker.com/) [![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/) [![Launch on Nextflow Tower](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Nextflow%20Tower-%234256e7)](https://tower.nf/launch?pipeline=https://github.com/nf-core/hgtseq) -[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23hgtseq-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/hgtseq)[![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%23hgtseq-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/hgtseq)[![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 @@ -40,49 +40,43 @@ A graphical view of the pipeline can be seen below. 7. Plotting Kraken2 results ([`Krona`](https://hpc.nih.gov/apps/kronatools.html)) 8. Html analysis report ([`RMarkDown`](https://rmarkdown.rstudio.com)) -## Quick Start - -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/) (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: - - - FASTQ input: - - ```console - nextflow run nf-core/hgtseq -profile test,YOURPROFILE --outdir - ``` - - - BAM input: - - ```console - nextflow run nf-core/hgtseq -profile test_bam,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. - -> - 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/hgtseq \ - --input .csv \ - --outdir \ - --genome GRCh38 \ - --taxonomy_id "TAXID" \ - -profile \ - --krakendb /path/to/kraken_db \ - --kronadb /path/to/krona_db/taxonomy.tab - ``` - -## Documentation - -The nf-core/hgtseq pipeline comes with documentation about the pipeline [usage](https://nf-co.re/hgtseq/usage), [parameters](https://nf-co.re/hgtseq/parameters) and [output](https://nf-co.re/hgtseq/output). +## Usage + +> **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. + +```console +nextflow run nf-core/hgtseq \ +--input .csv \ +--outdir \ +--genome GRCh38 \ +--taxonomy_id "TAXID" \ +-profile \ +--krakendb /path/to/kraken_db \ +--kronadb /path/to/krona_db/taxonomy.tab +``` + +```bash +nextflow run nf-core/hgtseq \ + -profile \ + --input samplesheet.csv \ + --outdir +``` + +> **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). + +For more details, please refer to the [usage documentation](https://nf-co.re/hgtseq/usage) and the [parameter documentation](https://nf-co.re/hgtseq/parameters). + +## Pipeline output + +To see the the results of a test run with a full size dataset refer to the [results](https://nf-co.re/hgtseq/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/hgtseq/output). ## Credits diff --git a/assets/adaptivecard.json b/assets/adaptivecard.json new file mode 100644 index 0000000..44e7be7 --- /dev/null +++ b/assets/adaptivecard.json @@ -0,0 +1,67 @@ +{ + "type": "message", + "attachments": [ + { + "contentType": "application/vnd.microsoft.card.adaptive", + "contentUrl": null, + "content": { + "\$schema": "http://adaptivecards.io/schemas/adaptive-card.json", + "msteams": { + "width": "Full" + }, + "type": "AdaptiveCard", + "version": "1.2", + "body": [ + { + "type": "TextBlock", + "size": "Large", + "weight": "Bolder", + "color": "<% if (success) { %>Good<% } else { %>Attention<%} %>", + "text": "nf-core/hgtseq v${version} - ${runName}", + "wrap": true + }, + { + "type": "TextBlock", + "spacing": "None", + "text": "Completed at ${dateComplete} (duration: ${duration})", + "isSubtle": true, + "wrap": true + }, + { + "type": "TextBlock", + "text": "<% if (success) { %>Pipeline completed successfully!<% } else { %>Pipeline completed with errors. The full error message was: ${errorReport}.<% } %>", + "wrap": true + }, + { + "type": "TextBlock", + "text": "The command used to launch the workflow was as follows:", + "wrap": true + }, + { + "type": "TextBlock", + "text": "${commandLine}", + "isSubtle": true, + "wrap": true + } + ], + "actions": [ + { + "type": "Action.ShowCard", + "title": "Pipeline Configuration", + "card": { + "type": "AdaptiveCard", + "\$schema": "http://adaptivecards.io/schemas/adaptive-card.json", + "body": [ + { + "type": "FactSet", + "facts": [<% out << summary.collect{ k,v -> "{\"title\": \"$k\", \"value\" : \"$v\"}"}.join(",\n") %> + ] + } + ] + } + } + ] + } + } + ] +} diff --git a/assets/methods_description_template.yml b/assets/methods_description_template.yml new file mode 100644 index 0000000..7f826e9 --- /dev/null +++ b/assets/methods_description_template.yml @@ -0,0 +1,25 @@ +id: "nf-core-hgtseq-methods-description" +description: "Suggested text and references to use when describing pipeline usage within the methods section of a publication." +section_name: "nf-core/hgtseq Methods Description" +section_href: "https://github.com/nf-core/hgtseq" +plot_type: "html" +## 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/hgtseq v${workflow.manifest.version} ${doi_text} of the nf-core collection of workflows (Ewels et al., 2020).

+

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

+ 
${workflow.commandLine}
+

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
    • +
+
+
Notes:
+
    + ${nodoi_text} +
  • The command above does not include parameters contained in any configs or profiles that may have been used. Ensure the config file is also uploaded with your publication!
    • +
  • You should also cite all software used within this run. Check the "Software Versions" of this report to get version information.
    • +
+
diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml index f6c4ee0..be5d6d4 100644 --- a/assets/multiqc_config.yml +++ b/assets/multiqc_config.yml @@ -3,9 +3,11 @@ report_comment: > analysis pipeline. For information about how to interpret these results, please see the documentation. report_section_order: - software_versions: + "nf-core-hgtseq-methods-description": order: -1000 - "nf-core-hgtseq-summary": + software_versions: order: -1001 + "nf-core-hgtseq-summary": + order: -1002 export_plots: true diff --git a/assets/slackreport.json b/assets/slackreport.json new file mode 100644 index 0000000..043d02f --- /dev/null +++ b/assets/slackreport.json @@ -0,0 +1,34 @@ +{ + "attachments": [ + { + "fallback": "Plain-text summary of the attachment.", + "color": "<% if (success) { %>good<% } else { %>danger<%} %>", + "author_name": "sanger-tol/readmapping v${version} - ${runName}", + "author_icon": "https://www.nextflow.io/docs/latest/_static/favicon.ico", + "text": "<% if (success) { %>Pipeline completed successfully!<% } else { %>Pipeline completed with errors<% } %>", + "fields": [ + { + "title": "Command used to launch the workflow", + "value": "```${commandLine}```", + "short": false + } + <% + if (!success) { %> + , + { + "title": "Full error message", + "value": "```${errorReport}```", + "short": false + }, + { + "title": "Pipeline configuration", + "value": "<% out << summary.collect{ k,v -> k == "hook_url" ? "_${k}_: (_hidden_)" : ( ( v.class.toString().contains('Path') || ( v.class.toString().contains('String') && v.contains('/') ) ) ? "_${k}_: `${v}`" : (v.class.toString().contains('DateTime') ? ("_${k}_: " + v.format(java.time.format.DateTimeFormatter.ofLocalizedDateTime(java.time.format.FormatStyle.MEDIUM))) : "_${k}_: ${v}") ) }.join(",\n") %>", + "short": false + } + <% } + %> + ], + "footer": "Completed at <% out << dateComplete.format(java.time.format.DateTimeFormatter.ofLocalizedDateTime(java.time.format.FormatStyle.MEDIUM)) %> (duration: ${duration})" + } + ] +} diff --git a/bin/check_samplesheet.py b/bin/check_samplesheet.py new file mode 100755 index 0000000..4a758fe --- /dev/null +++ b/bin/check_samplesheet.py @@ -0,0 +1,259 @@ +#!/usr/bin/env python + + +"""Provide a command line tool to validate and transform tabular samplesheets.""" + + +import argparse +import csv +import logging +import sys +from collections import Counter +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() + dialect = sniffer.sniff(peek) + return dialect + + +def check_samplesheet(file_in, file_out): + """ + Check that the tabular samplesheet has the structure expected by nf-core pipelines. + + Validate the general shape of the table, expected columns, and each row. Also add + an additional column which records whether one or two FASTQ reads were found. + + Args: + file_in (pathlib.Path): The given tabular samplesheet. The format can be either + CSV, TSV, or any other format automatically recognized by ``csv.Sniffer``. + file_out (pathlib.Path): Where the validated and transformed samplesheet should + be created; always in CSV format. + + Example: + This function checks that the samplesheet follows the following structure, + see also the `viral recon samplesheet`_:: + + sample,fastq_1,fastq_2 + SAMPLE_PE,SAMPLE_PE_RUN1_1.fastq.gz,SAMPLE_PE_RUN1_2.fastq.gz + SAMPLE_PE,SAMPLE_PE_RUN2_1.fastq.gz,SAMPLE_PE_RUN2_2.fastq.gz + SAMPLE_SE,SAMPLE_SE_RUN1_1.fastq.gz, + + .. _viral recon samplesheet: + https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv + + """ + required_columns = {"sample", "fastq_1", "fastq_2"} + # See https://docs.python.org/3.9/library/csv.html#id3 to read up on `newline=""`. + with file_in.open(newline="") as in_handle: + reader = csv.DictReader(in_handle, dialect=sniff_format(in_handle)) + # Validate the existence of the expected header columns. + if not required_columns.issubset(reader.fieldnames): + req_cols = ", ".join(required_columns) + logger.critical(f"The sample sheet **must** contain these column headers: {req_cols}.") + sys.exit(1) + # Validate each row. + checker = RowChecker() + for i, row in enumerate(reader): + try: + checker.validate_and_transform(row) + except AssertionError as error: + logger.critical(f"{str(error)} On line {i + 2}.") + sys.exit(1) + checker.validate_unique_samples() + header = list(reader.fieldnames) + header.insert(1, "single_end") + # See https://docs.python.org/3.9/library/csv.html#id3 to read up on `newline=""`. + with file_out.open(mode="w", newline="") as out_handle: + writer = csv.DictWriter(out_handle, header, delimiter=",") + writer.writeheader() + for row in checker.modified: + writer.writerow(row) + + +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 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/conf/base.config b/conf/base.config index 4193f3e..570a9d1 100644 --- a/conf/base.config +++ b/conf/base.config @@ -14,7 +14,7 @@ process { memory = { check_max( 6.GB * task.attempt, 'memory' ) } time = { check_max( 4.h * task.attempt, 'time' ) } - errorStrategy = { task.exitStatus in [143,137,104,134,139] ? 'retry' : 'finish' } + errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' } maxRetries = 1 maxErrors = '-1' 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 6d14c86..0be0919 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -100,6 +100,7 @@ process { mode: params.publish_dir_mode ] ext.args = '-b -f 5 -F 256' + ext.args2 = '-b -F 8' } withName: SAMTOOLS_VIEW_BOTH { diff --git a/conf/test_full.config b/conf/test_full.config index 297f6f3..75b2381 100644 --- a/conf/test_full.config +++ b/conf/test_full.config @@ -10,7 +10,11 @@ ---------------------------------------------------------------------------------------- */ -// this is temporarily a small dataset, waiting to load on AWS some full data for tests +cleanup = true + +params { + config_profile_name = 'Full test profile' + config_profile_description = 'Full test dataset to check pipeline function' params { config_profile_name = 'Test profile' diff --git a/docs/images/circos_example.png b/docs/images/circos_example.png new file mode 100644 index 0000000..b8231a9 Binary files /dev/null and b/docs/images/circos_example.png differ diff --git a/docs/images/kronaplot_example.png b/docs/images/kronaplot_example.png new file mode 100644 index 0000000..ff80640 Binary files /dev/null and b/docs/images/kronaplot_example.png differ diff --git a/docs/output.md b/docs/output.md index ad829fb..df4bc6e 100644 --- a/docs/output.md +++ b/docs/output.md @@ -148,8 +148,10 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d The `analysis_report.html` has two mainly functions: -- it displays a circular plot (made with GenomicRanges & ggbio R packages), which graphically shows the specific position on the chromosome of each read. - it contains a function that assigns a score to each reads based on the kmers analyzed by Kraken2 +- it displays a circular plot (made with GenomicRanges & ggbio R packages), which graphically shows the specific position on the chromosome of each read. + +
### Krona Plots @@ -165,6 +167,8 @@ The `analysis_report.html` has two mainly functions: [`KronaTools`](https://hpc.nih.gov/apps/kronatools.html) allows hierarchical data to be explored with zooming, multi-layered pie charts. KronaTools can be used to create Krona charts from several bioinformatics tools and raw data formats. The resulting interactive charts are self-contained and can be viewed with any modern web browser. +
+ ## Quality Control ### FastQC diff --git a/docs/usage.md b/docs/usage.md index 283db66..94ec891 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -24,9 +24,9 @@ The FASTQ file extension can be either _fastq.gz_ or _fastq_. ```console sample,input1,input2 -testsample01,/path/to/file1_1.fastq.gz/path/to/file1_2.fastq.gz +testsample01,/path/to/file1_1.fastq.gz,/path/to/file1_2.fastq.gz testsample02,/path/to/file2_1.fastq.gz,/path/to/file2_2.fastq.gz -testsample03,/path/to/file3_1.fastq,/path/to/file3_2.fastq.gz +testsample03,/path/to/file3_1.fastq.gz,/path/to/file3_2.fastq.gz ``` | Column | Description | @@ -59,11 +59,11 @@ The typical command for running the pipeline is as follows: ```console nextflow run nf-core/hgtseq \ +-profile \ --input samplesheet.csv \ --outdir \ --genome GRCh38 \ ---taxonomy_id "TAXID" \ --profile \ +--taxonomy_id \ --krakendb /path/to/kraken_db \ --kronadb /path/to/krona_db/taxonomy.tab ``` @@ -79,6 +79,29 @@ 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 `. + +> ⚠️ 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/hgtseq -profile docker -params-file params.yaml +``` + +with `params.yaml` containing: + +```yaml +input: './samplesheet.csv' +outdir: './results/' +genome: 'GRCh37' +input: 'data' +<...> +``` + +You can also generate such `YAML`/`JSON` files via [nf-core/launch](https://nf-co.re/launch). + ### Updating the pipeline When you run the above command, Nextflow automatically pulls the pipeline code from GitHub and stores it as a cached version. When running the pipeline after this, it will always use the cached version if available - even if the pipeline has been updated since. To make sure that you're running the latest version of the pipeline, make sure that you regularly update the cached version of the pipeline: @@ -91,9 +114,13 @@ nextflow pull nf-core/hgtseq It is a good idea to specify a pipeline version when running the pipeline on your data. This ensures that a specific version of the pipeline code and software are used when you run your pipeline. If you keep using the same tag, you'll be running the same version of the pipeline, even if there have been changes to the code since. -First, go to the [nf-core/hgtseq releases page](https://github.com/nf-core/hgtseq/releases) and find the latest version number - numeric only (eg. `1.3.1`). Then specify this when running the pipeline with `-r` (one hyphen) - eg. `-r 1.3.1`. +First, go to the [nf-core/hgtseq releases page](https://github.com/nf-core/hgtseq/releases) and find the latest pipeline version - numeric only (eg. `1.3.1`). Then specify this when running the pipeline with `-r` (one hyphen) - eg. `-r 1.3.1`. Of course, you can switch to another version by changing the number after the `-r` flag. + +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. -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. +To further assist in reproducbility, 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. + +> 💡 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. ## Pipeline arguments @@ -101,19 +128,19 @@ This version number will be logged in reports when you run the pipeline, so that Please note that, in addition to the classic parameters such as `--input` and `--outdir`, the pipeline requires other specific parameters. -### --genome +### `--genome` The user must specify the genome of interest. A list of genomes is available in the pipeline under the folder conf/igenomes.config, that contains illumina iGenomes reference file paths. This follows [nf-core guidelines](https://nf-co.re/usage/reference_genomes) for reference management, and sets all necessary parameters (like fasta, gtf, bwa). The user is recommended to primarily use the _genome_ parameter, and can follow instructions at [this](https://nf-co.re/usage/reference_genomes#adding-paths-to-a-config-file) page to add genomes not currently included in the repository. All parameters set automatically as a consequence, though hidden, can be accessed by the user at command line should they wish a finer control. -### --taxonomy_id +### `--taxonomy_id` Since the code in the report is executed differently based on the taxonomy id of the analyzed species, the user must enter it in the command line (must be taken from the Taxonomy Database of NCBI). -### --krakendb +### `--krakendb` User must provide a Kraken2 database in order to perform the classification. Can optionally be in a `.tar.gz` archive. -### --kronadb +### `--kronadb` User must also provide a Krona database in order to generate interactive pie charts with Kronatools. Can optionally be in a `.tar.gz` archive. @@ -125,7 +152,7 @@ User must also provide a Krona database in order to generate interactive pie cha 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. When using Biocontainers, most of these software packaging methods pull Docker containers from quay.io e.g [FastQC](https://quay.io/repository/biocontainers/fastqc) except for Singularity which directly downloads Singularity images via https hosted by the [Galaxy project](https://depot.galaxyproject.org/singularity/) and Conda which downloads and installs software locally from [Bioconda](https://bioconda.github.io/). +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 when this is not possible, Conda is also supported. @@ -134,8 +161,11 @@ The pipeline also dynamically loads configurations from [https://github.com/nf-c Note that multiple profiles can be loaded, for example: `-profile test,docker` - the order of arguments is important! 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. +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, since it can lead to different results on different machines dependent on the computer enviroment. +- `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` @@ -146,11 +176,10 @@ 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. -- `test` - - A profile with a complete configuration for automated testing - - Includes links to test data so needs no other parameters + - 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` @@ -168,96 +197,19 @@ 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 with most input data, you may find that you want to customise 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: +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. -```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` -``` - -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/software/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 - } -} -``` +### Custom Containers -> **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. +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. -### Updating containers +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. -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. 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 everytime 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`. +### Custom Tool Arguments -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: +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. - - For Docker: - - ```nextflow - process { - withName: PANGOLIN { - container = 'quay.io/biocontainers/pangolin:3.0.5--pyhdfd78af_0' - } - } - ``` - - - For Singularity: - - ```nextflow - process { - withName: PANGOLIN { - container = 'https://depot.galaxyproject.org/singularity/pangolin:3.0.5--pyhdfd78af_0' - } - } - ``` - - - For Conda: - - ```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. +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 @@ -267,6 +219,14 @@ See the main [Nextflow documentation](https://www.nextflow.io/docs/latest/config If you have any questions or issues please send us a message on [Slack](https://nf-co.re/join/slack) on the [`#configs` channel](https://nfcore.slack.com/channels/configs). +## Azure Resource Requests + +To be used with the `azurebatch` profile by specifying the `-profile azurebatch`. +We recommend providing a compute `params.vm_type` of `Standard_D16_v3` VMs by default but these options can be changed if required. + +Note that the choice of VM size depends on your quota and the overall workload during the analysis. +For a thorough list, please refer the [Azure Sizes for virtual machines in Azure](https://docs.microsoft.com/en-us/azure/virtual-machines/sizes). + ## Running in the background Nextflow handles job submissions and supervises the running jobs. The Nextflow process must run until the pipeline is finished. diff --git a/lib/NfcoreSchema.groovy b/lib/NfcoreSchema.groovy index b3d092f..9b34804 100755 --- a/lib/NfcoreSchema.groovy +++ b/lib/NfcoreSchema.groovy @@ -2,6 +2,7 @@ // This file holds several functions used to perform JSON parameter validation, help and summary rendering for the nf-core pipeline template. // +import nextflow.Nextflow import org.everit.json.schema.Schema import org.everit.json.schema.loader.SchemaLoader import org.everit.json.schema.ValidationException @@ -46,7 +47,6 @@ class NfcoreSchema { 'quiet', 'syslog', 'v', - 'version', // Options for `nextflow run` command 'ansi', @@ -84,6 +84,7 @@ class NfcoreSchema { 'stub-run', 'test', 'w', + 'with-apptainer', 'with-charliecloud', 'with-conda', 'with-dag', @@ -178,7 +179,7 @@ class NfcoreSchema { } if (has_error) { - System.exit(1) + Nextflow.error('Exiting!') } } diff --git a/lib/NfcoreTemplate.groovy b/lib/NfcoreTemplate.groovy index 27feb00..25a0a74 100755 --- a/lib/NfcoreTemplate.groovy +++ b/lib/NfcoreTemplate.groovy @@ -32,6 +32,25 @@ class NfcoreTemplate { } } + // + // 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${git_shortsha}" + } + + return version_string + } + // // Construct and send completion email // @@ -61,7 +80,7 @@ class NfcoreTemplate { misc_fields['Nextflow Compile Timestamp'] = workflow.nextflow.timestamp def email_fields = [:] - email_fields['version'] = workflow.manifest.version + email_fields['version'] = NfcoreTemplate.version(workflow) email_fields['runName'] = workflow.runName email_fields['success'] = workflow.success email_fields['dateComplete'] = workflow.complete @@ -146,10 +165,10 @@ class NfcoreTemplate { } // - // Construct and send adaptive card - // https://adaptivecards.io + // Construct and send a notification to a web server as JSON + // e.g. Microsoft Teams and Slack // - public static void adaptivecard(workflow, params, summary_params, projectDir, log) { + public static void IM_notification(workflow, params, summary_params, projectDir, log) { def hook_url = params.hook_url def summary = [:] @@ -170,7 +189,7 @@ class NfcoreTemplate { misc_fields['nxf_timestamp'] = workflow.nextflow.timestamp def msg_fields = [:] - msg_fields['version'] = workflow.manifest.version + msg_fields['version'] = NfcoreTemplate.version(workflow) msg_fields['runName'] = workflow.runName msg_fields['success'] = workflow.success msg_fields['dateComplete'] = workflow.complete @@ -178,13 +197,16 @@ class NfcoreTemplate { msg_fields['exitStatus'] = workflow.exitStatus msg_fields['errorMessage'] = (workflow.errorMessage ?: 'None') msg_fields['errorReport'] = (workflow.errorReport ?: 'None') - msg_fields['commandLine'] = workflow.commandLine + msg_fields['commandLine'] = workflow.commandLine.replaceFirst(/ +--hook_url +[^ ]+/, "") msg_fields['projectDir'] = workflow.projectDir msg_fields['summary'] = summary << misc_fields // Render the JSON template def engine = new groovy.text.GStringTemplateEngine() - def hf = new File("$projectDir/assets/adaptivecard.json") + // 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() @@ -209,7 +231,7 @@ class NfcoreTemplate { 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.red} Pipeline completed successfully, but with errored process(es) ${colors.reset}-" + log.info "-${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}-" @@ -297,6 +319,7 @@ class NfcoreTemplate { // public static String logo(workflow, monochrome_logs) { Map colors = logColours(monochrome_logs) + String workflow_version = NfcoreTemplate.version(workflow) String.format( """\n ${dashedLine(monochrome_logs)} @@ -305,7 +328,7 @@ class NfcoreTemplate { ${colors.blue} |\\ | |__ __ / ` / \\ |__) |__ ${colors.yellow}} {${colors.reset} ${colors.blue} | \\| | \\__, \\__/ | \\ |___ ${colors.green}\\`-._,-`-,${colors.reset} ${colors.green}`._,._,\'${colors.reset} - ${colors.purple} ${workflow.manifest.name} v${workflow.manifest.version}${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 old mode 100755 new mode 100644 index 28567bd..8d030f4 --- a/lib/Utils.groovy +++ b/lib/Utils.groovy @@ -21,19 +21,26 @@ class Utils { } // Check that all channels are present - def required_channels = ['conda-forge', 'bioconda', 'defaults'] - def conda_check_failed = !required_channels.every { ch -> ch in channels } + // 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 - conda_check_failed |= !(channels.indexOf('conda-forge') < channels.indexOf('bioconda')) - conda_check_failed |= !(channels.indexOf('bioconda') < channels.indexOf('defaults')) + 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 (conda_check_failed) { + 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/user/install.html#set-up-channels\n" + - " NB: The order of the channels matters!\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" + + " ${required_channels_in_order}\n" + "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~" } } diff --git a/lib/WorkflowHgtseq.groovy b/lib/WorkflowHgtseq.groovy index 0048a26..8fd9874 100755 --- a/lib/WorkflowHgtseq.groovy +++ b/lib/WorkflowHgtseq.groovy @@ -2,6 +2,9 @@ // This file holds several functions specific to the workflow/hgtseq.nf in the nf-core/hgtseq pipeline // +import nextflow.Nextflow +import groovy.text.SimpleTemplateEngine + class WorkflowHgtseq { // @@ -12,8 +15,7 @@ class WorkflowHgtseq { if (!params.fasta) { - log.error "Genome fasta file not specified with e.g. '--fasta genome.fa' or via a detectable config file." - System.exit(1) + Nextflow.error "Genome fasta file not specified with e.g. '--fasta genome.fa' or via a detectable config file." } } @@ -42,17 +44,36 @@ class WorkflowHgtseq { yaml_file_text += "data: |\n" yaml_file_text += "${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: ${meta.manifest_map.doi})" : "" + meta["nodoi_text"] = meta.manifest_map.doi ? "": "
  • If available, make sure to update the text to include the Zenodo DOI of version of the pipeline used.
    • " + + def methods_text = mqc_methods_yaml.text + + def engine = new SimpleTemplateEngine() + def description_html = engine.createTemplate(methods_text).make(meta) + + return description_html + } + + // // Exit pipeline if incorrect --genome key provided // private static void genomeExistsError(params, log) { if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) { - log.error "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" + + def error_string = "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" + " Genome '${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" + "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~" - System.exit(1) + Nextflow.error(error_string) } } } diff --git a/lib/WorkflowMain.groovy b/lib/WorkflowMain.groovy index 8a93afb..789fde6 100755 --- a/lib/WorkflowMain.groovy +++ b/lib/WorkflowMain.groovy @@ -2,6 +2,8 @@ // This file holds several functions specific to the main.nf workflow in the nf-core/hgtseq pipeline // +import nextflow.Nextflow + class WorkflowMain { // @@ -16,9 +18,9 @@ class WorkflowMain { } // - // Print help to screen if required + // Generate help string // - public static String help(workflow, params, log) { + public static String help(workflow, params) { def command = "nextflow run ${workflow.manifest.name} --input samplesheet.csv --genome GRCh37 -profile docker" def help_string = '' help_string += NfcoreTemplate.logo(workflow, params.monochrome_logs) @@ -29,9 +31,9 @@ class WorkflowMain { } // - // Print parameter summary log to screen + // Generate parameter summary log string // - public static String paramsSummaryLog(workflow, params, log) { + public static String paramsSummaryLog(workflow, params) { def summary_log = '' summary_log += NfcoreTemplate.logo(workflow, params.monochrome_logs) summary_log += NfcoreSchema.paramsSummaryLog(workflow, params) @@ -46,24 +48,30 @@ class WorkflowMain { public static void initialise(workflow, params, log) { // Print help to screen if required if (params.help) { - log.info help(workflow, params, log) + log.info help(workflow, params) System.exit(0) } - // Validate workflow parameters via the JSON schema - if (params.validate_params) { - NfcoreSchema.validateParameters(workflow, params, log) + // Print workflow version and exit on --version + if (params.version) { + String workflow_version = NfcoreTemplate.version(workflow) + log.info "${workflow.manifest.name} ${workflow_version}" + System.exit(0) } // Print parameter summary log to screen + log.info paramsSummaryLog(workflow, params) - log.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 (params.enable_conda) { + if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) { Utils.checkCondaChannels(log) } @@ -72,8 +80,7 @@ class WorkflowMain { // 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) + Nextflow.error("Please provide an input samplesheet to the pipeline e.g. '--input samplesheet.csv'") } } // diff --git a/main.nf b/main.nf index 12b9b94..f3100ed 100644 --- a/main.nf +++ b/main.nf @@ -4,7 +4,7 @@ nf-core/hgtseq ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Github : https://github.com/nf-core/hgtseq -Website: https://nf-co.re/hgtseq + Website: https://nf-co.re/hgtseq Slack : https://nfcore.slack.com/channels/hgtseq ---------------------------------------------------------------------------------------- */ diff --git a/modules.json b/modules.json index 535f106..f175992 100644 --- a/modules.json +++ b/modules.json @@ -7,87 +7,108 @@ "nf-core": { "bamtools/stats": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "bwa/index": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "bwa/mem": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "603ecbd9f45300c9788f197d2a15a005685b4220", + "installed_by": ["modules"] }, "bwamem2/index": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "bwamem2/mem": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "603ecbd9f45300c9788f197d2a15a005685b4220", + "installed_by": ["modules"] }, "custom/dumpsoftwareversions": { "branch": "master", - "git_sha": "8022c68e7403eecbd8ba9c49496f69f8c49d50f0" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "fastqc": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "kraken2/kraken2": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "603ecbd9f45300c9788f197d2a15a005685b4220", + "installed_by": ["modules"] }, "krona/ktimporttaxonomy": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "krona/ktupdatetaxonomy": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "multiqc": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "qualimap/bamqc": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "samtools/fastq": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "samtools/flagstat": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "samtools/idxstats": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "samtools/index": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "samtools/sort": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "samtools/stats": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "samtools/view": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "trimgalore": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules"] }, "untar": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905" + "git_sha": "5c460c5a4736974abde2843294f35307ee2b0e5e", + "installed_by": ["modules"] } } } diff --git a/modules/local/gawk/main.nf b/modules/local/gawk/main.nf index 582c274..273b1de 100644 --- a/modules/local/gawk/main.nf +++ b/modules/local/gawk/main.nf @@ -3,7 +3,7 @@ process GAWK { tag 'collate kraken' label 'process_low' - conda (params.enable_conda ? "gawk==5.1.0" : null) + conda "gawk==5.1.0" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/gawk:5.1.0': 'quay.io/biocontainers/gawk:5.1.0' }" diff --git a/modules/local/parseoutputs/main.nf b/modules/local/parseoutputs/main.nf index 2d51323..5de9f7b 100644 --- a/modules/local/parseoutputs/main.nf +++ b/modules/local/parseoutputs/main.nf @@ -2,10 +2,10 @@ process PARSEOUTPUTS { tag "$meta.id" label 'process_low' - conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null) + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' : - 'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }" + 'https://depot.galaxyproject.org/singularity/samtools:1.17--h00cdaf9_0' : + 'biocontainers/samtools:1.17--h00cdaf9_0' }" input: tuple val(meta), path(bam) diff --git a/modules/local/ranalysis/main.nf b/modules/local/ranalysis/main.nf index 061be86..95f3897 100644 --- a/modules/local/ranalysis/main.nf +++ b/modules/local/ranalysis/main.nf @@ -2,7 +2,7 @@ process RANALYSIS { tag "Ranalysis" label 'process_low' - conda (params.enable_conda ? "bioconda::bioconductor-ggbio==1.42.0--r41hdfd78af_0" : null) + conda "bioconda::bioconductor-ggbio==1.42.0--r41hdfd78af_0" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'library://lescailab/hgtseq/r-ggbio-reporting:sha256.eb829b05cf12e8d827813a6afb6e38592aac6568f685a6519f5ed7dd20125cb3' : 'ghcr.io/lescailab/r-ggbio-reporting:1.0.0' }" diff --git a/modules/local/samplesheet_check.nf b/modules/local/samplesheet_check.nf new file mode 100644 index 0000000..47b9f13 --- /dev/null +++ b/modules/local/samplesheet_check.nf @@ -0,0 +1,31 @@ +process SAMPLESHEET_CHECK { + tag "$samplesheet" + label 'process_single' + + conda "conda-forge::python=3.8.3" + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/python:3.8.3' : + 'biocontainers/python:3.8.3' }" + + input: + path samplesheet + + output: + path '*.csv' , emit: csv + path "versions.yml", emit: versions + + when: + task.ext.when == null || task.ext.when + + script: // This script is bundled with the pipeline, in nf-core/hgtseq/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/samtools/fastqlocal/main.nf b/modules/local/samtools/fastqlocal/main.nf index 095a63d..e94ecc8 100644 --- a/modules/local/samtools/fastqlocal/main.nf +++ b/modules/local/samtools/fastqlocal/main.nf @@ -2,10 +2,10 @@ process SAMTOOLS_FASTQ { tag "$meta.id" label 'process_low' - conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null) + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' : - 'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }" + 'https://depot.galaxyproject.org/singularity/samtools:1.17--h00cdaf9_0' : + 'biocontainers/samtools:1.17--h00cdaf9_0' }" input: tuple val(meta), path(bam) diff --git a/modules/local/samtools/viewsingle/main.nf b/modules/local/samtools/viewsingle/main.nf new file mode 100644 index 0000000..c1b65ff --- /dev/null +++ b/modules/local/samtools/viewsingle/main.nf @@ -0,0 +1,70 @@ +process SAMTOOLS_VIEW_SINGLE { + tag "$meta.id" + label 'process_low' + + conda "bioconda::samtools=1.17" + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/samtools:1.17--h00cdaf9_0' : + 'biocontainers/samtools:1.17--h00cdaf9_0' }" + + input: + tuple val(meta), path(input), path(index) + path fasta + path qname + + output: + tuple val(meta), path("*.bam"), emit: bam, optional: true + tuple val(meta), path("*.cram"), emit: cram, optional: true + tuple val(meta), path("*.sam"), emit: sam, optional: true + tuple val(meta), path("*.bai"), emit: bai, optional: true + tuple val(meta), path("*.csi"), emit: csi, optional: true + tuple val(meta), path("*.crai"), emit: crai, optional: true + path "versions.yml", emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + def args2 = task.ext.args2 ?: '' + def prefix = task.ext.prefix ?: "${meta.id}" + def reference = fasta ? "--reference ${fasta}" : "" + def readnames = qname ? "--qname-file ${qname}": "" + def file_type = args.contains("--output-fmt sam") ? "sam" : + args.contains("--output-fmt bam") ? "bam" : + args.contains("--output-fmt cram") ? "cram" : + input.getExtension() + if ("$input" == "${prefix}.${file_type}") error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!" + """ + samtools \\ + view \\ + --threads ${task.cpus-1} \\ + ${reference} \\ + ${readnames} \\ + $args \\ + $input \\ + | samtools view \\ + --threads ${task.cpus-1} \\ + ${reference} \\ + ${readnames} \\ + $args2 \\ + -o ${prefix}.${file_type} + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//') + END_VERSIONS + """ + + stub: + def prefix = task.ext.prefix ?: "${meta.id}" + """ + touch ${prefix}.bam + touch ${prefix}.cram + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//') + END_VERSIONS + """ +} diff --git a/modules/nf-core/bamtools/stats/main.nf b/modules/nf-core/bamtools/stats/main.nf index db46ce1..ace9023 100644 --- a/modules/nf-core/bamtools/stats/main.nf +++ b/modules/nf-core/bamtools/stats/main.nf @@ -2,10 +2,10 @@ process BAMTOOLS_STATS { tag "$meta.id" label 'process_single' - conda (params.enable_conda ? "bioconda::bamtools=2.5.1" : null) + conda "bioconda::bamtools=2.5.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/bamtools:2.5.1--h9a82719_9' : - 'quay.io/biocontainers/bamtools:2.5.1--h9a82719_9' }" + 'biocontainers/bamtools:2.5.1--h9a82719_9' }" input: tuple val(meta), path(bam) diff --git a/modules/nf-core/bamtools/stats/meta.yml b/modules/nf-core/bamtools/stats/meta.yml index 0e61b3f..19b5201 100644 --- a/modules/nf-core/bamtools/stats/meta.yml +++ b/modules/nf-core/bamtools/stats/meta.yml @@ -10,7 +10,7 @@ tools: homepage: http://github.com/pezmaster31/bamtools documentation: https://github.com/pezmaster31/bamtools/wiki tool_dev_url: http://github.com/pezmaster31/bamtools - doi: "" + licence: ["MIT"] input: diff --git a/modules/nf-core/bwa/index/main.nf b/modules/nf-core/bwa/index/main.nf index aa75ae5..8d2e56d 100644 --- a/modules/nf-core/bwa/index/main.nf +++ b/modules/nf-core/bwa/index/main.nf @@ -2,17 +2,17 @@ process BWA_INDEX { tag "$fasta" label 'process_single' - conda (params.enable_conda ? "bioconda::bwa=0.7.17" : null) + conda "bioconda::bwa=0.7.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/bwa:0.7.17--hed695b0_7' : - 'quay.io/biocontainers/bwa:0.7.17--hed695b0_7' }" + 'biocontainers/bwa:0.7.17--hed695b0_7' }" input: - path fasta + tuple val(meta), path(fasta) output: - path "bwa" , emit: index - path "versions.yml", emit: versions + tuple val(meta), path(bwa) , emit: index + path "versions.yml" , emit: versions when: task.ext.when == null || task.ext.when @@ -32,4 +32,20 @@ process BWA_INDEX { bwa: \$(echo \$(bwa 2>&1) | sed 's/^.*Version: //; s/Contact:.*\$//') END_VERSIONS """ + + stub: + """ + mkdir bwa + + touch bwa/genome.amb + touch bwa/genome.ann + touch bwa/genome.bwt + touch bwa/genome.pac + touch bwa/genome.sa + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + bwa: \$(echo \$(bwa 2>&1) | sed 's/^.*Version: //; s/Contact:.*\$//') + END_VERSIONS + """ } diff --git a/modules/nf-core/bwa/index/meta.yml b/modules/nf-core/bwa/index/meta.yml index 2bbd81d..2c6cfcd 100644 --- a/modules/nf-core/bwa/index/meta.yml +++ b/modules/nf-core/bwa/index/meta.yml @@ -15,10 +15,20 @@ tools: arxiv: arXiv:1303.3997 licence: ["GPL-3.0-or-later"] input: + - meta: + type: map + description: | + Groovy Map containing reference information. + e.g. [ id:'test', single_end:false ] - fasta: type: file description: Input genome fasta file output: + - meta: + type: map + description: | + Groovy Map containing reference information. + e.g. [ id:'test', single_end:false ] - index: type: file description: BWA genome index files diff --git a/modules/nf-core/bwa/mem/main.nf b/modules/nf-core/bwa/mem/main.nf index f55af94..d2f85da 100644 --- a/modules/nf-core/bwa/mem/main.nf +++ b/modules/nf-core/bwa/mem/main.nf @@ -2,14 +2,14 @@ process BWA_MEM { tag "$meta.id" label 'process_high' - conda (params.enable_conda ? "bioconda::bwa=0.7.17 bioconda::samtools=1.15.1" : null) + conda "bioconda::bwa=0.7.17 bioconda::samtools=1.16.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/mulled-v2-fe8faa35dbf6dc65a0f7f5d4ea12e31a79f73e40:8110a70be2bfe7f75a2ea7f2a89cda4cc7732095-0' : - 'quay.io/biocontainers/mulled-v2-fe8faa35dbf6dc65a0f7f5d4ea12e31a79f73e40:8110a70be2bfe7f75a2ea7f2a89cda4cc7732095-0' }" + 'https://depot.galaxyproject.org/singularity/mulled-v2-fe8faa35dbf6dc65a0f7f5d4ea12e31a79f73e40:219b6c272b25e7e642ae3ff0bf0c5c81a5135ab4-0' : + 'biocontainers/mulled-v2-fe8faa35dbf6dc65a0f7f5d4ea12e31a79f73e40:219b6c272b25e7e642ae3ff0bf0c5c81a5135ab4-0' }" input: tuple val(meta), path(reads) - path index + tuple val(meta2), path(index) val sort_bam output: @@ -25,7 +25,7 @@ process BWA_MEM { def prefix = task.ext.prefix ?: "${meta.id}" def samtools_command = sort_bam ? 'sort' : 'view' """ - INDEX=`find -L ./ -name "*.amb" | sed 's/.amb//'` + INDEX=`find -L ./ -name "*.amb" | sed 's/\\.amb\$//'` bwa mem \\ $args \\ diff --git a/modules/nf-core/bwa/mem/meta.yml b/modules/nf-core/bwa/mem/meta.yml index f84c522..62357bf 100644 --- a/modules/nf-core/bwa/mem/meta.yml +++ b/modules/nf-core/bwa/mem/meta.yml @@ -28,6 +28,11 @@ input: description: | List of input FastQ files of size 1 and 2 for single-end and paired-end data, respectively. + - meta2: + type: map + description: | + Groovy Map containing reference information. + e.g. [ id:'test', single_end:false ] - index: type: file description: BWA genome index files diff --git a/modules/nf-core/bwamem2/index/main.nf b/modules/nf-core/bwamem2/index/main.nf index 0b7ad19..3094085 100644 --- a/modules/nf-core/bwamem2/index/main.nf +++ b/modules/nf-core/bwamem2/index/main.nf @@ -2,10 +2,10 @@ process BWAMEM2_INDEX { tag "$fasta" label 'process_single' - conda (params.enable_conda ? "bioconda::bwa-mem2=2.2.1" : null) + conda "bioconda::bwa-mem2=2.2.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/bwa-mem2:2.2.1--he513fc3_0' : - 'quay.io/biocontainers/bwa-mem2:2.2.1--he513fc3_0' }" + 'biocontainers/bwa-mem2:2.2.1--he513fc3_0' }" input: tuple val(meta), path(fasta) diff --git a/modules/nf-core/bwamem2/index/meta.yml b/modules/nf-core/bwamem2/index/meta.yml index a6b11ae..40c26c3 100644 --- a/modules/nf-core/bwamem2/index/meta.yml +++ b/modules/nf-core/bwamem2/index/meta.yml @@ -6,7 +6,7 @@ keywords: - genome - reference tools: - - bwa: + - bwamem2: description: | BWA-mem2 is a software package for mapping DNA sequences against a large reference genome, such as the human genome. diff --git a/modules/nf-core/bwamem2/mem/main.nf b/modules/nf-core/bwamem2/mem/main.nf index 08dc5df..d427dea 100644 --- a/modules/nf-core/bwamem2/mem/main.nf +++ b/modules/nf-core/bwamem2/mem/main.nf @@ -2,10 +2,10 @@ process BWAMEM2_MEM { tag "$meta.id" label 'process_high' - conda (params.enable_conda ? "bioconda::bwa-mem2=2.2.1 bioconda::samtools=1.15.1" : null) + conda "bioconda::bwa-mem2=2.2.1 bioconda::samtools=1.16.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/mulled-v2-e5d375990341c5aef3c9aff74f96f66f65375ef6:38aed4501da19db366dc7c8d52d31d94e760cfaf-0' : - 'quay.io/biocontainers/mulled-v2-e5d375990341c5aef3c9aff74f96f66f65375ef6:38aed4501da19db366dc7c8d52d31d94e760cfaf-0' }" + 'https://depot.galaxyproject.org/singularity/mulled-v2-e5d375990341c5aef3c9aff74f96f66f65375ef6:2cdf6bf1e92acbeb9b2834b1c58754167173a410-0' : + 'biocontainers/mulled-v2-e5d375990341c5aef3c9aff74f96f66f65375ef6:2cdf6bf1e92acbeb9b2834b1c58754167173a410-0' }" input: tuple val(meta), path(reads) @@ -25,7 +25,7 @@ process BWAMEM2_MEM { def prefix = task.ext.prefix ?: "${meta.id}" def samtools_command = sort_bam ? 'sort' : 'view' """ - INDEX=`find -L ./ -name "*.amb" | sed 's/.amb//'` + INDEX=`find -L ./ -name "*.amb" | sed 's/\\.amb\$//'` bwa-mem2 \\ mem \\ diff --git a/modules/nf-core/custom/dumpsoftwareversions/main.nf b/modules/nf-core/custom/dumpsoftwareversions/main.nf index cebb6e0..ebc8727 100644 --- a/modules/nf-core/custom/dumpsoftwareversions/main.nf +++ b/modules/nf-core/custom/dumpsoftwareversions/main.nf @@ -2,10 +2,10 @@ process CUSTOM_DUMPSOFTWAREVERSIONS { label 'process_single' // Requires `pyyaml` which does not have a dedicated container but is in the MultiQC container - conda (params.enable_conda ? 'bioconda::multiqc=1.13' : null) + conda "bioconda::multiqc=1.14" 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:1.14--pyhdfd78af_0' : + 'biocontainers/multiqc:1.14--pyhdfd78af_0' }" input: path versions diff --git a/modules/nf-core/custom/dumpsoftwareversions/meta.yml b/modules/nf-core/custom/dumpsoftwareversions/meta.yml index 60b546a..c32657d 100644 --- a/modules/nf-core/custom/dumpsoftwareversions/meta.yml +++ b/modules/nf-core/custom/dumpsoftwareversions/meta.yml @@ -1,7 +1,9 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/yaml-schema.json name: custom_dumpsoftwareversions description: Custom module used to dump software versions within the nf-core pipeline template keywords: - custom + - dump - version tools: - custom: diff --git a/modules/nf-core/fastqc/main.nf b/modules/nf-core/fastqc/main.nf index 0573036..07d5e43 100644 --- a/modules/nf-core/fastqc/main.nf +++ b/modules/nf-core/fastqc/main.nf @@ -2,10 +2,10 @@ process FASTQC { tag "$meta.id" label 'process_medium' - conda (params.enable_conda ? "bioconda::fastqc=0.11.9" : null) + conda "bioconda::fastqc=0.11.9" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/fastqc:0.11.9--0' : - 'quay.io/biocontainers/fastqc:0.11.9--0' }" + 'biocontainers/fastqc:0.11.9--0' }" input: tuple val(meta), path(reads) @@ -20,30 +20,22 @@ process FASTQC { script: def args = task.ext.args ?: '' - // Add soft-links to original FastQs for consistent naming in pipeline def prefix = task.ext.prefix ?: "${meta.id}" - if (meta.single_end) { - """ - [ ! -f ${prefix}.fastq.gz ] && ln -s $reads ${prefix}.fastq.gz - fastqc $args --threads $task.cpus ${prefix}.fastq.gz - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - fastqc: \$( fastqc --version | sed -e "s/FastQC v//g" ) - END_VERSIONS - """ - } else { - """ - [ ! -f ${prefix}_1.fastq.gz ] && ln -s ${reads[0]} ${prefix}_1.fastq.gz - [ ! -f ${prefix}_2.fastq.gz ] && ln -s ${reads[1]} ${prefix}_2.fastq.gz - fastqc $args --threads $task.cpus ${prefix}_1.fastq.gz ${prefix}_2.fastq.gz - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - fastqc: \$( fastqc --version | sed -e "s/FastQC v//g" ) - END_VERSIONS - """ - } + // Make list of old name and new name pairs to use for renaming in the bash while loop + def old_new_pairs = reads instanceof Path || reads.size() == 1 ? [[ reads, "${prefix}.${reads.extension}" ]] : reads.withIndex().collect { entry, index -> [ entry, "${prefix}_${index + 1}.${entry.extension}" ] } + def rename_to = old_new_pairs*.join(' ').join(' ') + def renamed_files = old_new_pairs.collect{ old_name, new_name -> new_name }.join(' ') + """ + printf "%s %s\\n" $rename_to | while read old_name new_name; do + [ -f "\${new_name}" ] || ln -s \$old_name \$new_name + done + fastqc $args --threads $task.cpus $renamed_files + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + fastqc: \$( fastqc --version | sed -e "s/FastQC v//g" ) + END_VERSIONS + """ stub: def prefix = task.ext.prefix ?: "${meta.id}" diff --git a/modules/nf-core/kraken2/kraken2/main.nf b/modules/nf-core/kraken2/kraken2/main.nf index 43a1679..da8d8c6 100644 --- a/modules/nf-core/kraken2/kraken2/main.nf +++ b/modules/nf-core/kraken2/kraken2/main.nf @@ -2,10 +2,10 @@ process KRAKEN2_KRAKEN2 { tag "$meta.id" label 'process_high' - conda (params.enable_conda ? 'bioconda::kraken2=2.1.2 conda-forge::pigz=2.6' : null) + conda "bioconda::kraken2=2.1.2 conda-forge::pigz=2.6" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/mulled-v2-5799ab18b5fc681e75923b2450abaa969907ec98:87fc08d11968d081f3e8a37131c1f1f6715b6542-0' : - 'quay.io/biocontainers/mulled-v2-5799ab18b5fc681e75923b2450abaa969907ec98:87fc08d11968d081f3e8a37131c1f1f6715b6542-0' }" + 'biocontainers/mulled-v2-5799ab18b5fc681e75923b2450abaa969907ec98:87fc08d11968d081f3e8a37131c1f1f6715b6542-0' }" input: tuple val(meta), path(reads) @@ -31,7 +31,7 @@ process KRAKEN2_KRAKEN2 { def unclassified = meta.single_end ? "${prefix}.unclassified.fastq" : "${prefix}.unclassified#.fastq" def classified_option = save_output_fastqs ? "--classified-out ${classified}" : "" def unclassified_option = save_output_fastqs ? "--unclassified-out ${unclassified}" : "" - def readclassification_option = save_reads_assignment ? "--output ${prefix}.kraken2.classifiedreads.txt" : "" + def readclassification_option = save_reads_assignment ? "--output ${prefix}.kraken2.classifiedreads.txt" : "--output /dev/null" def compress_reads_command = save_output_fastqs ? "pigz -p $task.cpus *.fastq" : "" """ diff --git a/modules/nf-core/kraken2/kraken2/meta.yml b/modules/nf-core/kraken2/kraken2/meta.yml index 7129fe3..4721f45 100644 --- a/modules/nf-core/kraken2/kraken2/meta.yml +++ b/modules/nf-core/kraken2/kraken2/meta.yml @@ -28,12 +28,12 @@ input: type: directory description: Kraken2 database - save_output_fastqs: - type: boolean + type: string description: | If true, optional commands are added to save classified and unclassified reads as fastq files - save_reads_assignment: - type: boolean + type: string description: | If true, an optional command is added to save a file reporting the taxonomic classification of each input read diff --git a/modules/nf-core/krona/ktimporttaxonomy/main.nf b/modules/nf-core/krona/ktimporttaxonomy/main.nf index 79c01d7..0758a38 100644 --- a/modules/nf-core/krona/ktimporttaxonomy/main.nf +++ b/modules/nf-core/krona/ktimporttaxonomy/main.nf @@ -3,10 +3,10 @@ process KRONA_KTIMPORTTAXONOMY { label 'process_single' // WARN: Version information not provided by tool on CLI. Please update version string below when bumping container versions. - conda (params.enable_conda ? "bioconda::krona=2.8" : null) + conda "bioconda::krona=2.8" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/krona:2.8--pl5262hdfd78af_2' : - 'quay.io/biocontainers/krona:2.8--pl5262hdfd78af_2' }" + 'biocontainers/krona:2.8--pl5262hdfd78af_2' }" input: tuple val(meta), path(report) diff --git a/modules/nf-core/krona/ktimporttaxonomy/meta.yml b/modules/nf-core/krona/ktimporttaxonomy/meta.yml index 0fd7d5f..dfcd2f2 100644 --- a/modules/nf-core/krona/ktimporttaxonomy/meta.yml +++ b/modules/nf-core/krona/ktimporttaxonomy/meta.yml @@ -12,9 +12,7 @@ tools: description: Krona Tools is a set of scripts to create Krona charts from several Bioinformatics tools as well as from text and XML files. homepage: https://github.com/marbl/Krona/wiki/KronaTools documentation: http://manpages.ubuntu.com/manpages/impish/man1/ktImportTaxonomy.1.html - tool_dev_url: - doi: https://doi.org/10.1186/1471-2105-12-385 - licence: + doi: 10.1186/1471-2105-12-385 input: - meta: diff --git a/modules/nf-core/krona/ktupdatetaxonomy/main.nf b/modules/nf-core/krona/ktupdatetaxonomy/main.nf index ef51a29..169660c 100644 --- a/modules/nf-core/krona/ktupdatetaxonomy/main.nf +++ b/modules/nf-core/krona/ktupdatetaxonomy/main.nf @@ -3,10 +3,10 @@ def VERSION='2.7.1' // Version information not provided by tool on CLI process KRONA_KTUPDATETAXONOMY { label 'process_single' - conda (params.enable_conda ? "bioconda::krona=2.7.1" : null) + conda "bioconda::krona=2.7.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/krona:2.7.1--pl526_5' : - 'quay.io/biocontainers/krona:2.7.1--pl526_5' }" + 'biocontainers/krona:2.7.1--pl526_5' }" output: path 'taxonomy/taxonomy.tab', emit: db diff --git a/modules/nf-core/krona/ktupdatetaxonomy/meta.yml b/modules/nf-core/krona/ktupdatetaxonomy/meta.yml index 945b506..57b5dd2 100644 --- a/modules/nf-core/krona/ktupdatetaxonomy/meta.yml +++ b/modules/nf-core/krona/ktupdatetaxonomy/meta.yml @@ -10,12 +10,9 @@ tools: description: Krona Tools is a set of scripts to create Krona charts from several Bioinformatics tools as well as from text and XML files. homepage: https://github.com/marbl/Krona/wiki/KronaTools documentation: https://github.com/marbl/Krona/wiki/Installing - tool_dev_url: - doi: https://doi.org/10.1186/1471-2105-12-385 - licence: + doi: 10.1186/1471-2105-12-385 -input: - - none: There is no input. This module downloads a pre-built taxonomy database for use with Krona Tools. +# There is no input. This module downloads a pre-built taxonomy database for use with Krona Tools. output: - versions: diff --git a/modules/nf-core/multiqc/main.nf b/modules/nf-core/multiqc/main.nf index a8159a5..1fc387b 100644 --- a/modules/nf-core/multiqc/main.nf +++ b/modules/nf-core/multiqc/main.nf @@ -1,10 +1,10 @@ process MULTIQC { label 'process_single' - conda (params.enable_conda ? 'bioconda::multiqc=1.13' : null) + conda "bioconda::multiqc=1.14" container "${ 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:1.14--pyhdfd78af_0' : + 'biocontainers/multiqc:1.14--pyhdfd78af_0' }" input: path multiqc_files, stageAs: "?/*" diff --git a/modules/nf-core/multiqc/meta.yml b/modules/nf-core/multiqc/meta.yml index ebc29b2..f93b5ee 100644 --- a/modules/nf-core/multiqc/meta.yml +++ b/modules/nf-core/multiqc/meta.yml @@ -1,3 +1,4 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/yaml-schema.json name: MultiQC description: Aggregate results from bioinformatics analyses across many samples into a single report keywords: @@ -37,7 +38,7 @@ output: description: MultiQC report file pattern: "multiqc_report.html" - data: - type: dir + type: directory description: MultiQC data dir pattern: "multiqc_data" - plots: diff --git a/modules/nf-core/qualimap/bamqc/main.nf b/modules/nf-core/qualimap/bamqc/main.nf index 3bfcb4c..fef7307 100644 --- a/modules/nf-core/qualimap/bamqc/main.nf +++ b/modules/nf-core/qualimap/bamqc/main.nf @@ -2,10 +2,10 @@ process QUALIMAP_BAMQC { tag "$meta.id" label 'process_medium' - conda (params.enable_conda ? "bioconda::qualimap=2.2.2d" : null) + conda "bioconda::qualimap=2.2.2d" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/qualimap:2.2.2d--1' : - 'quay.io/biocontainers/qualimap:2.2.2d--1' }" + 'biocontainers/qualimap:2.2.2d--1' }" input: tuple val(meta), path(bam) @@ -23,7 +23,7 @@ process QUALIMAP_BAMQC { prefix = task.ext.prefix ?: "${meta.id}" def collect_pairs = meta.single_end ? '' : '--collect-overlap-pairs' - def memory = task.memory.toGiga() + "G" + def memory = (task.memory.mega*0.8).intValue() + 'M' def regions = gff ? "--gff $gff" : '' def strandedness = 'non-strand-specific' @@ -34,7 +34,7 @@ process QUALIMAP_BAMQC { } """ unset DISPLAY - mkdir tmp + mkdir -p tmp export _JAVA_OPTIONS=-Djava.io.tmpdir=./tmp qualimap \\ --java-mem-size=$memory \\ diff --git a/modules/nf-core/samtools/fastq/main.nf b/modules/nf-core/samtools/fastq/main.nf index 8d9b9d0..15d8976 100644 --- a/modules/nf-core/samtools/fastq/main.nf +++ b/modules/nf-core/samtools/fastq/main.nf @@ -2,17 +2,21 @@ process SAMTOOLS_FASTQ { tag "$meta.id" label 'process_low' - conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null) + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' : - 'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }" + 'https://depot.galaxyproject.org/singularity/samtools:1.17--h00cdaf9_0' : + 'biocontainers/samtools:1.17--h00cdaf9_0' }" input: - tuple val(meta), path(bam) + tuple val(meta), path(input) + val(interleave) output: - tuple val(meta), path("*.fastq.gz"), emit: fastq - path "versions.yml" , emit: versions + tuple val(meta), path("*_{1,2}.fastq.gz") , optional:true, emit: fastq + tuple val(meta), path("*_interleaved.fastq.gz"), optional:true, emit: interleaved + tuple val(meta), path("*_singleton.fastq.gz") , optional:true, emit: singleton + tuple val(meta), path("*_other.fastq.gz") , optional:true, emit: other + path "versions.yml" , emit: versions when: task.ext.when == null || task.ext.when @@ -20,14 +24,17 @@ process SAMTOOLS_FASTQ { script: def args = task.ext.args ?: '' def prefix = task.ext.prefix ?: "${meta.id}" - def endedness = meta.single_end ? "-0 ${prefix}.fastq.gz" : "-1 ${prefix}_1.fastq.gz -2 ${prefix}_2.fastq.gz" + def output = ( interleave && ! meta.single_end ) ? "> ${prefix}_interleaved.fastq.gz" : + meta.single_end ? "-1 ${prefix}_1.fastq.gz -s ${prefix}_singleton.fastq.gz" : + "-1 ${prefix}_1.fastq.gz -2 ${prefix}_2.fastq.gz -s ${prefix}_singleton.fastq.gz" """ samtools \\ fastq \\ $args \\ --threads ${task.cpus-1} \\ - $endedness \\ - $bam + -0 ${prefix}_other.fastq.gz \\ + $input \\ + $output cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/nf-core/samtools/fastq/meta.yml b/modules/nf-core/samtools/fastq/meta.yml index 41055cf..b1a1ed3 100644 --- a/modules/nf-core/samtools/fastq/meta.yml +++ b/modules/nf-core/samtools/fastq/meta.yml @@ -12,32 +12,51 @@ tools: short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. These files are generated as output by short read aligners like BWA. homepage: http://www.htslib.org/ - documentation: hhttp://www.htslib.org/doc/samtools.html + documentation: http://www.htslib.org/doc/samtools.html doi: 10.1093/bioinformatics/btp352 licence: ["MIT"] + input: - meta: type: map description: | Groovy Map containing sample information e.g. [ id:'test', single_end:false ] - - bam: + - input: type: file description: BAM/CRAM/SAM file pattern: "*.{bam,cram,sam}" + - interleave: + type: boolean + description: Set true for interleaved fastq file + output: - meta: type: map description: | Groovy Map containing sample information e.g. [ id:'test', single_end:false ] - - fastq: - type: file - description: compressed FASTQ file - pattern: "*.fastq.gz" - versions: type: file description: File containing software versions pattern: "versions.yml" + - fastq: + type: file + description: Compressed FASTQ file(s) with reads with either the READ1 or READ2 flag set in separate files. + pattern: "*_{1,2}.fastq.gz" + - interleaved: + type: file + description: Compressed FASTQ file with reads with either the READ1 or READ2 flag set in a combined file. Needs collated input file. + pattern: "*_interleaved.fastq.gz" + - singleton: + type: file + description: Compressed FASTQ file with singleton reads + pattern: "*_singleton.fastq.gz" + - other: + type: file + description: Compressed FASTQ file with reads with either both READ1 and READ2 flags set or unset + pattern: "*_other.fastq.gz" + authors: + - "@priyanka-surana" - "@suzannejin" diff --git a/modules/nf-core/samtools/flagstat/main.nf b/modules/nf-core/samtools/flagstat/main.nf index c3152ac..eb7e72f 100644 --- a/modules/nf-core/samtools/flagstat/main.nf +++ b/modules/nf-core/samtools/flagstat/main.nf @@ -2,10 +2,10 @@ process SAMTOOLS_FLAGSTAT { tag "$meta.id" label 'process_single' - conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null) + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' : - 'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }" + 'https://depot.galaxyproject.org/singularity/samtools:1.17--h00cdaf9_0' : + 'biocontainers/samtools:1.17--h00cdaf9_0' }" input: tuple val(meta), path(bam), path(bai) diff --git a/modules/nf-core/samtools/flagstat/meta.yml b/modules/nf-core/samtools/flagstat/meta.yml index 9526906..954225d 100644 --- a/modules/nf-core/samtools/flagstat/meta.yml +++ b/modules/nf-core/samtools/flagstat/meta.yml @@ -14,7 +14,7 @@ tools: short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. These files are generated as output by short read aligners like BWA. homepage: http://www.htslib.org/ - documentation: hhttp://www.htslib.org/doc/samtools.html + documentation: http://www.htslib.org/doc/samtools.html doi: 10.1093/bioinformatics/btp352 licence: ["MIT"] input: diff --git a/modules/nf-core/samtools/idxstats/main.nf b/modules/nf-core/samtools/idxstats/main.nf index 87618e5..a257d70 100644 --- a/modules/nf-core/samtools/idxstats/main.nf +++ b/modules/nf-core/samtools/idxstats/main.nf @@ -1,11 +1,11 @@ process SAMTOOLS_IDXSTATS { tag "$meta.id" - label 'process_low' + label 'process_single' - conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null) + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' : - 'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }" + 'https://depot.galaxyproject.org/singularity/samtools:1.17--h00cdaf9_0' : + 'biocontainers/samtools:1.17--h00cdaf9_0' }" input: tuple val(meta), path(bam), path(bai) diff --git a/modules/nf-core/samtools/idxstats/meta.yml b/modules/nf-core/samtools/idxstats/meta.yml index 3710ab8..dda87e1 100644 --- a/modules/nf-core/samtools/idxstats/meta.yml +++ b/modules/nf-core/samtools/idxstats/meta.yml @@ -15,7 +15,7 @@ tools: short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. These files are generated as output by short read aligners like BWA. homepage: http://www.htslib.org/ - documentation: hhttp://www.htslib.org/doc/samtools.html + documentation: http://www.htslib.org/doc/samtools.html doi: 10.1093/bioinformatics/btp352 licence: ["MIT"] input: diff --git a/modules/nf-core/samtools/index/main.nf b/modules/nf-core/samtools/index/main.nf index e04e63e..0b20aa4 100644 --- a/modules/nf-core/samtools/index/main.nf +++ b/modules/nf-core/samtools/index/main.nf @@ -2,10 +2,10 @@ process SAMTOOLS_INDEX { tag "$meta.id" label 'process_low' - conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null) + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' : - 'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }" + 'https://depot.galaxyproject.org/singularity/samtools:1.17--h00cdaf9_0' : + 'biocontainers/samtools:1.17--h00cdaf9_0' }" input: tuple val(meta), path(input) diff --git a/modules/nf-core/samtools/index/meta.yml b/modules/nf-core/samtools/index/meta.yml index e5cadbc..8bd2fa6 100644 --- a/modules/nf-core/samtools/index/meta.yml +++ b/modules/nf-core/samtools/index/meta.yml @@ -12,7 +12,7 @@ tools: short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. These files are generated as output by short read aligners like BWA. homepage: http://www.htslib.org/ - documentation: hhttp://www.htslib.org/doc/samtools.html + documentation: http://www.htslib.org/doc/samtools.html doi: 10.1093/bioinformatics/btp352 licence: ["MIT"] input: diff --git a/modules/nf-core/samtools/sort/main.nf b/modules/nf-core/samtools/sort/main.nf index ab7f1cc..1e5181d 100644 --- a/modules/nf-core/samtools/sort/main.nf +++ b/modules/nf-core/samtools/sort/main.nf @@ -2,10 +2,10 @@ process SAMTOOLS_SORT { tag "$meta.id" label 'process_medium' - conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null) + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' : - 'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }" + 'https://depot.galaxyproject.org/singularity/samtools:1.17--h00cdaf9_0' : + 'biocontainers/samtools:1.17--h00cdaf9_0' }" input: tuple val(meta), path(bam) @@ -21,9 +21,17 @@ process SAMTOOLS_SORT { script: def args = task.ext.args ?: '' def prefix = task.ext.prefix ?: "${meta.id}" + def sort_memory = (task.memory.mega/task.cpus).intValue() if ("$bam" == "${prefix}.bam") error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!" """ - samtools sort $args -@ $task.cpus -o ${prefix}.bam -T $prefix $bam + samtools sort \\ + $args \\ + -@ $task.cpus \\ + -m ${sort_memory}M \\ + -o ${prefix}.bam \\ + -T $prefix \\ + $bam + cat <<-END_VERSIONS > versions.yml "${task.process}": samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//') diff --git a/modules/nf-core/samtools/sort/meta.yml b/modules/nf-core/samtools/sort/meta.yml index 0928975..0732843 100644 --- a/modules/nf-core/samtools/sort/meta.yml +++ b/modules/nf-core/samtools/sort/meta.yml @@ -12,7 +12,7 @@ tools: short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. These files are generated as output by short read aligners like BWA. homepage: http://www.htslib.org/ - documentation: hhttp://www.htslib.org/doc/samtools.html + documentation: http://www.htslib.org/doc/samtools.html doi: 10.1093/bioinformatics/btp352 licence: ["MIT"] input: diff --git a/modules/nf-core/samtools/stats/main.nf b/modules/nf-core/samtools/stats/main.nf index 9b0c386..eb7f098 100644 --- a/modules/nf-core/samtools/stats/main.nf +++ b/modules/nf-core/samtools/stats/main.nf @@ -2,10 +2,10 @@ process SAMTOOLS_STATS { tag "$meta.id" label 'process_single' - conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null) + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' : - 'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }" + 'https://depot.galaxyproject.org/singularity/samtools:1.17--h00cdaf9_0' : + 'biocontainers/samtools:1.17--h00cdaf9_0' }" input: tuple val(meta), path(input), path(input_index) diff --git a/modules/nf-core/samtools/stats/meta.yml b/modules/nf-core/samtools/stats/meta.yml index cac50b1..1d68a5d 100644 --- a/modules/nf-core/samtools/stats/meta.yml +++ b/modules/nf-core/samtools/stats/meta.yml @@ -13,7 +13,7 @@ tools: short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. These files are generated as output by short read aligners like BWA. homepage: http://www.htslib.org/ - documentation: hhttp://www.htslib.org/doc/samtools.html + documentation: http://www.htslib.org/doc/samtools.html doi: 10.1093/bioinformatics/btp352 licence: ["MIT"] input: @@ -23,13 +23,13 @@ input: Groovy Map containing sample information e.g. [ id:'test', single_end:false ] - input: - type: file - description: BAM/CRAM file from alignment - pattern: "*.{bam,cram}" + type: file + description: BAM/CRAM file from alignment + pattern: "*.{bam,cram}" - input_index: - type: file - description: BAI/CRAI file from alignment - pattern: "*.{bai,crai}" + type: file + description: BAI/CRAI file from alignment + pattern: "*.{bai,crai}" - fasta: type: optional file description: Reference file the CRAM was created with diff --git a/modules/nf-core/samtools/view/main.nf b/modules/nf-core/samtools/view/main.nf index 94da5d6..b87369e 100644 --- a/modules/nf-core/samtools/view/main.nf +++ b/modules/nf-core/samtools/view/main.nf @@ -2,10 +2,10 @@ process SAMTOOLS_VIEW { tag "$meta.id" label 'process_low' - conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null) + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' : - 'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }" + 'https://depot.galaxyproject.org/singularity/samtools:1.17--h00cdaf9_0' : + 'biocontainers/samtools:1.17--h00cdaf9_0' }" input: tuple val(meta), path(input), path(index) @@ -26,6 +26,7 @@ process SAMTOOLS_VIEW { script: def args = task.ext.args ?: '' + def args2 = task.ext.args2 ?: '' def prefix = task.ext.prefix ?: "${meta.id}" def reference = fasta ? "--reference ${fasta}" : "" def readnames = qname ? "--qname-file ${qname}": "" @@ -42,7 +43,8 @@ process SAMTOOLS_VIEW { ${readnames} \\ $args \\ -o ${prefix}.${file_type} \\ - $input + $input \\ + $args2 cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/nf-core/samtools/view/meta.yml b/modules/nf-core/samtools/view/meta.yml index a52e4f8..7691603 100644 --- a/modules/nf-core/samtools/view/meta.yml +++ b/modules/nf-core/samtools/view/meta.yml @@ -12,7 +12,7 @@ tools: short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. These files are generated as output by short read aligners like BWA. homepage: http://www.htslib.org/ - documentation: hhttp://www.htslib.org/doc/samtools.html + documentation: http://www.htslib.org/doc/samtools.html doi: 10.1093/bioinformatics/btp352 licence: ["MIT"] input: @@ -27,8 +27,8 @@ input: pattern: "*.{bam,cram,sam}" - index: type: optional file - description: BAM.BAI/CRAM.CRAI file - pattern: "*.{.bai,.crai}" + description: BAM.BAI/BAM.CSI/CRAM.CRAI file + pattern: "*.{.bai,.csi,.crai}" - fasta: type: optional file description: Reference file the CRAM was created with diff --git a/modules/nf-core/trimgalore/main.nf b/modules/nf-core/trimgalore/main.nf index a69e3de..dcb77ae 100644 --- a/modules/nf-core/trimgalore/main.nf +++ b/modules/nf-core/trimgalore/main.nf @@ -2,22 +2,21 @@ process TRIMGALORE { tag "$meta.id" label 'process_high' - conda (params.enable_conda ? 'bioconda::trim-galore=0.6.7' : null) + conda "bioconda::trim-galore=0.6.7" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/trim-galore:0.6.7--hdfd78af_0' : - 'quay.io/biocontainers/trim-galore:0.6.7--hdfd78af_0' }" + 'biocontainers/trim-galore:0.6.7--hdfd78af_0' }" input: tuple val(meta), path(reads) output: - tuple val(meta), path("*{trimmed,val}*.fq.gz"), emit: reads - tuple val(meta), path("*report.txt") , emit: log - path "versions.yml" , emit: versions - - tuple val(meta), path("*unpaired*.fq.gz") , emit: unpaired, optional: true - tuple val(meta), path("*.html") , emit: html , optional: true - tuple val(meta), path("*.zip") , emit: zip , optional: true + tuple val(meta), path("*{3prime,5prime,trimmed,val}*.fq.gz"), emit: reads + tuple val(meta), path("*report.txt") , emit: log , optional: true + tuple val(meta), path("*unpaired*.fq.gz") , emit: unpaired, optional: true + tuple val(meta), path("*.html") , emit: html , optional: true + tuple val(meta), path("*.zip") , emit: zip , optional: true + path "versions.yml" , emit: versions when: task.ext.when == null || task.ext.when @@ -35,23 +34,17 @@ process TRIMGALORE { if (cores > 8) cores = 8 } - // Clipping presets have to be evaluated in the context of SE/PE - def c_r1 = params.clip_r1 > 0 ? "--clip_r1 ${params.clip_r1}" : '' - def c_r2 = params.clip_r2 > 0 ? "--clip_r2 ${params.clip_r2}" : '' - def tpc_r1 = params.three_prime_clip_r1 > 0 ? "--three_prime_clip_r1 ${params.three_prime_clip_r1}" : '' - def tpc_r2 = params.three_prime_clip_r2 > 0 ? "--three_prime_clip_r2 ${params.three_prime_clip_r2}" : '' - // Added soft-links to original fastqs for consistent naming in MultiQC def prefix = task.ext.prefix ?: "${meta.id}" if (meta.single_end) { + def args_list = args.split("\\s(?=--)").toList() + args_list.removeAll { it.toLowerCase().contains('_r2 ') } """ [ ! -f ${prefix}.fastq.gz ] && ln -s $reads ${prefix}.fastq.gz trim_galore \\ - $args \\ + ${args_list.join(' ')} \\ --cores $cores \\ --gzip \\ - $c_r1 \\ - $tpc_r1 \\ ${prefix}.fastq.gz cat <<-END_VERSIONS > versions.yml @@ -69,10 +62,6 @@ process TRIMGALORE { --cores $cores \\ --paired \\ --gzip \\ - $c_r1 \\ - $c_r2 \\ - $tpc_r1 \\ - $tpc_r2 \\ ${prefix}_1.fastq.gz \\ ${prefix}_2.fastq.gz diff --git a/modules/nf-core/trimgalore/meta.yml b/modules/nf-core/trimgalore/meta.yml index 439f566..f84c4d7 100644 --- a/modules/nf-core/trimgalore/meta.yml +++ b/modules/nf-core/trimgalore/meta.yml @@ -36,7 +36,7 @@ output: description: | List of input adapter trimmed FastQ files of size 1 and 2 for single-end and paired-end data, respectively. - pattern: "*.{fq.gz}" + pattern: "*{3prime,5prime,trimmed,val}*.fq.gz" - unpaired: type: file description: | diff --git a/modules/nf-core/untar/main.nf b/modules/nf-core/untar/main.nf index 71eea7b..8cd1856 100644 --- a/modules/nf-core/untar/main.nf +++ b/modules/nf-core/untar/main.nf @@ -2,17 +2,17 @@ process UNTAR { tag "$archive" label 'process_single' - conda (params.enable_conda ? "conda-forge::sed=4.7" : null) + conda "conda-forge::sed=4.7 bioconda::grep=3.4 conda-forge::tar=1.34" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/ubuntu:20.04' : - 'ubuntu:20.04' }" + 'nf-core/ubuntu:20.04' }" input: tuple val(meta), path(archive) output: - tuple val(meta), path("$untar"), emit: untar - path "versions.yml" , emit: versions + tuple val(meta), path("$prefix"), emit: untar + path "versions.yml" , emit: versions when: task.ext.when == null || task.ext.when @@ -20,31 +20,29 @@ process UNTAR { script: def args = task.ext.args ?: '' def args2 = task.ext.args2 ?: '' - untar = archive.toString() - '.tar.gz' + prefix = task.ext.prefix ?: ( meta.id ? "${meta.id}" : archive.baseName.toString().replaceFirst(/\.tar$/, "")) """ - mkdir output + mkdir $prefix ## Ensures --strip-components only applied when top level of tar contents is a directory - ## If just files or multiple directories, place all in output - if [[ \$(tar -tzf ${archive} | grep -o -P "^.*?\\/" | uniq | wc -l) -eq 1 ]]; then + ## If just files or multiple directories, place all in prefix + if [[ \$(tar -taf ${archive} | grep -o -P "^.*?\\/" | uniq | wc -l) -eq 1 ]]; then tar \\ - -C output --strip-components 1 \\ - -xzvf \\ + -C $prefix --strip-components 1 \\ + -xavf \\ $args \\ $archive \\ $args2 else tar \\ - -C output \\ - -xzvf \\ + -C $prefix \\ + -xavf \\ $args \\ $archive \\ $args2 fi - mv output ${untar} - cat <<-END_VERSIONS > versions.yml "${task.process}": untar: \$(echo \$(tar --version 2>&1) | sed 's/^.*(GNU tar) //; s/ Copyright.*\$//') @@ -52,9 +50,10 @@ process UNTAR { """ stub: - untar = archive.toString() - '.tar.gz' + prefix = task.ext.prefix ?: ( meta.id ? "${meta.id}" : archive.toString().replaceFirst(/\.[^\.]+(.gz)?$/, "")) """ - touch $untar + mkdir $prefix + touch ${prefix}/file.txt cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/nf-core/untar/meta.yml b/modules/nf-core/untar/meta.yml index ea7a3f3..db241a6 100644 --- a/modules/nf-core/untar/meta.yml +++ b/modules/nf-core/untar/meta.yml @@ -3,6 +3,7 @@ description: Extract files. keywords: - untar - uncompress + - extract tools: - untar: description: | diff --git a/nextflow.config b/nextflow.config index 7a88a8a..64c3e9c 100644 --- a/nextflow.config +++ b/nextflow.config @@ -26,17 +26,13 @@ params { aligner = "bwa-mem" istest = false - // Hard coded trimgalore params - clip_r1 = null - clip_r2 = null - three_prime_clip_r1 = null - three_prime_clip_r2 = null - // MultiQC options multiqc_config = null multiqc_title = null + multiqc_logo = null max_multiqc_email_size = '25.MB' multiqc_runkraken = true + multiqc_methods_description = null // Boilerplate options outdir = null @@ -46,11 +42,12 @@ params { email_on_fail = null plaintext_email = false monochrome_logs = false + hook_url = null help = false + version = false validate_params = true show_hidden_params = false schema_ignore_params = 'genomes' - enable_conda = false // Config options @@ -89,64 +86,91 @@ try { // } - profiles { - debug { process.beforeScript = 'echo $HOSTNAME' } + debug { + dumpHashes = true + process.beforeScript = 'echo $HOSTNAME' + cleanup = false + } conda { - params.enable_conda = true + conda.enabled = true docker.enabled = false singularity.enabled = false podman.enabled = false shifter.enabled = false charliecloud.enabled = false + apptainer.enabled = false } mamba { - params.enable_conda = true + conda.enabled = true conda.useMamba = true docker.enabled = false singularity.enabled = false podman.enabled = false shifter.enabled = false charliecloud.enabled = false + apptainer.enabled = false } docker { docker.enabled = true + docker.registry = 'quay.io' docker.userEmulation = true + conda.enabled = false singularity.enabled = false podman.enabled = false shifter.enabled = false charliecloud.enabled = false - docker.runOptions = "-v $baseDir:$baseDir" + apptainer.enabled = false + } + arm { + docker.runOptions = '-u $(id -u):$(id -g) --platform=linux/amd64' } singularity { - singularity.enabled = true - singularity.autoMounts = true - docker.enabled = false - podman.enabled = false - shifter.enabled = false - charliecloud.enabled = false - process.containerOptions = "-B $baseDir" + 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 + podman.registry = 'quay.io' + 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 + conda.enabled = false + docker.enabled = false + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false } gitpod { executor.name = 'local' @@ -208,12 +232,13 @@ dag { manifest { name = 'nf-core/hgtseq' - author = 'Simone Carpanzano, Francesco Lescai' + author = """Simone Carpanzano, Francesco Lescai""" homePage = 'https://github.com/nf-core/hgtseq' - description = 'A pipeline to investigate horizontal gene transfer from NGS data' + description = """A pipeline to investigate horizontal gene transfer from NGS data""" mainScript = 'main.nf' - nextflowVersion = '!>=21.10.3' - version = '1.0.0' + nextflowVersion = '!>=22.10.1' + version = '1.1.0' + doi = '' } // Load modules.config for DSL2 module specific options diff --git a/nextflow_schema.json b/nextflow_schema.json index ae2376a..6820cd6 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -241,6 +241,12 @@ "fa_icon": "fas fa-question-circle", "hidden": true }, + "version": { + "type": "boolean", + "description": "Display version and exit.", + "fa_icon": "fas fa-question-circle", + "hidden": true + }, "publish_dir_mode": { "type": "string", "default": "copy", @@ -278,12 +284,30 @@ "fa_icon": "fas fa-palette", "hidden": true }, + "hook_url": { + "type": "string", + "description": "Incoming hook URL for messaging service", + "fa_icon": "fas fa-people-group", + "help_text": "Incoming hook URL for messaging service. Currently, MS Teams and Slack are supported.", + "hidden": true + }, "multiqc_config": { "type": "string", "description": "Custom config file to supply to MultiQC.", "fa_icon": "fas fa-cog", "hidden": true }, + "multiqc_logo": { + "type": "string", + "description": "Custom logo file to supply to MultiQC. File name must also be set in the MultiQC config file", + "fa_icon": "fas fa-image", + "hidden": true + }, + "multiqc_methods_description": { + "type": "string", + "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.", @@ -304,44 +328,6 @@ "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." - }, - "enable_conda": { - "type": "boolean", - "description": "Run this workflow with Conda. You can also use '-profile conda' instead of providing this parameter.", - "hidden": true, - "fa_icon": "fas fa-bacon" - } - } - }, - "trimgalore_options": { - "title": "Trimgalore options", - "type": "object", - "description": "Trimgalore trimmings options", - "default": "", - "properties": { - "clip_r1": { - "type": "string", - "default": "None", - "hidden": true, - "description": "Instructs Trim Galore to remove bp from the 5' end of read 1." - }, - "clip_r2": { - "type": "string", - "default": "None", - "hidden": true, - "description": "Instructs Trim Galore to remove bp from the 5' end of read 2." - }, - "three_prime_clip_r1": { - "type": "string", - "default": "None", - "hidden": true, - "description": "Instructs Trim Galore to remove bp from the 3' end of read 1 after adapter/quality trimming has been performed." - }, - "three_prime_clip_r2": { - "type": "string", - "default": "None", - "hidden": true, - "description": "Instructs Trim Galore to remove bp from the 3' end of read 2 after adapter/quality trimming has been performed." } } } @@ -364,9 +350,6 @@ }, { "$ref": "#/definitions/generic_options" - }, - { - "$ref": "#/definitions/trimgalore_options" } ] } diff --git a/subworkflows/local/classify_unmapped/main.nf b/subworkflows/local/classify_unmapped/main.nf index bc3d0d0..ade72ea 100644 --- a/subworkflows/local/classify_unmapped/main.nf +++ b/subworkflows/local/classify_unmapped/main.nf @@ -1,7 +1,7 @@ include { SAMTOOLS_INDEX } from '../../../modules/nf-core/samtools/index/main.nf' include { SAMTOOLS_SORT } from '../../../modules/nf-core/samtools/sort/main.nf' -include { SAMTOOLS_VIEW as SAMTOOLS_VIEW_SINGLE } from '../../../modules/nf-core/samtools/view/main.nf' +include { SAMTOOLS_VIEW_SINGLE } from '../../../modules/local/samtools/viewsingle/main.nf' include { SAMTOOLS_VIEW as SAMTOOLS_VIEW_BOTH } from '../../../modules/nf-core/samtools/view/main.nf' include { SAMTOOLS_FASTQ as SAMTOOLS_FASTQ_SINGLE } from '../../../modules/local/samtools/fastqlocal/main.nf' include { SAMTOOLS_FASTQ as SAMTOOLS_FASTQ_BOTH } from '../../../modules/local/samtools/fastqlocal/main.nf' diff --git a/subworkflows/local/prepare_reads/main.nf b/subworkflows/local/prepare_reads/main.nf index 4b3dbf2..0c4aa6f 100644 --- a/subworkflows/local/prepare_reads/main.nf +++ b/subworkflows/local/prepare_reads/main.nf @@ -22,16 +22,18 @@ workflow PREPARE_READS { ch_versions = Channel.empty() aligned_bam = Channel.empty() + fasta_meta = Channel.value(file(fasta)).map{ it -> [[id:it[0].baseName], it] } + TRIMGALORE ( reads ) ch_versions = ch_versions.mix(TRIMGALORE.out.versions) if (aligner == "bwa-mem") { // reference is indexed if index not available in iGenomes - BWAMEM1_INDEX ( fasta ) + BWAMEM1_INDEX ( fasta_meta ) ch_versions = ch_versions.mix(BWAMEM1_INDEX.out.versions) // sets bwaindex to correct input - bwaindex = params.fasta ? params.bwaindex ? Channel.fromPath(params.bwaindex).collect() : BWAMEM1_INDEX.out.index : [] + bwaindex = params.fasta ? params.bwaindex ? Channel.fromPath(params.bwaindex).collect().map{ it -> [[id:it[0].baseName], it] } : BWAMEM1_INDEX.out.index : [] // appropriately tagged interleaved FASTQ reads are mapped to the reference BWAMEM1_MEM ( TRIMGALORE.out.reads, bwaindex, false ) @@ -39,7 +41,7 @@ workflow PREPARE_READS { aligned_bam = BWAMEM1_MEM.out.bam } else { // reference is indexed if index not available in iGenomes - BWAMEM2_INDEX ( fasta ) + BWAMEM2_INDEX ( fasta_meta ) ch_versions = ch_versions.mix(BWAMEM2_INDEX.out.versions) // sets bwamem2index to correct input 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/hgtseq.nf b/workflows/hgtseq.nf index ca8507f..a733122 100644 --- a/workflows/hgtseq.nf +++ b/workflows/hgtseq.nf @@ -21,8 +21,10 @@ if (params.input) { ch_input = file(params.input) } else { exit 1, 'Input sample ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -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() +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) /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -157,7 +159,7 @@ workflow HGTSEQ { } // execute reporting only if genome is Human - if (!params.enable_conda) { + if (!workflow.profile.contains('conda')) { REPORTING ( CLASSIFY_UNMAPPED.out.classified_single.collect{ it[1] }, CLASSIFY_UNMAPPED.out.classified_both.collect{ it[1] }, @@ -178,10 +180,12 @@ workflow HGTSEQ { workflow_summary = WorkflowHgtseq.paramsSummaryMultiqc(workflow, summary_params) ch_workflow_summary = Channel.value(workflow_summary) + methods_description = WorkflowHgtseq.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(Channel.from(ch_multiqc_config)) - ch_multiqc_files = ch_multiqc_files.mix(ch_multiqc_custom_config.collect().ifEmpty([])) 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()) // adding reads QC for both trimmed and untrimmed if (!params.isbam) { @@ -204,12 +208,11 @@ workflow HGTSEQ { MULTIQC ( ch_multiqc_files.collect(), - [], - [], - [] + ch_multiqc_config.toList(), + ch_multiqc_custom_config.toList(), + ch_multiqc_logo.toList() ) multiqc_report = MULTIQC.out.report.toList() - ch_versions = ch_versions.mix(MULTIQC.out.versions) } /* @@ -223,6 +226,9 @@ workflow.onComplete { 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) + } } /*