diff --git a/.editorconfig b/.editorconfig index dd9ffa5..72dda28 100644 --- a/.editorconfig +++ b/.editorconfig @@ -28,10 +28,6 @@ indent_style = unset [/assets/email*] indent_size = unset -# ignore Readme -[README.md] -indent_style = unset - -# ignore python +# ignore python and markdown [*.{py,md}] indent_style = unset diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index 25cb277..ff0fbb1 100644 --- a/.github/PULL_REQUEST_TEMPLATE.md +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -18,7 +18,7 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/demo - [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/demo/tree/master/.github/CONTRIBUTING.md) - [ ] If necessary, also make a PR on the nf-core/demo _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 (`nf-test test main.nf.test -profile test,docker`). +- [ ] Ensure the test suite passes (`nextflow run . -profile test,docker --outdir `). - [ ] Check for unexpected warnings in debug mode (`nextflow run . -profile debug,test,docker --outdir `). - [ ] Usage Documentation in `docs/usage.md` is updated. - [ ] Output Documentation in `docs/output.md` is updated. diff --git a/.github/workflows/awsfulltest.yml b/.github/workflows/awsfulltest.yml index d6b0d34..ba146cd 100644 --- a/.github/workflows/awsfulltest.yml +++ b/.github/workflows/awsfulltest.yml @@ -8,12 +8,12 @@ on: types: [published] workflow_dispatch: jobs: - run-tower: + run-platform: name: Run AWS full tests if: github.repository == 'nf-core/demo' runs-on: ubuntu-latest steps: - - name: Launch workflow via tower + - name: Launch workflow via Seqera Platform uses: seqeralabs/action-tower-launch@v2 # TODO nf-core: You can customise AWS full pipeline tests as required # Add full size test data (but still relatively small datasets for few samples) @@ -33,7 +33,7 @@ jobs: - uses: actions/upload-artifact@v4 with: - name: Tower debug log file + name: Seqera Platform debug log file path: | - tower_action_*.log - tower_action_*.json + seqera_platform_action_*.log + seqera_platform_action_*.json diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml index b4805e9..83eb92a 100644 --- a/.github/workflows/awstest.yml +++ b/.github/workflows/awstest.yml @@ -5,13 +5,13 @@ name: nf-core AWS test on: workflow_dispatch: jobs: - run-tower: + run-platform: name: Run AWS tests if: github.repository == 'nf-core/demo' runs-on: ubuntu-latest steps: - # Launch workflow using Tower CLI tool action - - name: Launch workflow via tower + # Launch workflow using Seqera Platform CLI tool action + - name: Launch workflow via Seqera Platform uses: seqeralabs/action-tower-launch@v2 with: workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} @@ -27,7 +27,7 @@ jobs: - uses: actions/upload-artifact@v4 with: - name: Tower debug log file + name: Seqera Platform debug log file path: | - tower_action_*.log - tower_action_*.json + seqera_platform_action_*.log + seqera_platform_action_*.json diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 4556f7e..210131c 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -28,10 +28,10 @@ jobs: - "latest-everything" steps: - name: Check out pipeline code - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4 + uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4 - name: Install Nextflow - uses: nf-core/setup-nextflow@v1 + uses: nf-core/setup-nextflow@v2 with: version: "${{ matrix.NXF_VER }}" @@ -39,8 +39,5 @@ jobs: uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1 - name: Run pipeline with test data - # TODO nf-core: You can customise CI pipeline run tests as required - # For example: adding multiple test runs with different parameters - # Remember that you can parallelise this by using strategy.matrix run: | nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results diff --git a/.github/workflows/download_pipeline.yml b/.github/workflows/download_pipeline.yml index 08622fd..2d20d64 100644 --- a/.github/workflows/download_pipeline.yml +++ b/.github/workflows/download_pipeline.yml @@ -14,6 +14,8 @@ on: pull_request: types: - opened + - edited + - synchronize branches: - master pull_request_target: @@ -28,11 +30,14 @@ jobs: runs-on: ubuntu-latest steps: - name: Install Nextflow - uses: nf-core/setup-nextflow@v1 + uses: nf-core/setup-nextflow@v2 - - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 + - name: Disk space cleanup + uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1 + + - uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5 with: - python-version: "3.11" + python-version: "3.12" architecture: "x64" - uses: eWaterCycle/setup-singularity@931d4e31109e875b13309ae1d07c70ca8fbc8537 # v7 with: @@ -65,8 +70,17 @@ jobs: - name: Inspect download run: tree ./${{ env.REPOTITLE_LOWERCASE }} - - name: Run the downloaded pipeline + - name: Run the downloaded pipeline (stub) + id: stub_run_pipeline + continue-on-error: true env: NXF_SINGULARITY_CACHEDIR: ./ NXF_SINGULARITY_HOME_MOUNT: true run: nextflow run ./${{ env.REPOTITLE_LOWERCASE }}/$( sed 's/\W/_/g' <<< ${{ env.REPO_BRANCH }}) -stub -profile test,singularity --outdir ./results + - name: Run the downloaded pipeline (stub run not supported) + id: run_pipeline + if: ${{ job.steps.stub_run_pipeline.status == failure() }} + env: + NXF_SINGULARITY_CACHEDIR: ./ + NXF_SINGULARITY_HOME_MOUNT: true + run: nextflow run ./${{ env.REPOTITLE_LOWERCASE }}/$( sed 's/\W/_/g' <<< ${{ env.REPO_BRANCH }}) -profile test,singularity --outdir ./results diff --git a/.github/workflows/fix-linting.yml b/.github/workflows/fix-linting.yml index 962d6f6..600cd15 100644 --- a/.github/workflows/fix-linting.yml +++ b/.github/workflows/fix-linting.yml @@ -13,7 +13,7 @@ jobs: runs-on: ubuntu-latest steps: # Use the @nf-core-bot token to check out so we can push later - - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4 + - uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4 with: token: ${{ secrets.nf_core_bot_auth_token }} @@ -32,9 +32,9 @@ jobs: GITHUB_TOKEN: ${{ secrets.nf_core_bot_auth_token }} # Install and run pre-commit - - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 + - uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5 with: - python-version: 3.11 + python-version: "3.12" - name: Install pre-commit run: pip install pre-commit diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index 073e187..1fcafe8 100644 --- a/.github/workflows/linting.yml +++ b/.github/workflows/linting.yml @@ -14,13 +14,12 @@ jobs: pre-commit: runs-on: ubuntu-latest steps: - - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4 + - uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4 - - name: Set up Python 3.11 - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 + - name: Set up Python 3.12 + uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5 with: - python-version: 3.11 - cache: "pip" + python-version: "3.12" - name: Install pre-commit run: pip install pre-commit @@ -32,14 +31,14 @@ jobs: runs-on: ubuntu-latest steps: - name: Check out pipeline code - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4 + uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4 - name: Install Nextflow - uses: nf-core/setup-nextflow@v1 + uses: nf-core/setup-nextflow@v2 - - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 + - uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5 with: - python-version: "3.11" + python-version: "3.12" architecture: "x64" - name: Install dependencies @@ -60,7 +59,7 @@ jobs: - name: Upload linting log file artifact if: ${{ always() }} - uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4 + uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4 with: name: linting-logs path: | diff --git a/.github/workflows/linting_comment.yml b/.github/workflows/linting_comment.yml index b706875..40acc23 100644 --- a/.github/workflows/linting_comment.yml +++ b/.github/workflows/linting_comment.yml @@ -11,7 +11,7 @@ jobs: runs-on: ubuntu-latest steps: - name: Download lint results - uses: dawidd6/action-download-artifact@f6b0bace624032e30a85a8fd9c1a7f8f611f5737 # v3 + uses: dawidd6/action-download-artifact@09f2f74827fd3a8607589e5ad7f9398816f540fe # v3 with: workflow: linting.yml workflow_conclusion: completed diff --git a/.github/workflows/release-announcements.yml b/.github/workflows/release-announcements.yml index d468aea..03ecfcf 100644 --- a/.github/workflows/release-announcements.yml +++ b/.github/workflows/release-announcements.yml @@ -12,7 +12,7 @@ jobs: - name: get topics and convert to hashtags id: get_topics run: | - curl -s https://nf-co.re/pipelines.json | jq -r '.remote_workflows[] | select(.full_name == "${{ github.repository }}") | .topics[]' | awk '{print "#"$0}' | tr '\n' ' ' >> $GITHUB_OUTPUT + echo "topics=$(curl -s https://nf-co.re/pipelines.json | jq -r '.remote_workflows[] | select(.full_name == "${{ github.repository }}") | .topics[]' | awk '{print "#"$0}' | tr '\n' ' ')" >> $GITHUB_OUTPUT - uses: rzr/fediverse-action@master with: @@ -25,13 +25,13 @@ jobs: Please see the changelog: ${{ github.event.release.html_url }} - ${{ steps.get_topics.outputs.GITHUB_OUTPUT }} #nfcore #openscience #nextflow #bioinformatics + ${{ steps.get_topics.outputs.topics }} #nfcore #openscience #nextflow #bioinformatics send-tweet: runs-on: ubuntu-latest steps: - - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 + - uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5 with: python-version: "3.10" - name: Install dependencies diff --git a/.nf-core.yml b/.nf-core.yml index 3805dc8..e0b85a7 100644 --- a/.nf-core.yml +++ b/.nf-core.yml @@ -1 +1,2 @@ repository_type: pipeline +nf_core_version: "2.14.1" diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index af57081..4dc0f1d 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -3,6 +3,9 @@ repos: rev: "v3.1.0" hooks: - id: prettier + additional_dependencies: + - prettier@3.2.5 + - repo: https://github.com/editorconfig-checker/editorconfig-checker.python rev: "2.7.3" hooks: diff --git a/CHANGELOG.md b/CHANGELOG.md index bd9cb42..4b635d1 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,14 +3,20 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). -## v1.0dev - [date] +## 1.0.0 2024-06-19 -Initial release of nf-core/demo, created with the [nf-core](https://nf-co.re/) template. +### Credits + +Special thanks to the following for their reviews and assistance: + +- [Maxime Garcia](https://github.com/maxulysse) +- [Friederike Hanssen](https://github.com/FriederikeHanssen) ### `Added` -### `Fixed` +- `nf-core/seqtk/trim` module +- `skip_trim` parameter -### `Dependencies` +## v1.0dev - 2024-05-5 -### `Deprecated` +Initial release of nf-core/demo, created with the [nf-core](https://nf-co.re/) template. diff --git a/CITATIONS.md b/CITATIONS.md index a24cac2..934aa07 100644 --- a/CITATIONS.md +++ b/CITATIONS.md @@ -14,6 +14,8 @@ > Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online]. +- [seqtk](https://github.com/lh3/seqtk) + - [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/) > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924. diff --git a/README.md b/README.md index 7912819..796989d 100644 --- a/README.md +++ b/README.md @@ -13,52 +13,41 @@ [![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/) [![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?labelColor=000000&logo=docker)](https://www.docker.com/) [![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/) -[![Launch on Seqera Platform](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Seqera%20Platform-%234256e7)](https://tower.nf/launch?pipeline=https://github.com/nf-core/demo) +[![Launch on Seqera Platform](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Seqera%20Platform-%234256e7)](https://cloud.seqera.io/launch?pipeline=https://github.com/nf-core/demo) [![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23demo-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/demo)[![Follow on Twitter](http://img.shields.io/badge/twitter-%40nf__core-1DA1F2?labelColor=000000&logo=twitter)](https://twitter.com/nf_core)[![Follow on Mastodon](https://img.shields.io/badge/mastodon-nf__core-6364ff?labelColor=FFFFFF&logo=mastodon)](https://mstdn.science/@nf_core)[![Watch on YouTube](http://img.shields.io/badge/youtube-nf--core-FF0000?labelColor=000000&logo=youtube)](https://www.youtube.com/c/nf-core) ## Introduction -**nf-core/demo** is a bioinformatics pipeline that ... +**nf-core/demo** is a simple nf-core style bioinformatics pipeline for workshops and demonstrations. It was created using the nf-core template and is designed to run quickly using small test data files. - +![nf-core/demo metro map](docs/images/nf-core-demo-subway.png) - - - -1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)) -2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/)) +1. Read QC ([`FASTQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)) +2. Adapter and quality trimming ([`SEQTK_TRIM`](https://github.com/lh3/seqtk)) +3. Present QC for raw reads ([`MULTIQC`](http://multiqc.info/)) ## 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. - - Now, you can run the pipeline using: - - ```bash nextflow run nf-core/demo \ -profile \ @@ -80,11 +69,9 @@ For more details about the output files and reports, please refer to the ## Credits -nf-core/demo was originally written by Christopher Hakkaart. - -We thank the following people for their extensive assistance in the development of this pipeline: +nf-core/demo was originally written by Chris Hakkaart ([@christopher-hakkaart](https://github.com/christopher-hakkaart)). - + ## Contributions and Support @@ -97,8 +84,6 @@ For further information or help, don't hesitate to get in touch on the [Slack `# - - An extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file. You can cite the `nf-core` publication as follows: diff --git a/assets/methods_description_template.yml b/assets/methods_description_template.yml index 8099274..1e32f22 100644 --- a/assets/methods_description_template.yml +++ b/assets/methods_description_template.yml @@ -3,7 +3,6 @@ description: "Suggested text and references to use when describing pipeline usag section_name: "nf-core/demo Methods Description" section_href: "https://github.com/nf-core/demo" plot_type: "html" -## TODO nf-core: Update the HTML below to your preferred methods description, e.g. add publication citation for this pipeline ## You inject any metadata in the Nextflow '${workflow}' object data: |

Methods

diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml index 16a6e09..1a9c348 100644 --- a/assets/multiqc_config.yml +++ b/assets/multiqc_config.yml @@ -1,7 +1,7 @@ report_comment: > - This report has been generated by the nf-core/demo + This report has been generated by the nf-core/demo analysis pipeline. For information about how to interpret these results, please see the - documentation. + documentation. report_section_order: "nf-core-demo-methods-description": order: -1000 diff --git a/assets/nf-core-demo_logo_light.png b/assets/nf-core-demo_logo_light.png index 0ef9fa5..2543e50 100644 Binary files a/assets/nf-core-demo_logo_light.png and b/assets/nf-core-demo_logo_light.png differ diff --git a/conf/base.config b/conf/base.config index 4639378..c726c3f 100644 --- a/conf/base.config +++ b/conf/base.config @@ -10,7 +10,6 @@ process { - // TODO nf-core: Check the defaults for all processes cpus = { check_max( 1 * task.attempt, 'cpus' ) } memory = { check_max( 6.GB * task.attempt, 'memory' ) } time = { check_max( 4.h * task.attempt, 'time' ) } @@ -20,12 +19,6 @@ process { maxErrors = '-1' // Process-specific resource requirements - // NOTE - Please try and re-use the labels below as much as possible. - // These labels are used and recognised by default in DSL2 files hosted on nf-core/modules. - // If possible, it would be nice to keep the same label naming convention when - // adding in your local modules too. - // TODO nf-core: Customise requirements for specific processes. - // See https://www.nextflow.io/docs/latest/config.html#config-process-selectors withLabel:process_single { cpus = { check_max( 1 , 'cpus' ) } memory = { check_max( 6.GB * task.attempt, 'memory' ) } @@ -59,7 +52,4 @@ process { errorStrategy = 'retry' maxRetries = 2 } - withName:CUSTOM_DUMPSOFTWAREVERSIONS { - cache = false - } } diff --git a/conf/modules.config b/conf/modules.config index e3ea8fa..189cef9 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -20,13 +20,19 @@ process { withName: FASTQC { ext.args = '--quiet' + publishDir = [ + path: { "${params.outdir}/fastqc/${meta.id}" }, + mode: params.publish_dir_mode, + pattern: "*.{html,json}" + ] } - withName: CUSTOM_DUMPSOFTWAREVERSIONS { + + withName: 'SEQTK_TRIM' { publishDir = [ - path: { "${params.outdir}/pipeline_info" }, + path: { "${params.outdir}/fq/${meta.id}" }, mode: params.publish_dir_mode, - pattern: '*_versions.yml' + pattern: "*.{fastq.gz}" ] } diff --git a/conf/test.config b/conf/test.config index 0d5e11e..5bff1d1 100644 --- a/conf/test.config +++ b/conf/test.config @@ -20,10 +20,6 @@ params { max_time = '6.h' // Input data - // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets - // TODO nf-core: Give any required params for the test so that command line flags are not needed - input = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv' + input = params.pipelines_testdata_base_path + 'viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv' - // Genome references - genome = 'R64-1-1' } diff --git a/conf/test_full.config b/conf/test_full.config index 26af182..6346afd 100644 --- a/conf/test_full.config +++ b/conf/test_full.config @@ -14,11 +14,7 @@ params { config_profile_name = 'Full test profile' config_profile_description = 'Full test dataset to check pipeline function' - // Input data for full size test - // TODO nf-core: Specify the paths to your full test data ( on nf-core/test-datasets or directly in repositories, e.g. SRA) - // TODO nf-core: Give any required params for the test so that command line flags are not needed - input = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_full_illumina_amplicon.csv' + // Input data + input = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv' - // Genome references - genome = 'R64-1-1' } diff --git a/docs/images/nf-core-demo-subway.png b/docs/images/nf-core-demo-subway.png new file mode 100644 index 0000000..e7914fe Binary files /dev/null and b/docs/images/nf-core-demo-subway.png differ diff --git a/docs/images/nf-core-demo-subway.svg b/docs/images/nf-core-demo-subway.svg new file mode 100644 index 0000000..2b8c2ab --- /dev/null +++ b/docs/images/nf-core-demo-subway.svg @@ -0,0 +1,29 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/docs/images/nf-core-demo_logo_dark.png b/docs/images/nf-core-demo_logo_dark.png index 5e22400..44f9995 100644 Binary files a/docs/images/nf-core-demo_logo_dark.png and b/docs/images/nf-core-demo_logo_dark.png differ diff --git a/docs/images/nf-core-demo_logo_light.png b/docs/images/nf-core-demo_logo_light.png index c9d0c4b..b945f8c 100644 Binary files a/docs/images/nf-core-demo_logo_light.png and b/docs/images/nf-core-demo_logo_light.png differ diff --git a/docs/output.md b/docs/output.md index c8b9d43..411fdf5 100644 --- a/docs/output.md +++ b/docs/output.md @@ -6,13 +6,12 @@ This document describes the output produced by the pipeline. Most of the plots a The directories listed below will be created in the results directory after the pipeline has finished. All paths are relative to the top-level results directory. - - ## Pipeline overview The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes data using the following steps: - [FastQC](#fastqc) - Raw read QC +- [seqtk](#seqtk) - Processing sequences in the FASTA or FASTQ format. - [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline - [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution @@ -39,6 +38,18 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d The FastQC plots displayed in the MultiQC report shows _untrimmed_ reads. They may contain adapter sequence and potentially regions with low quality. ::: +### seqtk + +
+Output files + +- `fq/` + - `*.fastq.gz`: Trimmed FASTQ files. + +
+ +[seqtk](https://github.com/lh3/seqtk) is a fast and lightweight tool for processing sequences in the FASTA or FASTQ format. It seamlessly parses both FASTA and FASTQ files which can also be optionally compressed by gzip. + ### MultiQC
diff --git a/docs/usage.md b/docs/usage.md index cd4d789..42d6722 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -6,8 +6,6 @@ ## Introduction - - ## Samplesheet input You will need to create a samplesheet with information about the samples you would like to analyse before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row as shown in the examples below. @@ -18,30 +16,26 @@ You will need to create a samplesheet with information about the samples you wou ### Multiple runs of the same sample -The `sample` identifiers have to be the same when you have re-sequenced the same sample more than once e.g. to increase sequencing depth. The pipeline will concatenate the raw reads before performing any downstream analysis. Below is an example for the same sample sequenced across 3 lanes: +The `sample` identifiers have to be the same when you have re-sequenced the same sample more than once e.g. to increase sequencing depth. The pipeline will concatenate the raw reads before performing any downstream analysis. Below is an example for the same sample sequenced across 2 lanes: ```csv title="samplesheet.csv" sample,fastq_1,fastq_2 -CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz -CONTROL_REP1,AEG588A1_S1_L003_R1_001.fastq.gz,AEG588A1_S1_L003_R2_001.fastq.gz -CONTROL_REP1,AEG588A1_S1_L004_R1_001.fastq.gz,AEG588A1_S1_L004_R2_001.fastq.gz +SAMPLE3_SE,https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/illumina/amplicon/sample1_R1.fastq.gz, +SAMPLE3_SE,https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/illumina/amplicon/sample2_R1.fastq.gz, ``` ### Full samplesheet -The pipeline will auto-detect whether a sample is single- or paired-end using the information provided in the samplesheet. The samplesheet can have as many columns as you desire, however, there is a strict requirement for the first 3 columns to match those defined in the table below. +The pipeline will auto-detect whether a sample is single- or paired-end using the information provided in the samplesheet. -A final samplesheet file consisting of both single- and paired-end data may look something like the one below. This is for 6 samples, where `TREATMENT_REP3` has been sequenced twice. +A final samplesheet file consisting of both single- and paired-end data may look something like the one below. This is for 3 samples, where `SAMPLE3_SE` has been sequenced twice. ```csv title="samplesheet.csv" sample,fastq_1,fastq_2 -CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz -CONTROL_REP2,AEG588A2_S2_L002_R1_001.fastq.gz,AEG588A2_S2_L002_R2_001.fastq.gz -CONTROL_REP3,AEG588A3_S3_L002_R1_001.fastq.gz,AEG588A3_S3_L002_R2_001.fastq.gz -TREATMENT_REP1,AEG588A4_S4_L003_R1_001.fastq.gz, -TREATMENT_REP2,AEG588A5_S5_L003_R1_001.fastq.gz, -TREATMENT_REP3,AEG588A6_S6_L003_R1_001.fastq.gz, -TREATMENT_REP3,AEG588A6_S6_L004_R1_001.fastq.gz, +SAMPLE1_PE,https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/illumina/amplicon/sample1_R1.fastq.gz,https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/illumina/amplicon/sample1_R2.fastq.gz +SAMPLE2_PE,https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/illumina/amplicon/sample2_R1.fastq.gz,https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/illumina/amplicon/sample2_R2.fastq.gz +SAMPLE3_SE,https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/illumina/amplicon/sample1_R1.fastq.gz, +SAMPLE3_SE,https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/illumina/amplicon/sample2_R1.fastq.gz, ``` | Column | Description | @@ -156,6 +150,8 @@ If `-profile` is not specified, the pipeline will run locally and expect all sof - 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/) +- `wave` + - A generic configuration profile to enable [Wave](https://seqera.io/wave/) containers. Use together with one of the above (requires Nextflow ` 24.03.0-edge` or later). - `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, Charliecloud, or Apptainer. diff --git a/main.nf b/main.nf index 0351d8e..b7a507c 100644 --- a/main.nf +++ b/main.nf @@ -29,9 +29,6 @@ include { getGenomeAttribute } from './subworkflows/local/utils_nfcore_demo ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -// TODO nf-core: Remove this line if you don't need a FASTA file -// This is an example of how to use getGenomeAttribute() to fetch parameters -// from igenomes.config using `--genome` params.fasta = getGenomeAttribute('fasta') /* diff --git a/modules.json b/modules.json index 83ecb34..67933c1 100644 --- a/modules.json +++ b/modules.json @@ -7,13 +7,18 @@ "nf-core": { "fastqc": { "branch": "master", - "git_sha": "f4ae1d942bd50c5c0b9bd2de1393ce38315ba57c", + "git_sha": "285a50500f9e02578d90b3ce6382ea3c30216acd", "installed_by": ["modules"] }, "multiqc": { "branch": "master", "git_sha": "b7ebe95761cd389603f9cc0e0dc384c0f663815a", "installed_by": ["modules"] + }, + "seqtk/trim": { + "branch": "master", + "git_sha": "71c669747731cbc360dc220069c9f83015558c07", + "installed_by": ["modules"] } } }, @@ -26,7 +31,7 @@ }, "utils_nfcore_pipeline": { "branch": "master", - "git_sha": "5caf7640a9ef1d18d765d55339be751bb0969dfa", + "git_sha": "92de218a329bfc9a9033116eb5f65fd270e72ba3", "installed_by": ["subworkflows"] }, "utils_nfvalidation_plugin": { diff --git a/modules/nf-core/fastqc/main.nf b/modules/nf-core/fastqc/main.nf index 9e19a74..d79f1c8 100644 --- a/modules/nf-core/fastqc/main.nf +++ b/modules/nf-core/fastqc/main.nf @@ -25,6 +25,11 @@ process FASTQC { 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(' ') + + def memory_in_mb = MemoryUnit.of("${task.memory}").toUnit('MB') + // FastQC memory value allowed range (100 - 10000) + def fastqc_memory = memory_in_mb > 10000 ? 10000 : (memory_in_mb < 100 ? 100 : memory_in_mb) + """ printf "%s %s\\n" $rename_to | while read old_name new_name; do [ -f "\${new_name}" ] || ln -s \$old_name \$new_name @@ -33,6 +38,7 @@ process FASTQC { fastqc \\ $args \\ --threads $task.cpus \\ + --memory $fastqc_memory \\ $renamed_files cat <<-END_VERSIONS > versions.yml diff --git a/modules/nf-core/seqtk/trim/environment.yml b/modules/nf-core/seqtk/trim/environment.yml new file mode 100644 index 0000000..389a3a9 --- /dev/null +++ b/modules/nf-core/seqtk/trim/environment.yml @@ -0,0 +1,7 @@ +name: seqtk_trim +channels: + - conda-forge + - bioconda + - defaults +dependencies: + - bioconda::seqtk=1.4 diff --git a/modules/nf-core/seqtk/trim/main.nf b/modules/nf-core/seqtk/trim/main.nf new file mode 100644 index 0000000..0f7e4d7 --- /dev/null +++ b/modules/nf-core/seqtk/trim/main.nf @@ -0,0 +1,38 @@ +process SEQTK_TRIM { + tag "$meta.id" + label 'process_low' + + conda "${moduleDir}/environment.yml" + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/seqtk:1.4--he4a0461_1' : + 'biocontainers/seqtk:1.4--he4a0461_1' }" + + input: + tuple val(meta), path(reads) + + output: + tuple val(meta), path("*.fastq.gz"), emit: reads + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}" + """ + printf "%s\\n" $reads | while read f; + do + seqtk \\ + trimfq \\ + $args \\ + \$f \\ + | gzip --no-name > ${prefix}_\$(basename \$f) + done + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + seqtk: \$(echo \$(seqtk 2>&1) | sed 's/^.*Version: //; s/ .*\$//') + END_VERSIONS + """ +} diff --git a/modules/nf-core/seqtk/trim/meta.yml b/modules/nf-core/seqtk/trim/meta.yml new file mode 100644 index 0000000..1177057 --- /dev/null +++ b/modules/nf-core/seqtk/trim/meta.yml @@ -0,0 +1,44 @@ +--- +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/yaml-schema.json +name: seqtk_trim +description: Trim low quality bases from FastQ files +keywords: + - trimfq + - fastq + - seqtk +tools: + - "seqtk": + description: "Seqtk is a fast and lightweight tool for processing sequences in the FASTA or FASTQ format" + homepage: https://github.com/lh3/seqtk + documentation: https://docs.csc.fi/apps/seqtk/ + tool_dev_url: https://github.com/lh3/seqtk + licence: ["MIT"] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - reads: + type: file + description: List of input FastQ files + pattern: "*.{fastq.gz}" + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" + - reads: + type: file + description: Filtered FastQ files + pattern: "*.{fastq.gz}" + +authors: + - "@laramiellindsey" diff --git a/modules/nf-core/seqtk/trim/tests/main.nf.test b/modules/nf-core/seqtk/trim/tests/main.nf.test new file mode 100644 index 0000000..d99b6b2 --- /dev/null +++ b/modules/nf-core/seqtk/trim/tests/main.nf.test @@ -0,0 +1,65 @@ +nextflow_process { + + name "Test Process SEQTK_TRIM" + script "modules/nf-core/seqtk/trim/main.nf" + process "SEQTK_TRIM" + + tag "modules" + tag "modules_nfcore" + tag "seqtk" + tag "seqtk/trim" + + test("Single-end") { + + when { + params { + outdir = $outputDir + } + process { + """ + input[0] = [ + [ id:'test', single_end:true ], // meta map + file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) + ] + """ + } + } + + then { + assertAll ( + { assert process.success }, + { assert snapshot(process.out).match()} + ) + } + + } + +test("Paired-end") { + + when { + params { + outdir = $outputDir + } + process { + """ + input[0] = [ + [ id:'test', single_end:false ], // meta map + [ + file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true), + file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) + ] + ] + """ + } + } + + then { + assertAll ( + { assert process.success }, + { assert snapshot(process.out).match()} + ) + } + + } + +} diff --git a/modules/nf-core/seqtk/trim/tests/main.nf.test.snap b/modules/nf-core/seqtk/trim/tests/main.nf.test.snap new file mode 100644 index 0000000..da181dc --- /dev/null +++ b/modules/nf-core/seqtk/trim/tests/main.nf.test.snap @@ -0,0 +1,78 @@ +{ + "Single-end": { + "content": [ + { + "0": [ + [ + { + "id": "test", + "single_end": true + }, + "test_test_1.fastq.gz:md5,4161df271f9bfcd25d5845a1e220dbec" + ] + ], + "1": [ + "versions.yml:md5,d061ca0231d089b087e22d2001cd7c32" + ], + "reads": [ + [ + { + "id": "test", + "single_end": true + }, + "test_test_1.fastq.gz:md5,4161df271f9bfcd25d5845a1e220dbec" + ] + ], + "versions": [ + "versions.yml:md5,d061ca0231d089b087e22d2001cd7c32" + ] + } + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-05-03T06:10:55.544977" + }, + "Paired-end": { + "content": [ + { + "0": [ + [ + { + "id": "test", + "single_end": false + }, + [ + "test_test_1.fastq.gz:md5,4161df271f9bfcd25d5845a1e220dbec", + "test_test_2.fastq.gz:md5,2ebae722295ea66d84075a3b042e2b42" + ] + ] + ], + "1": [ + "versions.yml:md5,d061ca0231d089b087e22d2001cd7c32" + ], + "reads": [ + [ + { + "id": "test", + "single_end": false + }, + [ + "test_test_1.fastq.gz:md5,4161df271f9bfcd25d5845a1e220dbec", + "test_test_2.fastq.gz:md5,2ebae722295ea66d84075a3b042e2b42" + ] + ] + ], + "versions": [ + "versions.yml:md5,d061ca0231d089b087e22d2001cd7c32" + ] + } + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-05-03T06:11:38.487227" + } +} \ No newline at end of file diff --git a/modules/nf-core/seqtk/trim/tests/tags.yml b/modules/nf-core/seqtk/trim/tests/tags.yml new file mode 100644 index 0000000..250a138 --- /dev/null +++ b/modules/nf-core/seqtk/trim/tests/tags.yml @@ -0,0 +1,2 @@ +seqtk/trim: + - "modules/nf-core/seqtk/trim/**" diff --git a/nextflow.config b/nextflow.config index d32d68c..d42b49e 100644 --- a/nextflow.config +++ b/nextflow.config @@ -9,44 +9,48 @@ // Global default params, used in configs params { - // TODO nf-core: Specify your pipeline's command line flags // Input options - input = null + input = null + // References genome = null igenomes_base = 's3://ngi-igenomes/igenomes/' igenomes_ignore = false - fasta = null// MultiQC options + + // MultiQC options multiqc_config = null multiqc_title = null multiqc_logo = null max_multiqc_email_size = '25.MB' multiqc_methods_description = null + // Trimming + skip_trim = false + // Boilerplate options - outdir = null - publish_dir_mode = 'copy' - email = null - email_on_fail = null - plaintext_email = false - monochrome_logs = false - hook_url = null - help = false - version = false + outdir = null + publish_dir_mode = 'copy' + email = null + email_on_fail = null + plaintext_email = false + monochrome_logs = false + hook_url = null + help = false + version = false + pipelines_testdata_base_path = 'https://raw.githubusercontent.com/nf-core/test-datasets/' // Config options - config_profile_name = null - config_profile_description = null - custom_config_version = 'master' - custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}" - config_profile_contact = null - config_profile_url = null + config_profile_name = null + config_profile_description = null + custom_config_version = 'master' + custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}" + config_profile_contact = null + config_profile_url = null // Max resource options - // Defaults only, expecting to be overwritten - max_memory = '128.GB' - max_cpus = 16 - max_time = '240.h' + max_memory = '48.GB' + max_cpus = 16 + max_time = '1.h' // Schema validation default options validationFailUnrecognisedParams = false @@ -68,103 +72,109 @@ try { } // Load nf-core/demo custom profiles from different institutions. -// Warning: Uncomment only if a pipeline-specific institutional config already exists on nf-core/configs! -// try { -// includeConfig "${params.custom_config_base}/pipeline/demo.config" -// } catch (Exception e) { -// System.err.println("WARNING: Could not load nf-core/config/demo profiles: ${params.custom_config_base}/pipeline/demo.config") -// } +try { + includeConfig "${params.custom_config_base}/pipeline/demo.config" +} catch (Exception e) { + System.err.println("WARNING: Could not load nf-core/config/demo profiles: ${params.custom_config_base}/pipeline/demo.config") +} profiles { debug { - dumpHashes = true - process.beforeScript = 'echo $HOSTNAME' - cleanup = false + dumpHashes = true + process.beforeScript = 'echo $HOSTNAME' + cleanup = false nextflow.enable.configProcessNamesValidation = true } conda { - conda.enabled = true - docker.enabled = false - singularity.enabled = false - podman.enabled = false - shifter.enabled = false - charliecloud.enabled = false - channels = ['conda-forge', 'bioconda', 'defaults'] - apptainer.enabled = false + conda.enabled = true + docker.enabled = false + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false + conda.channels = ['conda-forge', 'bioconda', 'defaults'] + apptainer.enabled = false } mamba { - conda.enabled = true - conda.useMamba = true - docker.enabled = false - singularity.enabled = false - podman.enabled = false - shifter.enabled = false - charliecloud.enabled = false - apptainer.enabled = false + 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 - conda.enabled = false - singularity.enabled = false - podman.enabled = false - shifter.enabled = false - charliecloud.enabled = false - apptainer.enabled = false - docker.runOptions = '-u $(id -u):$(id -g)' + docker.enabled = true + conda.enabled = false + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false + apptainer.enabled = false + docker.runOptions = '-u $(id -u):$(id -g)' } arm { - docker.runOptions = '-u $(id -u):$(id -g) --platform=linux/amd64' + docker.runOptions = '-u $(id -u):$(id -g) --platform=linux/amd64' } singularity { - singularity.enabled = true - singularity.autoMounts = true - conda.enabled = false - docker.enabled = false - podman.enabled = false - shifter.enabled = false - charliecloud.enabled = false - apptainer.enabled = false + singularity.enabled = true + singularity.autoMounts = true + conda.enabled = false + docker.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false + apptainer.enabled = false } podman { - podman.enabled = true - conda.enabled = false - docker.enabled = false - singularity.enabled = false - shifter.enabled = false - charliecloud.enabled = false - apptainer.enabled = false + podman.enabled = true + conda.enabled = false + docker.enabled = false + singularity.enabled = false + shifter.enabled = false + charliecloud.enabled = false + apptainer.enabled = false } shifter { - shifter.enabled = true - conda.enabled = false - docker.enabled = false - singularity.enabled = false - podman.enabled = false - charliecloud.enabled = false - apptainer.enabled = false + 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 + charliecloud.enabled = true + conda.enabled = false + docker.enabled = false + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + apptainer.enabled = false } apptainer { - apptainer.enabled = true - apptainer.autoMounts = true - conda.enabled = false - docker.enabled = false - singularity.enabled = false - podman.enabled = false - shifter.enabled = false - charliecloud.enabled = false + apptainer.enabled = true + apptainer.autoMounts = true + conda.enabled = false + docker.enabled = false + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false + } + wave { + apptainer.ociAutoPull = true + singularity.ociAutoPull = true + wave.enabled = true + wave.freeze = true + wave.strategy = 'conda,container' } gitpod { - executor.name = 'local' - executor.cpus = 4 - executor.memory = 8.GB + executor.name = 'local' + executor.cpus = 4 + executor.memory = 8.GB } test { includeConfig 'conf/test.config' } test_full { includeConfig 'conf/test_full.config' } @@ -231,7 +241,7 @@ manifest { description = """An nf-core demo pipeline""" mainScript = 'main.nf' nextflowVersion = '!>=23.04.0' - version = '1.0dev' + version = '1.0.0' doi = '' } diff --git a/nextflow_schema.json b/nextflow_schema.json index 2696051..005be41 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -74,6 +74,20 @@ } } }, + "process_skipping_options": { + "title": "Process skipping options", + "type": "object", + "description": "Options to skip various steps within the workflow.", + "default": "", + "fa_icon": "fas fa-forward", + "properties": { + "skip_trim": { + "type": "boolean", + "description": "Skip trimming fastq files with seqtk", + "fa_icon": "fas fa-chevron-circle-right" + } + } + }, "institutional_config_options": { "title": "Institutional config options", "type": "object", @@ -140,7 +154,7 @@ "max_memory": { "type": "string", "description": "Maximum amount of memory that can be requested for any single job.", - "default": "128.GB", + "default": "48.GB", "fa_icon": "fas fa-memory", "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$", "hidden": true, @@ -149,7 +163,7 @@ "max_time": { "type": "string", "description": "Maximum amount of time that can be requested for any single job.", - "default": "240.h", + "default": "1.h", "fa_icon": "far fa-clock", "pattern": "^(\\d+\\.?\\s*(s|m|h|d|day)\\s*)+$", "hidden": true, @@ -216,7 +230,7 @@ "hook_url": { "type": "string", "description": "Incoming hook URL for messaging service", - "fa_icon": "fas fa-people-group", + "fa_icon": "fas fa-broadcast-tower", "help_text": "Incoming hook URL for messaging service. Currently, MS Teams and Slack are supported.", "hidden": true }, @@ -265,6 +279,13 @@ "description": "Validation of parameters in lenient more.", "hidden": true, "help_text": "Allows string values that are parseable as numbers or booleans. For further information see [JSONSchema docs](https://github.com/everit-org/json-schema#lenient-mode)." + }, + "pipelines_testdata_base_path": { + "type": "string", + "fa_icon": "far fa-check-circle", + "description": "Base URL or local path to location of pipeline test dataset files", + "default": "https://raw.githubusercontent.com/nf-core/test-datasets/", + "hidden": true } } } @@ -276,6 +297,9 @@ { "$ref": "#/definitions/reference_genome_options" }, + { + "$ref": "#/definitions/process_skipping_options" + }, { "$ref": "#/definitions/institutional_config_options" }, diff --git a/pyproject.toml b/pyproject.toml deleted file mode 100644 index 5611062..0000000 --- a/pyproject.toml +++ /dev/null @@ -1,15 +0,0 @@ -# Config file for Python. Mostly used to configure linting of bin/*.py with Ruff. -# Should be kept the same as nf-core/tools to avoid fighting with template synchronisation. -[tool.ruff] -line-length = 120 -target-version = "py38" -cache-dir = "~/.cache/ruff" - -[tool.ruff.lint] -select = ["I", "E1", "E4", "E7", "E9", "F", "UP", "N"] - -[tool.ruff.lint.isort] -known-first-party = ["nf_core"] - -[tool.ruff.lint.per-file-ignores] -"__init__.py" = ["E402", "F401"] diff --git a/subworkflows/local/utils_nfcore_demo_pipeline/main.nf b/subworkflows/local/utils_nfcore_demo_pipeline/main.nf index 9457ca2..453a524 100644 --- a/subworkflows/local/utils_nfcore_demo_pipeline/main.nf +++ b/subworkflows/local/utils_nfcore_demo_pipeline/main.nf @@ -140,6 +140,10 @@ workflow PIPELINE_COMPLETION { imNotification(summary_params, hook_url) } } + + workflow.onError { + log.error "Pipeline failed. Please refer to troubleshooting docs: https://nf-co.re/docs/usage/troubleshooting" + } } /* @@ -198,9 +202,7 @@ def genomeExistsError() { // Generate methods description for MultiQC // def toolCitationText() { - // TODO nf-core: Optionally add in-text citation tools to this list. - // Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "Tool (Foo et al. 2023)" : "", - // Uncomment function in methodsDescriptionText to render in MultiQC report + def citation_text = [ "Tools used in the workflow included:", "FastQC (Andrews 2010),", @@ -212,12 +214,11 @@ def toolCitationText() { } def toolBibliographyText() { - // TODO nf-core: Optionally add bibliographic entries to this list. - // Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "
  • Author (2023) Pub name, Journal, DOI
    • " : "", // Uncomment function in methodsDescriptionText to render in MultiQC report def reference_text = [ "
  • Andrews S, (2010) FastQC, URL: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/).
    • ", - "
  • Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics , 32(19), 3047–3048. doi: /10.1093/bioinformatics/btw354
    • " + "
  • Chen, S., Zhou, Y., Chen, Y., & Gu, J. (2018). fastp: an ultra-fast all-in-one FASTQ preprocessor. Bioinformatics , 34(17), i884-i890. doi: /10.1093/bioinformatics/bty560
    • ", + "
  • Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics , 32(19), 3047-3048. doi: /10.1093/bioinformatics/btw354
    • " ].join(' ').trim() return reference_text @@ -230,16 +231,24 @@ def methodsDescriptionText(mqc_methods_yaml) { meta["manifest_map"] = workflow.manifest.toMap() // Pipeline DOI - meta["doi_text"] = meta.manifest_map.doi ? "(doi: ${meta.manifest_map.doi})" : "" - meta["nodoi_text"] = meta.manifest_map.doi ? "": "
  • If available, make sure to update the text to include the Zenodo DOI of version of the pipeline used.
    • " + if (meta.manifest_map.doi) { + // Using a loop to handle multiple DOIs + // Removing `https://doi.org/` to handle pipelines using DOIs vs DOI resolvers + // Removing ` ` since the manifest.doi is a string and not a proper list + def temp_doi_ref = "" + String[] manifest_doi = meta.manifest_map.doi.tokenize(",") + for (String doi_ref: manifest_doi) temp_doi_ref += "(doi: ${doi_ref.replace("https://doi.org/", "").replace(" ", "")}), " + meta["doi_text"] = temp_doi_ref.substring(0, temp_doi_ref.length() - 2) + } else meta["doi_text"] = "" + meta["nodoi_text"] = meta.manifest_map.doi ? "" : "
  • If available, make sure to update the text to include the Zenodo DOI of version of the pipeline used.
    • " // Tool references meta["tool_citations"] = "" meta["tool_bibliography"] = "" - // TODO nf-core: Only uncomment below if logic in toolCitationText/toolBibliographyText has been filled! - // meta["tool_citations"] = toolCitationText().replaceAll(", \\.", ".").replaceAll("\\. \\.", ".").replaceAll(", \\.", ".") - // meta["tool_bibliography"] = toolBibliographyText() + // nf-core: Only uncomment below if logic in toolCitationText/toolBibliographyText has been filled! + meta["tool_citations"] = toolCitationText().replaceAll(", \\.", ".").replaceAll("\\. \\.", ".").replaceAll(", \\.", ".") + meta["tool_bibliography"] = toolBibliographyText() def methods_text = mqc_methods_yaml.text diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/main.nf b/subworkflows/nf-core/utils_nfcore_pipeline/main.nf index a8b55d6..14558c3 100644 --- a/subworkflows/nf-core/utils_nfcore_pipeline/main.nf +++ b/subworkflows/nf-core/utils_nfcore_pipeline/main.nf @@ -65,9 +65,15 @@ def checkProfileProvided(nextflow_cli_args) { // Citation string for pipeline // def workflowCitation() { + def temp_doi_ref = "" + String[] manifest_doi = workflow.manifest.doi.tokenize(",") + // Using a loop to handle multiple DOIs + // Removing `https://doi.org/` to handle pipelines using DOIs vs DOI resolvers + // Removing ` ` since the manifest.doi is a string and not a proper list + for (String doi_ref: manifest_doi) temp_doi_ref += " https://doi.org/${doi_ref.replace('https://doi.org/', '').replace(' ', '')}\n" return "If you use ${workflow.manifest.name} for your analysis please cite:\n\n" + "* The pipeline\n" + - " ${workflow.manifest.doi}\n\n" + + temp_doi_ref + "\n" + "* The nf-core framework\n" + " https://doi.org/10.1038/s41587-020-0439-x\n\n" + "* Software dependencies\n" + diff --git a/workflows/demo.nf b/workflows/demo.nf index 4881298..80b1246 100644 --- a/workflows/demo.nf +++ b/workflows/demo.nf @@ -5,6 +5,7 @@ */ include { FASTQC } from '../modules/nf-core/fastqc/main' +include { SEQTK_TRIM } from '../modules/nf-core/seqtk/trim/main' include { MULTIQC } from '../modules/nf-core/multiqc/main' include { paramsSummaryMap } from 'plugin/nf-validation' include { paramsSummaryMultiqc } from '../subworkflows/nf-core/utils_nfcore_pipeline' @@ -28,7 +29,7 @@ workflow DEMO { ch_multiqc_files = Channel.empty() // - // MODULE: Run FastQC + // MODULE: Run FASTQC // FASTQC ( ch_samplesheet @@ -36,26 +37,59 @@ workflow DEMO { ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}) ch_versions = ch_versions.mix(FASTQC.out.versions.first()) + // + // MODULE: Run SEQTK_TRIM + // + if (!params.skip_trim) { + SEQTK_TRIM ( + ch_samplesheet + ) + ch_trimmed = SEQTK_TRIM.out.reads + ch_versions = ch_versions.mix(SEQTK_TRIM.out.versions.first()) + } + // // Collate and save software versions // softwareVersionsToYAML(ch_versions) - .collectFile(storeDir: "${params.outdir}/pipeline_info", name: 'nf_core_pipeline_software_mqc_versions.yml', sort: true, newLine: true) - .set { ch_collated_versions } + .collectFile( + storeDir: "${params.outdir}/pipeline_info", + name: 'nf_core_pipeline_software_mqc_versions.yml', + sort: true, + newLine: true + ).set { ch_collated_versions } // - // MODULE: MultiQC + // MODULE: MULTIQC // - ch_multiqc_config = Channel.fromPath("$projectDir/assets/multiqc_config.yml", checkIfExists: true) - ch_multiqc_custom_config = params.multiqc_config ? Channel.fromPath(params.multiqc_config, checkIfExists: true) : Channel.empty() - ch_multiqc_logo = params.multiqc_logo ? Channel.fromPath(params.multiqc_logo, checkIfExists: true) : Channel.empty() - summary_params = paramsSummaryMap(workflow, parameters_schema: "nextflow_schema.json") - ch_workflow_summary = Channel.value(paramsSummaryMultiqc(summary_params)) - ch_multiqc_custom_methods_description = params.multiqc_methods_description ? file(params.multiqc_methods_description, checkIfExists: true) : file("$projectDir/assets/methods_description_template.yml", checkIfExists: true) - ch_methods_description = Channel.value(methodsDescriptionText(ch_multiqc_custom_methods_description)) - ch_multiqc_files = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml')) - ch_multiqc_files = ch_multiqc_files.mix(ch_collated_versions) - ch_multiqc_files = ch_multiqc_files.mix(ch_methods_description.collectFile(name: 'methods_description_mqc.yaml', sort: false)) + ch_multiqc_config = Channel.fromPath( + "$projectDir/assets/multiqc_config.yml", checkIfExists: true) + ch_multiqc_custom_config = params.multiqc_config ? + Channel.fromPath(params.multiqc_config, checkIfExists: true) : + Channel.empty() + ch_multiqc_logo = params.multiqc_logo ? + Channel.fromPath(params.multiqc_logo, checkIfExists: true) : + Channel.empty() + + summary_params = paramsSummaryMap( + workflow, parameters_schema: "nextflow_schema.json") + ch_workflow_summary = Channel.value(paramsSummaryMultiqc(summary_params)) + + ch_multiqc_custom_methods_description = params.multiqc_methods_description ? + file(params.multiqc_methods_description, checkIfExists: true) : + file("$projectDir/assets/methods_description_template.yml", checkIfExists: true) + ch_methods_description = Channel.value( + methodsDescriptionText(ch_multiqc_custom_methods_description)) + + ch_multiqc_files = ch_multiqc_files.mix( + ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml')) + ch_multiqc_files = ch_multiqc_files.mix(ch_collated_versions) + ch_multiqc_files = ch_multiqc_files.mix( + ch_methods_description.collectFile( + name: 'methods_description_mqc.yaml', + sort: true + ) + ) MULTIQC ( ch_multiqc_files.collect(),