From fc66f94b18cecf476e7fe2a5298724315009ad01 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Tue, 25 Apr 2023 11:58:07 +0100 Subject: [PATCH 01/36] Bump pipeline version to 3.12.0dev --- CHANGELOG.md | 4 ++++ nextflow.config | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 71db55899..efa574de4 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,6 +3,10 @@ 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). +## [Unpublished Version / DEV] + +### Enhancements & fixes + ## [[3.11.2](https://github.com/nf-core/rnaseq/releases/tag/3.11.2)] - 2023-04-25 ### Credits diff --git a/nextflow.config b/nextflow.config index 2774ee936..f851618cf 100644 --- a/nextflow.config +++ b/nextflow.config @@ -261,7 +261,7 @@ manifest { description = """RNA sequencing analysis pipeline for gene/isoform quantification and extensive quality control.""" mainScript = 'main.nf' nextflowVersion = '!>=22.10.1' - version = '3.11.2' + version = '3.12.0dev' doi = 'https://doi.org/10.5281/zenodo.1400710' } From 46f8bb22469b0d07d36a860b0ab50eb6f8e34d87 Mon Sep 17 00:00:00 2001 From: nf-core-bot Date: Fri, 28 Apr 2023 14:25:57 +0000 Subject: [PATCH 02/36] Template update for nf-core/tools version 2.8 --- .editorconfig | 2 +- .github/ISSUE_TEMPLATE/bug_report.yml | 2 +- .github/PULL_REQUEST_TEMPLATE.md | 3 +- .github/workflows/awsfulltest.yml | 2 +- .github/workflows/awstest.yml | 2 +- .github/workflows/branch.yml | 2 +- .github/workflows/clean-up.yml | 24 ++++ .github/workflows/linting.yml | 2 +- .pre-commit-config.yaml | 5 + CHANGELOG.md | 2 +- README.md | 74 ++++++---- bin/check_samplesheet.py | 3 - conf/base.config | 2 +- conf/igenomes.config | 8 ++ conf/test_full.config | 2 + docs/usage.md | 130 +++++------------- lib/NfcoreSchema.groovy | 4 +- lib/WorkflowMain.groovy | 13 +- lib/WorkflowRnaseq.groovy | 12 +- main.nf | 1 - modules.json | 4 +- modules/local/samplesheet_check.nf | 2 +- .../custom/dumpsoftwareversions/main.nf | 6 +- .../custom/dumpsoftwareversions/meta.yml | 2 + modules/nf-core/multiqc/main.nf | 6 +- modules/nf-core/multiqc/meta.yml | 3 +- nextflow.config | 31 ++++- tower.yml | 5 + 28 files changed, 195 insertions(+), 159 deletions(-) create mode 100644 .github/workflows/clean-up.yml create mode 100644 .pre-commit-config.yaml create mode 100644 tower.yml diff --git a/.editorconfig b/.editorconfig index b78de6e65..b6b319077 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/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml index 49339ef78..3ce613833 100644 --- a/.github/ISSUE_TEMPLATE/bug_report.yml +++ b/.github/ISSUE_TEMPLATE/bug_report.yml @@ -45,6 +45,6 @@ body: * 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/rnaseq _(eg. 1.1, 1.5, 1.8.2)_ diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index 2a1a8a971..fdc75549e 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/rnas - [ ] 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/rnaseq/tree/master/.github/CONTRIBUTING.md)- [ ] If necessary, also make a PR on the nf-core/rnaseq _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/rnaseq/tree/master/.github/CONTRIBUTING.md) +- [ ] If necessary, also make a PR on the nf-core/rnaseq _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 2118341bb..2e6baf508 100644 --- a/.github/workflows/awsfulltest.yml +++ b/.github/workflows/awsfulltest.yml @@ -14,7 +14,7 @@ jobs: runs-on: ubuntu-latest steps: - name: Launch workflow via tower - uses: nf-core/tower-action@v3 + uses: seqeralabs/action-tower-launch@v1 # TODO nf-core: You can customise AWS full pipeline tests as required # Add full size test data (but still relatively small datasets for few samples) # on the `test_full.config` test runs with only one set of parameters diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml index d2b1b704e..9ce9dacb5 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 }} diff --git a/.github/workflows/branch.yml b/.github/workflows/branch.yml index fa15c1d59..d694b7b67 100644 --- a/.github/workflows/branch.yml +++ b/.github/workflows/branch.yml @@ -13,7 +13,7 @@ jobs: - name: Check PRs if: github.repository == 'nf-core/rnaseq' run: | - { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/rnaseq ]] && [[ $GITHUB_HEAD_REF = "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]] + { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/rnaseq ]] && [[ $GITHUB_HEAD_REF == "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]] # If the above check failed, post a comment on the PR explaining the failure # NOTE - this doesn't currently work if the PR is coming from a fork, due to limitations in GitHub actions secrets diff --git a/.github/workflows/clean-up.yml b/.github/workflows/clean-up.yml new file mode 100644 index 000000000..694e90ecb --- /dev/null +++ b/.github/workflows/clean-up.yml @@ -0,0 +1,24 @@ +name: "Close user-tagged issues and PRs" +on: + schedule: + - cron: "0 0 * * 0" # Once a week + +jobs: + clean-up: + runs-on: ubuntu-latest + permissions: + issues: write + pull-requests: write + steps: + - uses: actions/stale@v7 + with: + stale-issue-message: "This issue has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor. Remove stale label or add a comment otherwise this issue will be closed in 20 days." + stale-pr-message: "This PR has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor. Remove stale label or add a comment if it is still useful." + close-issue-message: "This issue was closed because it has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor and then staled for 20 days with no activity." + days-before-stale: 30 + days-before-close: 20 + days-before-pr-close: -1 + any-of-labels: "awaiting-changes,awaiting-feedback" + exempt-issue-labels: "WIP" + exempt-pr-labels: "WIP" + repo-token: "${{ secrets.GITHUB_TOKEN }}" diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index 858d622ef..888cb4bc3 100644 --- a/.github/workflows/linting.yml +++ b/.github/workflows/linting.yml @@ -78,7 +78,7 @@ jobs: - uses: actions/setup-python@v4 with: - python-version: "3.7" + python-version: "3.8" architecture: "x64" - name: Install dependencies diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml new file mode 100644 index 000000000..0c31cdb99 --- /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/CHANGELOG.md b/CHANGELOG.md index a1ccb2ad5..31a919f72 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,7 +3,7 @@ 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). -## v3.10dev - [date] +## v3.12.0dev - [date] Initial release of nf-core/rnaseq, created with the [nf-core](https://nf-co.re/) template. diff --git a/README.md b/README.md index 16a2f98ee..f86ed8d60 100644 --- a/README.md +++ b/README.md @@ -8,57 +8,71 @@ [![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/rnaseq) -[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23rnaseq-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/rnaseq)[![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%23rnaseq-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/rnaseq)[![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/rnaseq** is a bioinformatics pipeline that ... -**nf-core/rnaseq** is a bioinformatics best-practice analysis pipeline for RNA sequencing analysis pipeline for gene/isoform quantification and extensive quality control.. - -The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. It uses Docker/Singularity containers making installation trivial and results highly reproducible. The [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html) implementation of this pipeline uses one container per process which makes it much easier to maintain and update software dependencies. Where possible, these processes have been submitted to and installed from [nf-core/modules](https://github.com/nf-core/modules) in order to make them available to all nf-core pipelines, and to everyone within the Nextflow community! - - - -On release, automated continuous integration tests run the pipeline on a full-sized dataset on the AWS cloud infrastructure. This ensures that the pipeline runs on AWS, has sensible resource allocation defaults set to run on real-world datasets, and permits the persistent storage of results to benchmark between pipeline releases and other analysis sources.The results obtained from the full-sized test can be viewed on the [nf-core website](https://nf-co.re/rnaseq/results). - -## Pipeline summary + + 1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)) 2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/)) -## Quick Start +## 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. + + - 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. +Now, you can run the pipeline using: - > - 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! +```bash +nextflow run nf-core/rnaseq \ + -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). - ```bash - nextflow run nf-core/rnaseq --input samplesheet.csv --outdir --genome GRCh37 -profile - ``` +For more details, please refer to the [usage documentation](https://nf-co.re/rnaseq/usage) and the [parameter documentation](https://nf-co.re/rnaseq/parameters). -## Documentation +## Pipeline output -The nf-core/rnaseq pipeline comes with documentation about the pipeline [usage](https://nf-co.re/rnaseq/usage), [parameters](https://nf-co.re/rnaseq/parameters) and [output](https://nf-co.re/rnaseq/output). +To see the the results of a test run with a full size dataset refer to the [results](https://nf-co.re/rnaseq/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/rnaseq/output). ## Credits diff --git a/bin/check_samplesheet.py b/bin/check_samplesheet.py index 11b155723..4a758fe00 100755 --- a/bin/check_samplesheet.py +++ b/bin/check_samplesheet.py @@ -158,9 +158,6 @@ def sniff_format(handle): peek = read_head(handle) handle.seek(0) sniffer = csv.Sniffer() - if not sniffer.has_header(peek): - logger.critical("The given sample sheet does not appear to contain a header.") - sys.exit(1) dialect = sniffer.sniff(peek) return dialect diff --git a/conf/base.config b/conf/base.config index 6e7890045..a034808b0 100644 --- a/conf/base.config +++ b/conf/base.config @@ -15,7 +15,7 @@ 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 7a1b3ac6d..3f1143775 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/test_full.config b/conf/test_full.config index 505808b89..6d70c5c8e 100644 --- a/conf/test_full.config +++ b/conf/test_full.config @@ -10,6 +10,8 @@ ---------------------------------------------------------------------------------------- */ +cleanup = true + params { config_profile_name = 'Full test profile' config_profile_description = 'Full test dataset to check pipeline function' diff --git a/docs/usage.md b/docs/usage.md index 7687a1ef4..1e45b8d78 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -71,6 +71,29 @@ 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/rnaseq -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: @@ -87,6 +110,10 @@ First, go to the [nf-core/rnaseq releases page](https://github.com/nf-core/rnase This version number will be logged in reports when you run the pipeline, so that you'll know what you used when you look back in the future. For example, at the bottom of the MultiQC reports. +To further assist in 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. + ## Core Nextflow arguments > **NB:** These options are part of Nextflow and use a _single_ hyphen (pipeline parameters use a double-hyphen). @@ -95,7 +122,7 @@ This version number will be logged in reports when you run the pipeline, so that Use this parameter to choose a configuration profile. Profiles can give configuration presets for different compute environments. -Several generic profiles are bundled with the pipeline which instruct the pipeline to use software packaged using different methods (Docker, Singularity, Podman, Shifter, Charliecloud, Conda) - see below. +Several generic profiles are bundled with the pipeline which instruct the pipeline to use software packaged using different methods (Docker, Singularity, Podman, Shifter, Charliecloud, Apptainer, Conda) - see below. > We highly recommend the use of Docker or Singularity containers for full pipeline reproducibility, however when this is not possible, Conda is also supported. @@ -119,8 +146,10 @@ If `-profile` is not specified, the pipeline will run locally and expect all sof - A generic configuration profile to be used with [Shifter](https://nersc.gitlab.io/development/shifter/how-to-use/) - `charliecloud` - A generic configuration profile to be used with [Charliecloud](https://hpc.github.io/charliecloud/) +- `apptainer` + - A generic configuration profile to be used with [Apptainer](https://apptainer.org/) - `conda` - - A generic configuration profile to be used with [Conda](https://conda.io/docs/). Please only use Conda as a last resort i.e. when it's not possible to run the pipeline with Docker, Singularity, Podman, Shifter or Charliecloud. + - A generic configuration profile to be used with [Conda](https://conda.io/docs/). Please only use Conda as a last resort i.e. when it's not possible to run the pipeline with Docker, Singularity, Podman, Shifter, Charliecloud, or Apptainer. ### `-resume` @@ -138,102 +167,19 @@ 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: - -```console -[62/149eb0] NOTE: Process `NFCORE_RNASEQ:RNASEQ:ALIGN_STAR:STAR_ALIGN (WT_REP1)` terminated with an error exit status (137) -- Execution is retried (1) -Error executing process > 'NFCORE_RNASEQ:RNASEQ:ALIGN_STAR:STAR_ALIGN (WT_REP1)' - -Caused by: - Process `NFCORE_RNASEQ:RNASEQ:ALIGN_STAR:STAR_ALIGN (WT_REP1)` terminated with an error exit status (137) - -Command executed: - STAR \ - --genomeDir star \ - --readFilesIn WT_REP1_trimmed.fq.gz \ - --runThreadN 2 \ - --outFileNamePrefix WT_REP1. \ - - -Command exit status: - 137 - -Command output: - (empty) - -Command error: - .command.sh: line 9: 30 Killed STAR --genomeDir star --readFilesIn WT_REP1_trimmed.fq.gz --runThreadN 2 --outFileNamePrefix WT_REP1. -Work dir: - /home/pipelinetest/work/9d/172ca5881234073e8d76f2a19c88fb - -Tip: you can replicate the issue by changing to the process work dir and entering the command `bash .command.run` -``` - -#### For beginners - -A first step to bypass this error, you could try to increase the amount of CPUs, memory, and time for the whole pipeline. Therefor you can try to increase the resource for the parameters `--max_cpus`, `--max_memory`, and `--max_time`. Based on the error above, you have to increase the amount of memory. Therefore you can go to the [parameter documentation of rnaseq](https://nf-co.re/rnaseq/3.9/parameters) and scroll down to the `show hidden parameter` button to get the default value for `--max_memory`. In this case 128GB, you than can try to run your pipeline again with `--max_memory 200GB -resume` to skip all process, that were already calculated. If you can not increase the resource of the complete pipeline, you can try to adapt the resource for a single process as mentioned below. - -#### Advanced option on process level - -To bypass this error you would need to find exactly which resources are set by the `STAR_ALIGN` process. The quickest way is to search for `process STAR_ALIGN` in the [nf-core/rnaseq Github repo](https://github.com/nf-core/rnaseq/search?q=process+STAR_ALIGN). -We have standardised the structure of Nextflow DSL2 pipelines such that all module files will be present in the `modules/` directory and so, based on the search results, the file we want is `modules/nf-core/star/align/main.nf`. -If you click on the link to that file you will notice that there is a `label` directive at the top of the module that is set to [`label process_high`](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/modules/nf-core/software/star/align/main.nf#L9). -The [Nextflow `label`](https://www.nextflow.io/docs/latest/process.html#label) directive allows us to organise workflow processes in separate groups which can be referenced in a configuration file to select and configure subset of processes having similar computing requirements. -The default values for the `process_high` label are set in the pipeline's [`base.config`](https://github.com/nf-core/rnaseq/blob/4c27ef5610c87db00c3c5a3eed10b1d161abf575/conf/base.config#L33-L37) which in this case is defined as 72GB. -Providing you haven't set any other standard nf-core parameters to **cap** the [maximum resources](https://nf-co.re/usage/configuration#max-resources) used by the pipeline then we can try and bypass the `STAR_ALIGN` process failure by creating a custom config file that sets at least 72GB of memory, in this case increased to 100GB. -The custom config below can then be provided to the pipeline via the [`-c`](#-c) parameter as highlighted in previous sections. - -```nextflow -process { - withName: 'NFCORE_RNASEQ:RNASEQ:ALIGN_STAR:STAR_ALIGN' { - memory = 100.GB - } -} -``` - -> **NB:** We specify the full process name i.e. `NFCORE_RNASEQ:RNASEQ:ALIGN_STAR:STAR_ALIGN` in the config file because this takes priority over the short name (`STAR_ALIGN`) and allows existing configuration using the full process name to be correctly overridden. -> -> If you get a warning suggesting that the process selector isn't recognised check that the process name has been specified correctly. - -### Updating containers (advanced users) - -The [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html) implementation of this pipeline uses one container per process which makes 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`. - -1. Check the default version used by the pipeline in the module file for [Pangolin](https://github.com/nf-core/viralrecon/blob/a85d5969f9025409e3618d6c280ef15ce417df65/modules/nf-core/software/pangolin/main.nf#L14-L19) -2. Find the latest version of the Biocontainer available on [Quay.io](https://quay.io/repository/biocontainers/pangolin?tag=latest&tab=tags) -3. Create the custom config accordingly: - - - For Docker: +To change the resource requests, please see the [max resources](https://nf-co.re/docs/usage/configuration#max-resources) and [tuning workflow resources](https://nf-co.re/docs/usage/configuration#tuning-workflow-resources) section of the nf-core website. - ```nextflow - process { - withName: PANGOLIN { - container = 'quay.io/biocontainers/pangolin:3.0.5--pyhdfd78af_0' - } - } - ``` +### Custom Containers - - For Singularity: +In some cases you may wish to change which container or conda environment a step of the pipeline uses for a particular tool. By default nf-core pipelines use containers and software from the [biocontainers](https://biocontainers.pro/) or [bioconda](https://bioconda.github.io/) projects. However in some cases the pipeline specified version maybe out of date. - ```nextflow - process { - withName: PANGOLIN { - container = 'https://depot.galaxyproject.org/singularity/pangolin:3.0.5--pyhdfd78af_0' - } - } - ``` +To use a different container from the default container or conda environment specified in a pipeline, please see the [updating tool versions](https://nf-co.re/docs/usage/configuration#updating-tool-versions) section of the nf-core website. - - For Conda: +### Custom Tool Arguments - ```nextflow - process { - withName: PANGOLIN { - conda = 'bioconda::pangolin=3.0.5' - } - } - ``` +A pipeline might not always support every possible argument or option of a particular tool used in pipeline. Fortunately, nf-core pipelines provide some freedom to users to insert additional parameters that the pipeline does not include by default. -> **NB:** If you wish to periodically update individual tool-specific results (e.g. Pangolin) generated by the pipeline then you must ensure to keep the `work/` directory otherwise the `-resume` ability of the pipeline will be compromised and it will restart from scratch. +To learn how to provide additional arguments to a particular tool of the pipeline, please see the [customising tool arguments](https://nf-co.re/docs/usage/configuration#customising-tool-arguments) section of the nf-core website. ### nf-core/configs diff --git a/lib/NfcoreSchema.groovy b/lib/NfcoreSchema.groovy index 33cd4f6e8..9b34804d6 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 @@ -83,6 +84,7 @@ class NfcoreSchema { 'stub-run', 'test', 'w', + 'with-apptainer', 'with-charliecloud', 'with-conda', 'with-dag', @@ -177,7 +179,7 @@ class NfcoreSchema { } if (has_error) { - System.exit(1) + Nextflow.error('Exiting!') } } diff --git a/lib/WorkflowMain.groovy b/lib/WorkflowMain.groovy index dddca3ea4..ec7707164 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/rnaseq pipeline // +import nextflow.Nextflow + class WorkflowMain { // @@ -21,7 +23,7 @@ class WorkflowMain { // // 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) @@ -34,7 +36,7 @@ class WorkflowMain { // // 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) @@ -49,7 +51,7 @@ 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) } @@ -61,7 +63,7 @@ class WorkflowMain { } // Print parameter summary log to screen - log.info paramsSummaryLog(workflow, params, log) + log.info paramsSummaryLog(workflow, params) // Validate workflow parameters via the JSON schema if (params.validate_params) { @@ -81,8 +83,7 @@ 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/lib/WorkflowRnaseq.groovy b/lib/WorkflowRnaseq.groovy index 2e7a86e25..69855db20 100755 --- a/lib/WorkflowRnaseq.groovy +++ b/lib/WorkflowRnaseq.groovy @@ -2,6 +2,7 @@ // This file holds several functions specific to the workflow/rnaseq.nf in the nf-core/rnaseq pipeline // +import nextflow.Nextflow import groovy.text.SimpleTemplateEngine class WorkflowRnaseq { @@ -14,8 +15,7 @@ class WorkflowRnaseq { 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." } } @@ -61,17 +61,19 @@ class WorkflowRnaseq { 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" + " ${params.genomes.keySet().join(", ")}\n" + "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~" - System.exit(1) + Nextflow.error(error_string) } } } diff --git a/main.nf b/main.nf index 360996dfa..92b516125 100644 --- a/main.nf +++ b/main.nf @@ -4,7 +4,6 @@ nf-core/rnaseq ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Github : https://github.com/nf-core/rnaseq - Website: https://nf-co.re/rnaseq Slack : https://nfcore.slack.com/channels/rnaseq ---------------------------------------------------------------------------------------- diff --git a/modules.json b/modules.json index ba5a6a3f7..143740d08 100644 --- a/modules.json +++ b/modules.json @@ -7,7 +7,7 @@ "nf-core": { "custom/dumpsoftwareversions": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "76cc4938c1f6ea5c7d83fed1eeffc146787f9543", "installed_by": ["modules"] }, "fastqc": { @@ -17,7 +17,7 @@ }, "multiqc": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "f2d63bd5b68925f98f572eed70993d205cc694b7", "installed_by": ["modules"] } } diff --git a/modules/local/samplesheet_check.nf b/modules/local/samplesheet_check.nf index e837d49f5..5014c663f 100644 --- a/modules/local/samplesheet_check.nf +++ b/modules/local/samplesheet_check.nf @@ -5,7 +5,7 @@ process SAMPLESHEET_CHECK { conda "conda-forge::python=3.8.3" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/python:3.8.3' : - 'quay.io/biocontainers/python:3.8.3' }" + 'biocontainers/python:3.8.3' }" input: path samplesheet diff --git a/modules/nf-core/custom/dumpsoftwareversions/main.nf b/modules/nf-core/custom/dumpsoftwareversions/main.nf index 3df21765b..800a60991 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 "bioconda::multiqc=1.13" + 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' : + 'quay.io/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 60b546a01..c32657de7 100644 --- a/modules/nf-core/custom/dumpsoftwareversions/meta.yml +++ b/modules/nf-core/custom/dumpsoftwareversions/meta.yml @@ -1,7 +1,9 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/yaml-schema.json name: custom_dumpsoftwareversions description: Custom module used to dump software versions within the nf-core pipeline template keywords: - custom + - dump - version tools: - custom: diff --git a/modules/nf-core/multiqc/main.nf b/modules/nf-core/multiqc/main.nf index 68f66bea7..4b604749f 100644 --- a/modules/nf-core/multiqc/main.nf +++ b/modules/nf-core/multiqc/main.nf @@ -1,10 +1,10 @@ process MULTIQC { label 'process_single' - conda "bioconda::multiqc=1.13" + conda "bioconda::multiqc=1.14" container "${ 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' : + 'quay.io/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 ebc29b279..f93b5ee51 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/nextflow.config b/nextflow.config index b143935df..cc94a96c9 100644 --- a/nextflow.config +++ b/nextflow.config @@ -78,7 +78,11 @@ try { profiles { - debug { process.beforeScript = 'echo $HOSTNAME' } + debug { + dumpHashes = true + process.beforeScript = 'echo $HOSTNAME' + cleanup = false + } conda { conda.enabled = true docker.enabled = false @@ -86,6 +90,7 @@ profiles { podman.enabled = false shifter.enabled = false charliecloud.enabled = false + apptainer.enabled = false } mamba { conda.enabled = true @@ -95,14 +100,18 @@ profiles { 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 + apptainer.enabled = false } arm { docker.runOptions = '-u $(id -u):$(id -g) --platform=linux/amd64' @@ -110,31 +119,49 @@ profiles { singularity { singularity.enabled = true singularity.autoMounts = true + conda.enabled = false docker.enabled = false podman.enabled = false shifter.enabled = false charliecloud.enabled = false + apptainer.enabled = false } podman { podman.enabled = true + 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' @@ -193,7 +220,7 @@ manifest { description = """RNA sequencing analysis pipeline for gene/isoform quantification and extensive quality control.""" mainScript = 'main.nf' nextflowVersion = '!>=22.10.1' - version = '3.10dev' + version = '3.12.0dev' doi = '' } diff --git a/tower.yml b/tower.yml new file mode 100644 index 000000000..787aedfe9 --- /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" From 54721c6946daf6d602d7069dc127deef9cbe6b33 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Sat, 6 May 2023 21:05:35 +0100 Subject: [PATCH 03/36] Update all nf-core modules and subworkflows --- modules.json | 108 +++++++++--------- modules/nf-core/bbmap/bbsplit/main.nf | 2 +- modules/nf-core/cat/fastq/main.nf | 2 +- modules/nf-core/cat/fastq/meta.yml | 3 +- .../custom/dumpsoftwareversions/main.nf | 2 +- .../templates/dumpsoftwareversions.py | 0 modules/nf-core/custom/getchromsizes/main.nf | 2 +- modules/nf-core/fastp/main.nf | 2 +- modules/nf-core/fastqc/main.nf | 2 +- modules/nf-core/fq/subsample/main.nf | 2 +- modules/nf-core/gffread/main.nf | 2 +- modules/nf-core/gunzip/main.nf | 2 +- modules/nf-core/gunzip/meta.yml | 1 + modules/nf-core/hisat2/build/main.nf | 2 +- .../nf-core/hisat2/extractsplicesites/main.nf | 2 +- modules/nf-core/picard/markduplicates/main.nf | 2 +- modules/nf-core/preseq/lcextrap/main.nf | 2 +- modules/nf-core/qualimap/rnaseq/main.nf | 2 +- modules/nf-core/rseqc/bamstat/main.nf | 2 +- modules/nf-core/rseqc/inferexperiment/main.nf | 2 +- modules/nf-core/rseqc/innerdistance/main.nf | 2 +- .../nf-core/rseqc/junctionannotation/main.nf | 2 +- .../nf-core/rseqc/junctionsaturation/main.nf | 2 +- .../nf-core/rseqc/readdistribution/main.nf | 2 +- modules/nf-core/rseqc/readduplication/main.nf | 2 +- modules/nf-core/rseqc/tin/main.nf | 2 +- modules/nf-core/salmon/index/main.nf | 2 +- modules/nf-core/salmon/quant/main.nf | 2 +- modules/nf-core/samtools/flagstat/main.nf | 6 +- modules/nf-core/samtools/idxstats/main.nf | 6 +- modules/nf-core/samtools/index/main.nf | 6 +- modules/nf-core/samtools/sort/main.nf | 16 ++- modules/nf-core/samtools/stats/main.nf | 6 +- modules/nf-core/sortmerna/main.nf | 2 +- modules/nf-core/star/align/main.nf | 9 ++ modules/nf-core/star/align/meta.yml | 8 ++ modules/nf-core/stringtie/stringtie/main.nf | 2 +- modules/nf-core/subread/featurecounts/main.nf | 2 +- modules/nf-core/trimgalore/main.nf | 2 +- modules/nf-core/ucsc/bedclip/main.nf | 2 +- modules/nf-core/ucsc/bedgraphtobigwig/main.nf | 2 +- modules/nf-core/umitools/dedup/main.nf | 2 +- modules/nf-core/umitools/extract/main.nf | 2 +- modules/nf-core/untar/main.nf | 2 +- modules/nf-core/untar/meta.yml | 1 + .../meta.yml | 1 + .../bam_markduplicates_picard/meta.yml | 1 + subworkflows/nf-core/bam_rseqc/meta.yml | 12 +- .../nf-core/bam_sort_stats_samtools/meta.yml | 1 + .../nf-core/bam_stats_samtools/meta.yml | 1 + .../meta.yml | 9 +- .../nf-core/fastq_align_hisat2/meta.yml | 1 + .../fastq_fastqc_umitools_fastp/meta.yml | 30 ++--- .../fastq_fastqc_umitools_trimgalore/main.nf | 1 - .../fastq_fastqc_umitools_trimgalore/meta.yml | 13 ++- .../fastq_subsample_fq_salmon/meta.yml | 1 + 56 files changed, 170 insertions(+), 137 deletions(-) mode change 100644 => 100755 modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py diff --git a/modules.json b/modules.json index 92583025b..952e378fb 100644 --- a/modules.json +++ b/modules.json @@ -7,47 +7,47 @@ "nf-core": { "bbmap/bbsplit": { "branch": "master", - "git_sha": "75027bf77472b1f4fd2cdd7e46f83119dfb0f2c6", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "cat/fastq": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "5c460c5a4736974abde2843294f35307ee2b0e5e", "installed_by": ["modules"] }, "custom/dumpsoftwareversions": { "branch": "master", - "git_sha": "7101db4432d3268b7fcb5b8f75fa0a022dc5561b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "custom/getchromsizes": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "fastp": { "branch": "master", - "git_sha": "20a508676f40d0fd3f911ac595af91ec845704c4", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules", "fastq_fastqc_umitools_fastp"] }, "fastqc": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["fastq_fastqc_umitools_trimgalore", "fastq_fastqc_umitools_fastp"] }, "fq/subsample": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", - "installed_by": ["fastq_subsample_fq_salmon", "modules"] + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "installed_by": ["modules", "fastq_subsample_fq_salmon"] }, "gffread": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "gunzip": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "5c460c5a4736974abde2843294f35307ee2b0e5e", "installed_by": ["modules"] }, "hisat2/align": { @@ -57,27 +57,27 @@ }, "hisat2/build": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "hisat2/extractsplicesites": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "picard/markduplicates": { "branch": "master", - "git_sha": "75027bf77472b1f4fd2cdd7e46f83119dfb0f2c6", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["bam_markduplicates_picard"] }, "preseq/lcextrap": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "qualimap/rnaseq": { "branch": "master", - "git_sha": "0a9c4eb264cce197707491861ce058a4c79d9c4f", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "rsem/calculateexpression": { @@ -92,91 +92,91 @@ }, "rseqc/bamstat": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["bam_rseqc"] }, "rseqc/inferexperiment": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["bam_rseqc"] }, "rseqc/innerdistance": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["bam_rseqc"] }, "rseqc/junctionannotation": { "branch": "master", - "git_sha": "2f398a6342db61e7ab0f4cb4d395eed74b65db7c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["bam_rseqc"] }, "rseqc/junctionsaturation": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["bam_rseqc"] }, "rseqc/readdistribution": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["bam_rseqc"] }, "rseqc/readduplication": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["bam_rseqc"] }, "rseqc/tin": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["bam_rseqc"] }, "salmon/index": { "branch": "master", - "git_sha": "5d2c0dd6a8e2790e7ff511f7f4d761f4ed627a91", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["fastq_subsample_fq_salmon"] }, "salmon/quant": { "branch": "master", - "git_sha": "5d2c0dd6a8e2790e7ff511f7f4d761f4ed627a91", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules", "fastq_subsample_fq_salmon"] }, "samtools/flagstat": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["bam_stats_samtools"] }, "samtools/idxstats": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["bam_stats_samtools"] }, "samtools/index": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": [ - "bam_dedup_stats_samtools_umitools", "bam_markduplicates_picard", - "bam_sort_stats_samtools" + "bam_sort_stats_samtools", + "bam_dedup_stats_samtools_umitools" ] }, "samtools/sort": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["bam_sort_stats_samtools"] }, "samtools/stats": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["bam_stats_samtools"] }, "sortmerna": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "star/align": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "140d5a0d014138524e21dea80588817ddfc5dcf4", "installed_by": ["modules"] }, "star/genomegenerate": { @@ -186,42 +186,42 @@ }, "stringtie/stringtie": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "subread/featurecounts": { "branch": "master", - "git_sha": "f2d63bd5b68925f98f572eed70993d205cc694b7", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "trimgalore": { "branch": "master", - "git_sha": "64a3dbc0a30a94cdaed7869d8e34fbb85e886614", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["fastq_fastqc_umitools_trimgalore"] }, "ucsc/bedclip": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["bedgraph_bedclip_bedgraphtobigwig"] }, "ucsc/bedgraphtobigwig": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["bedgraph_bedclip_bedgraphtobigwig"] }, "umitools/dedup": { "branch": "master", - "git_sha": "ffe2f5865f608848e440a52b73c304ea79aaf818", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["bam_dedup_stats_samtools_umitools"] }, "umitools/extract": { "branch": "master", - "git_sha": "ffe2f5865f608848e440a52b73c304ea79aaf818", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["fastq_fastqc_umitools_fastp", "fastq_fastqc_umitools_trimgalore"] }, "untar": { "branch": "master", - "git_sha": "cc1f997fab6d8fde5dc0e6e2a310814df5b53ce7", + "git_sha": "5c460c5a4736974abde2843294f35307ee2b0e5e", "installed_by": ["modules"] } } @@ -230,56 +230,56 @@ "nf-core": { "bam_dedup_stats_samtools_umitools": { "branch": "master", - "git_sha": "901fab507683647b43e7032f3ae9e4c234eb68eb", + "git_sha": "a9784afdd5dcda23b84e64db75dc591065d64653", "installed_by": ["subworkflows"] }, "bam_markduplicates_picard": { "branch": "master", - "git_sha": "6f1697c121719dedde9e0537b6ed6a9cb8c13583", + "git_sha": "a9784afdd5dcda23b84e64db75dc591065d64653", "installed_by": ["subworkflows"] }, "bam_rseqc": { "branch": "master", - "git_sha": "b8f7bdc6f0e37f2946c84c5ac676c6030ebbf8c4", + "git_sha": "a9784afdd5dcda23b84e64db75dc591065d64653", "installed_by": ["subworkflows"] }, "bam_sort_stats_samtools": { "branch": "master", - "git_sha": "3911652a6b24249358f79e8b8466338d63efb2a2", + "git_sha": "a9784afdd5dcda23b84e64db75dc591065d64653", "installed_by": ["fastq_align_hisat2"] }, "bam_stats_samtools": { "branch": "master", - "git_sha": "b4b7f89e7fd6d2293f0c176213f710e0bcdaf19e", + "git_sha": "a9784afdd5dcda23b84e64db75dc591065d64653", "installed_by": [ - "bam_dedup_stats_samtools_umitools", "bam_markduplicates_picard", - "bam_sort_stats_samtools" + "bam_sort_stats_samtools", + "bam_dedup_stats_samtools_umitools" ] }, "bedgraph_bedclip_bedgraphtobigwig": { "branch": "master", - "git_sha": "b81a313d8fac0a82a8a4ff0de80590b2f97f11ad", + "git_sha": "a9784afdd5dcda23b84e64db75dc591065d64653", "installed_by": ["subworkflows"] }, "fastq_align_hisat2": { "branch": "master", - "git_sha": "9057e75e8ac959373a72a9402130fdea2e2d1398", + "git_sha": "a9784afdd5dcda23b84e64db75dc591065d64653", "installed_by": ["subworkflows"] }, "fastq_fastqc_umitools_fastp": { "branch": "master", - "git_sha": "4c8c5b5c084a99d9bf4f987040ebe88ec12b705d", + "git_sha": "a9784afdd5dcda23b84e64db75dc591065d64653", "installed_by": ["subworkflows"] }, "fastq_fastqc_umitools_trimgalore": { "branch": "master", - "git_sha": "100caf3506850ffcc04953f724a97f422940c377", + "git_sha": "a9784afdd5dcda23b84e64db75dc591065d64653", "installed_by": ["subworkflows"] }, "fastq_subsample_fq_salmon": { "branch": "master", - "git_sha": "82d60046b4519e9dbef4a934371a53fa7666eabc", + "git_sha": "a9784afdd5dcda23b84e64db75dc591065d64653", "installed_by": ["subworkflows"] } } diff --git a/modules/nf-core/bbmap/bbsplit/main.nf b/modules/nf-core/bbmap/bbsplit/main.nf index 2d9196871..6046184d0 100644 --- a/modules/nf-core/bbmap/bbsplit/main.nf +++ b/modules/nf-core/bbmap/bbsplit/main.nf @@ -4,7 +4,7 @@ process BBMAP_BBSPLIT { conda "bioconda::bbmap=39.01" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/bbmap:39.01--h5c4e2a8_0': - 'quay.io/biocontainers/bbmap:39.01--h5c4e2a8_0' }" + 'biocontainers/bbmap:39.01--h5c4e2a8_0' }" input: tuple val(meta), path(reads) diff --git a/modules/nf-core/cat/fastq/main.nf b/modules/nf-core/cat/fastq/main.nf index 8a0b5600c..5021e6fcb 100644 --- a/modules/nf-core/cat/fastq/main.nf +++ b/modules/nf-core/cat/fastq/main.nf @@ -5,7 +5,7 @@ process CAT_FASTQ { conda "conda-forge::sed=4.7" container "${ 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(reads, stageAs: "input*/*") diff --git a/modules/nf-core/cat/fastq/meta.yml b/modules/nf-core/cat/fastq/meta.yml index c836598e4..8a39e309f 100644 --- a/modules/nf-core/cat/fastq/meta.yml +++ b/modules/nf-core/cat/fastq/meta.yml @@ -1,6 +1,7 @@ name: cat_fastq description: Concatenates fastq files keywords: + - cat - fastq - concatenate tools: @@ -16,7 +17,7 @@ input: Groovy Map containing sample information e.g. [ id:'test', single_end:false ] - reads: - type: list + type: file description: | List of input FastQ files to be concatenated. output: diff --git a/modules/nf-core/custom/dumpsoftwareversions/main.nf b/modules/nf-core/custom/dumpsoftwareversions/main.nf index 800a60991..ebc872733 100644 --- a/modules/nf-core/custom/dumpsoftwareversions/main.nf +++ b/modules/nf-core/custom/dumpsoftwareversions/main.nf @@ -5,7 +5,7 @@ process CUSTOM_DUMPSOFTWAREVERSIONS { conda "bioconda::multiqc=1.14" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/multiqc:1.14--pyhdfd78af_0' : - 'quay.io/biocontainers/multiqc:1.14--pyhdfd78af_0' }" + 'biocontainers/multiqc:1.14--pyhdfd78af_0' }" input: path versions diff --git a/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py b/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py old mode 100644 new mode 100755 diff --git a/modules/nf-core/custom/getchromsizes/main.nf b/modules/nf-core/custom/getchromsizes/main.nf index 580f87fea..060a2e885 100644 --- a/modules/nf-core/custom/getchromsizes/main.nf +++ b/modules/nf-core/custom/getchromsizes/main.nf @@ -5,7 +5,7 @@ process CUSTOM_GETCHROMSIZES { conda "bioconda::samtools=1.16.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/samtools:1.16.1--h6899075_1' : - 'quay.io/biocontainers/samtools:1.16.1--h6899075_1' }" + 'biocontainers/samtools:1.16.1--h6899075_1' }" input: tuple val(meta), path(fasta) diff --git a/modules/nf-core/fastp/main.nf b/modules/nf-core/fastp/main.nf index 5eeb9b09e..2ca2d3ee0 100644 --- a/modules/nf-core/fastp/main.nf +++ b/modules/nf-core/fastp/main.nf @@ -5,7 +5,7 @@ process FASTP { conda "bioconda::fastp=0.23.2" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/fastp:0.23.2--h79da9fb_0' : - 'quay.io/biocontainers/fastp:0.23.2--h79da9fb_0' }" + 'biocontainers/fastp:0.23.2--h79da9fb_0' }" input: tuple val(meta), path(reads) diff --git a/modules/nf-core/fastqc/main.nf b/modules/nf-core/fastqc/main.nf index 9ae583815..07d5e4331 100644 --- a/modules/nf-core/fastqc/main.nf +++ b/modules/nf-core/fastqc/main.nf @@ -5,7 +5,7 @@ process FASTQC { conda "bioconda::fastqc=0.11.9" container "${ 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) diff --git a/modules/nf-core/fq/subsample/main.nf b/modules/nf-core/fq/subsample/main.nf index c95691908..8b4ff5be0 100644 --- a/modules/nf-core/fq/subsample/main.nf +++ b/modules/nf-core/fq/subsample/main.nf @@ -5,7 +5,7 @@ process FQ_SUBSAMPLE { conda "bioconda::fq=0.9.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/fq:0.9.1--h9ee0642_0': - 'quay.io/biocontainers/fq:0.9.1--h9ee0642_0' }" + 'biocontainers/fq:0.9.1--h9ee0642_0' }" input: tuple val(meta), path(fastq) diff --git a/modules/nf-core/gffread/main.nf b/modules/nf-core/gffread/main.nf index b1a8996fe..f4472b0e8 100644 --- a/modules/nf-core/gffread/main.nf +++ b/modules/nf-core/gffread/main.nf @@ -5,7 +5,7 @@ process GFFREAD { conda "bioconda::gffread=0.12.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/gffread:0.12.1--h8b12597_0' : - 'quay.io/biocontainers/gffread:0.12.1--h8b12597_0' }" + 'biocontainers/gffread:0.12.1--h8b12597_0' }" input: path gff diff --git a/modules/nf-core/gunzip/main.nf b/modules/nf-core/gunzip/main.nf index d906034c3..e7189d2fb 100644 --- a/modules/nf-core/gunzip/main.nf +++ b/modules/nf-core/gunzip/main.nf @@ -5,7 +5,7 @@ process GUNZIP { conda "conda-forge::sed=4.7" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/ubuntu:20.04' : - 'ubuntu:20.04' }" + 'nf-core/ubuntu:20.04' }" input: tuple val(meta), path(archive) diff --git a/modules/nf-core/gunzip/meta.yml b/modules/nf-core/gunzip/meta.yml index 2e0e4054d..4cdcdf4c4 100644 --- a/modules/nf-core/gunzip/meta.yml +++ b/modules/nf-core/gunzip/meta.yml @@ -3,6 +3,7 @@ description: Compresses and decompresses files. keywords: - gunzip - compression + - decompression tools: - gunzip: description: | diff --git a/modules/nf-core/hisat2/build/main.nf b/modules/nf-core/hisat2/build/main.nf index e0a7f6525..b3475f758 100644 --- a/modules/nf-core/hisat2/build/main.nf +++ b/modules/nf-core/hisat2/build/main.nf @@ -7,7 +7,7 @@ process HISAT2_BUILD { conda "bioconda::hisat2=2.2.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/hisat2:2.2.1--h1b792b2_3' : - 'quay.io/biocontainers/hisat2:2.2.1--h1b792b2_3' }" + 'biocontainers/hisat2:2.2.1--h1b792b2_3' }" input: path fasta diff --git a/modules/nf-core/hisat2/extractsplicesites/main.nf b/modules/nf-core/hisat2/extractsplicesites/main.nf index db6cbe6a2..f6d28c1a5 100644 --- a/modules/nf-core/hisat2/extractsplicesites/main.nf +++ b/modules/nf-core/hisat2/extractsplicesites/main.nf @@ -6,7 +6,7 @@ process HISAT2_EXTRACTSPLICESITES { conda "bioconda::hisat2=2.2.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/hisat2:2.2.1--h1b792b2_3' : - 'quay.io/biocontainers/hisat2:2.2.1--h1b792b2_3' }" + 'biocontainers/hisat2:2.2.1--h1b792b2_3' }" input: path gtf diff --git a/modules/nf-core/picard/markduplicates/main.nf b/modules/nf-core/picard/markduplicates/main.nf index 1fe6ee2d2..7ba8448f7 100644 --- a/modules/nf-core/picard/markduplicates/main.nf +++ b/modules/nf-core/picard/markduplicates/main.nf @@ -5,7 +5,7 @@ process PICARD_MARKDUPLICATES { conda "bioconda::picard=3.0.0" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/picard:3.0.0--hdfd78af_1' : - 'quay.io/biocontainers/picard:3.0.0--hdfd78af_1' }" + 'biocontainers/picard:3.0.0--hdfd78af_1' }" input: tuple val(meta), path(bam) diff --git a/modules/nf-core/preseq/lcextrap/main.nf b/modules/nf-core/preseq/lcextrap/main.nf index 38275910b..12546f0a2 100644 --- a/modules/nf-core/preseq/lcextrap/main.nf +++ b/modules/nf-core/preseq/lcextrap/main.nf @@ -6,7 +6,7 @@ process PRESEQ_LCEXTRAP { conda "bioconda::preseq=3.1.2" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/preseq:3.1.2--h445547b_2': - 'quay.io/biocontainers/preseq:3.1.2--h445547b_2' }" + 'biocontainers/preseq:3.1.2--h445547b_2' }" input: tuple val(meta), path(bam) diff --git a/modules/nf-core/qualimap/rnaseq/main.nf b/modules/nf-core/qualimap/rnaseq/main.nf index b84ca060b..2c0e4105f 100644 --- a/modules/nf-core/qualimap/rnaseq/main.nf +++ b/modules/nf-core/qualimap/rnaseq/main.nf @@ -5,7 +5,7 @@ process QUALIMAP_RNASEQ { conda "bioconda::qualimap=2.2.2d" container "${ 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) diff --git a/modules/nf-core/rseqc/bamstat/main.nf b/modules/nf-core/rseqc/bamstat/main.nf index 943053ebb..04c1eefd0 100644 --- a/modules/nf-core/rseqc/bamstat/main.nf +++ b/modules/nf-core/rseqc/bamstat/main.nf @@ -5,7 +5,7 @@ process RSEQC_BAMSTAT { conda "bioconda::rseqc=3.0.1 'conda-forge::r-base>=3.5'" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1' : - 'quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1' }" + 'biocontainers/rseqc:3.0.1--py37h516909a_1' }" input: tuple val(meta), path(bam) diff --git a/modules/nf-core/rseqc/inferexperiment/main.nf b/modules/nf-core/rseqc/inferexperiment/main.nf index f054c4822..5f9f4b111 100644 --- a/modules/nf-core/rseqc/inferexperiment/main.nf +++ b/modules/nf-core/rseqc/inferexperiment/main.nf @@ -5,7 +5,7 @@ process RSEQC_INFEREXPERIMENT { conda "bioconda::rseqc=3.0.1 'conda-forge::r-base>=3.5'" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1' : - 'quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1' }" + 'biocontainers/rseqc:3.0.1--py37h516909a_1' }" input: tuple val(meta), path(bam) diff --git a/modules/nf-core/rseqc/innerdistance/main.nf b/modules/nf-core/rseqc/innerdistance/main.nf index 3d11d2b3e..a63a2bf03 100644 --- a/modules/nf-core/rseqc/innerdistance/main.nf +++ b/modules/nf-core/rseqc/innerdistance/main.nf @@ -5,7 +5,7 @@ process RSEQC_INNERDISTANCE { conda "bioconda::rseqc=3.0.1 'conda-forge::r-base>=3.5'" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1' : - 'quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1' }" + 'biocontainers/rseqc:3.0.1--py37h516909a_1' }" input: tuple val(meta), path(bam) diff --git a/modules/nf-core/rseqc/junctionannotation/main.nf b/modules/nf-core/rseqc/junctionannotation/main.nf index bc0497293..4029ac765 100644 --- a/modules/nf-core/rseqc/junctionannotation/main.nf +++ b/modules/nf-core/rseqc/junctionannotation/main.nf @@ -5,7 +5,7 @@ process RSEQC_JUNCTIONANNOTATION { conda "bioconda::rseqc=3.0.1 'conda-forge::r-base>=3.5'" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1' : - 'quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1' }" + 'biocontainers/rseqc:3.0.1--py37h516909a_1' }" input: tuple val(meta), path(bam) diff --git a/modules/nf-core/rseqc/junctionsaturation/main.nf b/modules/nf-core/rseqc/junctionsaturation/main.nf index 1b56bd1a9..93cc61b23 100644 --- a/modules/nf-core/rseqc/junctionsaturation/main.nf +++ b/modules/nf-core/rseqc/junctionsaturation/main.nf @@ -5,7 +5,7 @@ process RSEQC_JUNCTIONSATURATION { conda "bioconda::rseqc=3.0.1 'conda-forge::r-base>=3.5'" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1' : - 'quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1' }" + 'biocontainers/rseqc:3.0.1--py37h516909a_1' }" input: tuple val(meta), path(bam) diff --git a/modules/nf-core/rseqc/readdistribution/main.nf b/modules/nf-core/rseqc/readdistribution/main.nf index a8477a098..f3e588d69 100644 --- a/modules/nf-core/rseqc/readdistribution/main.nf +++ b/modules/nf-core/rseqc/readdistribution/main.nf @@ -5,7 +5,7 @@ process RSEQC_READDISTRIBUTION { conda "bioconda::rseqc=3.0.1 'conda-forge::r-base>=3.5'" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1' : - 'quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1' }" + 'biocontainers/rseqc:3.0.1--py37h516909a_1' }" input: tuple val(meta), path(bam) diff --git a/modules/nf-core/rseqc/readduplication/main.nf b/modules/nf-core/rseqc/readduplication/main.nf index 7457c280d..023118536 100644 --- a/modules/nf-core/rseqc/readduplication/main.nf +++ b/modules/nf-core/rseqc/readduplication/main.nf @@ -5,7 +5,7 @@ process RSEQC_READDUPLICATION { conda "bioconda::rseqc=3.0.1 'conda-forge::r-base>=3.5'" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1' : - 'quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1' }" + 'biocontainers/rseqc:3.0.1--py37h516909a_1' }" input: tuple val(meta), path(bam) diff --git a/modules/nf-core/rseqc/tin/main.nf b/modules/nf-core/rseqc/tin/main.nf index 29627e94e..872938b62 100644 --- a/modules/nf-core/rseqc/tin/main.nf +++ b/modules/nf-core/rseqc/tin/main.nf @@ -5,7 +5,7 @@ process RSEQC_TIN { conda "bioconda::rseqc=3.0.1 'conda-forge::r-base>=3.5'" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/rseqc:3.0.1--py37h516909a_1' : - 'quay.io/biocontainers/rseqc:3.0.1--py37h516909a_1' }" + 'biocontainers/rseqc:3.0.1--py37h516909a_1' }" input: tuple val(meta), path(bam), path(bai) diff --git a/modules/nf-core/salmon/index/main.nf b/modules/nf-core/salmon/index/main.nf index 668b62287..118ee6704 100644 --- a/modules/nf-core/salmon/index/main.nf +++ b/modules/nf-core/salmon/index/main.nf @@ -5,7 +5,7 @@ process SALMON_INDEX { conda "bioconda::salmon=1.10.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/salmon:1.10.1--h7e5ed60_0' : - 'quay.io/biocontainers/salmon:1.10.1--h7e5ed60_0' }" + 'biocontainers/salmon:1.10.1--h7e5ed60_0' }" input: path genome_fasta diff --git a/modules/nf-core/salmon/quant/main.nf b/modules/nf-core/salmon/quant/main.nf index 978faf6c5..e356af26d 100644 --- a/modules/nf-core/salmon/quant/main.nf +++ b/modules/nf-core/salmon/quant/main.nf @@ -5,7 +5,7 @@ process SALMON_QUANT { conda "bioconda::salmon=1.10.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/salmon:1.10.1--h7e5ed60_0' : - 'quay.io/biocontainers/salmon:1.10.1--h7e5ed60_0' }" + 'biocontainers/salmon:1.10.1--h7e5ed60_0' }" input: tuple val(meta), path(reads) diff --git a/modules/nf-core/samtools/flagstat/main.nf b/modules/nf-core/samtools/flagstat/main.nf index 2120cd7d3..eb7e72fc6 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 "$meta.id" label 'process_single' - conda "bioconda::samtools=1.16.1" + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.16.1--h6899075_1' : - 'quay.io/biocontainers/samtools:1.16.1--h6899075_1' }" + '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/main.nf b/modules/nf-core/samtools/idxstats/main.nf index a7b87d8b9..a257d7002 100644 --- a/modules/nf-core/samtools/idxstats/main.nf +++ b/modules/nf-core/samtools/idxstats/main.nf @@ -2,10 +2,10 @@ process SAMTOOLS_IDXSTATS { tag "$meta.id" label 'process_single' - conda "bioconda::samtools=1.16.1" + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.16.1--h6899075_1' : - 'quay.io/biocontainers/samtools:1.16.1--h6899075_1' }" + '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/index/main.nf b/modules/nf-core/samtools/index/main.nf index 8b95687a9..0b20aa4bb 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 "$meta.id" label 'process_low' - conda "bioconda::samtools=1.16.1" + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.16.1--h6899075_1' : - 'quay.io/biocontainers/samtools:1.16.1--h6899075_1' }" + '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/sort/main.nf b/modules/nf-core/samtools/sort/main.nf index 84c167cdd..1e5181d41 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 "$meta.id" label 'process_medium' - conda "bioconda::samtools=1.16.1" + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.16.1--h6899075_1' : - 'quay.io/biocontainers/samtools:1.16.1--h6899075_1' }" + '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/stats/main.nf b/modules/nf-core/samtools/stats/main.nf index 0a2a36401..eb7f098b0 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 "$meta.id" label 'process_single' - conda "bioconda::samtools=1.16.1" + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.16.1--h6899075_1' : - 'quay.io/biocontainers/samtools:1.16.1--h6899075_1' }" + '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/sortmerna/main.nf b/modules/nf-core/sortmerna/main.nf index 171f6401b..7afae5a68 100644 --- a/modules/nf-core/sortmerna/main.nf +++ b/modules/nf-core/sortmerna/main.nf @@ -5,7 +5,7 @@ process SORTMERNA { conda "bioconda::sortmerna=4.3.4" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/sortmerna:4.3.4--h9ee0642_0' : - 'quay.io/biocontainers/sortmerna:4.3.4--h9ee0642_0' }" + 'biocontainers/sortmerna:4.3.4--h9ee0642_0' }" input: tuple val(meta), path(reads) diff --git a/modules/nf-core/star/align/main.nf b/modules/nf-core/star/align/main.nf index 0e3bd7133..e6c4443cb 100644 --- a/modules/nf-core/star/align/main.nf +++ b/modules/nf-core/star/align/main.nf @@ -27,8 +27,12 @@ process STAR_ALIGN { tuple val(meta), path('*Aligned.unsort.out.bam') , optional:true, emit: bam_unsorted tuple val(meta), path('*fastq.gz') , optional:true, emit: fastq tuple val(meta), path('*.tab') , optional:true, emit: tab + tuple val(meta), path('*.SJ.out.tab') , optional:true, emit: spl_junc_tab + tuple val(meta), path('*.ReadsPerGene.out.tab') , optional:true, emit: read_per_gene_tab tuple val(meta), path('*.out.junction') , optional:true, emit: junction tuple val(meta), path('*.out.sam') , optional:true, emit: sam + tuple val(meta), path('*.wig') , optional:true, emit: wig + tuple val(meta), path('*.bg') , optional:true, emit: bedgraph when: task.ext.when == null || task.ext.when @@ -81,11 +85,16 @@ process STAR_ALIGN { touch ${prefix}.sortedByCoord.out.bam touch ${prefix}.toTranscriptome.out.bam touch ${prefix}.Aligned.unsort.out.bam + touch ${prefix}.Aligned.sortedByCoord.out.bam touch ${prefix}.unmapped_1.fastq.gz touch ${prefix}.unmapped_2.fastq.gz touch ${prefix}.tab + touch ${prefix}.SJ.out.tab + touch ${prefix}.ReadsPerGene.out.tab touch ${prefix}.Chimeric.out.junction touch ${prefix}.out.sam + touch ${prefix}.Signal.UniqueMultiple.str1.out.wig + touch ${prefix}.Signal.UniqueMultiple.str1.out.bg cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/nf-core/star/align/meta.yml b/modules/nf-core/star/align/meta.yml index 7ee10f1cc..bce16d360 100644 --- a/modules/nf-core/star/align/meta.yml +++ b/modules/nf-core/star/align/meta.yml @@ -74,6 +74,14 @@ output: type: file description: STAR chimeric junction output file (optional) pattern: "*.out.junction" + - wig: + type: file + description: STAR output wiggle format file(s) (optional) + pattern: "*.wig" + - bedgraph: + type: file + description: STAR output bedGraph format file(s) (optional) + pattern: "*.bg" authors: - "@kevinmenden" diff --git a/modules/nf-core/stringtie/stringtie/main.nf b/modules/nf-core/stringtie/stringtie/main.nf index 2d5b035f7..d0f8b563f 100644 --- a/modules/nf-core/stringtie/stringtie/main.nf +++ b/modules/nf-core/stringtie/stringtie/main.nf @@ -5,7 +5,7 @@ process STRINGTIE_STRINGTIE { conda "bioconda::stringtie=2.2.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/stringtie:2.2.1--hecb563c_2' : - 'quay.io/biocontainers/stringtie:2.2.1--hecb563c_2' }" + 'biocontainers/stringtie:2.2.1--hecb563c_2' }" input: tuple val(meta), path(bam) diff --git a/modules/nf-core/subread/featurecounts/main.nf b/modules/nf-core/subread/featurecounts/main.nf index cbc833fe8..a524b92f1 100644 --- a/modules/nf-core/subread/featurecounts/main.nf +++ b/modules/nf-core/subread/featurecounts/main.nf @@ -5,7 +5,7 @@ process SUBREAD_FEATURECOUNTS { conda "bioconda::subread=2.0.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/subread:2.0.1--hed695b0_0' : - 'quay.io/biocontainers/subread:2.0.1--hed695b0_0' }" + 'biocontainers/subread:2.0.1--hed695b0_0' }" input: tuple val(meta), path(bams), path(annotation) diff --git a/modules/nf-core/trimgalore/main.nf b/modules/nf-core/trimgalore/main.nf index dc2957846..dcb77ae7b 100644 --- a/modules/nf-core/trimgalore/main.nf +++ b/modules/nf-core/trimgalore/main.nf @@ -5,7 +5,7 @@ process TRIMGALORE { conda "bioconda::trim-galore=0.6.7" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/trim-galore:0.6.7--hdfd78af_0' : - 'quay.io/biocontainers/trim-galore:0.6.7--hdfd78af_0' }" + 'biocontainers/trim-galore:0.6.7--hdfd78af_0' }" input: tuple val(meta), path(reads) diff --git a/modules/nf-core/ucsc/bedclip/main.nf b/modules/nf-core/ucsc/bedclip/main.nf index 365c53196..4bad9a399 100755 --- a/modules/nf-core/ucsc/bedclip/main.nf +++ b/modules/nf-core/ucsc/bedclip/main.nf @@ -6,7 +6,7 @@ process UCSC_BEDCLIP { conda "bioconda::ucsc-bedclip=377" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/ucsc-bedclip:377--h0b8a92a_2' : - 'quay.io/biocontainers/ucsc-bedclip:377--h0b8a92a_2' }" + 'biocontainers/ucsc-bedclip:377--h0b8a92a_2' }" input: tuple val(meta), path(bedgraph) diff --git a/modules/nf-core/ucsc/bedgraphtobigwig/main.nf b/modules/nf-core/ucsc/bedgraphtobigwig/main.nf index defda3ef5..054924e7e 100644 --- a/modules/nf-core/ucsc/bedgraphtobigwig/main.nf +++ b/modules/nf-core/ucsc/bedgraphtobigwig/main.nf @@ -6,7 +6,7 @@ process UCSC_BEDGRAPHTOBIGWIG { conda "bioconda::ucsc-bedgraphtobigwig=377" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/ucsc-bedgraphtobigwig:377--h446ed27_1' : - 'quay.io/biocontainers/ucsc-bedgraphtobigwig:377--h446ed27_1' }" + 'biocontainers/ucsc-bedgraphtobigwig:377--h446ed27_1' }" input: tuple val(meta), path(bedgraph) diff --git a/modules/nf-core/umitools/dedup/main.nf b/modules/nf-core/umitools/dedup/main.nf index aa6fdd24e..2bd95da7c 100644 --- a/modules/nf-core/umitools/dedup/main.nf +++ b/modules/nf-core/umitools/dedup/main.nf @@ -5,7 +5,7 @@ process UMITOOLS_DEDUP { conda "bioconda::umi_tools=1.1.4" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/umi_tools:1.1.4--py38hbff2b2d_1' : - 'quay.io/biocontainers/umi_tools:1.1.4--py38hbff2b2d_1' }" + 'biocontainers/umi_tools:1.1.4--py38hbff2b2d_1' }" input: tuple val(meta), path(bam), path(bai) diff --git a/modules/nf-core/umitools/extract/main.nf b/modules/nf-core/umitools/extract/main.nf index 64fdd367f..2f94fa93e 100644 --- a/modules/nf-core/umitools/extract/main.nf +++ b/modules/nf-core/umitools/extract/main.nf @@ -6,7 +6,7 @@ process UMITOOLS_EXTRACT { conda "bioconda::umi_tools=1.1.4" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/umi_tools:1.1.4--py38hbff2b2d_1' : - 'quay.io/biocontainers/umi_tools:1.1.4--py38hbff2b2d_1' }" + 'biocontainers/umi_tools:1.1.4--py38hbff2b2d_1' }" input: tuple val(meta), path(reads) diff --git a/modules/nf-core/untar/main.nf b/modules/nf-core/untar/main.nf index 3384847aa..8cd1856c7 100644 --- a/modules/nf-core/untar/main.nf +++ b/modules/nf-core/untar/main.nf @@ -5,7 +5,7 @@ process UNTAR { conda "conda-forge::sed=4.7 bioconda::grep=3.4 conda-forge::tar=1.34" container "${ 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) diff --git a/modules/nf-core/untar/meta.yml b/modules/nf-core/untar/meta.yml index ea7a3f382..db241a6e5 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/subworkflows/nf-core/bam_dedup_stats_samtools_umitools/meta.yml b/subworkflows/nf-core/bam_dedup_stats_samtools_umitools/meta.yml index c5ecdb01a..3af412fab 100644 --- a/subworkflows/nf-core/bam_dedup_stats_samtools_umitools/meta.yml +++ b/subworkflows/nf-core/bam_dedup_stats_samtools_umitools/meta.yml @@ -1,3 +1,4 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json name: "bam_dedup_stats_samtools_umitools" description: UMI-tools dedup, index BAM file and run samtools stats, flagstat and idxstats keywords: diff --git a/subworkflows/nf-core/bam_markduplicates_picard/meta.yml b/subworkflows/nf-core/bam_markduplicates_picard/meta.yml index 822c61328..d5e716092 100644 --- a/subworkflows/nf-core/bam_markduplicates_picard/meta.yml +++ b/subworkflows/nf-core/bam_markduplicates_picard/meta.yml @@ -1,3 +1,4 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json name: "bam_markduplicates_picard" description: Picard MarkDuplicates, index BAM file and run samtools stats, flagstat and idxstats keywords: diff --git a/subworkflows/nf-core/bam_rseqc/meta.yml b/subworkflows/nf-core/bam_rseqc/meta.yml index cc074c21f..428b83e6d 100644 --- a/subworkflows/nf-core/bam_rseqc/meta.yml +++ b/subworkflows/nf-core/bam_rseqc/meta.yml @@ -1,3 +1,4 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json name: bam_rseqc description: Subworkflow to run multiple commands in the RSeqC package keywords: @@ -11,15 +12,8 @@ keywords: - readdistribution - readduplication - tin -tools: - - rseqc: - description: | - RSeQC package provides a number of useful modules that can comprehensively evaluate - high throughput sequence data especially RNA-seq data. - homepage: http://rseqc.sourceforge.net/ - documentation: http://rseqc.sourceforge.net/ - doi: 10.1093/bioinformatics/bts356 - licence: ["GPL-3.0-or-later"] +modules: + - rseqc input: - meta: type: map diff --git a/subworkflows/nf-core/bam_sort_stats_samtools/meta.yml b/subworkflows/nf-core/bam_sort_stats_samtools/meta.yml index 131065be1..8dfbd58df 100644 --- a/subworkflows/nf-core/bam_sort_stats_samtools/meta.yml +++ b/subworkflows/nf-core/bam_sort_stats_samtools/meta.yml @@ -1,3 +1,4 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json name: bam_sort_stats_samtools description: Sort SAM/BAM/CRAM file keywords: diff --git a/subworkflows/nf-core/bam_stats_samtools/meta.yml b/subworkflows/nf-core/bam_stats_samtools/meta.yml index b6072686e..b05086bc2 100644 --- a/subworkflows/nf-core/bam_stats_samtools/meta.yml +++ b/subworkflows/nf-core/bam_stats_samtools/meta.yml @@ -1,3 +1,4 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json name: bam_stats_samtools description: Produces comprehensive statistics from SAM/BAM/CRAM file keywords: diff --git a/subworkflows/nf-core/bedgraph_bedclip_bedgraphtobigwig/meta.yml b/subworkflows/nf-core/bedgraph_bedclip_bedgraphtobigwig/meta.yml index 3fb767486..8d3257773 100644 --- a/subworkflows/nf-core/bedgraph_bedclip_bedgraphtobigwig/meta.yml +++ b/subworkflows/nf-core/bedgraph_bedclip_bedgraphtobigwig/meta.yml @@ -1,19 +1,22 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json name: "bedgraph_bedclip_bedgraphtobigwig" -description: Convert gedgraph to bigwig with clip +description: Convert bedgraph to bigwig with clip keywords: - bedgraph - bigwig + - clip + - conversion modules: - ucsc/bedclip - ucsc/bedgraphtobigwig input: - bedgraph: type: file - description: bedGraph file whoch should be converted + description: bedGraph file which should be converted pattern: "*.bedGraph" - sizes: type: file - description: File with chromosom sizes + description: File with chromosome sizes pattern: "*.sizes" output: - bigwig: diff --git a/subworkflows/nf-core/fastq_align_hisat2/meta.yml b/subworkflows/nf-core/fastq_align_hisat2/meta.yml index ed37ed7ff..36c7c78ec 100644 --- a/subworkflows/nf-core/fastq_align_hisat2/meta.yml +++ b/subworkflows/nf-core/fastq_align_hisat2/meta.yml @@ -1,3 +1,4 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json name: "fastq_align_hisat2" description: Align reads to a reference genome using hisat2 then sort with samtools keywords: diff --git a/subworkflows/nf-core/fastq_fastqc_umitools_fastp/meta.yml b/subworkflows/nf-core/fastq_fastqc_umitools_fastp/meta.yml index d80ebc0a1..8f1620093 100644 --- a/subworkflows/nf-core/fastq_fastqc_umitools_fastp/meta.yml +++ b/subworkflows/nf-core/fastq_fastqc_umitools_fastp/meta.yml @@ -1,3 +1,5 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json +# yaml-language-server: $schema=yaml-schema.json name: "fastq_fastqc_umitools_fastp" description: Read QC, UMI extraction and trimming keywords: @@ -65,12 +67,12 @@ output: Groovy Map containing sample information e.g. [ id:'test' ] - reads: - type: file - description: > - Extracted FASTQ files. | - For single-end reads, pattern is \${prefix}.umi_extract.fastq.gz. | - For paired-end reads, pattern is \${prefix}.umi_extract_{1,2}.fastq.gz. - pattern: "*.{fastq.gz}" + type: file + description: > + Extracted FASTQ files. | + For single-end reads, pattern is \${prefix}.umi_extract.fastq.gz. | + For paired-end reads, pattern is \${prefix}.umi_extract_{1,2}.fastq.gz. + pattern: "*.{fastq.gz}" - fastqc_html: type: file description: FastQC report @@ -96,16 +98,16 @@ output: description: Logfile FastP pattern: "*.{fastp.log}" - trim_reads_fail: - type: file - description: Trimmed fastq files failing QC - pattern: "*.{fastq.gz}" + type: file + description: Trimmed fastq files failing QC + pattern: "*.{fastq.gz}" - trim_reads_merged: - type: file - description: Trimmed and merged fastq files - pattern: "*.{fastq.gz}" + type: file + description: Trimmed and merged fastq files + pattern: "*.{fastq.gz}" - trim_read_count: - type: integer - description: Number of reads after trimming + type: integer + description: Number of reads after trimming - fastqc_trim_html: type: file description: FastQC report diff --git a/subworkflows/nf-core/fastq_fastqc_umitools_trimgalore/main.nf b/subworkflows/nf-core/fastq_fastqc_umitools_trimgalore/main.nf index f7f48d15b..db2e5b329 100644 --- a/subworkflows/nf-core/fastq_fastqc_umitools_trimgalore/main.nf +++ b/subworkflows/nf-core/fastq_fastqc_umitools_trimgalore/main.nf @@ -33,7 +33,6 @@ workflow FASTQ_FASTQC_UMITOOLS_TRIMGALORE { main: ch_versions = Channel.empty() - fastqc_html = Channel.empty() fastqc_zip = Channel.empty() if (!skip_fastqc) { diff --git a/subworkflows/nf-core/fastq_fastqc_umitools_trimgalore/meta.yml b/subworkflows/nf-core/fastq_fastqc_umitools_trimgalore/meta.yml index b05004d45..3b1a675c3 100644 --- a/subworkflows/nf-core/fastq_fastqc_umitools_trimgalore/meta.yml +++ b/subworkflows/nf-core/fastq_fastqc_umitools_trimgalore/meta.yml @@ -1,3 +1,4 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json name: "fastq_fastqc_umitools_trimgalore" description: Read QC, UMI extraction and trimming keywords: @@ -49,12 +50,12 @@ input: output: - reads: - type: file - description: > - Extracted FASTQ files. | - For single-end reads, pattern is \${prefix}.umi_extract.fastq.gz. | - For paired-end reads, pattern is \${prefix}.umi_extract_{1,2}.fastq.gz. - pattern: "*.{fastq.gz}" + type: file + description: > + Extracted FASTQ files. | + For single-end reads, pattern is \${prefix}.umi_extract.fastq.gz. | + For paired-end reads, pattern is \${prefix}.umi_extract_{1,2}.fastq.gz. + pattern: "*.{fastq.gz}" - fastqc_html: type: file description: FastQC report diff --git a/subworkflows/nf-core/fastq_subsample_fq_salmon/meta.yml b/subworkflows/nf-core/fastq_subsample_fq_salmon/meta.yml index fd13a3748..db96312aa 100644 --- a/subworkflows/nf-core/fastq_subsample_fq_salmon/meta.yml +++ b/subworkflows/nf-core/fastq_subsample_fq_salmon/meta.yml @@ -1,3 +1,4 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json name: "fastq_subsample_fq_salmon" description: Subsample fastq keywords: From 0a1bdcfbb498987643b74e9fccab85ccd9f2a17d Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Sat, 6 May 2023 21:09:15 +0100 Subject: [PATCH 04/36] Update all local modules --- modules/local/bedtools_genomecov.nf | 2 +- modules/local/cat_additional_fasta.nf | 2 +- modules/local/dupradar.nf | 2 +- modules/local/gtf2bed.nf | 2 +- modules/local/gtf_gene_filter.nf | 2 +- modules/local/multiqc.nf | 2 +- modules/local/multiqc_custom_biotype.nf | 2 +- modules/local/preprocess_transcripts_fasta_gencode.nf | 2 +- modules/local/rsem_merge_counts.nf | 2 +- modules/local/salmon_summarizedexperiment.nf | 2 +- modules/local/salmon_tx2gene.nf | 2 +- modules/local/salmon_tximport.nf | 2 +- modules/local/samplesheet_check.nf | 2 +- modules/local/umitools_prepareforrsem.nf | 2 +- 14 files changed, 14 insertions(+), 14 deletions(-) diff --git a/modules/local/bedtools_genomecov.nf b/modules/local/bedtools_genomecov.nf index 8c684da30..0a0fb3c8b 100644 --- a/modules/local/bedtools_genomecov.nf +++ b/modules/local/bedtools_genomecov.nf @@ -5,7 +5,7 @@ process BEDTOOLS_GENOMECOV { conda "bioconda::bedtools=2.30.0" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/bedtools:2.30.0--hc088bd4_0' : - 'quay.io/biocontainers/bedtools:2.30.0--hc088bd4_0' }" + 'biocontainers/bedtools:2.30.0--hc088bd4_0' }" input: tuple val(meta), path(bam) diff --git a/modules/local/cat_additional_fasta.nf b/modules/local/cat_additional_fasta.nf index 1ec41b8f2..72af4bc54 100644 --- a/modules/local/cat_additional_fasta.nf +++ b/modules/local/cat_additional_fasta.nf @@ -4,7 +4,7 @@ process CAT_ADDITIONAL_FASTA { conda "conda-forge::python=3.9.5" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/python:3.9--1' : - 'quay.io/biocontainers/python:3.9--1' }" + 'biocontainers/python:3.9--1' }" input: path fasta diff --git a/modules/local/dupradar.nf b/modules/local/dupradar.nf index b2d40ad50..9f9152d1e 100644 --- a/modules/local/dupradar.nf +++ b/modules/local/dupradar.nf @@ -5,7 +5,7 @@ process DUPRADAR { conda "bioconda::bioconductor-dupradar=1.28.0" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/bioconductor-dupradar:1.28.0--r42hdfd78af_0' : - 'quay.io/biocontainers/bioconductor-dupradar:1.28.0--r42hdfd78af_0' }" + 'biocontainers/bioconductor-dupradar:1.28.0--r42hdfd78af_0' }" input: tuple val(meta), path(bam) diff --git a/modules/local/gtf2bed.nf b/modules/local/gtf2bed.nf index 30e2f1a6a..8a4bae8ff 100644 --- a/modules/local/gtf2bed.nf +++ b/modules/local/gtf2bed.nf @@ -5,7 +5,7 @@ process GTF2BED { conda "conda-forge::perl=5.26.2" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/perl:5.26.2' : - 'quay.io/biocontainers/perl:5.26.2' }" + 'biocontainers/perl:5.26.2' }" input: path gtf diff --git a/modules/local/gtf_gene_filter.nf b/modules/local/gtf_gene_filter.nf index 84d91e7ec..cd8e16adb 100644 --- a/modules/local/gtf_gene_filter.nf +++ b/modules/local/gtf_gene_filter.nf @@ -4,7 +4,7 @@ process GTF_GENE_FILTER { conda "conda-forge::python=3.9.5" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/python:3.9--1' : - 'quay.io/biocontainers/python:3.9--1' }" + 'biocontainers/python:3.9--1' }" input: path fasta diff --git a/modules/local/multiqc.nf b/modules/local/multiqc.nf index 802cebea9..6beb43310 100644 --- a/modules/local/multiqc.nf +++ b/modules/local/multiqc.nf @@ -4,7 +4,7 @@ process MULTIQC { conda "bioconda::multiqc=1.14" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/multiqc:1.14--pyhdfd78af_0' : - 'quay.io/biocontainers/multiqc:1.14--pyhdfd78af_0' }" + 'biocontainers/multiqc:1.14--pyhdfd78af_0' }" input: path multiqc_config diff --git a/modules/local/multiqc_custom_biotype.nf b/modules/local/multiqc_custom_biotype.nf index 49699826b..9c0fe94eb 100644 --- a/modules/local/multiqc_custom_biotype.nf +++ b/modules/local/multiqc_custom_biotype.nf @@ -4,7 +4,7 @@ process MULTIQC_CUSTOM_BIOTYPE { conda "conda-forge::python=3.9.5" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/python:3.9--1' : - 'quay.io/biocontainers/python:3.9--1' }" + 'biocontainers/python:3.9--1' }" input: tuple val(meta), path(count) diff --git a/modules/local/preprocess_transcripts_fasta_gencode.nf b/modules/local/preprocess_transcripts_fasta_gencode.nf index f882a24fc..41f1d42f6 100644 --- a/modules/local/preprocess_transcripts_fasta_gencode.nf +++ b/modules/local/preprocess_transcripts_fasta_gencode.nf @@ -4,7 +4,7 @@ process PREPROCESS_TRANSCRIPTS_FASTA_GENCODE { conda "conda-forge::sed=4.7" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/ubuntu:20.04' : - 'ubuntu:20.04' }" + 'nf-core/ubuntu:20.04' }" input: path fasta diff --git a/modules/local/rsem_merge_counts.nf b/modules/local/rsem_merge_counts.nf index 79548cc27..3f226f54d 100644 --- a/modules/local/rsem_merge_counts.nf +++ b/modules/local/rsem_merge_counts.nf @@ -4,7 +4,7 @@ process RSEM_MERGE_COUNTS { conda "conda-forge::sed=4.7" container "${ 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: path ('genes/*') diff --git a/modules/local/salmon_summarizedexperiment.nf b/modules/local/salmon_summarizedexperiment.nf index 5f0442db6..2278ea14e 100644 --- a/modules/local/salmon_summarizedexperiment.nf +++ b/modules/local/salmon_summarizedexperiment.nf @@ -5,7 +5,7 @@ process SALMON_SUMMARIZEDEXPERIMENT { conda "bioconda::bioconductor-summarizedexperiment=1.24.0" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/bioconductor-summarizedexperiment:1.24.0--r41hdfd78af_0' : - 'quay.io/biocontainers/bioconductor-summarizedexperiment:1.24.0--r41hdfd78af_0' }" + 'biocontainers/bioconductor-summarizedexperiment:1.24.0--r41hdfd78af_0' }" input: path counts diff --git a/modules/local/salmon_tx2gene.nf b/modules/local/salmon_tx2gene.nf index d19a436eb..b6e9df662 100644 --- a/modules/local/salmon_tx2gene.nf +++ b/modules/local/salmon_tx2gene.nf @@ -5,7 +5,7 @@ process SALMON_TX2GENE { conda "conda-forge::python=3.9.5" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/python:3.9--1' : - 'quay.io/biocontainers/python:3.9--1' }" + 'biocontainers/python:3.9--1' }" input: path ("salmon/*") diff --git a/modules/local/salmon_tximport.nf b/modules/local/salmon_tximport.nf index 8d58bb924..181c897cd 100644 --- a/modules/local/salmon_tximport.nf +++ b/modules/local/salmon_tximport.nf @@ -4,7 +4,7 @@ process SALMON_TXIMPORT { conda "bioconda::bioconductor-tximeta=1.12.0" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/bioconductor-tximeta:1.12.0--r41hdfd78af_0' : - 'quay.io/biocontainers/bioconductor-tximeta:1.12.0--r41hdfd78af_0' }" + 'biocontainers/bioconductor-tximeta:1.12.0--r41hdfd78af_0' }" input: path ("salmon/*") diff --git a/modules/local/samplesheet_check.nf b/modules/local/samplesheet_check.nf index 8e9079d9f..f8251de88 100644 --- a/modules/local/samplesheet_check.nf +++ b/modules/local/samplesheet_check.nf @@ -5,7 +5,7 @@ process SAMPLESHEET_CHECK { conda "conda-forge::python=3.9.5" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/python:3.9--1' : - 'quay.io/biocontainers/python:3.9--1' }" + 'biocontainers/python:3.9--1' }" input: path samplesheet diff --git a/modules/local/umitools_prepareforrsem.nf b/modules/local/umitools_prepareforrsem.nf index 416df567e..9ee41737d 100644 --- a/modules/local/umitools_prepareforrsem.nf +++ b/modules/local/umitools_prepareforrsem.nf @@ -5,7 +5,7 @@ process UMITOOLS_PREPAREFORRSEM { conda "bioconda::umi_tools=1.1.4" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/umi_tools:1.1.4--py38hbff2b2d_1' : - 'quay.io/biocontainers/umi_tools:1.1.4--py38hbff2b2d_1' }" + 'biocontainers/umi_tools:1.1.4--py38hbff2b2d_1' }" input: tuple val(meta), path(bam) From 94e371a8b0c19828cbd048ae20cdac52c26d9cb9 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Sat, 6 May 2023 21:19:24 +0100 Subject: [PATCH 05/36] Update CHANGELOG --- CHANGELOG.md | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 8cf2b7672..cfad407b5 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -9,6 +9,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - [PR #1016](https://github.com/nf-core/rnaseq/pull/1016) - Updated pipeline template to [nf-core/tools 2.8](https://github.com/nf-core/tools/releases/tag/2.8) +### Software dependencies + +| Dependency | Old version | New version | +| ---------- | ----------- | ----------- | +| `samtools` | 1.16.1 | 1.17 | + +> **NB:** Dependency has been **updated** if both old and new version information is present. +> +> **NB:** Dependency has been **added** if just the new version information is present. +> +> **NB:** Dependency has been **removed** if new version information isn't present. + ## [[3.11.2](https://github.com/nf-core/rnaseq/releases/tag/3.11.2)] - 2023-04-25 ### Credits From 8249632204f39eeea063f6d4d70e282d3fa6f9f7 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Sat, 6 May 2023 21:23:17 +0100 Subject: [PATCH 06/36] Update usage docs --- docs/usage.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/usage.md b/docs/usage.md index c4019fbee..2c4c45cf5 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -167,7 +167,7 @@ Please get in touch with us on the #rnaseq channel in the [nf-core Slack workspa The typical command for running the pipeline is as follows: ```bash -nextflow run nf-core/rnaseq --input samplesheet.csv --outdir --genome GRCh37 -profile docker +nextflow run nf-core/rnaseq --input ./samplesheet.csv --outdir ./results --genome GRCh37 -profile docker ``` This will launch the pipeline with the `docker` configuration profile. See below for more information about profiles. @@ -186,7 +186,8 @@ If you wish to repeatedly use the same parameters for multiple runs, rather than 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: + +The above pipeline run specified with a params file in yaml format: ```bash nextflow run nf-core/rnaseq -profile docker -params-file params.yaml @@ -198,7 +199,6 @@ with `params.yaml` containing: input: './samplesheet.csv' outdir: './results/' genome: 'GRCh37' -input: 'data' <...> ``` From 3b5b64cb91937be53e4edb22c06af138961584a0 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Sun, 7 May 2023 09:04:48 +0100 Subject: [PATCH 07/36] Fix alignment in nextflow.config --- nextflow.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/nextflow.config b/nextflow.config index bf711bf42..bf8158983 100644 --- a/nextflow.config +++ b/nextflow.config @@ -145,7 +145,7 @@ profiles { debug { dumpHashes = true process.beforeScript = 'echo $HOSTNAME' - cleanup = false + cleanup = false } conda { conda.enabled = true From 92b2a7857de1dda9d1c19a088941fc81e2976ff7 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Mon, 8 May 2023 19:18:20 +0100 Subject: [PATCH 08/36] Remove quay.io prefix from mulled containers --- modules/local/deseq2_qc.nf | 2 +- modules/local/star_align_igenomes.nf | 2 +- modules/local/star_genomegenerate_igenomes.nf | 2 +- modules/nf-core/hisat2/align/main.nf | 2 +- modules/nf-core/rsem/calculateexpression/main.nf | 2 +- modules/nf-core/rsem/preparereference/main.nf | 2 +- modules/nf-core/star/align/main.nf | 2 +- modules/nf-core/star/genomegenerate/main.nf | 2 +- 8 files changed, 8 insertions(+), 8 deletions(-) diff --git a/modules/local/deseq2_qc.nf b/modules/local/deseq2_qc.nf index 73953119d..7b3fac57b 100644 --- a/modules/local/deseq2_qc.nf +++ b/modules/local/deseq2_qc.nf @@ -6,7 +6,7 @@ process DESEQ2_QC { conda "conda-forge::r-base bioconda::bioconductor-deseq2 bioconda::bioconductor-biocparallel bioconda::bioconductor-tximport bioconda::bioconductor-complexheatmap conda-forge::r-optparse conda-forge::r-ggplot2 conda-forge::r-rcolorbrewer conda-forge::r-pheatmap" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/mulled-v2-8849acf39a43cdd6c839a369a74c0adc823e2f91:ab110436faf952a33575c64dd74615a84011450b-0' : - 'quay.io/biocontainers/mulled-v2-8849acf39a43cdd6c839a369a74c0adc823e2f91:ab110436faf952a33575c64dd74615a84011450b-0' }" + 'biocontainers/mulled-v2-8849acf39a43cdd6c839a369a74c0adc823e2f91:ab110436faf952a33575c64dd74615a84011450b-0' }" input: path counts diff --git a/modules/local/star_align_igenomes.nf b/modules/local/star_align_igenomes.nf index d09e6df02..3e5a169d8 100644 --- a/modules/local/star_align_igenomes.nf +++ b/modules/local/star_align_igenomes.nf @@ -5,7 +5,7 @@ process STAR_ALIGN_IGENOMES { conda "bioconda::star=2.6.1d bioconda::samtools=1.10 conda-forge::gawk=5.1.0" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0' : - 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0' }" + 'biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0' }" input: tuple val(meta), path(reads) diff --git a/modules/local/star_genomegenerate_igenomes.nf b/modules/local/star_genomegenerate_igenomes.nf index 1b9b34cf7..7766faaaf 100644 --- a/modules/local/star_genomegenerate_igenomes.nf +++ b/modules/local/star_genomegenerate_igenomes.nf @@ -5,7 +5,7 @@ process STAR_GENOMEGENERATE_IGENOMES { conda "bioconda::star=2.6.1d bioconda::samtools=1.10 conda-forge::gawk=5.1.0" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0' : - 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0' }" + 'biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0' }" input: path fasta diff --git a/modules/nf-core/hisat2/align/main.nf b/modules/nf-core/hisat2/align/main.nf index eefb5819e..542815d2c 100644 --- a/modules/nf-core/hisat2/align/main.nf +++ b/modules/nf-core/hisat2/align/main.nf @@ -6,7 +6,7 @@ process HISAT2_ALIGN { conda "bioconda::hisat2=2.2.1 bioconda::samtools=1.16.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/mulled-v2-a97e90b3b802d1da3d6958e0867610c718cb5eb1:2cdf6bf1e92acbeb9b2834b1c58754167173a410-0' : - 'quay.io/biocontainers/mulled-v2-a97e90b3b802d1da3d6958e0867610c718cb5eb1:2cdf6bf1e92acbeb9b2834b1c58754167173a410-0' }" + 'biocontainers/mulled-v2-a97e90b3b802d1da3d6958e0867610c718cb5eb1:2cdf6bf1e92acbeb9b2834b1c58754167173a410-0' }" input: tuple val(meta), path(reads) diff --git a/modules/nf-core/rsem/calculateexpression/main.nf b/modules/nf-core/rsem/calculateexpression/main.nf index aa9de7bc3..54041aedb 100644 --- a/modules/nf-core/rsem/calculateexpression/main.nf +++ b/modules/nf-core/rsem/calculateexpression/main.nf @@ -5,7 +5,7 @@ process RSEM_CALCULATEEXPRESSION { conda "bioconda::rsem=1.3.3 bioconda::star=2.7.10a" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' : - 'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' }" + 'biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' }" input: tuple val(meta), path(reads) diff --git a/modules/nf-core/rsem/preparereference/main.nf b/modules/nf-core/rsem/preparereference/main.nf index 25c037b33..62b93d08a 100644 --- a/modules/nf-core/rsem/preparereference/main.nf +++ b/modules/nf-core/rsem/preparereference/main.nf @@ -5,7 +5,7 @@ process RSEM_PREPAREREFERENCE { conda "bioconda::rsem=1.3.3 bioconda::star=2.7.10a" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' : - 'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' }" + 'biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' }" input: path fasta, stageAs: "rsem/*" diff --git a/modules/nf-core/star/align/main.nf b/modules/nf-core/star/align/main.nf index e6c4443cb..54d35f7d3 100644 --- a/modules/nf-core/star/align/main.nf +++ b/modules/nf-core/star/align/main.nf @@ -5,7 +5,7 @@ process STAR_ALIGN { conda "bioconda::star=2.7.10a bioconda::samtools=1.16.1 conda-forge::gawk=5.1.0" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1df389393721fc66f3fd8778ad938ac711951107-0' : - 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1df389393721fc66f3fd8778ad938ac711951107-0' }" + 'biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1df389393721fc66f3fd8778ad938ac711951107-0' }" input: tuple val(meta), path(reads) diff --git a/modules/nf-core/star/genomegenerate/main.nf b/modules/nf-core/star/genomegenerate/main.nf index 91462489f..2407d0066 100644 --- a/modules/nf-core/star/genomegenerate/main.nf +++ b/modules/nf-core/star/genomegenerate/main.nf @@ -5,7 +5,7 @@ process STAR_GENOMEGENERATE { conda "bioconda::star=2.7.10a bioconda::samtools=1.16.1 conda-forge::gawk=5.1.0" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1df389393721fc66f3fd8778ad938ac711951107-0' : - 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1df389393721fc66f3fd8778ad938ac711951107-0' }" + 'biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1df389393721fc66f3fd8778ad938ac711951107-0' }" input: path fasta From 252fd9df32c0036d14a07bcfa8c1254e428e7609 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Tue, 9 May 2023 18:01:21 +0100 Subject: [PATCH 09/36] Update usage docs --- docs/usage.md | 6 +++--- modules.json | 10 +++++----- modules/nf-core/rsem/preparereference/meta.yml | 3 ++- 3 files changed, 10 insertions(+), 9 deletions(-) diff --git a/docs/usage.md b/docs/usage.md index 2c4c45cf5..69c906c47 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -167,7 +167,7 @@ Please get in touch with us on the #rnaseq channel in the [nf-core Slack workspa The typical command for running the pipeline is as follows: ```bash -nextflow run nf-core/rnaseq --input ./samplesheet.csv --outdir ./results --genome GRCh37 -profile docker +nextflow run nf-core/rnaseq --input --outdir --genome GRCh37 -profile docker ``` This will launch the pipeline with the `docker` configuration profile. See below for more information about profiles. @@ -196,8 +196,8 @@ nextflow run nf-core/rnaseq -profile docker -params-file params.yaml with `params.yaml` containing: ```yaml -input: './samplesheet.csv' -outdir: './results/' +input: +outdir: genome: 'GRCh37' <...> ``` diff --git a/modules.json b/modules.json index 952e378fb..468cc2b86 100644 --- a/modules.json +++ b/modules.json @@ -52,7 +52,7 @@ }, "hisat2/align": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "603ecbd9f45300c9788f197d2a15a005685b4220", "installed_by": ["fastq_align_hisat2"] }, "hisat2/build": { @@ -82,12 +82,12 @@ }, "rsem/calculateexpression": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "603ecbd9f45300c9788f197d2a15a005685b4220", "installed_by": ["modules"] }, "rsem/preparereference": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "603ecbd9f45300c9788f197d2a15a005685b4220", "installed_by": ["modules"] }, "rseqc/bamstat": { @@ -176,12 +176,12 @@ }, "star/align": { "branch": "master", - "git_sha": "140d5a0d014138524e21dea80588817ddfc5dcf4", + "git_sha": "603ecbd9f45300c9788f197d2a15a005685b4220", "installed_by": ["modules"] }, "star/genomegenerate": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "603ecbd9f45300c9788f197d2a15a005685b4220", "installed_by": ["modules"] }, "stringtie/stringtie": { diff --git a/modules/nf-core/rsem/preparereference/meta.yml b/modules/nf-core/rsem/preparereference/meta.yml index b1d013b9c..3568e1911 100644 --- a/modules/nf-core/rsem/preparereference/meta.yml +++ b/modules/nf-core/rsem/preparereference/meta.yml @@ -2,7 +2,8 @@ name: rsem_preparereference description: Prepare a reference genome for RSEM keywords: - rsem - - reference + - genome + - index tools: - rseqc: description: | From a350ca1905570e0b98f3e18e877b611037edb491 Mon Sep 17 00:00:00 2001 From: Robert Syme Date: Thu, 11 May 2023 03:11:26 +0000 Subject: [PATCH 10/36] Set a default docker registry outside of profile scope. The `docker.registry` configuration should always be set, as running on cloud executors will need to pull docker images but will not necessarily use the `docker` profile. --- nextflow.config | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/nextflow.config b/nextflow.config index bf8158983..ef99b3ff2 100644 --- a/nextflow.config +++ b/nextflow.config @@ -168,7 +168,6 @@ profiles { } docker { docker.enabled = true - docker.registry = 'quay.io' docker.userEmulation = true conda.enabled = false singularity.enabled = false @@ -263,6 +262,9 @@ env { JULIA_DEPOT_PATH = "/usr/local/share/julia" } +// Set default docker registry (will be unused unless pulling docker images) +docker.registry = 'quay.io' + def trace_timestamp = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss') timeline { enabled = true From 969be28a90d0b914eca848af0e2a297049aabc8c Mon Sep 17 00:00:00 2001 From: Maxime U Garcia Date: Thu, 11 May 2023 11:09:15 +0200 Subject: [PATCH 11/36] Update nextflow.config --- nextflow.config | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/nextflow.config b/nextflow.config index ef99b3ff2..d3ac56756 100644 --- a/nextflow.config +++ b/nextflow.config @@ -191,7 +191,6 @@ profiles { } podman { podman.enabled = true - podman.registry = 'quay.io' conda.enabled = false docker.enabled = false singularity.enabled = false @@ -262,8 +261,11 @@ env { JULIA_DEPOT_PATH = "/usr/local/share/julia" } -// Set default docker registry (will be unused unless pulling docker images) +// Set default registry for Docker and Podman independent of -profile +// Will not be used unless Docker / Podman are enabled +// Set to your registry if you have a mirror of containers docker.registry = 'quay.io' +podman.registry = 'quay.io' def trace_timestamp = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss') timeline { From deffccbeacadef2f6034db8a797a04b0a5aad427 Mon Sep 17 00:00:00 2001 From: Maxime U Garcia Date: Thu, 11 May 2023 11:15:51 +0200 Subject: [PATCH 12/36] Update nextflow.config restore process.shell declaration --- nextflow.config | 3 +++ 1 file changed, 3 insertions(+) diff --git a/nextflow.config b/nextflow.config index d3ac56756..9703d47a0 100644 --- a/nextflow.config +++ b/nextflow.config @@ -261,6 +261,9 @@ env { JULIA_DEPOT_PATH = "/usr/local/share/julia" } +// Capture exit codes from upstream processes when piping +process.shell = ['/bin/bash', '-euo', 'pipefail'] + // Set default registry for Docker and Podman independent of -profile // Will not be used unless Docker / Podman are enabled // Set to your registry if you have a mirror of containers From e2a482ebec804c241fb507af8deb8c5baeec21a8 Mon Sep 17 00:00:00 2001 From: Ghepardo <71766441+Ghepardo@users.noreply.github.com> Date: Thu, 11 May 2023 11:21:38 +0100 Subject: [PATCH 13/36] Update README.md Corrected spelling of name "Edmund Miller". --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 7d64b451b..8d3893e36 100644 --- a/README.md +++ b/README.md @@ -104,7 +104,7 @@ Many thanks to other who have helped out along the way too, including (but not l - [Alex Peltzer](https://github.com/apeltzer) - [Colin Davenport](https://github.com/colindaven) - [Denis Moreno](https://github.com/Galithil) -- [Edumnd Miller](https://github.com/Emiller88) +- [Edmund Miller](https://github.com/Emiller88) - [Gregor Sturm](https://github.com/grst) - [Jacki Buros Novik](https://github.com/jburos) - [Lorena Pantano](https://github.com/lpantano) From b1115abe895486663aa9a39d052e7d01d9ae8732 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Sun, 14 May 2023 20:51:05 +0100 Subject: [PATCH 14/36] Add public_aws_ecr.config and use in CI tests --- .github/workflows/cloud_tests_full.yml | 2 +- .github/workflows/cloud_tests_small.yml | 2 +- conf/public_aws_ecr.config | 54 +++++++++++++++++++++++++ nextflow.config | 7 +++- 4 files changed, 62 insertions(+), 3 deletions(-) create mode 100644 conf/public_aws_ecr.config diff --git a/.github/workflows/cloud_tests_full.yml b/.github/workflows/cloud_tests_full.yml index 3c4b23106..4738d9045 100644 --- a/.github/workflows/cloud_tests_full.yml +++ b/.github/workflows/cloud_tests_full.yml @@ -30,7 +30,7 @@ jobs: compute_env: ${{ secrets.TOWER_CE_AWS_CPU }} workdir: "${{ secrets.TOWER_BUCKET_AWS }}/work/rnaseq/work-${{ github.sha }}" run_name: "aws_rnaseq_full_${{ matrix.aligner }}" - profiles: test_full_aws + profiles: test_full_aws,public_aws_ecr parameters: | { "hook_url": "${{ secrets.MEGATESTS_ALERTS_SLACK_HOOK_URL }}", diff --git a/.github/workflows/cloud_tests_small.yml b/.github/workflows/cloud_tests_small.yml index 6f2e6d8a9..1f430067b 100644 --- a/.github/workflows/cloud_tests_small.yml +++ b/.github/workflows/cloud_tests_small.yml @@ -25,7 +25,7 @@ jobs: compute_env: ${{ secrets.TOWER_CE_AWS_CPU }} workdir: "${{ secrets.TOWER_BUCKET_AWS }}/work/rnaseq/work-${{ github.sha }}" run_name: "aws_rnaseq_small" - profiles: test + profiles: test,public_aws_ecr parameters: | { "outdir": "${{ secrets.TOWER_BUCKET_AWS }}/rnaseq/results-test-${{ github.sha }}" diff --git a/conf/public_aws_ecr.config b/conf/public_aws_ecr.config new file mode 100644 index 000000000..da951fc62 --- /dev/null +++ b/conf/public_aws_ecr.config @@ -0,0 +1,54 @@ +/* +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + AWS ECR Config +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Config to set public AWS ECR images wherever possible + This improves speed when running on AWS infrastructure. + Use this as an example template when using your own private registry. +---------------------------------------------------------------------------------------- +*/ + +docker.registry = 'public.ecr.aws' +podman.registry = 'public.ecr.aws' + +process { + withName: '.*:CAT_FASTQ' { + container = 'quay.io/nf-core/ubuntu:20.04' + } + withName: '.*:DESEQ2_QC' { + container = 'quay.io/biocontainers/mulled-v2-8849acf39a43cdd6c839a369a74c0adc823e2f91:ab110436faf952a33575c64dd74615a84011450b-0' + } + withName: '.*:GUNZIP' { + container = 'quay.io/nf-core/ubuntu:20.04' + } + withName: '.*:HISAT2_ALIGN' { + container = 'quay.io/biocontainers/mulled-v2-a97e90b3b802d1da3d6958e0867610c718cb5eb1:2cdf6bf1e92acbeb9b2834b1c58754167173a410-0' + } + withName: '.*:PREPROCESS_TRANSCRIPTS_FASTA_GENCODE' { + container = 'quay.io/nf-core/ubuntu:20.04' + } + withName: '.*:RSEM_CALCULATEEXPRESSION' { + container = 'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' + } + withName: '.*:RSEM_MERGE_COUNTS' { + container = 'quay.io/nf-core/ubuntu:20.04' + } + withName: '.*:RSEM_PREPAREREFERENCE' { + container = 'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' + } + withName: '.*:STAR_ALIGN' { + container = 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1df389393721fc66f3fd8778ad938ac711951107-0' + } + withName: '.*:STAR_ALIGN_IGENOMES' { + container = 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0' + } + withName: '.*:STAR_GENOMEGENERATE' { + container = 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1df389393721fc66f3fd8778ad938ac711951107-0' + } + withName: '.*:STAR_GENOMEGENERATE_IGENOMES' { + container = 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0' + } + withName: '.*:UNTAR' { + container = 'quay.io/nf-core/ubuntu:20.04' + } +} diff --git a/nextflow.config b/nextflow.config index 9703d47a0..633b2fc41 100644 --- a/nextflow.config +++ b/nextflow.config @@ -230,9 +230,14 @@ profiles { executor.cpus = 16 executor.memory = 60.GB } + public_aws_ecr { + includeConfig 'conf/public_aws_ecr.config' + } test { includeConfig 'conf/test.config' } test_full { includeConfig 'conf/test_full.config' } - test_full_aws { includeConfig 'conf/test_full.config' } + test_full_aws { + includeConfig 'conf/test_full.config' + } test_full_gcp { includeConfig 'conf/test_full.config' params.input = 'https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq/samplesheet/v3.10/samplesheet_full_gcp.csv' From e6ee9599746dbf8506ae9baa9053977ea3848b36 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Sun, 14 May 2023 20:53:13 +0100 Subject: [PATCH 15/36] Update CHANGELOG --- CHANGELOG.md | 1 + 1 file changed, 1 insertion(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index cfad407b5..9412327f6 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -8,6 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Enhancements & fixes - [PR #1016](https://github.com/nf-core/rnaseq/pull/1016) - Updated pipeline template to [nf-core/tools 2.8](https://github.com/nf-core/tools/releases/tag/2.8) +- [PR #1025](https://github.com/nf-core/fetchngs/pull/1025) - Add `public_aws_ecr.config` to source mulled containers when using `public.ecr.aws` Docker Biocontainer registry ### Software dependencies From 65651d62a07b324231cdc8f95d7d077a5eaac1f0 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Sun, 14 May 2023 20:53:46 +0100 Subject: [PATCH 16/36] Fix ECLint --- conf/public_aws_ecr.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/public_aws_ecr.config b/conf/public_aws_ecr.config index da951fc62..ac6179a9a 100644 --- a/conf/public_aws_ecr.config +++ b/conf/public_aws_ecr.config @@ -16,7 +16,7 @@ process { container = 'quay.io/nf-core/ubuntu:20.04' } withName: '.*:DESEQ2_QC' { - container = 'quay.io/biocontainers/mulled-v2-8849acf39a43cdd6c839a369a74c0adc823e2f91:ab110436faf952a33575c64dd74615a84011450b-0' + container = 'quay.io/biocontainers/mulled-v2-8849acf39a43cdd6c839a369a74c0adc823e2f91:ab110436faf952a33575c64dd74615a84011450b-0' } withName: '.*:GUNZIP' { container = 'quay.io/nf-core/ubuntu:20.04' From 93a30ae0438a1dacbe33aa55b0a84ec027a81fc0 Mon Sep 17 00:00:00 2001 From: maxulysse Date: Mon, 15 May 2023 09:23:41 +0200 Subject: [PATCH 17/36] PROFILES: test -> test_cache + restore test --- .github/workflows/ci.yml | 10 ++++---- conf/test_cache.config | 49 ++++++++++++++++++++++++++++++++++++++++ nextflow.config | 1 + 3 files changed, 55 insertions(+), 5 deletions(-) create mode 100644 conf/test_cache.config diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 52b9001b5..ba11abeab 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -66,7 +66,7 @@ jobs: - name: Run pipeline with test data run: | - nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/ + nextflow run ${GITHUB_WORKSPACE} -profile test_cache,docker --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/ star_salmon: name: Test STAR Salmon with workflow parameters @@ -128,7 +128,7 @@ jobs: - name: Run pipeline with STAR and various parameters run: | - nextflow run ${GITHUB_WORKSPACE} -profile test,docker --aligner star_salmon ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/ + nextflow run ${GITHUB_WORKSPACE} -profile test_cache,docker --aligner star_salmon ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/ star_rsem: name: Test STAR RSEM with workflow parameters @@ -179,7 +179,7 @@ jobs: - name: Run pipeline with RSEM STAR and various parameters run: | - nextflow run ${GITHUB_WORKSPACE} -profile test,docker --aligner star_rsem ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/ + nextflow run ${GITHUB_WORKSPACE} -profile test_cache,docker --aligner star_rsem ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/ hisat2: name: Test HISAT2 with workflow parameters @@ -230,7 +230,7 @@ jobs: - name: Run pipeline with HISAT2 and various parameters run: | - nextflow run ${GITHUB_WORKSPACE} -profile test,docker --aligner hisat2 ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/ + nextflow run ${GITHUB_WORKSPACE} -profile test_cache,docker --aligner hisat2 ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/ salmon: name: Test Salmon with workflow parameters @@ -281,4 +281,4 @@ jobs: - name: Run pipeline with Salmon and various parameters run: | - nextflow run ${GITHUB_WORKSPACE} -profile test,docker --pseudo_aligner salmon ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/ + nextflow run ${GITHUB_WORKSPACE} -profile test_cache,docker --pseudo_aligner salmon ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/ diff --git a/conf/test_cache.config b/conf/test_cache.config new file mode 100644 index 000000000..caddf594c --- /dev/null +++ b/conf/test_cache.config @@ -0,0 +1,49 @@ +/* +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Nextflow config file for running minimal tests +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Defines input files and everything required to run a fast and simple pipeline test. + + Use as follows: + nextflow run nf-core/rnaseq -profile test, --outdir + +---------------------------------------------------------------------------------------- +*/ + +params { + config_profile_name = 'Test profile' + config_profile_description = 'Minimal test dataset to check pipeline function' + + // Limit resources so that this can run on GitHub Actions + max_cpus = 2 + max_memory = '6.GB' + max_time = '6.h' + + + // Input data + input = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/samplesheet/v3.10/samplesheet_test.csv" + + // Genome references + fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/genome.fasta" + gtf = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/genes.gtf.gz" + gff = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/genes.gff.gz" + transcript_fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/transcriptome.fasta" + additional_fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/gfp.fa.gz" + + bbsplit_fasta_list = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/bbsplit_fasta_list.txt" + hisat2_index = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/hisat2.tar.gz" + salmon_index = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/salmon.tar.gz" + rsem_index = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/rsem.tar.gz" + + // Other parameters + skip_bbsplit = false + pseudo_aligner = 'salmon' + umitools_bc_pattern = 'NNNN' +} + +// When using RSEM, remove warning from STAR whilst building tiny indices +process { + withName: 'RSEM_PREPAREREFERENCE_GENOME' { + ext.args2 = "--genomeSAindexNbases 7" + } +} diff --git a/nextflow.config b/nextflow.config index 9703d47a0..4831e0f03 100644 --- a/nextflow.config +++ b/nextflow.config @@ -231,6 +231,7 @@ profiles { executor.memory = 60.GB } test { includeConfig 'conf/test.config' } + test_cache { includeConfig 'conf/test_cache.config' } test_full { includeConfig 'conf/test_full.config' } test_full_aws { includeConfig 'conf/test_full.config' } test_full_gcp { From bca283b8a89e3b94c55c2888fa89451477222fc8 Mon Sep 17 00:00:00 2001 From: maxulysse Date: Mon, 15 May 2023 18:37:51 +0200 Subject: [PATCH 18/36] actually swap the files --- conf/test.config | 23 +++++++++++------------ conf/test_cache.config | 23 ++++++++++++----------- 2 files changed, 23 insertions(+), 23 deletions(-) diff --git a/conf/test.config b/conf/test.config index 7ba43957c..caddf594c 100644 --- a/conf/test.config +++ b/conf/test.config @@ -21,20 +21,19 @@ params { // Input data - // params.test_data_base (default) = 'https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/' - input = "${params.test_data_base}/samplesheet/v3.10/samplesheet_test.csv" + input = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/samplesheet/v3.10/samplesheet_test.csv" // Genome references - fasta = "${params.test_data_base}/reference/genome.fasta" - gtf = "${params.test_data_base}/reference/genes.gtf.gz" - gff = "${params.test_data_base}/reference/genes.gff.gz" - transcript_fasta = "${params.test_data_base}/reference/transcriptome.fasta" - additional_fasta = "${params.test_data_base}/reference/gfp.fa.gz" - - bbsplit_fasta_list = "${params.test_data_base}/reference/bbsplit_fasta_list.txt" - hisat2_index = "${params.test_data_base}/reference/hisat2.tar.gz" - salmon_index = "${params.test_data_base}/reference/salmon.tar.gz" - rsem_index = "${params.test_data_base}/reference/rsem.tar.gz" + fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/genome.fasta" + gtf = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/genes.gtf.gz" + gff = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/genes.gff.gz" + transcript_fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/transcriptome.fasta" + additional_fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/gfp.fa.gz" + + bbsplit_fasta_list = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/bbsplit_fasta_list.txt" + hisat2_index = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/hisat2.tar.gz" + salmon_index = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/salmon.tar.gz" + rsem_index = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/rsem.tar.gz" // Other parameters skip_bbsplit = false diff --git a/conf/test_cache.config b/conf/test_cache.config index caddf594c..7ba43957c 100644 --- a/conf/test_cache.config +++ b/conf/test_cache.config @@ -21,19 +21,20 @@ params { // Input data - input = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/samplesheet/v3.10/samplesheet_test.csv" + // params.test_data_base (default) = 'https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/' + input = "${params.test_data_base}/samplesheet/v3.10/samplesheet_test.csv" // Genome references - fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/genome.fasta" - gtf = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/genes.gtf.gz" - gff = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/genes.gff.gz" - transcript_fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/transcriptome.fasta" - additional_fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/gfp.fa.gz" - - bbsplit_fasta_list = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/bbsplit_fasta_list.txt" - hisat2_index = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/hisat2.tar.gz" - salmon_index = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/salmon.tar.gz" - rsem_index = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/rsem.tar.gz" + fasta = "${params.test_data_base}/reference/genome.fasta" + gtf = "${params.test_data_base}/reference/genes.gtf.gz" + gff = "${params.test_data_base}/reference/genes.gff.gz" + transcript_fasta = "${params.test_data_base}/reference/transcriptome.fasta" + additional_fasta = "${params.test_data_base}/reference/gfp.fa.gz" + + bbsplit_fasta_list = "${params.test_data_base}/reference/bbsplit_fasta_list.txt" + hisat2_index = "${params.test_data_base}/reference/hisat2.tar.gz" + salmon_index = "${params.test_data_base}/reference/salmon.tar.gz" + rsem_index = "${params.test_data_base}/reference/rsem.tar.gz" // Other parameters skip_bbsplit = false From 3b41ca82c915ed3397c594bd4b54229de3315595 Mon Sep 17 00:00:00 2001 From: maxulysse Date: Mon, 15 May 2023 18:40:36 +0200 Subject: [PATCH 19/36] spacing --- nextflow.config | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/nextflow.config b/nextflow.config index 4831e0f03..4248c1176 100644 --- a/nextflow.config +++ b/nextflow.config @@ -230,10 +230,10 @@ profiles { executor.cpus = 16 executor.memory = 60.GB } - test { includeConfig 'conf/test.config' } - test_cache { includeConfig 'conf/test_cache.config' } - test_full { includeConfig 'conf/test_full.config' } - test_full_aws { includeConfig 'conf/test_full.config' } + test { includeConfig 'conf/test.config' } + test_cache { includeConfig 'conf/test_cache.config' } + test_full { includeConfig 'conf/test_full.config' } + test_full_aws { includeConfig 'conf/test_full.config' } test_full_gcp { includeConfig 'conf/test_full.config' params.input = 'https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq/samplesheet/v3.10/samplesheet_full_gcp.csv' From cfe179a20ccd38f61d32c1b249764f28354ceb54 Mon Sep 17 00:00:00 2001 From: Maxime U Garcia Date: Tue, 23 May 2023 13:37:10 +0200 Subject: [PATCH 20/36] Update conf/test.config Co-authored-by: Harshil Patel --- conf/test.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/test.config b/conf/test.config index caddf594c..f77abd48b 100644 --- a/conf/test.config +++ b/conf/test.config @@ -21,7 +21,7 @@ params { // Input data - input = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/samplesheet/v3.10/samplesheet_test.csv" + input = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq/samplesheet/v3.10/samplesheet_test.csv" // Genome references fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/genome.fasta" From ed230703363463af47cc09af3c39abce303de7f1 Mon Sep 17 00:00:00 2001 From: Adam Talbot Date: Wed, 24 May 2023 18:03:08 +0100 Subject: [PATCH 21/36] Fix for public_aws_ecr profile that didn't match modules sometimes --- conf/public_aws_ecr.config | 32 +++++++++++++++++++------------- 1 file changed, 19 insertions(+), 13 deletions(-) diff --git a/conf/public_aws_ecr.config b/conf/public_aws_ecr.config index ac6179a9a..7356010d8 100644 --- a/conf/public_aws_ecr.config +++ b/conf/public_aws_ecr.config @@ -12,43 +12,49 @@ docker.registry = 'public.ecr.aws' podman.registry = 'public.ecr.aws' process { - withName: '.*:CAT_FASTQ' { + withName: 'CAT_FASTQ' { container = 'quay.io/nf-core/ubuntu:20.04' } - withName: '.*:DESEQ2_QC' { + withName: 'SAMPLESHEET_CHECK|CAT_ADDITIONAL_FASTA|GTF_GENE_FILTER|MULTIQC_CUSTOM_BIOTYPE|SALMON_TX2GENE' { + container = 'quay.io/biocontainers/python:3.9--1' + } + withName: 'GTF2BED' { + container = 'quay.io/biocontainers/perl:5.26.2' + } + withName: 'DESEQ2_QC' { container = 'quay.io/biocontainers/mulled-v2-8849acf39a43cdd6c839a369a74c0adc823e2f91:ab110436faf952a33575c64dd74615a84011450b-0' } - withName: '.*:GUNZIP' { + withName: 'GUNZIP' { container = 'quay.io/nf-core/ubuntu:20.04' } - withName: '.*:HISAT2_ALIGN' { + withName: 'HISAT2_ALIGN' { container = 'quay.io/biocontainers/mulled-v2-a97e90b3b802d1da3d6958e0867610c718cb5eb1:2cdf6bf1e92acbeb9b2834b1c58754167173a410-0' } - withName: '.*:PREPROCESS_TRANSCRIPTS_FASTA_GENCODE' { + withName: 'PREPROCESS_TRANSCRIPTS_FASTA_GENCODE' { container = 'quay.io/nf-core/ubuntu:20.04' } - withName: '.*:RSEM_CALCULATEEXPRESSION' { + withName: 'RSEM_CALCULATEEXPRESSION' { container = 'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' } - withName: '.*:RSEM_MERGE_COUNTS' { + withName: 'RSEM_MERGE_COUNTS' { container = 'quay.io/nf-core/ubuntu:20.04' } - withName: '.*:RSEM_PREPAREREFERENCE' { + withName: 'RSEM_PREPAREREFERENCE' { container = 'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' } - withName: '.*:STAR_ALIGN' { + withName: 'STAR_ALIGN' { container = 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1df389393721fc66f3fd8778ad938ac711951107-0' } - withName: '.*:STAR_ALIGN_IGENOMES' { + withName: 'STAR_ALIGN_IGENOMES' { container = 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0' } - withName: '.*:STAR_GENOMEGENERATE' { + withName: 'STAR_GENOMEGENERATE' { container = 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1df389393721fc66f3fd8778ad938ac711951107-0' } - withName: '.*:STAR_GENOMEGENERATE_IGENOMES' { + withName: 'STAR_GENOMEGENERATE_IGENOMES' { container = 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0' } - withName: '.*:UNTAR' { + withName: 'UNTAR' { container = 'quay.io/nf-core/ubuntu:20.04' } } From ed32820f7d20e6b46a2af848989ca8f6ea34b2a2 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Thu, 25 May 2023 13:11:27 +0100 Subject: [PATCH 22/36] Update test configs --- conf/test.config | 20 ++++++++++---------- conf/test_cache.config | 2 +- 2 files changed, 11 insertions(+), 11 deletions(-) diff --git a/conf/test.config b/conf/test.config index f77abd48b..d0430eacb 100644 --- a/conf/test.config +++ b/conf/test.config @@ -24,16 +24,16 @@ params { input = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq/samplesheet/v3.10/samplesheet_test.csv" // Genome references - fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/genome.fasta" - gtf = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/genes.gtf.gz" - gff = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/genes.gff.gz" - transcript_fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/transcriptome.fasta" - additional_fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/gfp.fa.gz" - - bbsplit_fasta_list = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/bbsplit_fasta_list.txt" - hisat2_index = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/hisat2.tar.gz" - salmon_index = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/salmon.tar.gz" - rsem_index = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq3/reference/rsem.tar.gz" + fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq/reference/genome.fasta" + gtf = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq/reference/genes.gtf.gz" + gff = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq/reference/genes.gff.gz" + transcript_fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq/reference/transcriptome.fasta" + additional_fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq/reference/gfp.fa.gz" + + bbsplit_fasta_list = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq/reference/bbsplit_fasta_list.txt" + hisat2_index = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq/reference/hisat2.tar.gz" + salmon_index = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq/reference/salmon.tar.gz" + rsem_index = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq/reference/rsem.tar.gz" // Other parameters skip_bbsplit = false diff --git a/conf/test_cache.config b/conf/test_cache.config index 7ba43957c..51aad577e 100644 --- a/conf/test_cache.config +++ b/conf/test_cache.config @@ -1,6 +1,6 @@ /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - Nextflow config file for running minimal tests + Nextflow config file for running minimal tests using cached / offline test data ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Defines input files and everything required to run a fast and simple pipeline test. From ea3427b69d066f9239508b88f818487f7f7364b2 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Tue, 30 May 2023 21:18:30 +0100 Subject: [PATCH 23/36] Fix #1011 --- CHANGELOG.md | 2 ++ modules.json | 4 ++-- modules/nf-core/fastp/main.nf | 6 +++--- subworkflows/nf-core/fastq_fastqc_umitools_fastp/main.nf | 2 +- 4 files changed, 8 insertions(+), 6 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 9412327f6..fe4de1224 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Enhancements & fixes +- [[#1011](https://github.com/nf-core/rnaseq/issues/1011)] - FastQ files from UMI-tools not being passed to fastp - [PR #1016](https://github.com/nf-core/rnaseq/pull/1016) - Updated pipeline template to [nf-core/tools 2.8](https://github.com/nf-core/tools/releases/tag/2.8) - [PR #1025](https://github.com/nf-core/fetchngs/pull/1025) - Add `public_aws_ecr.config` to source mulled containers when using `public.ecr.aws` Docker Biocontainer registry @@ -14,6 +15,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 | Dependency | Old version | New version | | ---------- | ----------- | ----------- | +| `fastp` | 0.23.2 | 0.23.3 | | `samtools` | 1.16.1 | 1.17 | > **NB:** Dependency has been **updated** if both old and new version information is present. diff --git a/modules.json b/modules.json index 468cc2b86..13f71805b 100644 --- a/modules.json +++ b/modules.json @@ -27,7 +27,7 @@ }, "fastp": { "branch": "master", - "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "git_sha": "37a98dd100d74d9188a272197663587de1331a0e", "installed_by": ["modules", "fastq_fastqc_umitools_fastp"] }, "fastqc": { @@ -269,7 +269,7 @@ }, "fastq_fastqc_umitools_fastp": { "branch": "master", - "git_sha": "a9784afdd5dcda23b84e64db75dc591065d64653", + "git_sha": "48dbb403fb2849b3d2c6c2e3eaaedbcca799428d", "installed_by": ["subworkflows"] }, "fastq_fastqc_umitools_trimgalore": { diff --git a/modules/nf-core/fastp/main.nf b/modules/nf-core/fastp/main.nf index 2ca2d3ee0..e75c96cc9 100644 --- a/modules/nf-core/fastp/main.nf +++ b/modules/nf-core/fastp/main.nf @@ -2,10 +2,10 @@ process FASTP { tag "$meta.id" label 'process_medium' - conda "bioconda::fastp=0.23.2" + conda "bioconda::fastp=0.23.3" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/fastp:0.23.2--h79da9fb_0' : - 'biocontainers/fastp:0.23.2--h79da9fb_0' }" + 'https://depot.galaxyproject.org/singularity/fastp:0.23.3--h5f740d0_0' : + 'biocontainers/fastp:0.23.3--h5f740d0_0' }" input: tuple val(meta), path(reads) diff --git a/subworkflows/nf-core/fastq_fastqc_umitools_fastp/main.nf b/subworkflows/nf-core/fastq_fastqc_umitools_fastp/main.nf index 42638943d..64ec88f23 100644 --- a/subworkflows/nf-core/fastq_fastqc_umitools_fastp/main.nf +++ b/subworkflows/nf-core/fastq_fastqc_umitools_fastp/main.nf @@ -77,7 +77,7 @@ workflow FASTQ_FASTQC_UMITOOLS_FASTP { trim_read_count = Channel.empty() if (!skip_trimming) { FASTP ( - reads, + umi_reads, adapter_fasta, save_trimmed_fail, save_merged From 55398de6ab7577acfe9b1180016a93d7af7eb859 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Wed, 31 May 2023 09:33:54 +0100 Subject: [PATCH 24/36] Update all modules / subworkflows --- CHANGELOG.md | 2 +- modules.json | 26 ++++++++--------- modules/nf-core/fastp/main.nf | 6 ++-- modules/nf-core/hisat2/align/main.nf | 4 +-- modules/nf-core/hisat2/align/meta.yml | 11 ++++++++ modules/nf-core/hisat2/build/main.nf | 10 +++---- modules/nf-core/hisat2/build/meta.yml | 28 ++++++++++++++++--- .../nf-core/hisat2/extractsplicesites/main.nf | 6 ++-- .../hisat2/extractsplicesites/meta.yml | 11 ++++++++ modules/nf-core/picard/markduplicates/main.nf | 4 +-- .../nf-core/picard/markduplicates/meta.yml | 11 ++++++++ modules/nf-core/samtools/stats/main.nf | 2 +- modules/nf-core/samtools/stats/meta.yml | 10 +++++-- modules/nf-core/star/align/main.nf | 13 +++++---- subworkflows/local/prepare_genome.nf | 4 +-- subworkflows/local/quantify_rsem.nf | 12 ++++---- .../bam_dedup_stats_samtools_umitools/main.nf | 2 +- .../nf-core/bam_sort_stats_samtools/main.nf | 2 +- .../nf-core/bam_stats_samtools/main.nf | 2 +- workflows/rnaseq.nf | 14 +++++----- 20 files changed, 121 insertions(+), 59 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index fe4de1224..af8aa9289 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -15,7 +15,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 | Dependency | Old version | New version | | ---------- | ----------- | ----------- | -| `fastp` | 0.23.2 | 0.23.3 | +| `fastp` | 0.23.2 | 0.23.4 | | `samtools` | 1.16.1 | 1.17 | > **NB:** Dependency has been **updated** if both old and new version information is present. diff --git a/modules.json b/modules.json index 13f71805b..57d648390 100644 --- a/modules.json +++ b/modules.json @@ -27,8 +27,8 @@ }, "fastp": { "branch": "master", - "git_sha": "37a98dd100d74d9188a272197663587de1331a0e", - "installed_by": ["modules", "fastq_fastqc_umitools_fastp"] + "git_sha": "d497a4868ace3302016ea8ed4b395072d5e833cd", + "installed_by": ["fastq_fastqc_umitools_fastp", "modules"] }, "fastqc": { "branch": "master", @@ -52,22 +52,22 @@ }, "hisat2/align": { "branch": "master", - "git_sha": "603ecbd9f45300c9788f197d2a15a005685b4220", + "git_sha": "735e1e04e7e01751d2d6e97055bbdb6f70683cc1", "installed_by": ["fastq_align_hisat2"] }, "hisat2/build": { "branch": "master", - "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "git_sha": "735e1e04e7e01751d2d6e97055bbdb6f70683cc1", "installed_by": ["modules"] }, "hisat2/extractsplicesites": { "branch": "master", - "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "git_sha": "735e1e04e7e01751d2d6e97055bbdb6f70683cc1", "installed_by": ["modules"] }, "picard/markduplicates": { "branch": "master", - "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "git_sha": "735e1e04e7e01751d2d6e97055bbdb6f70683cc1", "installed_by": ["bam_markduplicates_picard"] }, "preseq/lcextrap": { @@ -166,7 +166,7 @@ }, "samtools/stats": { "branch": "master", - "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "git_sha": "735e1e04e7e01751d2d6e97055bbdb6f70683cc1", "installed_by": ["bam_stats_samtools"] }, "sortmerna": { @@ -176,7 +176,7 @@ }, "star/align": { "branch": "master", - "git_sha": "603ecbd9f45300c9788f197d2a15a005685b4220", + "git_sha": "57d75dbac06812c59798a48585032f6e50bb1914", "installed_by": ["modules"] }, "star/genomegenerate": { @@ -230,7 +230,7 @@ "nf-core": { "bam_dedup_stats_samtools_umitools": { "branch": "master", - "git_sha": "a9784afdd5dcda23b84e64db75dc591065d64653", + "git_sha": "735e1e04e7e01751d2d6e97055bbdb6f70683cc1", "installed_by": ["subworkflows"] }, "bam_markduplicates_picard": { @@ -245,16 +245,16 @@ }, "bam_sort_stats_samtools": { "branch": "master", - "git_sha": "a9784afdd5dcda23b84e64db75dc591065d64653", + "git_sha": "735e1e04e7e01751d2d6e97055bbdb6f70683cc1", "installed_by": ["fastq_align_hisat2"] }, "bam_stats_samtools": { "branch": "master", - "git_sha": "a9784afdd5dcda23b84e64db75dc591065d64653", + "git_sha": "735e1e04e7e01751d2d6e97055bbdb6f70683cc1", "installed_by": [ + "bam_dedup_stats_samtools_umitools", "bam_markduplicates_picard", - "bam_sort_stats_samtools", - "bam_dedup_stats_samtools_umitools" + "bam_sort_stats_samtools" ] }, "bedgraph_bedclip_bedgraphtobigwig": { diff --git a/modules/nf-core/fastp/main.nf b/modules/nf-core/fastp/main.nf index e75c96cc9..831b7f128 100644 --- a/modules/nf-core/fastp/main.nf +++ b/modules/nf-core/fastp/main.nf @@ -2,10 +2,10 @@ process FASTP { tag "$meta.id" label 'process_medium' - conda "bioconda::fastp=0.23.3" + conda "bioconda::fastp=0.23.4" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/fastp:0.23.3--h5f740d0_0' : - 'biocontainers/fastp:0.23.3--h5f740d0_0' }" + 'https://depot.galaxyproject.org/singularity/fastp:0.23.4--h5f740d0_0' : + 'biocontainers/fastp:0.23.4--h5f740d0_0' }" input: tuple val(meta), path(reads) diff --git a/modules/nf-core/hisat2/align/main.nf b/modules/nf-core/hisat2/align/main.nf index 542815d2c..e69204692 100644 --- a/modules/nf-core/hisat2/align/main.nf +++ b/modules/nf-core/hisat2/align/main.nf @@ -10,8 +10,8 @@ process HISAT2_ALIGN { input: tuple val(meta), path(reads) - path index - path splicesites + tuple val(meta2), path(index) + tuple val(meta3), path(splicesites) output: tuple val(meta), path("*.bam") , emit: bam diff --git a/modules/nf-core/hisat2/align/meta.yml b/modules/nf-core/hisat2/align/meta.yml index 7550aefab..008a9611f 100644 --- a/modules/nf-core/hisat2/align/meta.yml +++ b/modules/nf-core/hisat2/align/meta.yml @@ -25,10 +25,20 @@ 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:'genome' ] - index: type: file description: HISAT2 genome index file pattern: "*.ht2" + - meta3: + type: map + description: | + Groovy Map containing reference information + e.g. [ id:'genome' ] - splicesites: type: file description: Splices sites in gtf file @@ -55,3 +65,4 @@ output: authors: - "@ntoda03" + - "@ramprasadn" diff --git a/modules/nf-core/hisat2/build/main.nf b/modules/nf-core/hisat2/build/main.nf index b3475f758..5ad36a548 100644 --- a/modules/nf-core/hisat2/build/main.nf +++ b/modules/nf-core/hisat2/build/main.nf @@ -10,13 +10,13 @@ process HISAT2_BUILD { 'biocontainers/hisat2:2.2.1--h1b792b2_3' }" input: - path fasta - path gtf - path splicesites + tuple val(meta), path(fasta) + tuple val(meta2), path(gtf) + tuple val(meta3), path(splicesites) output: - path "hisat2" , emit: index - path "versions.yml" , emit: versions + tuple val(meta), path("hisat2") , emit: index + path "versions.yml" , emit: versions when: task.ext.when == null || task.ext.when diff --git a/modules/nf-core/hisat2/build/meta.yml b/modules/nf-core/hisat2/build/meta.yml index a2e1fd67e..e61bf2a3f 100644 --- a/modules/nf-core/hisat2/build/meta.yml +++ b/modules/nf-core/hisat2/build/meta.yml @@ -15,28 +15,48 @@ tools: licence: ["MIT"] input: + - meta: + type: map + description: | + Groovy Map containing reference information + e.g. [ id:'genome' ] - fasta: type: file description: Reference fasta file pattern: "*.{fa,fasta,fna}" + - meta2: + type: map + description: | + Groovy Map containing reference information + e.g. [ id:'genome' ] - gtf: type: file description: Reference gtf annotation file pattern: "*.{gtf}" + - meta3: + type: map + description: | + Groovy Map containing reference information + e.g. [ id:'genome' ] - splicesites: type: file description: Splices sites in gtf file pattern: "*.{txt}" output: - - versions: - type: file - description: File containing software versions - pattern: "versions.yml" + - meta: + type: map + description: | + Groovy Map containing reference information + e.g. [ id:'genome' ] - index: type: file description: HISAT2 genome index file pattern: "*.ht2" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" authors: - "@ntoda03" diff --git a/modules/nf-core/hisat2/extractsplicesites/main.nf b/modules/nf-core/hisat2/extractsplicesites/main.nf index f6d28c1a5..a6e59e202 100644 --- a/modules/nf-core/hisat2/extractsplicesites/main.nf +++ b/modules/nf-core/hisat2/extractsplicesites/main.nf @@ -9,11 +9,11 @@ process HISAT2_EXTRACTSPLICESITES { 'biocontainers/hisat2:2.2.1--h1b792b2_3' }" input: - path gtf + tuple val(meta), path(gtf) output: - path "*.splice_sites.txt", emit: txt - path "versions.yml" , emit: versions + tuple val(meta), path("*.splice_sites.txt"), emit: txt + path "versions.yml" , emit: versions when: task.ext.when == null || task.ext.when diff --git a/modules/nf-core/hisat2/extractsplicesites/meta.yml b/modules/nf-core/hisat2/extractsplicesites/meta.yml index 7dc1bac81..f70de082a 100644 --- a/modules/nf-core/hisat2/extractsplicesites/meta.yml +++ b/modules/nf-core/hisat2/extractsplicesites/meta.yml @@ -15,12 +15,22 @@ tools: licence: ["MIT"] input: + - meta: + type: map + description: | + Groovy Map containing reference information + e.g. [ id:'genome' ] - gtf: type: file description: Reference gtf annotation file pattern: "*.{gtf}" output: + - meta: + type: map + description: | + Groovy Map containing reference information + e.g. [ id:'genome' ] - versions: type: file description: File containing software versions @@ -32,3 +42,4 @@ output: authors: - "@ntoda03" + - "@ramprasadn" diff --git a/modules/nf-core/picard/markduplicates/main.nf b/modules/nf-core/picard/markduplicates/main.nf index 7ba8448f7..facd7efb9 100644 --- a/modules/nf-core/picard/markduplicates/main.nf +++ b/modules/nf-core/picard/markduplicates/main.nf @@ -9,8 +9,8 @@ process PICARD_MARKDUPLICATES { input: tuple val(meta), path(bam) - path fasta - path fai + tuple val(meta2), path(fasta) + tuple val(meta3), path(fai) output: tuple val(meta), path("*.bam") , emit: bam diff --git a/modules/nf-core/picard/markduplicates/meta.yml b/modules/nf-core/picard/markduplicates/meta.yml index 3f2357bbf..f7693d2f0 100644 --- a/modules/nf-core/picard/markduplicates/meta.yml +++ b/modules/nf-core/picard/markduplicates/meta.yml @@ -25,10 +25,20 @@ input: type: file description: BAM file pattern: "*.{bam,cram,sam}" + - meta2: + type: map + description: | + Groovy Map containing reference information + e.g. [ id:'genome' ] - fasta: type: file description: Reference genome fasta file pattern: "*.{fasta,fa}" + - meta3: + type: map + description: | + Groovy Map containing reference information + e.g. [ id:'genome' ] - fai: type: file description: Reference genome fasta index @@ -58,3 +68,4 @@ output: authors: - "@drpatelh" - "@projectoriented" + - "@ramprasadn" diff --git a/modules/nf-core/samtools/stats/main.nf b/modules/nf-core/samtools/stats/main.nf index eb7f098b0..4a2607ded 100644 --- a/modules/nf-core/samtools/stats/main.nf +++ b/modules/nf-core/samtools/stats/main.nf @@ -9,7 +9,7 @@ process SAMTOOLS_STATS { input: tuple val(meta), path(input), path(input_index) - path fasta + tuple val(meta2), path(fasta) output: tuple val(meta), path("*.stats"), emit: stats diff --git a/modules/nf-core/samtools/stats/meta.yml b/modules/nf-core/samtools/stats/meta.yml index 1d68a5d83..90e6345f5 100644 --- a/modules/nf-core/samtools/stats/meta.yml +++ b/modules/nf-core/samtools/stats/meta.yml @@ -30,9 +30,14 @@ input: type: file description: BAI/CRAI file from alignment pattern: "*.{bai,crai}" + - meta2: + type: map + description: | + Groovy Map containing reference information + e.g. [ id:'genome' ] - fasta: - type: optional file - description: Reference file the CRAM was created with + type: file + description: Reference file the CRAM was created with (optional) pattern: "*.{fasta,fa}" output: - meta: @@ -51,3 +56,4 @@ output: authors: - "@drpatelh" - "@FriederikeHanssen" + - "@ramprasadn" diff --git a/modules/nf-core/star/align/main.nf b/modules/nf-core/star/align/main.nf index 54d35f7d3..8cb8e9a4d 100644 --- a/modules/nf-core/star/align/main.nf +++ b/modules/nf-core/star/align/main.nf @@ -8,7 +8,7 @@ process STAR_ALIGN { 'biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1df389393721fc66f3fd8778ad938ac711951107-0' }" input: - tuple val(meta), path(reads) + tuple val(meta), path(reads, stageAs: "input*/*") path index path gtf val star_ignore_sjdbgtf @@ -16,12 +16,12 @@ process STAR_ALIGN { val seq_center output: - tuple val(meta), path('*d.out.bam') , emit: bam tuple val(meta), path('*Log.final.out') , emit: log_final tuple val(meta), path('*Log.out') , emit: log_out tuple val(meta), path('*Log.progress.out'), emit: log_progress path "versions.yml" , emit: versions + tuple val(meta), path('*d.out.bam') , optional:true, emit: bam tuple val(meta), path('*sortedByCoord.out.bam') , optional:true, emit: bam_sorted tuple val(meta), path('*toTranscriptome.out.bam'), optional:true, emit: bam_transcript tuple val(meta), path('*Aligned.unsort.out.bam') , optional:true, emit: bam_unsorted @@ -40,20 +40,23 @@ process STAR_ALIGN { script: def args = task.ext.args ?: '' def prefix = task.ext.prefix ?: "${meta.id}" + def reads1 = [], reads2 = [] + meta.single_end ? [reads].flatten().each{reads1 << it} : reads.eachWithIndex{ v, ix -> ( ix & 1 ? reads2 : reads1) << v } def ignore_gtf = star_ignore_sjdbgtf ? '' : "--sjdbGTFfile $gtf" def seq_platform = seq_platform ? "'PL:$seq_platform'" : "" - def seq_center = seq_center ? "--outSAMattrRGline ID:$prefix 'CN:$seq_center' 'SM:$prefix' $seq_platform " : "--outSAMattrRGline ID:$prefix 'SM:$prefix' $seq_platform " + def seq_center = seq_center ? "'CN:$seq_center'" : "" + def attrRG = args.contains("--outSAMattrRGline") ? "" : "--outSAMattrRGline 'ID:$prefix' $seq_center 'SM:$prefix' $seq_platform" def out_sam_type = (args.contains('--outSAMtype')) ? '' : '--outSAMtype BAM Unsorted' def mv_unsorted_bam = (args.contains('--outSAMtype BAM Unsorted SortedByCoordinate')) ? "mv ${prefix}.Aligned.out.bam ${prefix}.Aligned.unsort.out.bam" : '' """ STAR \\ --genomeDir $index \\ - --readFilesIn $reads \\ + --readFilesIn ${reads1.join(",")} ${reads2.join(",")} \\ --runThreadN $task.cpus \\ --outFileNamePrefix $prefix. \\ $out_sam_type \\ $ignore_gtf \\ - $seq_center \\ + $attrRG \\ $args $mv_unsorted_bam diff --git a/subworkflows/local/prepare_genome.nf b/subworkflows/local/prepare_genome.nf index 52e09c774..b83126cd7 100644 --- a/subworkflows/local/prepare_genome.nf +++ b/subworkflows/local/prepare_genome.nf @@ -222,7 +222,7 @@ workflow PREPARE_GENOME { ch_hisat2_index = Channel.empty() if ('hisat2' in prepare_tool_indices) { if (!splicesites) { - ch_splicesites = HISAT2_EXTRACTSPLICESITES ( ch_gtf ).txt + ch_splicesites = HISAT2_EXTRACTSPLICESITES ( ch_gtf.map { [ [:], it ] } ).txt.map { it[1] } ch_versions = ch_versions.mix(HISAT2_EXTRACTSPLICESITES.out.versions) } else { ch_splicesites = Channel.value(file(splicesites)) @@ -235,7 +235,7 @@ workflow PREPARE_GENOME { ch_hisat2_index = Channel.value(file(hisat2_index)) } } else { - ch_hisat2_index = HISAT2_BUILD ( ch_fasta, ch_gtf, ch_splicesites ).index + ch_hisat2_index = HISAT2_BUILD ( ch_fasta.map { [ [:], it ] }, ch_gtf.map { [ [:], it ] }, ch_splicesites.map { [ [:], it ] } ).index.map { it[1] } ch_versions = ch_versions.mix(HISAT2_BUILD.out.versions) } } diff --git a/subworkflows/local/quantify_rsem.nf b/subworkflows/local/quantify_rsem.nf index e61e8dda1..9b272b057 100644 --- a/subworkflows/local/quantify_rsem.nf +++ b/subworkflows/local/quantify_rsem.nf @@ -45,12 +45,12 @@ workflow QUANTIFY_RSEM { bam_genome = RSEM_CALCULATEEXPRESSION.out.bam_genome // channel: [ val(meta), bam ] bam_transcript = RSEM_CALCULATEEXPRESSION.out.bam_transcript // channel: [ val(meta), bam ] - bam = BAM_SORT_STATS_SAMTOOLS.out.bam // channel: [ val(meta), [ bam ] ] - bai = BAM_SORT_STATS_SAMTOOLS.out.bai // channel: [ val(meta), [ bai ] ] - csi = BAM_SORT_STATS_SAMTOOLS.out.csi // channel: [ val(meta), [ csi ] ] - stats = BAM_SORT_STATS_SAMTOOLS.out.stats // channel: [ val(meta), [ stats ] ] - flagstat = BAM_SORT_STATS_SAMTOOLS.out.flagstat // channel: [ val(meta), [ flagstat ] ] - idxstats = BAM_SORT_STATS_SAMTOOLS.out.idxstats // channel: [ val(meta), [ idxstats ] ] + bam = BAM_SORT_STATS_SAMTOOLS.out.bam // channel: [ val(meta), [ bam ] ] + bai = BAM_SORT_STATS_SAMTOOLS.out.bai // channel: [ val(meta), [ bai ] ] + csi = BAM_SORT_STATS_SAMTOOLS.out.csi // channel: [ val(meta), [ csi ] ] + stats = BAM_SORT_STATS_SAMTOOLS.out.stats // channel: [ val(meta), [ stats ] ] + flagstat = BAM_SORT_STATS_SAMTOOLS.out.flagstat // channel: [ val(meta), [ flagstat ] ] + idxstats = BAM_SORT_STATS_SAMTOOLS.out.idxstats // channel: [ val(meta), [ idxstats ] ] merged_counts_gene = RSEM_MERGE_COUNTS.out.counts_gene // path: *.gene_counts.tsv merged_tpm_gene = RSEM_MERGE_COUNTS.out.tpm_gene // path: *.gene_tpm.tsv diff --git a/subworkflows/nf-core/bam_dedup_stats_samtools_umitools/main.nf b/subworkflows/nf-core/bam_dedup_stats_samtools_umitools/main.nf index 6b9e2e7a0..a3fc7ff75 100644 --- a/subworkflows/nf-core/bam_dedup_stats_samtools_umitools/main.nf +++ b/subworkflows/nf-core/bam_dedup_stats_samtools_umitools/main.nf @@ -39,7 +39,7 @@ workflow BAM_DEDUP_STATS_SAMTOOLS_UMITOOLS { } } - BAM_STATS_SAMTOOLS ( ch_bam_bai_dedup, [] ) + BAM_STATS_SAMTOOLS ( ch_bam_bai_dedup, [[],[]] ) ch_versions = ch_versions.mix(BAM_STATS_SAMTOOLS.out.versions) emit: diff --git a/subworkflows/nf-core/bam_sort_stats_samtools/main.nf b/subworkflows/nf-core/bam_sort_stats_samtools/main.nf index 617871fe3..fc1c652b9 100644 --- a/subworkflows/nf-core/bam_sort_stats_samtools/main.nf +++ b/subworkflows/nf-core/bam_sort_stats_samtools/main.nf @@ -9,7 +9,7 @@ include { BAM_STATS_SAMTOOLS } from '../bam_stats_samtools/main' workflow BAM_SORT_STATS_SAMTOOLS { take: ch_bam // channel: [ val(meta), [ bam ] ] - ch_fasta // channel: [ fasta ] + ch_fasta // channel: [ val(meta), path(fasta) ] main: diff --git a/subworkflows/nf-core/bam_stats_samtools/main.nf b/subworkflows/nf-core/bam_stats_samtools/main.nf index c9d7c8b75..44d4c010a 100644 --- a/subworkflows/nf-core/bam_stats_samtools/main.nf +++ b/subworkflows/nf-core/bam_stats_samtools/main.nf @@ -9,7 +9,7 @@ include { SAMTOOLS_FLAGSTAT } from '../../../modules/nf-core/samtools/flagstat/m workflow BAM_STATS_SAMTOOLS { take: ch_bam_bai // channel: [ val(meta), path(bam), path(bai) ] - ch_fasta // channel: [ path(fasta) ] + ch_fasta // channel: [ val(meta), path(fasta) ] main: ch_versions = Channel.empty() diff --git a/workflows/rnaseq.nf b/workflows/rnaseq.nf index 9876e09b1..b8a3d749d 100755 --- a/workflows/rnaseq.nf +++ b/workflows/rnaseq.nf @@ -394,7 +394,7 @@ workflow RNASEQ { '', params.seq_center ?: '', is_aws_igenome, - PREPARE_GENOME.out.fasta + PREPARE_GENOME.out.fasta.map { [ [:], it ] } ) ch_genome_bam = ALIGN_STAR.out.bam ch_genome_bam_index = ALIGN_STAR.out.bai @@ -430,7 +430,7 @@ workflow RNASEQ { // Co-ordinate sort, index and run stats on transcriptome BAM BAM_SORT_STATS_SAMTOOLS ( ch_transcriptome_bam, - PREPARE_GENOME.out.fasta + PREPARE_GENOME.out.fasta.map { [ [:], it ] } ) ch_transcriptome_sorted_bam = BAM_SORT_STATS_SAMTOOLS.out.bam ch_transcriptome_sorted_bai = BAM_SORT_STATS_SAMTOOLS.out.bai @@ -537,9 +537,9 @@ workflow RNASEQ { if (!params.skip_alignment && params.aligner == 'hisat2') { FASTQ_ALIGN_HISAT2 ( ch_filtered_reads, - PREPARE_GENOME.out.hisat2_index, - PREPARE_GENOME.out.splicesites, - PREPARE_GENOME.out.fasta + PREPARE_GENOME.out.hisat2_index.map { [ [:], it ] }, + PREPARE_GENOME.out.splicesites.map { [ [:], it ] }, + PREPARE_GENOME.out.fasta.map { [ [:], it ] } ) ch_genome_bam = FASTQ_ALIGN_HISAT2.out.bam ch_genome_bam_index = FASTQ_ALIGN_HISAT2.out.bai @@ -632,8 +632,8 @@ workflow RNASEQ { if (!params.skip_alignment && !params.skip_markduplicates && !params.with_umi) { BAM_MARKDUPLICATES_PICARD ( ch_genome_bam, - PREPARE_GENOME.out.fasta, - PREPARE_GENOME.out.fai + PREPARE_GENOME.out.fasta.map { [ [:], it ] }, + PREPARE_GENOME.out.fai.map { [ [:], it ] } ) ch_genome_bam = BAM_MARKDUPLICATES_PICARD.out.bam ch_genome_bam_index = BAM_MARKDUPLICATES_PICARD.out.bai From 3ff2be634a158d117b70c155f0bc270c5da90c9d Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Wed, 31 May 2023 10:06:10 +0100 Subject: [PATCH 25/36] Fix RSEM tests --- subworkflows/local/quantify_rsem.nf | 3 ++- subworkflows/nf-core/bam_dedup_stats_samtools_umitools/main.nf | 2 +- workflows/rnaseq.nf | 3 ++- 3 files changed, 5 insertions(+), 3 deletions(-) diff --git a/subworkflows/local/quantify_rsem.nf b/subworkflows/local/quantify_rsem.nf index 9b272b057..666af33b1 100644 --- a/subworkflows/local/quantify_rsem.nf +++ b/subworkflows/local/quantify_rsem.nf @@ -10,6 +10,7 @@ workflow QUANTIFY_RSEM { take: reads // channel: [ val(meta), [ reads ] ] index // channel: /path/to/rsem/index/ + fasta // channel: [ val(meta), [ fasta ] ] main: @@ -24,7 +25,7 @@ workflow QUANTIFY_RSEM { // // Sort, index BAM file and run samtools stats, flagstat and idxstats // - BAM_SORT_STATS_SAMTOOLS ( RSEM_CALCULATEEXPRESSION.out.bam_star, [] ) + BAM_SORT_STATS_SAMTOOLS ( RSEM_CALCULATEEXPRESSION.out.bam_star, fasta ) ch_versions = ch_versions.mix(BAM_SORT_STATS_SAMTOOLS.out.versions) // diff --git a/subworkflows/nf-core/bam_dedup_stats_samtools_umitools/main.nf b/subworkflows/nf-core/bam_dedup_stats_samtools_umitools/main.nf index a3fc7ff75..7c07084ff 100644 --- a/subworkflows/nf-core/bam_dedup_stats_samtools_umitools/main.nf +++ b/subworkflows/nf-core/bam_dedup_stats_samtools_umitools/main.nf @@ -39,7 +39,7 @@ workflow BAM_DEDUP_STATS_SAMTOOLS_UMITOOLS { } } - BAM_STATS_SAMTOOLS ( ch_bam_bai_dedup, [[],[]] ) + BAM_STATS_SAMTOOLS ( ch_bam_bai_dedup, [ [:], [] ] ) ch_versions = ch_versions.mix(BAM_STATS_SAMTOOLS.out.versions) emit: diff --git a/workflows/rnaseq.nf b/workflows/rnaseq.nf index b8a3d749d..706283a26 100755 --- a/workflows/rnaseq.nf +++ b/workflows/rnaseq.nf @@ -504,7 +504,8 @@ workflow RNASEQ { if (!params.skip_alignment && params.aligner == 'star_rsem') { QUANTIFY_RSEM ( ch_filtered_reads, - PREPARE_GENOME.out.rsem_index + PREPARE_GENOME.out.rsem_index, + PREPARE_GENOME.out.fasta.map { [ [:], it ] } ) ch_genome_bam = QUANTIFY_RSEM.out.bam ch_genome_bam_index = QUANTIFY_RSEM.out.bai From 277bd337739a8b8f753fa7b5eda6743b9b6acb89 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Wed, 31 May 2023 11:18:40 +0100 Subject: [PATCH 26/36] Add retry strategy to bbmap/bbsplit --- modules.json | 4 ++-- modules/nf-core/bbmap/bbsplit/main.nf | 1 + modules/nf-core/bbmap/bbsplit/meta.yml | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/modules.json b/modules.json index 57d648390..b2fe8ca92 100644 --- a/modules.json +++ b/modules.json @@ -7,7 +7,7 @@ "nf-core": { "bbmap/bbsplit": { "branch": "master", - "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "git_sha": "e228790f2957152ad2534e39abd7b3878963e89d", "installed_by": ["modules"] }, "cat/fastq": { @@ -230,7 +230,7 @@ "nf-core": { "bam_dedup_stats_samtools_umitools": { "branch": "master", - "git_sha": "735e1e04e7e01751d2d6e97055bbdb6f70683cc1", + "git_sha": "e228790f2957152ad2534e39abd7b3878963e89d", "installed_by": ["subworkflows"] }, "bam_markduplicates_picard": { diff --git a/modules/nf-core/bbmap/bbsplit/main.nf b/modules/nf-core/bbmap/bbsplit/main.nf index 6046184d0..67190ff1d 100644 --- a/modules/nf-core/bbmap/bbsplit/main.nf +++ b/modules/nf-core/bbmap/bbsplit/main.nf @@ -1,5 +1,6 @@ process BBMAP_BBSPLIT { label 'process_high' + label 'error_retry' conda "bioconda::bbmap=39.01" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? diff --git a/modules/nf-core/bbmap/bbsplit/meta.yml b/modules/nf-core/bbmap/bbsplit/meta.yml index 4cdc31a87..caa3dd66c 100644 --- a/modules/nf-core/bbmap/bbsplit/meta.yml +++ b/modules/nf-core/bbmap/bbsplit/meta.yml @@ -30,7 +30,7 @@ input: description: Directory to place generated index pattern: "*" - primary_ref: - type: path + type: file description: Path to the primary reference pattern: "*" - other_ref_names: From 5dececa4c05a4a371a0e05d6d85886dec77a30cf Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Wed, 31 May 2023 15:12:35 +0100 Subject: [PATCH 27/36] Fix #1018 --- .github/workflows/ci.yml | 3 ++- CHANGELOG.md | 11 +++++++++++ conf/modules.config | 2 +- docs/usage.md | 4 +++- lib/WorkflowRnaseq.groovy | 5 +---- nextflow.config | 1 + nextflow_schema.json | 5 +++++ workflows/rnaseq.nf | 8 ++++---- 8 files changed, 28 insertions(+), 11 deletions(-) diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index ba11abeab..f5d8dcf88 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -239,7 +239,8 @@ jobs: strategy: matrix: parameters: - - "--skip_qc --skip_alignment" + - "--skip_qc" + - "--skip_alignment --skip_pseudo_alignment" - "--salmon_index false --transcript_fasta false" steps: - name: Check out pipeline code diff --git a/CHANGELOG.md b/CHANGELOG.md index af8aa9289..0b0ba042e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -8,9 +8,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Enhancements & fixes - [[#1011](https://github.com/nf-core/rnaseq/issues/1011)] - FastQ files from UMI-tools not being passed to fastp +- [[#1018](https://github.com/nf-core/rnaseq/issues/1018)] - Ability to skip both alignment and pseudo-alignment to only run pre-processing QC steps. - [PR #1016](https://github.com/nf-core/rnaseq/pull/1016) - Updated pipeline template to [nf-core/tools 2.8](https://github.com/nf-core/tools/releases/tag/2.8) - [PR #1025](https://github.com/nf-core/fetchngs/pull/1025) - Add `public_aws_ecr.config` to source mulled containers when using `public.ecr.aws` Docker Biocontainer registry +### Parameters + +| Old parameter | New parameter | +| ------------- | ------------------------- | +| | `--skip_pseudo_alignment` | + +> **NB:** Parameter has been **updated** if both old and new parameter information is present. +> **NB:** Parameter has been **added** if just the new parameter information is present. +> **NB:** Parameter has been **removed** if new parameter information isn't present. + ### Software dependencies | Dependency | Old version | New version | diff --git a/conf/modules.config b/conf/modules.config index 0513ef0c2..3c31fb469 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -1137,7 +1137,7 @@ if (!params.skip_multiqc) { // Salmon pseudo-alignment options // -if (params.pseudo_aligner == 'salmon') { +if (!params.skip_pseudo_alignment && params.pseudo_aligner == 'salmon') { process { withName: '.*:QUANTIFY_SALMON:SALMON_QUANT' { ext.args = params.extra_salmon_quant_args ?: '' diff --git a/docs/usage.md b/docs/usage.md index 69c906c47..856e00c7f 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -71,6 +71,8 @@ When running Salmon in mapping-based mode via `--pseudo_aligner salmon` the enti Two additional parameters `--extra_star_align_args` and `--extra_salmon_quant_args` were added in v3.10 of the pipeline that allow you to append any custom parameters to the STAR align and Salmon quant commands, respectively. Note, the `--seqBias` and `--gcBias` are not provided to Salmon quant by default so you can provide these via `--extra_salmon_quant_args '--seqBias --gcBias'` if required. +> **NB:** You can use `--skip_alignment --skip_pseudo_alignment` if you only want to run the pre-processing QC steps in the pipeline like FastQ, trimming etc. This will skip alignment, pseudo-alignment and any post-alignment processing steps. + ## Quantification options The current options align with STAR and quantify using either Salmon (`--aligner star_salmon`) / RSEM (`--aligner star_rsem`). You also have the option to pseudo-align and quantify your data with Salmon by providing the `--pseudo_aligner salmon` parameter. @@ -133,7 +135,7 @@ If unique molecular identifiers were used to prepare the library, add the follow Please refer to the [nf-core website](https://nf-co.re/usage/reference_genomes) for general usage docs and guidelines regarding reference genomes. -The minimum reference genome requirements for this pipeline are a FASTA and GTF file, all other files required to run the pipeline can be generated from these files. However, it is more storage and compute friendly if you are able to re-use reference genome files as efficiently as possible. It is recommended to use the `--save_reference` parameter if you are using the pipeline to build new indices (e.g. custom genomes that are unavailable on [AWS iGenomes](https://nf-co.re/usage/reference_genomes#custom-genomes)) so that you can save them somewhere locally. The index building step can be quite a time-consuming process and it permits their reuse for future runs of the pipeline to save disk space. You can then either provide the appropriate reference genome files on the command-line via the appropriate parameters (e.g. `--star_index '/path/to/STAR/index/'`) or via a custom config file. +The minimum reference genome requirements for this pipeline are a FASTA and GTF file, all other files required to run the pipeline can be generated from these files. However, it is more storage and compute friendly if you are able to re-use reference genome files as efficiently as possible. It is recommended to use the `--save_reference` parameter if you are using the pipeline to build new indices (e.g. custom genomes that are unavailable on [AWS iGenomes](https://nf-co.re/usage/reference_genomes#custom-genomes)) so that you can save them somewhere locally. The index building step can be quite a time-consuming process and it permits their reuse for future runs of the pipeline to save disk space. You can then either provide the appropriate reference genome files on the command-line via the appropriate parameters (e.g. `--star_index '/path/to/STAR/index/'`) or via a custom config file. Another option is to run the pipeline once with `--save_reference --skip_alignment --skip_pseudo_alignment` to generate and save all of the required reference files and indices to the results directory. You can then move the reference files in `/genome/` to a more permanent location and use these paths to override the relevant parameters in the pipeline e.g. `--star_index`. - If `--genome` is provided then the FASTA and GTF files (and existing indices) will be automatically obtained from AWS-iGenomes unless these have already been downloaded locally in the path specified by `--igenomes_base`. - If `--gff` is provided as input then this will be converted to a GTF file, or the latter will be used if both are provided. diff --git a/lib/WorkflowRnaseq.groovy b/lib/WorkflowRnaseq.groovy index ff577917b..14f1493a8 100755 --- a/lib/WorkflowRnaseq.groovy +++ b/lib/WorkflowRnaseq.groovy @@ -65,13 +65,10 @@ class WorkflowRnaseq { Nextflow.error("Invalid option: '${params.aligner}'. Valid options for '--aligner': ${valid_params['aligners'].join(', ')}.") } } else { - if (!params.pseudo_aligner) { - Nextflow.error("--skip_alignment specified without --pseudo_aligner...please specify e.g. --pseudo_aligner ${valid_params['pseudoaligners'][0]}.") - } skipAlignmentWarn(log) } - if (params.pseudo_aligner) { + if (!params.skip_pseudo_alignment) { if (!valid_params['pseudoaligners'].contains(params.pseudo_aligner)) { Nextflow.error("Invalid option: '${params.pseudo_aligner}'. Valid options for '--pseudo_aligner': ${valid_params['pseudoaligners'].join(', ')}.") } else { diff --git a/nextflow.config b/nextflow.config index a24b0a070..c270bae12 100644 --- a/nextflow.config +++ b/nextflow.config @@ -71,6 +71,7 @@ params { save_align_intermeds = false skip_markduplicates = false skip_alignment = false + skip_pseudo_alignment = false // QC skip_qc = false diff --git a/nextflow_schema.json b/nextflow_schema.json index 9f6d7529d..4bb08ed2d 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -446,6 +446,11 @@ "type": "boolean", "fa_icon": "fas fa-fast-forward", "description": "Skip all of the alignment-based processes within the pipeline." + }, + "skip_pseudo_alignment": { + "type": "boolean", + "fa_icon": "fas fa-fast-forward", + "description": "Skip all of the pseudo-alignment-based processes within the pipeline." } } }, diff --git a/workflows/rnaseq.nf b/workflows/rnaseq.nf index 706283a26..5f62c2171 100755 --- a/workflows/rnaseq.nf +++ b/workflows/rnaseq.nf @@ -43,9 +43,9 @@ if (!params.skip_bbsplit && !params.bbsplit_index && params.bbsplit_fasta_list) // Check alignment parameters def prepareToolIndices = [] -if (!params.skip_bbsplit) { prepareToolIndices << 'bbsplit' } -if (!params.skip_alignment) { prepareToolIndices << params.aligner } -if (params.pseudo_aligner) { prepareToolIndices << params.pseudo_aligner } +if (!params.skip_bbsplit) { prepareToolIndices << 'bbsplit' } +if (!params.skip_alignment) { prepareToolIndices << params.aligner } +if (!params.skip_pseudo_alignment) { prepareToolIndices << params.pseudo_aligner } // Get RSeqC modules to run def rseqc_modules = params.rseqc_modules ? params.rseqc_modules.split(',').collect{ it.trim().toLowerCase() } : [] @@ -799,7 +799,7 @@ workflow RNASEQ { ch_salmon_multiqc = Channel.empty() ch_pseudoaligner_pca_multiqc = Channel.empty() ch_pseudoaligner_clustering_multiqc = Channel.empty() - if (params.pseudo_aligner == 'salmon') { + if (!params.skip_pseudo_alignment && params.pseudo_aligner == 'salmon') { QUANTIFY_SALMON ( ch_filtered_reads, PREPARE_GENOME.out.salmon_index, From 65ed2b95ba730b735d697fcbce25e96169a82ebd Mon Sep 17 00:00:00 2001 From: Adam Talbot Date: Thu, 1 Jun 2023 10:46:16 +0100 Subject: [PATCH 28/36] Update warning when using --additional_fasta to show clarify gene_bed --- CHANGELOG.md | 1 + lib/WorkflowRnaseq.groovy | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 0b0ba042e..4a014d844 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -11,6 +11,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - [[#1018](https://github.com/nf-core/rnaseq/issues/1018)] - Ability to skip both alignment and pseudo-alignment to only run pre-processing QC steps. - [PR #1016](https://github.com/nf-core/rnaseq/pull/1016) - Updated pipeline template to [nf-core/tools 2.8](https://github.com/nf-core/tools/releases/tag/2.8) - [PR #1025](https://github.com/nf-core/fetchngs/pull/1025) - Add `public_aws_ecr.config` to source mulled containers when using `public.ecr.aws` Docker Biocontainer registry +- Updated error log for count values when supplying `--additional_fasta` ### Parameters diff --git a/lib/WorkflowRnaseq.groovy b/lib/WorkflowRnaseq.groovy index 14f1493a8..7fcdb5573 100755 --- a/lib/WorkflowRnaseq.groovy +++ b/lib/WorkflowRnaseq.groovy @@ -405,6 +405,10 @@ class WorkflowRnaseq { " Set '--additional_fasta --${index}_index false --save_reference' to\n" + " re-build the index with transgenes included and the index will be saved in\n" + " 'results/genome/index/${index}/' for re-use with '--${index}_index'.\n\n" + + " In addition, regions in '--additional_fasta' will not be included in count \n" + + " values. If you wish to include this supply a '--gene_bed' file including \n" + + " of interest or use '--gene_bed false to generate a new one containing all \n" + + " of the '--additional_fasta' regions.\n\n" + " Ignore this warning if you know that the index already contains transgenes.\n\n" + " Please see:\n" + " https://github.com/nf-core/rnaseq/issues/556\n" + From 58f005e1b7f07a8c6150f132b4dac5296c9bfd24 Mon Sep 17 00:00:00 2001 From: Adam Talbot Date: Thu, 1 Jun 2023 10:49:15 +0100 Subject: [PATCH 29/36] changelog --- CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 4a014d844..7ca8f329f 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -11,7 +11,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - [[#1018](https://github.com/nf-core/rnaseq/issues/1018)] - Ability to skip both alignment and pseudo-alignment to only run pre-processing QC steps. - [PR #1016](https://github.com/nf-core/rnaseq/pull/1016) - Updated pipeline template to [nf-core/tools 2.8](https://github.com/nf-core/tools/releases/tag/2.8) - [PR #1025](https://github.com/nf-core/fetchngs/pull/1025) - Add `public_aws_ecr.config` to source mulled containers when using `public.ecr.aws` Docker Biocontainer registry -- Updated error log for count values when supplying `--additional_fasta` +- [PR #1038](https://github.com/nf-core/rnaseq/pull/1038) - Updated error log for count values when supplying `--additional_fasta` ### Parameters From 73eae67017e421c406a28db0c94ecc582fc3a949 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Thu, 1 Jun 2023 13:08:15 +0100 Subject: [PATCH 30/36] Update WorkflowRnaseq.groovy --- lib/WorkflowRnaseq.groovy | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/lib/WorkflowRnaseq.groovy b/lib/WorkflowRnaseq.groovy index 7fcdb5573..7c674d590 100755 --- a/lib/WorkflowRnaseq.groovy +++ b/lib/WorkflowRnaseq.groovy @@ -402,13 +402,9 @@ class WorkflowRnaseq { " When using '--additional_fasta ' the aligner index will not\n" + " be re-built with the transgenes incorporated by default since you have \n" + " already provided an index via '--${index}_index '.\n\n" + - " Set '--additional_fasta --${index}_index false --save_reference' to\n" + - " re-build the index with transgenes included and the index will be saved in\n" + + " Set '--additional_fasta --${index}_index false --gene_bed false --save_reference'\n" + + " to re-build the index with transgenes included and the index and gene BED file will be saved in\n" + " 'results/genome/index/${index}/' for re-use with '--${index}_index'.\n\n" + - " In addition, regions in '--additional_fasta' will not be included in count \n" + - " values. If you wish to include this supply a '--gene_bed' file including \n" + - " of interest or use '--gene_bed false to generate a new one containing all \n" + - " of the '--additional_fasta' regions.\n\n" + " Ignore this warning if you know that the index already contains transgenes.\n\n" + " Please see:\n" + " https://github.com/nf-core/rnaseq/issues/556\n" + From 84890da7989b83cbce4448e222023e7318c6df5d Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Thu, 1 Jun 2023 13:16:59 +0100 Subject: [PATCH 31/36] Bump pipeline version to 3.12.0 --- nextflow.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/nextflow.config b/nextflow.config index c270bae12..09bed2da2 100644 --- a/nextflow.config +++ b/nextflow.config @@ -302,7 +302,7 @@ manifest { description = """RNA sequencing analysis pipeline for gene/isoform quantification and extensive quality control.""" mainScript = 'main.nf' nextflowVersion = '!>=22.10.1' - version = '3.12.0dev' + version = '3.12.0' doi = 'https://doi.org/10.5281/zenodo.1400710' } From 993fff67ba7590c85cb107143513943ff39dbd21 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Thu, 1 Jun 2023 13:18:02 +0100 Subject: [PATCH 32/36] Be more explicit with --skip_pseudo_aligner logic --- lib/WorkflowRnaseq.groovy | 2 +- workflows/rnaseq.nf | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/WorkflowRnaseq.groovy b/lib/WorkflowRnaseq.groovy index 7c674d590..08d684e77 100755 --- a/lib/WorkflowRnaseq.groovy +++ b/lib/WorkflowRnaseq.groovy @@ -68,7 +68,7 @@ class WorkflowRnaseq { skipAlignmentWarn(log) } - if (!params.skip_pseudo_alignment) { + if (!params.skip_pseudo_alignment && params.pseudo_aligner) { if (!valid_params['pseudoaligners'].contains(params.pseudo_aligner)) { Nextflow.error("Invalid option: '${params.pseudo_aligner}'. Valid options for '--pseudo_aligner': ${valid_params['pseudoaligners'].join(', ')}.") } else { diff --git a/workflows/rnaseq.nf b/workflows/rnaseq.nf index 5f62c2171..8c6b7260d 100755 --- a/workflows/rnaseq.nf +++ b/workflows/rnaseq.nf @@ -45,7 +45,7 @@ if (!params.skip_bbsplit && !params.bbsplit_index && params.bbsplit_fasta_list) def prepareToolIndices = [] if (!params.skip_bbsplit) { prepareToolIndices << 'bbsplit' } if (!params.skip_alignment) { prepareToolIndices << params.aligner } -if (!params.skip_pseudo_alignment) { prepareToolIndices << params.pseudo_aligner } +if (!params.skip_pseudo_alignment && params.pseudo_aligner) { prepareToolIndices << params.pseudo_aligner } // Get RSeqC modules to run def rseqc_modules = params.rseqc_modules ? params.rseqc_modules.split(',').collect{ it.trim().toLowerCase() } : [] From 910a7fecb58837a3a6cc1813cec24ce65399f153 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Thu, 1 Jun 2023 13:21:50 +0100 Subject: [PATCH 33/36] Update CHANGELOG --- CHANGELOG.md | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 7ca8f329f..dafad351a 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,7 +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). -## [Unpublished Version / DEV] +## [[3.12.0](https://github.com/nf-core/rnaseq/releases/tag/3.12.0)] - 2023-06-02 + +### Credits + +Special thanks to the following for their contributions to the release: + +- [Adam Talbot](https://github.com/adamrtalbot) +- [Esha Joshi](https://github.com/ejseqera) +- [Ghepardo](https://github.com/Ghepardo) +- [Matthias Zepper](https://github.com/MatthiasZepper) +- [Maxime Garcia](https://github.com/maxulysse) +- [Rob Syme](https://github.com/robsyme) + +Thank you to everyone else that has contributed by reporting bugs, enhancements or in any other way, shape or form. ### Enhancements & fixes From f15b587a3988802a8426d626b927b7d52bd4f1b2 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Thu, 1 Jun 2023 17:26:32 +0100 Subject: [PATCH 34/36] Update public_aws_ecr.config --- conf/public_aws_ecr.config | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/conf/public_aws_ecr.config b/conf/public_aws_ecr.config index 7356010d8..f584b3926 100644 --- a/conf/public_aws_ecr.config +++ b/conf/public_aws_ecr.config @@ -12,17 +12,20 @@ docker.registry = 'public.ecr.aws' podman.registry = 'public.ecr.aws' process { + withName: 'CAT_ADDITIONAL_FASTA' { + container = 'quay.io/biocontainers/python:3.9--1' + } withName: 'CAT_FASTQ' { container = 'quay.io/nf-core/ubuntu:20.04' } - withName: 'SAMPLESHEET_CHECK|CAT_ADDITIONAL_FASTA|GTF_GENE_FILTER|MULTIQC_CUSTOM_BIOTYPE|SALMON_TX2GENE' { - container = 'quay.io/biocontainers/python:3.9--1' + withName: 'DESEQ2_QC' { + container = 'quay.io/biocontainers/mulled-v2-8849acf39a43cdd6c839a369a74c0adc823e2f91:ab110436faf952a33575c64dd74615a84011450b-0' } withName: 'GTF2BED' { container = 'quay.io/biocontainers/perl:5.26.2' } - withName: 'DESEQ2_QC' { - container = 'quay.io/biocontainers/mulled-v2-8849acf39a43cdd6c839a369a74c0adc823e2f91:ab110436faf952a33575c64dd74615a84011450b-0' + withName: 'GTF_GENE_FILTER' { + container = 'quay.io/biocontainers/python:3.9--1' } withName: 'GUNZIP' { container = 'quay.io/nf-core/ubuntu:20.04' @@ -30,6 +33,9 @@ process { withName: 'HISAT2_ALIGN' { container = 'quay.io/biocontainers/mulled-v2-a97e90b3b802d1da3d6958e0867610c718cb5eb1:2cdf6bf1e92acbeb9b2834b1c58754167173a410-0' } + withName: 'MULTIQC_CUSTOM_BIOTYPE' { + container = 'quay.io/biocontainers/python:3.9--1' + } withName: 'PREPROCESS_TRANSCRIPTS_FASTA_GENCODE' { container = 'quay.io/nf-core/ubuntu:20.04' } @@ -42,6 +48,12 @@ process { withName: 'RSEM_PREPAREREFERENCE' { container = 'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' } + withName: 'SALMON_TX2GENE' { + container = 'quay.io/biocontainers/python:3.9--1' + } + withName: 'SAMPLESHEET_CHECK' { + container = 'quay.io/biocontainers/python:3.9--1' + } withName: 'STAR_ALIGN' { container = 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1df389393721fc66f3fd8778ad938ac711951107-0' } From 88280ca1e495f0e1f0ec014635799c784f1f0ca3 Mon Sep 17 00:00:00 2001 From: maxulysse Date: Fri, 2 Jun 2023 13:48:38 +0200 Subject: [PATCH 35/36] revert samtools_sort to no memory assignement --- modules.json | 6 +++--- modules/nf-core/samtools/sort/main.nf | 2 -- 2 files changed, 3 insertions(+), 5 deletions(-) diff --git a/modules.json b/modules.json index b2fe8ca92..030893337 100644 --- a/modules.json +++ b/modules.json @@ -161,7 +161,7 @@ }, "samtools/sort": { "branch": "master", - "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", + "git_sha": "a0f7be95788366c1923171e358da7d049eb440f9", "installed_by": ["bam_sort_stats_samtools"] }, "samtools/stats": { @@ -252,9 +252,9 @@ "branch": "master", "git_sha": "735e1e04e7e01751d2d6e97055bbdb6f70683cc1", "installed_by": [ - "bam_dedup_stats_samtools_umitools", "bam_markduplicates_picard", - "bam_sort_stats_samtools" + "bam_sort_stats_samtools", + "bam_dedup_stats_samtools_umitools" ] }, "bedgraph_bedclip_bedgraphtobigwig": { diff --git a/modules/nf-core/samtools/sort/main.nf b/modules/nf-core/samtools/sort/main.nf index 1e5181d41..2b7753fd8 100644 --- a/modules/nf-core/samtools/sort/main.nf +++ b/modules/nf-core/samtools/sort/main.nf @@ -21,13 +21,11 @@ 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 \\ - -m ${sort_memory}M \\ -o ${prefix}.bam \\ -T $prefix \\ $bam From d286eb3e971e3ae36e4ca6991f339550048f8cfa Mon Sep 17 00:00:00 2001 From: maxulysse Date: Fri, 2 Jun 2023 13:49:52 +0200 Subject: [PATCH 36/36] update CHANGELOG --- CHANGELOG.md | 1 + 1 file changed, 1 insertion(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index dafad351a..daae6c447 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -25,6 +25,7 @@ Thank you to everyone else that has contributed by reporting bugs, enhancements - [PR #1016](https://github.com/nf-core/rnaseq/pull/1016) - Updated pipeline template to [nf-core/tools 2.8](https://github.com/nf-core/tools/releases/tag/2.8) - [PR #1025](https://github.com/nf-core/fetchngs/pull/1025) - Add `public_aws_ecr.config` to source mulled containers when using `public.ecr.aws` Docker Biocontainer registry - [PR #1038](https://github.com/nf-core/rnaseq/pull/1038) - Updated error log for count values when supplying `--additional_fasta` +- [PR #1042](https://github.com/nf-core/rnaseq/pull/1042) - revert samtools_sort modules to no memory assignement ### Parameters