diff --git a/.editorconfig b/.editorconfig index b78de6e6..b6b31907 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 b280b79e..137da49f 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/smrnaseq _(eg. 1.1, 1.5, 1.8.2)_ diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index cf3fb13d..e278390b 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/smrn - [ ] 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/smrnaseq/tree/master/.github/CONTRIBUTING.md)- [ ] If necessary, also make a PR on the nf-core/smrnaseq _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/smrnaseq/tree/master/.github/CONTRIBUTING.md) +- [ ] If necessary, also make a PR on the nf-core/smrnaseq _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 55a87ee4..f96fb17c 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 with: workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} access_token: ${{ secrets.TOWER_ACCESS_TOKEN }} @@ -24,7 +24,7 @@ jobs: { "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/smrnaseq/results-${{ github.sha }}" } - profiles: test_full,aws_tower + profiles: test_full,public_aws_ecr - uses: actions/upload-artifact@v3 with: name: Tower debug log file diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml index 03a442a1..a1f96d73 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: ${{ secrets.TOWER_ACCESS_TOKEN }} @@ -22,7 +22,7 @@ jobs: { "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/smrnaseq/results-test-${{ github.sha }}" } - profiles: test,aws_tower + profiles: test,public_aws_ecr - uses: actions/upload-artifact@v3 with: name: Tower debug log file diff --git a/.github/workflows/branch.yml b/.github/workflows/branch.yml index afde4c08..96080391 100644 --- a/.github/workflows/branch.yml +++ b/.github/workflows/branch.yml @@ -13,7 +13,7 @@ jobs: - name: Check PRs if: github.repository == 'nf-core/smrnaseq' run: | - { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/smrnaseq ]] && [[ $GITHUB_HEAD_REF = "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]] + { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/smrnaseq ]] && [[ $GITHUB_HEAD_REF == "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]] # If the above check failed, post a comment on the PR explaining the failure # NOTE - this doesn't currently work if the PR is coming from a fork, due to limitations in GitHub actions secrets diff --git a/.github/workflows/clean-up.yml b/.github/workflows/clean-up.yml new file mode 100644 index 00000000..694e90ec --- /dev/null +++ b/.github/workflows/clean-up.yml @@ -0,0 +1,24 @@ +name: "Close user-tagged issues and PRs" +on: + schedule: + - cron: "0 0 * * 0" # Once a week + +jobs: + clean-up: + runs-on: ubuntu-latest + permissions: + issues: write + pull-requests: write + steps: + - uses: actions/stale@v7 + with: + stale-issue-message: "This issue has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor. Remove stale label or add a comment otherwise this issue will be closed in 20 days." + stale-pr-message: "This PR has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor. Remove stale label or add a comment if it is still useful." + close-issue-message: "This issue was closed because it has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor and then staled for 20 days with no activity." + days-before-stale: 30 + days-before-close: 20 + days-before-pr-close: -1 + any-of-labels: "awaiting-changes,awaiting-feedback" + exempt-issue-labels: "WIP" + exempt-pr-labels: "WIP" + repo-token: "${{ secrets.GITHUB_TOKEN }}" diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index 858d622e..888cb4bc 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 00000000..0c31cdb9 --- /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 fe86157a..8024dbeb 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,6 +3,13 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). +## [v2.2.1](https://github.com/nf-core/smrnaseq/releases/tag/2.2.1) - 2023-05-08 + +### Enhancements & fixes + +- [[#238](https://github.com/nf-core/smrnaseq/issues/238)] - Restored the missing mirtop outputs +- [[#242](https://github.com/nf-core/smrnaseq/issues/242)] - Fixed mirtrace using wrong input fastq files (untrimmed) + ## [v2.2.0](https://github.com/nf-core/smrnaseq/releases/tag/2.2.0) - 2023-04-26 - [[#220](https://github.com/nf-core/smrnaseq/issues/220)] - Fixed an issue where miRTrace reports fastq basename instead of sample ID diff --git a/README.md b/README.md index 65208e0b..6fb16c5e 100644 --- a/README.md +++ b/README.md @@ -8,11 +8,11 @@ [![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/smrnaseq) -[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23smrnaseq-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/smrnaseq)[![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%23smrnaseq-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/smrnaseq)[![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/smrnaseq** is a bioinformatics best-practice analysis pipeline for Small RNA-Seq Best Practice Analysis Pipeline. +**nf-core/smrnaseq** is a bioinformatics best-practice analysis pipeline for Small RNA-Seq. 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! @@ -50,38 +50,61 @@ You can find numerous talks on the nf-core events page from various topics inclu 9. miRNA quality control ([`mirtrace`](https://github.com/friedlanderlab/mirtrace)) 10. Present QC for raw read, alignment, and expression results ([`MultiQC`](http://multiqc.info/)) -## Quick Start +## Usage -1. Install [`Nextflow`](https://www.nextflow.io/docs/latest/getstarted.html#installation) (`>=22.10.1`) +> **Note** +> If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how +> to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline) +> with `-profile test` before running the workflow on actual data. -2. Install any of [`Docker`](https://docs.docker.com/engine/installation/), [`Singularity`](https://www.sylabs.io/guides/3.0/user-guide/) (you can follow [this tutorial](https://singularity-tutorial.github.io/01-installation/)), [`Podman`](https://podman.io/), [`Shifter`](https://nersc.gitlab.io/development/shifter/how-to-use/) or [`Charliecloud`](https://hpc.github.io/charliecloud/) for full pipeline reproducibility _(you can use [`Conda`](https://conda.io/miniconda.html) both to install Nextflow itself and also to manage software within pipelines. Please only use it within pipelines as a last resort; see [docs](https://nf-co.re/usage/configuration#basic-configuration-profiles))_. + - ```bash - nextflow run nf-core/smrnaseq --input samplesheet.csv --outdir --genome GRCh37 -profile - ``` +Now, you can run the pipeline using: -## Documentation + -The nf-core/smrnaseq pipeline comes with documentation about the pipeline [usage](https://nf-co.re/smrnaseq/usage), [parameters](https://nf-co.re/smrnaseq/parameters) and [output](https://nf-co.re/smrnaseq/output). +```bash +nextflow run nf-core/smrnaseq \ + -profile \ + --input samplesheet.csv \ + --genome 'GRCh37' \ + --mirtrace_species 'hsa' \ + --protocol 'illumina' \ + --outdir +``` + +> **Warning:** +> Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those +> provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_; +> see [docs](https://nf-co.re/usage/configuration#custom-configuration-files). + +For more details, please refer to the [usage documentation](https://nf-co.re/smrnaseq/usage) and the [parameter documentation](https://nf-co.re/smrnaseq/parameters). + +## Pipeline output + +To see the the results of a test run with a full size dataset refer to the [results](https://nf-co.re/smrnaseq/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/smrnaseq/output). ## Credits -nf-core/smrnaseq was originally written for use at the [National Genomics Infrastructure](https://portal.scilifelab.se/genomics/) at [SciLifeLab](http://www.scilifelab.se/) in Stockholm, Sweden, by Phil Ewels ([@ewels](https://github.com/ewels)), Chuan Wang ([@chuan-wang](https://github.com/chuan-wang)) and Rickard Hammarén ([@Hammarn](https://github.com/hammarn)). +nf-core/smrnaseq was originally written by P. Ewels, C. Wang, R. Hammarén, L. Pantano, A. Peltzer. + +We thank the following people for their extensive assistance in the development of this pipeline: Lorena Pantano ([@lpantano](https://github.com/lpantano)) from MIT updated the pipeline to Nextflow DSL2. diff --git a/conf/base.config b/conf/base.config index 74748079..544ed42d 100644 --- a/conf/base.config +++ b/conf/base.config @@ -14,7 +14,7 @@ process { memory = { check_max( 6.GB * task.attempt, 'memory' ) } time = { check_max( 4.h * task.attempt, 'time' ) } - errorStrategy = { task.exitStatus in [143,137,104,134,139] ? 'retry' : 'finish' } + errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' } maxRetries = 1 maxErrors = '-1' diff --git a/conf/igenomes.config b/conf/igenomes.config index b55f7a2b..d608b45b 100644 --- a/conf/igenomes.config +++ b/conf/igenomes.config @@ -38,6 +38,14 @@ params { blacklist = "${projectDir}/assets/blacklists/hg38-blacklist.bed" mirtrace_species = "hsa" } + 'CHM13' { + fasta = "${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/public_aws_ecr.config b/conf/public_aws_ecr.config new file mode 100644 index 00000000..8152e14a --- /dev/null +++ b/conf/public_aws_ecr.config @@ -0,0 +1,30 @@ +/* +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + 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: '.*:SAMPLESHEET_CHECK' { + container = "quay.io/biocontainers/python:3.8.3" + } + withName: '.*:BOWTIE_MAP.*' { + container = 'quay.io/biocontainers/mulled-v2-ffbf83a6b0ab6ec567a336cf349b80637135bca3:40128b496751b037e2bd85f6789e83d4ff8a4837-0' + } + withName: '.*:EDGER_QC' { + container = 'quay.io/biocontainers/mulled-v2-419bd7f10b2b902489ac63bbaafc7db76f8e0ae1:709335c37934db1b481054cbec637c6e5b5971cb-0' + } + withName: '.*:MIRTOP_QUANT' { + container = 'quay.io/biocontainers/mulled-v2-0c13ef770dd7cc5c76c2ce23ba6669234cf03385:63be019f50581cc5dfe4fc0f73ae50f2d4d661f7-0' + } + withName: '.*:TABLE_MERGE' { + container = 'quay.io/biocontainers/r-data.table:1.12.2' + } +} diff --git a/docs/usage.md b/docs/usage.md index f0027bcf..1893e2e6 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -118,6 +118,29 @@ 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/smrnaseq -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: @@ -141,6 +164,10 @@ The `bin` directory contains some scripts used by the pipeline which may also be - `edgeR_miRBase.r`: R script using for processing reads counts of mature miRNAs and miRNA precursors (hairpins). 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). @@ -149,7 +176,7 @@ The `bin` directory contains some scripts used by the pipeline which may also be 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. @@ -173,8 +200,10 @@ 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` @@ -192,102 +221,19 @@ 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 33cd4f6e..9b34804d 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 9cecee1c..9a0db96c 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/smrnaseq pipeline // +import nextflow.Nextflow + class WorkflowMain { // @@ -20,7 +22,7 @@ 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) @@ -33,7 +35,7 @@ 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) @@ -52,7 +54,7 @@ class WorkflowMain { // Print help to screen if required if (params.help) { - log.info help(workflow, params, log) + log.info help(workflow, params) System.exit(0) } @@ -64,7 +66,7 @@ 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) { @@ -84,8 +86,7 @@ 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/WorkflowSmrnaseq.groovy b/lib/WorkflowSmrnaseq.groovy index cd8b1e1e..7013e903 100755 --- a/lib/WorkflowSmrnaseq.groovy +++ b/lib/WorkflowSmrnaseq.groovy @@ -2,6 +2,7 @@ // This file holds several functions specific to the workflow/smrnaseq.nf in the nf-core/smrnaseq pipeline // +import nextflow.Nextflow import groovy.text.SimpleTemplateEngine class WorkflowSmrnaseq { @@ -55,17 +56,19 @@ class WorkflowSmrnaseq { 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/modules.json b/modules.json index a4d925ab..0b6daac5 100644 --- a/modules.json +++ b/modules.json @@ -7,52 +7,52 @@ "nf-core": { "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"] }, "fastp": { "branch": "master", - "git_sha": "20a508676f40d0fd3f911ac595af91ec845704c4", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "fastqc": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "multiqc": { "branch": "master", - "git_sha": "ee80d14721e76e2e079103b8dcd5d57129e584ba", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "samtools/flagstat": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "samtools/idxstats": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "samtools/index": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "samtools/sort": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "samtools/stats": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] } } diff --git a/modules/local/blat_mirna.nf b/modules/local/blat_mirna.nf index 198e001c..7f8a2324 100644 --- a/modules/local/blat_mirna.nf +++ b/modules/local/blat_mirna.nf @@ -5,7 +5,7 @@ process BLAT_MIRNA { conda 'bioconda::blat=36' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/blat:36--0' : - 'quay.io/biocontainers/blat:36--0' }" + 'biocontainers/blat:36--0' }" input: val db_type diff --git a/modules/local/bowtie_contaminants.nf b/modules/local/bowtie_contaminants.nf index a68b8530..e6a594a7 100644 --- a/modules/local/bowtie_contaminants.nf +++ b/modules/local/bowtie_contaminants.nf @@ -4,7 +4,7 @@ process INDEX_CONTAMINANTS { conda 'bowtie2=2.4.5' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/bowtie2:2.4.5--py39hd2f7db1_2' : - 'quay.io/biocontainers/bowtie2:2.4.5--py36hfca12d5_2'}" + 'biocontainers/bowtie2:2.4.5--py36hfca12d5_2'}" input: path fasta diff --git a/modules/local/bowtie_genome.nf b/modules/local/bowtie_genome.nf index 1405467a..b132e1da 100644 --- a/modules/local/bowtie_genome.nf +++ b/modules/local/bowtie_genome.nf @@ -5,7 +5,7 @@ process INDEX_GENOME { conda 'bioconda::bowtie=1.3.1-4' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/bowtie%3A1.3.1--py39hd400a0c_2' : - 'quay.io/biocontainers/bowtie:1.3.1--py310h4070885_4' }" + 'biocontainers/bowtie:1.3.1--py310h4070885_4' }" input: path fasta diff --git a/modules/local/bowtie_map_contaminants.nf b/modules/local/bowtie_map_contaminants.nf index 09ad0162..d10f13b5 100644 --- a/modules/local/bowtie_map_contaminants.nf +++ b/modules/local/bowtie_map_contaminants.nf @@ -4,7 +4,7 @@ process BOWTIE_MAP_CONTAMINANTS { conda 'bowtie2=2.4.5' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/bowtie2:2.4.5--py39hd2f7db1_2' : - 'quay.io/biocontainers/bowtie2:2.4.5--py36hfca12d5_2' }" + 'biocontainers/bowtie2:2.4.5--py36hfca12d5_2' }" input: tuple val(meta), path(reads) diff --git a/modules/local/bowtie_map_mirna.nf b/modules/local/bowtie_map_mirna.nf index 8202838f..148b47f5 100644 --- a/modules/local/bowtie_map_mirna.nf +++ b/modules/local/bowtie_map_mirna.nf @@ -5,7 +5,7 @@ process BOWTIE_MAP_SEQ { conda 'bowtie=1.3.0-2 bioconda::samtools=1.13' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/mulled-v2-ffbf83a6b0ab6ec567a336cf349b80637135bca3:40128b496751b037e2bd85f6789e83d4ff8a4837-0' : - 'quay.io/biocontainers/mulled-v2-ffbf83a6b0ab6ec567a336cf349b80637135bca3:40128b496751b037e2bd85f6789e83d4ff8a4837-0' }" + 'biocontainers/mulled-v2-ffbf83a6b0ab6ec567a336cf349b80637135bca3:40128b496751b037e2bd85f6789e83d4ff8a4837-0' }" input: tuple val(meta), path(reads) diff --git a/modules/local/bowtie_mirna.nf b/modules/local/bowtie_mirna.nf index 601c9f43..9390730a 100644 --- a/modules/local/bowtie_mirna.nf +++ b/modules/local/bowtie_mirna.nf @@ -4,7 +4,7 @@ process INDEX_MIRNA { conda 'bioconda::bowtie=1.3.0-2' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/bowtie%3A1.3.1--py39hd400a0c_2' : - 'quay.io/biocontainers/bowtie:1.3.1--py310h4070885_4' }" + 'biocontainers/bowtie:1.3.1--py310h4070885_4' }" input: path fasta diff --git a/modules/local/datatable_merge.nf b/modules/local/datatable_merge.nf index 5b238c06..c71b9c4d 100644 --- a/modules/local/datatable_merge.nf +++ b/modules/local/datatable_merge.nf @@ -4,7 +4,7 @@ process TABLE_MERGE { conda 'conda-base::r-data.table=1.12.2' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/r-data.table:1.12.2' : - 'quay.io/biocontainers/r-data.table:1.12.2' }" + 'biocontainers/r-data.table:1.12.2' }" input: path mirtop diff --git a/modules/local/edger_qc.nf b/modules/local/edger_qc.nf index 0d8efe64..729d5eed 100644 --- a/modules/local/edger_qc.nf +++ b/modules/local/edger_qc.nf @@ -4,7 +4,7 @@ process EDGER_QC { conda 'bioconda::bioconductor-limma=3.50.0 bioconda::bioconductor-edger=3.36.0 conda-forge::r-data.table=1.14.2 conda-forge::r-gplots=3.1.1 conda-forge::r-statmod=1.4.36' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/mulled-v2-419bd7f10b2b902489ac63bbaafc7db76f8e0ae1:709335c37934db1b481054cbec637c6e5b5971cb-0' : - 'quay.io/biocontainers/mulled-v2-419bd7f10b2b902489ac63bbaafc7db76f8e0ae1:709335c37934db1b481054cbec637c6e5b5971cb-0' }" + 'biocontainers/mulled-v2-419bd7f10b2b902489ac63bbaafc7db76f8e0ae1:709335c37934db1b481054cbec637c6e5b5971cb-0' }" input: path input_files diff --git a/modules/local/filter_stats.nf b/modules/local/filter_stats.nf index c9336f22..18e7016b 100644 --- a/modules/local/filter_stats.nf +++ b/modules/local/filter_stats.nf @@ -4,7 +4,7 @@ process FILTER_STATS { conda 'bowtie2=2.4.5' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/bowtie2:2.4.5--py39hd2f7db1_2' : - 'quay.io/biocontainers/bowtie2:2.4.5--py36hfca12d5_2' }" + 'biocontainers/bowtie2:2.4.5--py36hfca12d5_2' }" input: tuple val(meta), path(reads) diff --git a/modules/local/format_fasta_mirna.nf b/modules/local/format_fasta_mirna.nf index 2c39c0aa..3e247ce4 100644 --- a/modules/local/format_fasta_mirna.nf +++ b/modules/local/format_fasta_mirna.nf @@ -7,7 +7,7 @@ process FORMAT_FASTA_MIRNA { conda 'bioconda::fastx_toolkit=0.0.14-9' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/fastx_toolkit:0.0.14--he1b5a44_8' : - 'quay.io/biocontainers/fastx_toolkit:0.0.14--he1b5a44_8' }" + 'biocontainers/fastx_toolkit:0.0.14--he1b5a44_8' }" input: path fasta diff --git a/modules/local/mirdeep2_mapper.nf b/modules/local/mirdeep2_mapper.nf index 2293ef87..842af6e6 100644 --- a/modules/local/mirdeep2_mapper.nf +++ b/modules/local/mirdeep2_mapper.nf @@ -7,7 +7,7 @@ process MIRDEEP2_MAPPER { conda 'bioconda::mirdeep2=2.0.1' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/mirdeep2:2.0.1.3--hdfd78af_1' : - 'quay.io/biocontainers/mirdeep2:2.0.1.3--hdfd78af_1' }" + 'biocontainers/mirdeep2:2.0.1.3--hdfd78af_1' }" input: tuple val(meta), path(reads) diff --git a/modules/local/mirdeep2_prepare.nf b/modules/local/mirdeep2_prepare.nf index 3d117d4a..7e2f2437 100644 --- a/modules/local/mirdeep2_prepare.nf +++ b/modules/local/mirdeep2_prepare.nf @@ -6,7 +6,7 @@ process MIRDEEP2_PIGZ { conda 'bioconda::bioconvert=0.4.3' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/bioconvert:0.4.3--py_0' : - 'quay.io/biocontainers/bioconvert:0.4.3--py_0' }" + 'biocontainers/bioconvert:0.4.3--py_0' }" input: tuple val(meta), path(reads) diff --git a/modules/local/mirdeep2_run.nf b/modules/local/mirdeep2_run.nf index 2035658c..74044e4a 100644 --- a/modules/local/mirdeep2_run.nf +++ b/modules/local/mirdeep2_run.nf @@ -7,7 +7,7 @@ process MIRDEEP2_RUN { conda 'bioconda::mirdeep2=2.0.1' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/mirdeep2:2.0.1.3--hdfd78af_1' : - 'quay.io/biocontainers/mirdeep2:2.0.1.3--hdfd78af_1' }" + 'biocontainers/mirdeep2:2.0.1.3--hdfd78af_1' }" input: path fasta diff --git a/modules/local/mirtop_quant.nf b/modules/local/mirtop_quant.nf index c4e76a3c..3ebb65ac 100644 --- a/modules/local/mirtop_quant.nf +++ b/modules/local/mirtop_quant.nf @@ -4,7 +4,7 @@ process MIRTOP_QUANT { conda 'mirtop=0.4.25 bioconda::samtools=1.15.1 conda-base::r-base=4.1.1 conda-base::r-data.table=1.14.2' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/mulled-v2-0c13ef770dd7cc5c76c2ce23ba6669234cf03385:63be019f50581cc5dfe4fc0f73ae50f2d4d661f7-0' : - 'quay.io/biocontainers/mulled-v2-0c13ef770dd7cc5c76c2ce23ba6669234cf03385:63be019f50581cc5dfe4fc0f73ae50f2d4d661f7-0' }" + 'biocontainers/mulled-v2-0c13ef770dd7cc5c76c2ce23ba6669234cf03385:63be019f50581cc5dfe4fc0f73ae50f2d4d661f7-0' }" input: path ("bams/*") diff --git a/modules/local/mirtrace.nf b/modules/local/mirtrace.nf index f37a4b3c..f576ebc0 100644 --- a/modules/local/mirtrace.nf +++ b/modules/local/mirtrace.nf @@ -4,7 +4,7 @@ process MIRTRACE_RUN { conda 'bioconda::mirtrace=1.0.1' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/mirtrace:1.0.1--hdfd78af_1' : - 'quay.io/biocontainers/mirtrace:1.0.1--hdfd78af_1' }" + 'biocontainers/mirtrace:1.0.1--hdfd78af_1' }" input: tuple val(adapter), val(ids), path(reads) diff --git a/modules/local/parse_fasta_mirna.nf b/modules/local/parse_fasta_mirna.nf index 5418f597..ab7a91f0 100644 --- a/modules/local/parse_fasta_mirna.nf +++ b/modules/local/parse_fasta_mirna.nf @@ -4,7 +4,7 @@ process PARSE_FASTA_MIRNA { conda 'bioconda::seqkit=2.3.1' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/seqkit:2.3.1--h9ee0642_0' : - 'quay.io/biocontainers/seqkit:2.3.1--h9ee0642_0' }" + 'biocontainers/seqkit:2.3.1--h9ee0642_0' }" input: path fasta diff --git a/modules/local/samplesheet_check.nf b/modules/local/samplesheet_check.nf index 721874ef..c1b0967f 100644 --- a/modules/local/samplesheet_check.nf +++ b/modules/local/samplesheet_check.nf @@ -6,7 +6,7 @@ process SAMPLESHEET_CHECK { conda "conda-forge::python=3.8.3" container "${ 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/local/seqcluster_collapse.nf b/modules/local/seqcluster_collapse.nf index 36645ee1..39f6ce85 100644 --- a/modules/local/seqcluster_collapse.nf +++ b/modules/local/seqcluster_collapse.nf @@ -5,7 +5,7 @@ process SEQCLUSTER_SEQUENCES { conda 'bioconda::seqcluster=1.2.9-0' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/seqcluster:1.2.9--pyh5e36f6f_0' : - 'quay.io/biocontainers/seqcluster:1.2.8--pyh5e36f6f_0' }" + 'biocontainers/seqcluster:1.2.8--pyh5e36f6f_0' }" input: tuple val(meta), path(reads) diff --git a/modules/nf-core/cat/fastq/main.nf b/modules/nf-core/cat/fastq/main.nf index 8a0b5600..5021e6fc 100644 --- a/modules/nf-core/cat/fastq/main.nf +++ b/modules/nf-core/cat/fastq/main.nf @@ -5,7 +5,7 @@ process CAT_FASTQ { conda "conda-forge::sed=4.7" container "${ 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 c836598e..8a39e309 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 800a6099..ebc87273 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/meta.yml b/modules/nf-core/custom/dumpsoftwareversions/meta.yml index 60b546a0..c32657de 100644 --- a/modules/nf-core/custom/dumpsoftwareversions/meta.yml +++ b/modules/nf-core/custom/dumpsoftwareversions/meta.yml @@ -1,7 +1,9 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/yaml-schema.json name: custom_dumpsoftwareversions description: Custom module used to dump software versions within the nf-core pipeline template keywords: - custom + - dump - version tools: - custom: diff --git a/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py b/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py old mode 100644 new mode 100755 diff --git a/modules/nf-core/fastp/main.nf b/modules/nf-core/fastp/main.nf index 5eeb9b09..2ca2d3ee 100644 --- a/modules/nf-core/fastp/main.nf +++ b/modules/nf-core/fastp/main.nf @@ -5,7 +5,7 @@ process FASTP { conda "bioconda::fastp=0.23.2" container "${ 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 9ae58381..07d5e433 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 "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/fastqc:0.11.9--0' : - 'quay.io/biocontainers/fastqc:0.11.9--0' }" + 'biocontainers/fastqc:0.11.9--0' }" input: tuple val(meta), path(reads) diff --git a/modules/nf-core/multiqc/main.nf b/modules/nf-core/multiqc/main.nf index 4b604749..1fc387be 100644 --- a/modules/nf-core/multiqc/main.nf +++ b/modules/nf-core/multiqc/main.nf @@ -4,7 +4,7 @@ process MULTIQC { conda "bioconda::multiqc=1.14" container "${ 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_files, stageAs: "?/*" diff --git a/modules/nf-core/multiqc/meta.yml b/modules/nf-core/multiqc/meta.yml index ebc29b27..f93b5ee5 100644 --- a/modules/nf-core/multiqc/meta.yml +++ b/modules/nf-core/multiqc/meta.yml @@ -1,3 +1,4 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/yaml-schema.json name: MultiQC description: Aggregate results from bioinformatics analyses across many samples into a single report keywords: @@ -37,7 +38,7 @@ output: description: MultiQC report file pattern: "multiqc_report.html" - data: - type: dir + type: directory description: MultiQC data dir pattern: "multiqc_data" - plots: diff --git a/modules/nf-core/samtools/flagstat/main.nf b/modules/nf-core/samtools/flagstat/main.nf index 2120cd7d..eb7e72fc 100644 --- a/modules/nf-core/samtools/flagstat/main.nf +++ b/modules/nf-core/samtools/flagstat/main.nf @@ -2,10 +2,10 @@ process SAMTOOLS_FLAGSTAT { tag "$meta.id" label 'process_single' - conda "bioconda::samtools=1.16.1" + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.16.1--h6899075_1' : - 'quay.io/biocontainers/samtools:1.16.1--h6899075_1' }" + 'https://depot.galaxyproject.org/singularity/samtools:1.17--h00cdaf9_0' : + 'biocontainers/samtools:1.17--h00cdaf9_0' }" input: tuple val(meta), path(bam), path(bai) diff --git a/modules/nf-core/samtools/idxstats/main.nf b/modules/nf-core/samtools/idxstats/main.nf index a7b87d8b..a257d700 100644 --- a/modules/nf-core/samtools/idxstats/main.nf +++ b/modules/nf-core/samtools/idxstats/main.nf @@ -2,10 +2,10 @@ process SAMTOOLS_IDXSTATS { tag "$meta.id" label 'process_single' - conda "bioconda::samtools=1.16.1" + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.16.1--h6899075_1' : - 'quay.io/biocontainers/samtools:1.16.1--h6899075_1' }" + 'https://depot.galaxyproject.org/singularity/samtools:1.17--h00cdaf9_0' : + 'biocontainers/samtools:1.17--h00cdaf9_0' }" input: tuple val(meta), path(bam), path(bai) diff --git a/modules/nf-core/samtools/index/main.nf b/modules/nf-core/samtools/index/main.nf index 8b95687a..0b20aa4b 100644 --- a/modules/nf-core/samtools/index/main.nf +++ b/modules/nf-core/samtools/index/main.nf @@ -2,10 +2,10 @@ process SAMTOOLS_INDEX { tag "$meta.id" label 'process_low' - conda "bioconda::samtools=1.16.1" + conda "bioconda::samtools=1.17" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/samtools:1.16.1--h6899075_1' : - 'quay.io/biocontainers/samtools:1.16.1--h6899075_1' }" + 'https://depot.galaxyproject.org/singularity/samtools:1.17--h00cdaf9_0' : + 'biocontainers/samtools:1.17--h00cdaf9_0' }" input: tuple val(meta), path(input) diff --git a/modules/nf-core/samtools/sort/main.nf b/modules/nf-core/samtools/sort/main.nf index 84c167cd..1e5181d4 100644 --- a/modules/nf-core/samtools/sort/main.nf +++ b/modules/nf-core/samtools/sort/main.nf @@ -2,10 +2,10 @@ process SAMTOOLS_SORT { tag "$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 0a2a3640..eb7f098b 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/nextflow.config b/nextflow.config index 7b6f2d8e..2f9dd945 100644 --- a/nextflow.config +++ b/nextflow.config @@ -110,7 +110,11 @@ try { // } profiles { - debug { process.beforeScript = 'echo $HOSTNAME' } + debug { + dumpHashes = true + process.beforeScript = 'echo $HOSTNAME' + cleanup = false + } conda { conda.enabled = true docker.enabled = false @@ -118,6 +122,7 @@ profiles { podman.enabled = false shifter.enabled = false charliecloud.enabled = false + apptainer.enabled = false } mamba { conda.enabled = true @@ -127,53 +132,76 @@ profiles { podman.enabled = false shifter.enabled = false charliecloud.enabled = false + apptainer.enabled = false } docker { - docker.enabled = true - docker.userEmulation = true - singularity.enabled = false - podman.enabled = false - shifter.enabled = false - charliecloud.enabled = false - docker.runOptions = '-u $(id -u):$(id -g)' + docker.enabled = true + docker.userEmulation = true + docker.runOptions = '-u $(id -u):$(id -g)' + 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' } singularity { - singularity.enabled = true - singularity.autoMounts = true - docker.enabled = false - podman.enabled = false - shifter.enabled = false - charliecloud.enabled = false + singularity.enabled = true + singularity.autoMounts = true + conda.enabled = false + docker.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false + apptainer.enabled = false } podman { - podman.enabled = true - docker.enabled = false - singularity.enabled = false - shifter.enabled = false - charliecloud.enabled = false + podman.enabled = true + conda.enabled = false + docker.enabled = false + singularity.enabled = false + shifter.enabled = false + charliecloud.enabled = false + apptainer.enabled = false } shifter { - shifter.enabled = true - docker.enabled = false - singularity.enabled = false - podman.enabled = false - charliecloud.enabled = false + shifter.enabled = true + conda.enabled = false + docker.enabled = false + singularity.enabled = false + podman.enabled = false + charliecloud.enabled = false + apptainer.enabled = false } charliecloud { - charliecloud.enabled = true - docker.enabled = false - singularity.enabled = false - podman.enabled = false - shifter.enabled = false + charliecloud.enabled = true + conda.enabled = false + docker.enabled = false + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + apptainer.enabled = false + } + apptainer { + apptainer.enabled = true + conda.enabled = false + docker.enabled = false + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false } gitpod { executor.name = 'local' executor.cpus = 16 executor.memory = 60.GB } + public_aws_ecr { + includeConfig 'conf/public_aws_ecr.config' + } test { includeConfig 'conf/test.config' } test_no_genome { includeConfig 'conf/test_no_genome.config' } test_full { includeConfig 'conf/test_full.config' } @@ -200,6 +228,12 @@ env { // 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 +docker.registry = 'quay.io' +podman.registry = 'quay.io' + def trace_timestamp = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss') timeline { enabled = true @@ -225,7 +259,7 @@ manifest { description = """Small RNA-Seq Best Practice Analysis Pipeline.""" mainScript = 'main.nf' nextflowVersion = '!>=22.10.1' - version = '2.2.0' + version = '2.2.1' doi = '' } diff --git a/subworkflows/local/fastqc_fastp.nf b/subworkflows/local/fastqc_fastp.nf index 3ab260a8..9e4d952e 100644 --- a/subworkflows/local/fastqc_fastp.nf +++ b/subworkflows/local/fastqc_fastp.nf @@ -105,7 +105,7 @@ workflow FASTQC_FASTP { trim_log // channel: [ val(meta), [ log ] ] trim_reads_fail // channel: [ val(meta), [ fastq.gz ] ] trim_reads_merged // channel: [ val(meta), [ fastq.gz ] ] - adapterseq // channel: [ val(meat), [ adapterseq ] ] + adapterseq // channel: [ val(meta), [ adapterseq ] ] fastqc_raw_html // channel: [ val(meta), [ html ] ] fastqc_raw_zip // channel: [ val(meta), [ zip ] ] diff --git a/subworkflows/local/mirtrace.nf b/subworkflows/local/mirtrace.nf index 566b7a1b..317c4444 100644 --- a/subworkflows/local/mirtrace.nf +++ b/subworkflows/local/mirtrace.nf @@ -9,9 +9,7 @@ workflow MIRTRACE { reads // channel: [ val(adapterseq), [ val(ids) ], [ path(reads) ] ] main: - reads - | map { adapterseq, ids, read_collection -> [adapterseq, ids, read_collection*.first()]} - | MIRTRACE_RUN + reads | MIRTRACE_RUN emit: results = MIRTRACE_RUN.out.mirtrace diff --git a/workflows/smrnaseq.nf b/workflows/smrnaseq.nf index 0f8b16a7..ad5ecfef 100644 --- a/workflows/smrnaseq.nf +++ b/workflows/smrnaseq.nf @@ -137,12 +137,12 @@ workflow SMRNASEQ { // SUBWORKFLOW: mirtrace QC // FASTQC_FASTP.out.adapterseq - .join( ch_cat_fastq ) - .map { meta, adapterseq, fastq -> [adapterseq, meta.id, fastq] } + .join( FASTQC_FASTP.out.reads ) + .map { meta, adapterseq, reads -> [adapterseq, meta.id, reads] } .groupTuple() - .set { ch_mitrace_inputs } + .set { ch_mirtrace_inputs } - MIRTRACE(ch_mitrace_inputs) + MIRTRACE(ch_mirtrace_inputs) ch_versions = ch_versions.mix(MIRTRACE.out.versions.ifEmpty(null)) @@ -150,6 +150,7 @@ workflow SMRNASEQ { // SUBWORKFLOW: remove contaminants from reads // contamination_stats = Channel.empty() + mirna_reads = FASTQC_FASTP.out.reads if (params.filter_contamination){ CONTAMINANT_FILTER ( reference_hairpin, @@ -164,6 +165,7 @@ workflow SMRNASEQ { contamination_stats = CONTAMINANT_FILTER.out.filter_stats ch_versions = ch_versions.mix(CONTAMINANT_FILTER.out.versions) + mirna_reads = CONTAMINANT_FILTER.out.filtered_reads } @@ -171,7 +173,7 @@ workflow SMRNASEQ { reference_mature, reference_hairpin, mirna_gtf, - contamination_stats + mirna_reads ) ch_versions = ch_versions.mix(MIRNA_QUANT.out.versions.ifEmpty(null))