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 d16d1ea1..85665d42 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/scrnaseq _(eg. 1.1, 1.5, 1.8.2)_ diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index 9d907223..e66587f6 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/scrn - [ ] 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/scrnaseq/tree/master/.github/CONTRIBUTING.md)- [ ] If necessary, also make a PR on the nf-core/scrnaseq _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/scrnaseq/tree/master/.github/CONTRIBUTING.md) +- [ ] If necessary, also make a PR on the nf-core/scrnaseq _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 90186379..a4c9a575 100644 --- a/.github/workflows/awsfulltest.yml +++ b/.github/workflows/awsfulltest.yml @@ -17,7 +17,7 @@ jobs: aligner: ["alevin", "kallisto", "star", "cellranger", "universc"] 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: ${{ secrets.TOWER_ACCESS_TOKEN }} @@ -28,7 +28,7 @@ jobs: "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/scrnaseq/results-${{ github.sha }}/aligner_${{ matrix.aligner }}", "aligner": "${{ matrix.aligner }}" } - 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 1e10a64e..e51330ee 100644 --- a/.github/workflows/awstest.yml +++ b/.github/workflows/awstest.yml @@ -15,7 +15,7 @@ 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: ${{ secrets.TOWER_ACCESS_TOKEN }} @@ -26,7 +26,7 @@ jobs: "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/scrnaseq/results-test-${{ github.sha }}/aligner_${{ matrix.aligner }}", "aligner": "${{ matrix.aligner }}" } - 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 4dd60cf7..ae5b5d4b 100644 --- a/.github/workflows/branch.yml +++ b/.github/workflows/branch.yml @@ -13,7 +13,7 @@ jobs: - name: Check PRs if: github.repository == 'nf-core/scrnaseq' run: | - { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/scrnaseq ]] && [[ $GITHUB_HEAD_REF = "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]] + { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/scrnaseq ]] && [[ $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/.nf-core.yml b/.nf-core.yml index 3805dc81..a76e0ec8 100644 --- a/.nf-core.yml +++ b/.nf-core.yml @@ -1 +1,3 @@ repository_type: pipeline +lint: + template_strings: False 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 603229e5..113692a9 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). +## v2.3.1 - 2023-06-02 Yellow Strontium Pinscher + +- Add `public_aws_ecr` config for using the AWS mirror of containers where possible ([#225](https://github.com/nf-core/scrnaseq/pull/225)) + ## v2.3.0 Steelblue Waspaloy Dachshund - Fix problem on samplesheet check related to amount of columns ([[#211](https://github.com/nf-core/scrnaseq/issues/211)]) diff --git a/README.md b/README.md index 2577ae5e..f9f3eb20 100644 --- a/README.md +++ b/README.md @@ -10,16 +10,12 @@ [![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/scrnaseq) -[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23scrnaseq-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/scrnaseq)[![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%23scrnaseq-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/scrnaseq)[![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/scrnaseq** is a bioinformatics best-practice analysis pipeline for processing 10x Genomics single-cell RNA-seq data. -The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. It uses Docker/Singularity containers making installation trivial and results highly reproducible. The [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html) implementation of this pipeline uses one container per process which makes it much easier to maintain and update software dependencies. Where possible, these processes have been submitted to and installed from [nf-core/modules](https://github.com/nf-core/modules) in order to make them available to all nf-core pipelines, and to everyone within the Nextflow community! - -On release, automated continuous integration tests run the pipeline on a full-sized dataset on the AWS cloud infrastructure. This ensures that the pipeline runs on AWS, has sensible resource allocation defaults set to run on real-world datasets, and permits the persistent storage of results to benchmark between pipeline releases and other analysis sources. The results obtained from the full-sized test can be viewed on the [nf-core website](https://nf-co.re/scrnaseq/results). - This is a community effort in building a pipeline capable to support: - Alevin-Fry + AlevinQC @@ -34,30 +30,44 @@ The nf-core/scrnaseq pipeline comes with documentation about the pipeline [usage ![scrnaseq workflow](docs/images/scrnaseq_pipeline_v1.0_metro_clean.png) -## 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))_. +First, prepare a samplesheet with your input data that looks as follows: -3. Download the pipeline and test it on a minimal dataset with a single command: +`samplesheet.csv`: - ```bash - nextflow run nf-core/scrnaseq -profile test,YOURPROFILE --outdir - ``` +```csv +sample,fastq_1,fastq_2,expected_cells +pbmc8k,pbmc8k_S1_L007_R1_001.fastq.gz,pbmc8k_S1_L007_R2_001.fastq.gz,"10000" +pbmc8k,pbmc8k_S1_L008_R1_001.fastq.gz,pbmc8k_S1_L008_R2_001.fastq.gz,"10000" +``` - 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. +Each row represents a fastq file (single-end) or a pair of fastq files (paired end). - > - 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. +Now, you can run the pipeline using: -4. Start running your own analysis! +```bash +nextflow run nf-core/scrnaseq \ + -profile \ + --input samplesheet.csv \ + --genome_fasta GRCm38.p6.genome.chr19.fa \ + --gtf gencode.vM19.annotation.chr19.gtf \ + --protocol 10XV2 \ + --aligner \ + --outdir +``` - ```console - nextflow run nf-core/scrnaseq --input samplesheet.csv --outdir --genome_fasta GRCm38.p6.genome.chr19.fa --gtf gencode.vM19.annotation.chr19.gtf --protocol 10XV2 --aligner -profile - ``` +> **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/scrnaseq/usage) and the [parameter documentation](https://nf-co.re/scrnaseq/parameters). ## Decision Tree for users @@ -74,6 +84,12 @@ graph TD Options for the respective alignment method can be found [here](https://github.com/nf-core/scrnaseq/blob/dev/docs/usage.md#aligning-options) to choose between methods. +## Pipeline output + +To see the the results of a test run with a full size dataset refer to the [results](https://nf-co.re/scrnaseq/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/scrnaseq/output). + ## Credits nf-core/scrnaseq was originally written by Bailey PJ, Botvinnik O, Marques de Almeida F, Gabernet G, Peltzer A, Sturm G. diff --git a/bin/check_samplesheet.py b/bin/check_samplesheet.py index 3283c11e..47d1b446 100755 --- a/bin/check_samplesheet.py +++ b/bin/check_samplesheet.py @@ -51,9 +51,6 @@ 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 69be238b..8c6f6db9 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 7a1b3ac6..3f114377 100644 --- a/conf/igenomes.config +++ b/conf/igenomes.config @@ -36,6 +36,14 @@ params { macs_gsize = "2.7e9" blacklist = "${projectDir}/assets/blacklists/hg38-blacklist.bed" } + 'CHM13' { + fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/BWAIndex/" + bwamem2 = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/BWAmem2Index/" + gtf = "${params.igenomes_base}/Homo_sapiens/NCBI/CHM13/Annotation/Genes/genes.gtf" + gff = "ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/914/755/GCF_009914755.1_T2T-CHM13v2.0/GCF_009914755.1_T2T-CHM13v2.0_genomic.gff.gz" + mito_name = "chrM" + } 'GRCm38' { fasta = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.fa" bwa = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BWAIndex/version0.6.0/" diff --git a/conf/modules.config b/conf/modules.config index 1f504b63..253c25e6 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -84,14 +84,14 @@ if(params.aligner == "universc") { saveAs: { filename -> filename.equals('versions.yml') ? null : filename } ] ext.args = "--attribute=gene_biotype:protein_coding --attribute=gene_biotype:lncRNA --attribute=gene_biotype:pseudogene" - container = "nfcore/universc:1.2.5.1" + container = "docker.io/nfcore/universc:1.2.5.1" } withName: CELLRANGER_MKREF { publishDir = [ path: "${params.outdir}/cellranger/mkref", mode: params.publish_dir_mode ] - container = "nfcore/universc:1.2.5.1" + container = "docker.io/nfcore/universc:1.2.5.1" } withName: UNIVERSC { publishDir = [ diff --git a/conf/public_aws_ecr.config b/conf/public_aws_ecr.config new file mode 100644 index 00000000..4ebc067f --- /dev/null +++ b/conf/public_aws_ecr.config @@ -0,0 +1,36 @@ +/* +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + 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: 'CONCAT_H5AD' { + container = 'quay.io/biocontainers/scanpy:1.7.2--pyhdfd78af_0' + } + withName: 'GENE_MAP' { + container = 'quay.io/biocontainers/python:3.8.3' + } + withName: 'GTF_GENE_FILTER' { + container = 'quay.io/biocontainers/python:3.9--1' + } + withName: 'GUNZIP' { + container = 'quay.io/nf-core/ubuntu:20.04' + } + withName: 'MTX_TO_H5AD' { + container = 'quay.io/biocontainers/scanpy:1.7.2--pyhdfd78af_0' + } + withName: 'SAMPLESHEET_CHECK' { + container = 'quay.io/biocontainers/python:3.8.3' + } + withName: 'STAR_GENOMEGENERATE' { + container = 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1df389393721fc66f3fd8778ad938ac711951107-0' + } +} diff --git a/docs/usage.md b/docs/usage.md index 61e820d8..bfa53ac2 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -113,6 +113,29 @@ 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/scrnaseq -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: @@ -129,6 +152,10 @@ First, go to the [nf-core/scrnaseq releases page](https://github.com/nf-core/scr 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). @@ -139,7 +166,7 @@ Use this parameter to choose a configuration profile. Profiles can give configur 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. @@ -163,8 +190,10 @@ 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` @@ -182,102 +211,19 @@ 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 ec2219a4..e6f4f1a2 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/scrnaseq 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 --fasta human.fasta --gtf human.gtf -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) @@ -48,7 +50,7 @@ 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) } @@ -60,7 +62,7 @@ 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) { @@ -80,8 +82,7 @@ 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/WorkflowScrnaseq.groovy b/lib/WorkflowScrnaseq.groovy index 8fee34f4..e4089a57 100755 --- a/lib/WorkflowScrnaseq.groovy +++ b/lib/WorkflowScrnaseq.groovy @@ -2,6 +2,7 @@ // This file holds several functions specific to the workflow/scrnaseq.nf in the nf-core/scrnaseq pipeline // +import nextflow.Nextflow import groovy.text.SimpleTemplateEngine class WorkflowScrnaseq { @@ -18,8 +19,7 @@ class WorkflowScrnaseq { } 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." } } @@ -65,16 +65,18 @@ class WorkflowScrnaseq { def description_html = engine.createTemplate(methods_text).make(meta) return description_html - }// + } + + // // Exit pipeline if incorrect --genome key provided static void genomeExists(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 c8455cbf..fe560c6d 100644 --- a/main.nf +++ b/main.nf @@ -4,7 +4,6 @@ nf-core/scrnaseq ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Github : https://github.com/nf-core/scrnaseq - Website: https://nf-co.re/scrnaseq Slack : https://nfcore.slack.com/channels/scrnaseq ---------------------------------------------------------------------------------------- diff --git a/modules.json b/modules.json index 68c1f32d..3e01672d 100644 --- a/modules.json +++ b/modules.json @@ -7,62 +7,62 @@ "nf-core": { "cellranger/count": { "branch": "master", - "git_sha": "abe9c71bdc56686abd337995580fbf35a6e5e013", + "git_sha": "d68b2e6526fcd22a2a6349e0859dbdc9924df93d", "installed_by": ["modules"] }, "cellranger/mkgtf": { "branch": "master", - "git_sha": "abe9c71bdc56686abd337995580fbf35a6e5e013", + "git_sha": "d68b2e6526fcd22a2a6349e0859dbdc9924df93d", "installed_by": ["modules"] }, "cellranger/mkref": { "branch": "master", - "git_sha": "abe9c71bdc56686abd337995580fbf35a6e5e013", + "git_sha": "d68b2e6526fcd22a2a6349e0859dbdc9924df93d", "installed_by": ["modules"] }, "custom/dumpsoftwareversions": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "fastqc": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "gffread": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "gunzip": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "5c460c5a4736974abde2843294f35307ee2b0e5e", "installed_by": ["modules"] }, "kallistobustools/count": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "kallistobustools/ref": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "multiqc": { "branch": "master", - "git_sha": "ee80d14721e76e2e079103b8dcd5d57129e584ba", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "star/genomegenerate": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "603ecbd9f45300c9788f197d2a15a005685b4220", "installed_by": ["modules"] }, "universc": { "branch": "master", - "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", + "git_sha": "b9829e1064382745d8dff7f1d74d2138d2864f71", "installed_by": ["modules"] } } diff --git a/modules/local/alevinqc.nf b/modules/local/alevinqc.nf index da9e5fe0..9000d79e 100644 --- a/modules/local/alevinqc.nf +++ b/modules/local/alevinqc.nf @@ -6,7 +6,7 @@ process ALEVINQC { conda "bioconda::bioconductor-alevinqc=1.12.1" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/bioconductor-alevinqc:1.12.1--r41h9f5acd7_0' : - 'quay.io/biocontainers/bioconductor-alevinqc:1.12.1--r41h9f5acd7_0' }" + 'biocontainers/bioconductor-alevinqc:1.12.1--r41h9f5acd7_0' }" input: tuple val(meta), path(alevin_results) diff --git a/modules/local/concat_h5ad.nf b/modules/local/concat_h5ad.nf index cf21408d..96920f9e 100644 --- a/modules/local/concat_h5ad.nf +++ b/modules/local/concat_h5ad.nf @@ -4,7 +4,7 @@ process CONCAT_H5AD { conda "conda-forge::scanpy conda-forge::python-igraph conda-forge::leidenalg" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/scanpy:1.7.2--pyhdfd78af_0' : - 'quay.io/biocontainers/scanpy:1.7.2--pyhdfd78af_0' }" + 'biocontainers/scanpy:1.7.2--pyhdfd78af_0' }" input: path h5ad diff --git a/modules/local/gene_map.nf b/modules/local/gene_map.nf index c332757f..9fd29e0a 100644 --- a/modules/local/gene_map.nf +++ b/modules/local/gene_map.nf @@ -8,7 +8,7 @@ process GENE_MAP { conda "conda-forge::python=3.8.3" container "${ 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 gtf diff --git a/modules/local/gffread_transcriptome.nf b/modules/local/gffread_transcriptome.nf index ec92dfb1..ab573b07 100644 --- a/modules/local/gffread_transcriptome.nf +++ b/modules/local/gffread_transcriptome.nf @@ -5,7 +5,7 @@ process GFFREAD_TRANSCRIPTOME { conda "bioconda::gffread=0.12.7" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/gffread:0.12.7--hd03093a_1' : - 'quay.io/biocontainers/gffread:0.12.7--hd03093a_1' }" + 'biocontainers/gffread:0.12.7--hd03093a_1' }" input: path genome_fasta diff --git a/modules/local/gtf_gene_filter.nf b/modules/local/gtf_gene_filter.nf index 4a2b7e1f..063bd228 100644 --- a/modules/local/gtf_gene_filter.nf +++ b/modules/local/gtf_gene_filter.nf @@ -5,7 +5,7 @@ process GTF_GENE_FILTER { conda "conda-forge::python=3.9.5" container "${ 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/mtx_to_h5ad.nf b/modules/local/mtx_to_h5ad.nf index 6a75f345..7961e057 100644 --- a/modules/local/mtx_to_h5ad.nf +++ b/modules/local/mtx_to_h5ad.nf @@ -5,7 +5,7 @@ process MTX_TO_H5AD { conda "conda-forge::scanpy conda-forge::python-igraph conda-forge::leidenalg" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/scanpy:1.7.2--pyhdfd78af_0' : - 'quay.io/biocontainers/scanpy:1.7.2--pyhdfd78af_0' }" + 'biocontainers/scanpy:1.7.2--pyhdfd78af_0' }" input: // inputs from cellranger nf-core module does not come in a single sample dir diff --git a/modules/local/mtx_to_seurat.nf b/modules/local/mtx_to_seurat.nf index f3d477d8..b55008bb 100644 --- a/modules/local/mtx_to_seurat.nf +++ b/modules/local/mtx_to_seurat.nf @@ -3,7 +3,7 @@ process MTX_TO_SEURAT { label 'process_medium' conda "r-seurat" - container 'satijalab/seurat:4.3.0' + container 'docker.io/satijalab/seurat:4.3.0' input: // inputs from cellranger nf-core module does not come in a single sample dir diff --git a/modules/local/samplesheet_check.nf b/modules/local/samplesheet_check.nf index b0febd87..feaf3dfc 100644 --- a/modules/local/samplesheet_check.nf +++ b/modules/local/samplesheet_check.nf @@ -5,7 +5,7 @@ process SAMPLESHEET_CHECK { conda "conda-forge::python=3.8.3" container "${ 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/local/simpleaf_index.nf b/modules/local/simpleaf_index.nf index d2c9bc7a..5e8f5c42 100644 --- a/modules/local/simpleaf_index.nf +++ b/modules/local/simpleaf_index.nf @@ -5,7 +5,7 @@ process SIMPLEAF_INDEX { conda 'bioconda::simpleaf=0.10.0-1' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/simpleaf:0.10.0--h9f5acd7_1' : - 'quay.io/biocontainers/simpleaf:0.10.0--h9f5acd7_1' }" + 'biocontainers/simpleaf:0.10.0--h9f5acd7_1' }" input: path genome_fasta diff --git a/modules/local/simpleaf_quant.nf b/modules/local/simpleaf_quant.nf index d97efbe7..eb95979e 100644 --- a/modules/local/simpleaf_quant.nf +++ b/modules/local/simpleaf_quant.nf @@ -5,7 +5,7 @@ process SIMPLEAF_QUANT { conda 'bioconda::simpleaf=0.10.0-1' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/simpleaf:0.10.0--h9f5acd7_1' : - 'quay.io/biocontainers/simpleaf:0.10.0--h9f5acd7_1' }" + 'biocontainers/simpleaf:0.10.0--h9f5acd7_1' }" input: // diff --git a/modules/local/star_align.nf b/modules/local/star_align.nf index 4dc963d3..480b14d3 100644 --- a/modules/local/star_align.nf +++ b/modules/local/star_align.nf @@ -5,7 +5,7 @@ process STAR_ALIGN { conda 'bioconda::star=2.7.10b' container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/star:2.7.10b--h9ee0642_0' : - 'quay.io/biocontainers/star:2.7.10b--h9ee0642_0' }" + 'biocontainers/star:2.7.10b--h9ee0642_0' }" input: // diff --git a/modules/nf-core/cellranger/count/main.nf b/modules/nf-core/cellranger/count/main.nf index 5c143b53..7c481d6e 100644 --- a/modules/nf-core/cellranger/count/main.nf +++ b/modules/nf-core/cellranger/count/main.nf @@ -1,8 +1,8 @@ process CELLRANGER_COUNT { - tag "$meta.gem" + tag "$meta.id" label 'process_high' - container "nfcore/cellranger:7.1.0" + container "docker.io/nfcore/cellranger:7.1.0" // Exit if running this module with -profile conda / -profile mamba if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) { @@ -14,23 +14,22 @@ process CELLRANGER_COUNT { path reference output: - tuple val(meta), path("sample-${meta.gem}/outs/*"), emit: outs - path "versions.yml" , emit: versions + tuple val(meta), path("**/outs/**"), emit: outs + path "versions.yml" , emit: versions when: task.ext.when == null || task.ext.when script: def args = task.ext.args ?: '' - def sample_arg = meta.samples.unique().join(",") + def prefix = task.ext.prefix ?: "${meta.id}" def reference_name = reference.name """ cellranger \\ count \\ - --id='sample-${meta.gem}' \\ + --id='$prefix' \\ --fastqs=. \\ --transcriptome=$reference_name \\ - --sample=$sample_arg \\ --localcores=$task.cpus \\ --localmem=${task.memory.toGiga()} \\ $args @@ -42,9 +41,10 @@ process CELLRANGER_COUNT { """ stub: + def prefix = task.ext.prefix ?: "${meta.id}" """ - mkdir -p "sample-${meta.gem}/outs/" - touch sample-${meta.gem}/outs/fake_file.txt + mkdir -p "${prefix}/outs/" + touch ${prefix}/outs/fake_file.txt cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/nf-core/cellranger/count/meta.yml b/modules/nf-core/cellranger/count/meta.yml index f0d1fef0..51d82dd5 100644 --- a/modules/nf-core/cellranger/count/meta.yml +++ b/modules/nf-core/cellranger/count/meta.yml @@ -23,14 +23,15 @@ input: description: | List of input FastQ files of size 1 and 2 for single-end and paired-end data, respectively. + pattern: "${Sample_Name}_S1_L00${Lane_Number}_${I1,I2,R1,R2}_001.fastq.gz" - reference: type: directory description: Folder containing all the reference indices needed by Cell Ranger output: - outs: type: file - description: Files containing the outputs of Cell Ranger - pattern: "sample-${meta.gem}/outs/*" + description: Files containing the outputs of Cell Ranger, see official 10X Genomics documentation for a complete list + pattern: "${meta.id}/outs/*" - versions: type: file description: File containing software version diff --git a/modules/nf-core/cellranger/mkgtf/main.nf b/modules/nf-core/cellranger/mkgtf/main.nf index 2e75a153..40a27a31 100644 --- a/modules/nf-core/cellranger/mkgtf/main.nf +++ b/modules/nf-core/cellranger/mkgtf/main.nf @@ -2,7 +2,7 @@ process CELLRANGER_MKGTF { tag "$gtf" label 'process_low' - container "nfcore/cellranger:7.1.0" + container "docker.io/nfcore/cellranger:7.1.0" // Exit if running this module with -profile conda / -profile mamba if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) { @@ -13,7 +13,7 @@ process CELLRANGER_MKGTF { path gtf output: - path "*.filtered.gtf", emit: gtf + path "*.gtf" , emit: gtf path "versions.yml" , emit: versions when: @@ -21,11 +21,12 @@ process CELLRANGER_MKGTF { script: def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${gtf.baseName}.filtered" """ cellranger \\ mkgtf \\ $gtf \\ - ${gtf.baseName}.filtered.gtf \\ + ${prefix}.gtf \\ $args cat <<-END_VERSIONS > versions.yml diff --git a/modules/nf-core/cellranger/mkref/main.nf b/modules/nf-core/cellranger/mkref/main.nf index 94a41202..d3826f97 100644 --- a/modules/nf-core/cellranger/mkref/main.nf +++ b/modules/nf-core/cellranger/mkref/main.nf @@ -2,7 +2,7 @@ process CELLRANGER_MKREF { tag "$fasta" label 'process_high' - container "nfcore/cellranger:7.1.0" + container "docker.io/nfcore/cellranger:7.1.0" // Exit if running this module with -profile conda / -profile mamba if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) { diff --git a/modules/nf-core/custom/dumpsoftwareversions/main.nf b/modules/nf-core/custom/dumpsoftwareversions/main.nf index 3df21765..ebc87273 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' : + '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: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/yaml-schema.json name: custom_dumpsoftwareversions description: Custom module used to dump software versions within the nf-core pipeline template keywords: - custom + - dump - version tools: - custom: diff --git a/modules/nf-core/fastqc/main.nf b/modules/nf-core/fastqc/main.nf index 9ae58381..07d5e433 100644 --- a/modules/nf-core/fastqc/main.nf +++ b/modules/nf-core/fastqc/main.nf @@ -5,7 +5,7 @@ process FASTQC { conda "bioconda::fastqc=0.11.9" container "${ 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/gffread/main.nf b/modules/nf-core/gffread/main.nf index b1a8996f..f4472b0e 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 "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/gffread:0.12.1--h8b12597_0' : - 'quay.io/biocontainers/gffread:0.12.1--h8b12597_0' }" + 'biocontainers/gffread:0.12.1--h8b12597_0' }" input: path gff diff --git a/modules/nf-core/gunzip/main.nf b/modules/nf-core/gunzip/main.nf index d906034c..e7189d2f 100644 --- a/modules/nf-core/gunzip/main.nf +++ b/modules/nf-core/gunzip/main.nf @@ -5,7 +5,7 @@ process GUNZIP { conda "conda-forge::sed=4.7" container "${ 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 2e0e4054..4cdcdf4c 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/kallistobustools/count/main.nf b/modules/nf-core/kallistobustools/count/main.nf index c585eb07..b7942fc2 100644 --- a/modules/nf-core/kallistobustools/count/main.nf +++ b/modules/nf-core/kallistobustools/count/main.nf @@ -5,7 +5,7 @@ process KALLISTOBUSTOOLS_COUNT { conda "bioconda::kb-python=0.27.2" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/kb-python:0.27.2--pyhdfd78af_0' : - 'quay.io/biocontainers/kb-python:0.27.2--pyhdfd78af_0' }" + 'biocontainers/kb-python:0.27.2--pyhdfd78af_0' }" input: tuple val(meta), path(reads) diff --git a/modules/nf-core/kallistobustools/ref/main.nf b/modules/nf-core/kallistobustools/ref/main.nf index 22bb2b6f..9d7f1741 100644 --- a/modules/nf-core/kallistobustools/ref/main.nf +++ b/modules/nf-core/kallistobustools/ref/main.nf @@ -5,7 +5,7 @@ process KALLISTOBUSTOOLS_REF { conda "bioconda::kb-python=0.27.2" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/kb-python:0.27.2--pyhdfd78af_0' : - 'quay.io/biocontainers/kb-python:0.27.2--pyhdfd78af_0' }" + 'biocontainers/kb-python:0.27.2--pyhdfd78af_0' }" input: path fasta 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: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/yaml-schema.json name: MultiQC description: Aggregate results from bioinformatics analyses across many samples into a single report keywords: @@ -37,7 +38,7 @@ output: description: MultiQC report file pattern: "multiqc_report.html" - data: - type: dir + type: directory description: MultiQC data dir pattern: "multiqc_data" - plots: diff --git a/modules/nf-core/star/genomegenerate/main.nf b/modules/nf-core/star/genomegenerate/main.nf index 91462489..2407d006 100644 --- a/modules/nf-core/star/genomegenerate/main.nf +++ b/modules/nf-core/star/genomegenerate/main.nf @@ -5,7 +5,7 @@ process STAR_GENOMEGENERATE { conda "bioconda::star=2.7.10a bioconda::samtools=1.16.1 conda-forge::gawk=5.1.0" container "${ 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 diff --git a/modules/nf-core/universc/CITATION.md b/modules/nf-core/universc/CITATION.md new file mode 100644 index 00000000..4f420bb8 --- /dev/null +++ b/modules/nf-core/universc/CITATION.md @@ -0,0 +1,37 @@ +### Citation + +A submission to a journal and biorXiv is in progress. Please cite these when +they are available. Currently, the package can be cited +as follows: + +Kelly, S.T., Battenberg, Hetherington, N.A., K., Hayashi, K., and Minoda, A. (2021) +UniverSC: a flexible cross-platform single-cell data processing pipeline. +bioRxiv 2021.01.19.427209; doi: [https://doi.org/10.1101/2021.01.19.427209](https://doi.org/10.1101/2021.01.19.427209) +package version 1.2.5.1. [https://github.com/minoda-lab/universc](https://github.com/minoda-lab/universc) + +``` +@article {Kelly2021.01.19.427209, + author = {Kelly, S. Thomas and Battenberg, Kai and Hetherington, Nicola A. and Hayashi, Makoto and Minoda, Aki}, + title = {{UniverSC}: a flexible cross-platform single-cell data processing pipeline}, + elocation-id = {2021.01.19.427209}, + year = {2021}, + doi = {10.1101/2021.01.19.427209}, + publisher = {Cold Spring Harbor Laboratory}, + abstract = {Single-cell RNA-sequencing analysis to quantify RNA molecules in individual cells has become popular owing to the large amount of information one can obtain from each experiment. We have developed UniverSC (https://github.com/minoda-lab/universc), a universal single-cell processing tool that supports any UMI-based platform. Our command-line tool enables consistent and comprehensive integration, comparison, and evaluation across data generated from a wide range of platforms.Competing Interest StatementThe authors have declared no competing interest.}, + eprint = {https://www.biorxiv.org/content/early/2021/01/19/2021.01.19.427209.full.pdf}, + journal = {{bioRxiv}}, + note = {package version 1.2.5.1}, + URL = {https://github.com/minoda-lab/universc}, +} + +``` + +``` +@Manual{, + title = {{UniverSC}: a flexible cross-platform single-cell data processing pipeline}, + author = {S. Thomas Kelly, Kai Battenberg, Nicola A. Hetherington, Makoto Hayashi, and Aki Minoda}, + year = {2021}, + note = {package version 1.2.5.1}, + url = {https://github.com/minoda-lab/universc}, + } +``` diff --git a/modules/nf-core/universc/README.md b/modules/nf-core/universc/README.md index 8b6f6144..30b6b65e 100644 --- a/modules/nf-core/universc/README.md +++ b/modules/nf-core/universc/README.md @@ -45,10 +45,10 @@ process { ... withName: CELLRANGER_MKGTF { - container = "nfcore/universc:1.2.5.1" + container = "docker.io/nfcore/universc:1.2.5.1" } withName: CELLRANGER_MKREF{ - container = "nfcore/universc:1.2.5.1" + container = "docker.io/nfcore/universc:1.2.5.1" } ... } @@ -66,7 +66,7 @@ and for singularity use the `--writeable` parameter. These are set as default in universc/main.nf: ``` - container "nfcore/universc:1.2.5.1" + container "docker.io/nfcore/universc:1.2.5.1" if (workflow.containerEngine == 'docker'){ containerOptions = "--privileged" } diff --git a/modules/nf-core/universc/main.nf b/modules/nf-core/universc/main.nf index a23cb05b..2108624d 100644 --- a/modules/nf-core/universc/main.nf +++ b/modules/nf-core/universc/main.nf @@ -6,7 +6,7 @@ process UNIVERSC { if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) { exit 1, "UNIVERSC module does not support Conda. Please use Docker / Singularity / Podman instead." } - container "nfcore/universc:1.2.5.1" + container "docker.io/nfcore/universc:1.2.5.1" if (workflow.containerEngine == 'docker'){ containerOptions = "--privileged" } diff --git a/nextflow.config b/nextflow.config index c2977bd7..d583913f 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 @@ -127,14 +132,17 @@ profiles { podman.enabled = false shifter.enabled = false charliecloud.enabled = false + apptainer.enabled = false } docker { docker.enabled = true 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' @@ -142,37 +150,57 @@ 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 + 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' 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' } } @@ -198,6 +226,12 @@ 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 @@ -223,7 +257,7 @@ manifest { description = """Pipeline for processing 10x Genomics single cell rnaseq data""" mainScript = 'main.nf' nextflowVersion = '!>=22.10.1' - version = '2.3.0' + version = '2.3.1' doi = '10.5281/zenodo.3568187' } diff --git a/workflows/scrnaseq.nf b/workflows/scrnaseq.nf index 3c607c5e..30ca6359 100644 --- a/workflows/scrnaseq.nf +++ b/workflows/scrnaseq.nf @@ -193,7 +193,7 @@ workflow SCRNASEQ { ch_star_index = CELLRANGER_ALIGN.out.star_index } - // Run cellranger pipeline + // Run universc pipeline if (params.aligner == "universc") { UNIVERSC_ALIGN( ch_genome_fasta,