diff --git a/.editorconfig b/.editorconfig index b78de6e..b6b3190 100644 --- a/.editorconfig +++ b/.editorconfig @@ -8,7 +8,7 @@ trim_trailing_whitespace = true indent_size = 4 indent_style = space -[*.{md,yml,yaml,html,css,scss,js,cff}] +[*.{md,yml,yaml,html,css,scss,js}] indent_size = 2 # These files are edited and tested upstream in nf-core/modules diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml index 6f91f7c..4f0c060 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/taxprofiler _(eg. 1.1, 1.5, 1.8.2)_ diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index 333c4f1..ae4285a 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/taxp - [ ] 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/taxprofiler/tree/master/.github/CONTRIBUTING.md)- [ ] If necessary, also make a PR on the nf-core/taxprofiler _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/taxprofiler/tree/master/.github/CONTRIBUTING.md) +- [ ] If necessary, also make a PR on the nf-core/taxprofiler _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 a8974a0..0c2d9b6 100644 --- a/.github/workflows/awsfulltest.yml +++ b/.github/workflows/awsfulltest.yml @@ -14,9 +14,7 @@ jobs: runs-on: ubuntu-latest steps: - name: Launch workflow via tower - uses: nf-core/tower-action@v3 - # Add full size test data (but still relatively small datasets for few samples) - # on the `test_full.config` test runs with only one set of parameters + uses: seqeralabs/action-tower-launch@v1 with: workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} access_token: ${{ secrets.TOWER_ACCESS_TOKEN }} diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml index a580097..694f1c3 100644 --- a/.github/workflows/awstest.yml +++ b/.github/workflows/awstest.yml @@ -12,7 +12,7 @@ jobs: steps: # Launch workflow using Tower CLI tool action - name: Launch workflow via tower - uses: nf-core/tower-action@v3 + uses: seqeralabs/action-tower-launch@v1 with: workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} access_token: ${{ secrets.TOWER_ACCESS_TOKEN }} diff --git a/.github/workflows/branch.yml b/.github/workflows/branch.yml index b5b9ae2..7ebd2e1 100644 --- a/.github/workflows/branch.yml +++ b/.github/workflows/branch.yml @@ -13,7 +13,7 @@ jobs: - name: Check PRs if: github.repository == 'nf-core/taxprofiler' run: | - { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/taxprofiler ]] && [[ $GITHUB_HEAD_REF = "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]] + { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/taxprofiler ]] && [[ $GITHUB_HEAD_REF == "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]] # If the above check failed, post a comment on the PR explaining the failure # NOTE - this doesn't currently work if the PR is coming from a fork, due to limitations in GitHub actions secrets diff --git a/.github/workflows/clean-up.yml b/.github/workflows/clean-up.yml new file mode 100644 index 0000000..694e90e --- /dev/null +++ b/.github/workflows/clean-up.yml @@ -0,0 +1,24 @@ +name: "Close user-tagged issues and PRs" +on: + schedule: + - cron: "0 0 * * 0" # Once a week + +jobs: + clean-up: + runs-on: ubuntu-latest + permissions: + issues: write + pull-requests: write + steps: + - uses: actions/stale@v7 + with: + stale-issue-message: "This issue has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor. Remove stale label or add a comment otherwise this issue will be closed in 20 days." + stale-pr-message: "This PR has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor. Remove stale label or add a comment if it is still useful." + close-issue-message: "This issue was closed because it has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor and then staled for 20 days with no activity." + days-before-stale: 30 + days-before-close: 20 + days-before-pr-close: -1 + any-of-labels: "awaiting-changes,awaiting-feedback" + exempt-issue-labels: "WIP" + exempt-pr-labels: "WIP" + repo-token: "${{ secrets.GITHUB_TOKEN }}" diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index 858d622..888cb4b 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 0000000..0c31cdb --- /dev/null +++ b/.pre-commit-config.yaml @@ -0,0 +1,5 @@ +repos: + - repo: https://github.com/pre-commit/mirrors-prettier + rev: "v2.7.1" + hooks: + - id: prettier diff --git a/CHANGELOG.md b/CHANGELOG.md index 083efc4..f9b1853 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,7 +3,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). -## dev +## v1.1.0dev - [date] ### `Added` @@ -19,6 +19,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - [#275](https://github.com/nf-core/taxprofiler/pull/275/files) Replaced function used for error reporting to more Nextflow friendly method (fix by @jfy133) - [#285](https://github.com/nf-core/taxprofiler/pull/285/files) Fixed overly large log files in Kraken2 output (♥ to @prototaxites for reporting, fix by @Midnighter & @jfy133) - [#286](https://github.com/nf-core/taxprofiler/pull/286/files) Runtime optimisation of MultiQC step via improved log file processing (fix by @Midnighter & @jfy133) +- [#289](https://github.com/nf-core/taxprofiler/pull/289/files) Pipeline updated to nf-core template 2.8 (fix by @Midnighter & @jfy133) +- [#290](https://github.com/nf-core/taxprofiler/pull/286/files) Minor database input documentation improvements (♥ to @alneberg for reporting, fix by @jfy133) + +### `Dependencies` + +| Tool | Previous version | New version | +| ------- | ---------------- | ----------- | +| MultiQC | 1.13 | 1.14 | + +### `Deprecated` + ## v1.0.1 - Dodgy Dachshund Patch [2023-05-15] ### `Added` @@ -27,10 +38,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - [#291](https://github.com/nf-core/taxprofiler/pull/291) - Fix Taxpasta not receiving taxonomy directory (❤️ to @SannaAb for reporting, fix by @jfy133) -### `Dependencies` - -### `Deprecated` - ## v1.0.0 - Dodgy Dachshund [2023-03-13] Initial release of nf-core/taxprofiler, created with the [nf-core](https://nf-co.re/) template. diff --git a/README.md b/README.md index 8362141..6f47098 100644 --- a/README.md +++ b/README.md @@ -8,17 +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/taxprofiler) -[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23taxprofiler-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/taxprofiler)[![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%23taxprofiler-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/taxprofiler)[![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/taxprofiler** is a bioinformatics best-practice analysis pipeline for taxonomic classification and profiling of shotgun metagenomic data. It allows for in-parallel taxonomic identification of reads or taxonomic abundance estimation with multiple classification and profiling tools against multiple databases, produces standardised output tables. - -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/taxprofiler/results). - -The nf-core/taxprofiler CI test dataset uses sequencing data from [Maixner et al. (2021) Curr. Bio.](https://doi.org/10.1016/j.cub.2021.09.031). The AWS full test dataset uses sequencing data and reference genomes from [Meslier (2022) _Sci. Data_](https://doi.org/10.1038/s41597-022-01762-z) +**nf-core/taxprofiler** is a bioinformatics best-practice analysis pipeline for taxonomic classification and profiling of shotgun and long-read metagenomic data. It allows for in-parallel taxonomic identification of reads or taxonomic abundance estimation with multiple classification and profiling tools against multiple databases, produces standardised output tables. ## Pipeline summary @@ -46,43 +40,74 @@ The nf-core/taxprofiler CI test dataset uses sequencing data from [Maixner et al 7. Present QC for raw reads ([`MultiQC`](http://multiqc.info/)) 8. Plotting Kraken2, Centrifuge, Kaiju and MALT results ([`Krona`](https://hpc.nih.gov/apps/kronatools.html)) -## 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/taxprofiler -profile test,YOURPROFILE --outdir - ``` +```csv +sample,run_accession,instrument_platform,fastq_1,fastq_2,fasta +2612,run1,ILLUMINA,2612_run1_R1.fq.gz,, +2612,run2,ILLUMINA,2612_run2_R1.fq.gz,, +2612,run3,ILLUMINA,2612_run3_R1.fq.gz,2612_run3_R2.fq.gz, +``` - 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), a pair of fastq files (paired end), or a fasta (with long reads). - > - 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. +Additionally, you will need a database sheet that looks as follows: -4. Start running your own analysis! +`databases.csv`: - ```console - nextflow run nf-core/taxprofiler --input samplesheet.csv --databases database.csv --outdir --run_ --run_ -profile - ``` +``` +tool,db_name,db_params,db_path +kraken2,db2,--quick,///kraken2/testdb-kraken2.tar.gz +metaphlan3,db1,,///metaphlan3/metaphlan_database/ +``` -## Documentation +That includes directories or `.tar.gz` archives containing databases for the tools you wish to run the pipeline against. -The nf-core/taxprofiler pipeline comes with documentation about the pipeline [usage](https://nf-co.re/taxprofiler/usage), [parameters](https://nf-co.re/taxprofiler/parameters) and [output](https://nf-co.re/taxprofiler/output). +Now, you can run the pipeline using: -## Credits +```bash +nextflow run nf-core/taxprofiler \ + -profile \ + --input samplesheet.csv \ + --databases databases.csv \ + --outdir \ + --run_kraken2 --run_metaphlan3 +``` -nf-core/taxprofiler was originally written by [James A. Fellows Yates](https://github.com/jfy133), [Moritz Beber](https://github.com/Midnighter), and [Sofia Stamouli](https://github.com/sofsam). +> **Warning:** +> Please provide pipeline parameters via the CLI (as above) 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). -We thank the following people for their contributions to the development of this pipeline: +For more details, please refer to the [usage documentation](https://nf-co.re/taxprofiler/usage) and the [parameter documentation](https://nf-co.re/taxprofiler/parameters). + +## Pipeline output + +To see the results of a test run with a full size dataset refer to the [results](https://nf-co.re/taxprofiler/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/taxprofiler/output). + +## Credits + +nf-core/taxprofiler was originally written by James A. Fellows Yates, Sofia Stamouli, Moritz E. Beber, and the nf-core/taxprofiler team. ### Team +- [James A. Fellows Yates](https://github.com/jfy133) +- [Sofia Stamouli](https://github.com/sofstam) +- [Moritz E. Beber](https://github.com/Midnighter) + +We thank the following people for their contributions to the development of this pipeline: + - [Lauri Mesilaakso](https://github.com/ljmesi) - [Tanja Normark](https://github.com/talnor) - [Maxime Borry](https://github.com/maxibor) diff --git a/assets/email_template.html b/assets/email_template.html index af9bb07..dfa4460 100644 --- a/assets/email_template.html +++ b/assets/email_template.html @@ -4,7 +4,7 @@ - + nf-core/taxprofiler Pipeline Report diff --git a/conf/base.config b/conf/base.config index 7c454dc..61b3018 100644 --- a/conf/base.config +++ b/conf/base.config @@ -14,7 +14,7 @@ process { memory = { check_max( 6.GB * task.attempt, 'memory' ) } time = { check_max( 4.h * task.attempt, 'time' ) } - errorStrategy = { task.exitStatus in [143,137,104,134,139] ? 'retry' : 'finish' } + errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' } maxRetries = 1 maxErrors = '-1' diff --git a/conf/igenomes.config b/conf/igenomes.config index 7a1b3ac..3f11437 100644 --- a/conf/igenomes.config +++ b/conf/igenomes.config @@ -36,6 +36,14 @@ params { macs_gsize = "2.7e9" blacklist = "${projectDir}/assets/blacklists/hg38-blacklist.bed" } + 'CHM13' { + fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/WholeGenomeFasta/genome.fa" + bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/BWAIndex/" + bwamem2 = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/BWAmem2Index/" + gtf = "${params.igenomes_base}/Homo_sapiens/NCBI/CHM13/Annotation/Genes/genes.gtf" + gff = "ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/914/755/GCF_009914755.1_T2T-CHM13v2.0/GCF_009914755.1_T2T-CHM13v2.0_genomic.gff.gz" + mito_name = "chrM" + } 'GRCm38' { fasta = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.fa" bwa = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BWAIndex/version0.6.0/" diff --git a/conf/test_full.config b/conf/test_full.config index e0673e0..85db8d3 100644 --- a/conf/test_full.config +++ b/conf/test_full.config @@ -8,6 +8,8 @@ ---------------------------------------------------------------------------------------- */ +cleanup = true + params { config_profile_name = 'Full test profile' config_profile_description = 'Full test dataset to check pipeline function' diff --git a/docs/usage.md b/docs/usage.md index a98da95..5f9c497 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -120,7 +120,7 @@ Column specifications are as follows: nf-core/taxprofiler will automatically decompress and extract any compressed archives for you. -The (uncompressed) database paths (`db_path`) for each tool are expected to contain the contents of: +The (uncompressed) database paths (`db_path`) for each tool are expected to contain: - [**Bracken**:](#bracken-custom-database) output of the combined `kraken2-build` and `bracken-build` process. - [**Centrifuge**:](#centrifuge-custom-database) output of `centrifuge-build`. @@ -130,9 +130,9 @@ The (uncompressed) database paths (`db_path`) for each tool are expected to cont - [**KrakenUniq**:](#krakenuniq-custom-database) output of `krakenuniq-build` command(s). - [**MALT**](#malt-custom-database) output of `malt-build`. - [**MetaPhlAn3**:](#metaphlan3-custom-database) output of with `metaphlan --install` or downloaded from links on the [MetaPhlAn3 wiki](https://github.com/biobakery/MetaPhlAn/wiki/MetaPhlAn-3.0#customizing-the-database). -- [**mOTUs**:](#motus-custom-database) is composed of code and database together. +- [**mOTUs**:](#motus-custom-database) the directory `db_mOTU/` that is downloaded via `motus downloadDB`. -Click the links in the list above for short quick-reference tutorials how to generate custom databases for each tool. +> ℹ️ Click the links in the list above for short quick-reference tutorials how to generate custom databases for each tool. ## Running the pipeline @@ -155,6 +155,29 @@ 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/taxprofiler -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). + ### Sequencing quality control [`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/) gives general quality metrics about your reads. It provides information about the quality score distribution across your reads, per base sequence content (%A/T/G/C), adapter contamination and overrepresented sequences. nf-core taxprofiler offers [`falco`](https://github.com/smithlabcode/falco) as an drop-in replacement, with supposedly better improvement particularly for long reads. @@ -329,6 +352,10 @@ First, go to the [nf-core/taxprofiler releases page](https://github.com/nf-core/ 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). @@ -337,7 +364,7 @@ This version number will be logged in reports when you run the pipeline, so that Use this parameter to choose a configuration profile. Profiles can give configuration presets for different compute environments. -Several generic profiles are bundled with the pipeline which instruct the pipeline to use software packaged using different methods (Docker, Singularity, Podman, Shifter, Charliecloud, Conda) - see below. +Several generic profiles are bundled with the pipeline which instruct the pipeline to use software packaged using different methods (Docker, Singularity, Podman, Shifter, Charliecloud, Apptainer, Conda) - see below. > We highly recommend the use of Docker or Singularity containers for full pipeline reproducibility, however when this is not possible, Conda is also supported. @@ -361,8 +388,10 @@ 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` @@ -380,102 +409,19 @@ 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 33cd4f6..9b34804 100755 --- a/lib/NfcoreSchema.groovy +++ b/lib/NfcoreSchema.groovy @@ -2,6 +2,7 @@ // This file holds several functions used to perform JSON parameter validation, help and summary rendering for the nf-core pipeline template. // +import nextflow.Nextflow import org.everit.json.schema.Schema import org.everit.json.schema.loader.SchemaLoader import org.everit.json.schema.ValidationException @@ -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 24511f6..ba8c8fb 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/taxprofiler 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) @@ -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/WorkflowTaxprofiler.groovy b/lib/WorkflowTaxprofiler.groovy index 10504bf..d3dcdc8 100755 --- a/lib/WorkflowTaxprofiler.groovy +++ b/lib/WorkflowTaxprofiler.groovy @@ -2,6 +2,7 @@ // This file holds several functions specific to the workflow/taxprofiler.nf in the nf-core/taxprofiler pipeline // +import nextflow.Nextflow import groovy.text.SimpleTemplateEngine class WorkflowTaxprofiler { @@ -9,11 +10,15 @@ class WorkflowTaxprofiler { // // Check and validate parameters // + public static void initialise(params, log) { genomeExistsError(params, log) - + //if (!params.fasta) { + // Nextflow.error "Genome fasta file not specified with e.g. '--fasta genome.fa' or via a detectable config file." + //} } + // // Get workflow summary for MultiQC // @@ -56,17 +61,19 @@ class WorkflowTaxprofiler { def description_html = engine.createTemplate(methods_text).make(meta) return description_html - }// + } + + // // Exit pipeline if incorrect --genome key provided // private static void genomeExistsError(params, log) { if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) { - log.error "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" + + def error_string = "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" + " Genome '${params.genome}' not found in any config files provided to the pipeline.\n" + " Currently, the available genome keys are:\n" + " ${params.genomes.keySet().join(", ")}\n" + "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~" - System.exit(1) + Nextflow.error(error_string) } } } diff --git a/main.nf b/main.nf index ff1c4ec..29517f4 100644 --- a/main.nf +++ b/main.nf @@ -4,7 +4,6 @@ nf-core/taxprofiler ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Github : https://github.com/nf-core/taxprofiler - Website: https://nf-co.re/taxprofiler Slack : https://nfcore.slack.com/channels/taxprofiler ---------------------------------------------------------------------------------------- diff --git a/modules.json b/modules.json index f69c777..498e5eb 100644 --- a/modules.json +++ b/modules.json @@ -37,7 +37,7 @@ }, "cat/fastq": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "b9829e1064382745d8dff7f1d74d2138d2864f71", "installed_by": ["modules"] }, "centrifuge/centrifuge": { @@ -52,7 +52,7 @@ }, "custom/dumpsoftwareversions": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "76cc4938c1f6ea5c7d83fed1eeffc146787f9543", "installed_by": ["modules"] }, "diamond/blastx": { @@ -83,7 +83,7 @@ }, "gunzip": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "b9829e1064382745d8dff7f1d74d2138d2864f71", "installed_by": ["modules"] }, "kaiju/kaiju": { @@ -173,7 +173,7 @@ }, "multiqc": { "branch": "master", - "git_sha": "ee80d14721e76e2e079103b8dcd5d57129e584ba", + "git_sha": "f2d63bd5b68925f98f572eed70993d205cc694b7", "installed_by": ["modules"] }, "porechop/porechop": { @@ -214,7 +214,7 @@ }, "untar": { "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "b9829e1064382745d8dff7f1d74d2138d2864f71", "installed_by": ["modules"] } } diff --git a/modules/local/kraken2_standard_report.nf b/modules/local/kraken2_standard_report.nf index fcd2c32..8fa2521 100644 --- a/modules/local/kraken2_standard_report.nf +++ b/modules/local/kraken2_standard_report.nf @@ -5,7 +5,7 @@ process KRAKEN2_STANDARD_REPORT { 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' }" + 'docker.io/ubuntu:20.04' }" input: tuple val(meta), path(report) diff --git a/modules/local/krona_cleanup.nf b/modules/local/krona_cleanup.nf index 082c22b..4b33b73 100644 --- a/modules/local/krona_cleanup.nf +++ b/modules/local/krona_cleanup.nf @@ -5,7 +5,7 @@ process KRONA_CLEANUP { conda "conda-forge::sed=4.7" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/ubuntu:20.04' : - 'ubuntu:20.04' }" + 'docker.io/ubuntu:20.04' }" input: tuple val(meta), path(krona, stageAs: 'uncleaned.krona.txt') diff --git a/modules/local/samplesheet_check.nf b/modules/local/samplesheet_check.nf index ed686c8..7cd27e3 100644 --- a/modules/local/samplesheet_check.nf +++ b/modules/local/samplesheet_check.nf @@ -5,7 +5,7 @@ process SAMPLESHEET_CHECK { conda "conda-forge::python=3.8.3" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/python:3.8.3' : - 'quay.io/biocontainers/python:3.8.3' }" + 'biocontainers/python:3.8.3' }" input: path samplesheet diff --git a/modules/nf-core/cat/fastq/main.nf b/modules/nf-core/cat/fastq/main.nf index 8a0b560..4bdec89 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 "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/ubuntu:20.04' : - 'ubuntu:20.04' }" + 'docker.io/ubuntu:20.04' }" input: tuple val(meta), path(reads, stageAs: "input*/*") diff --git a/modules/nf-core/cat/fastq/meta.yml b/modules/nf-core/cat/fastq/meta.yml index c836598..8a39e30 100644 --- a/modules/nf-core/cat/fastq/meta.yml +++ b/modules/nf-core/cat/fastq/meta.yml @@ -1,6 +1,7 @@ name: cat_fastq description: Concatenates fastq files keywords: + - cat - fastq - concatenate tools: @@ -16,7 +17,7 @@ input: Groovy Map containing sample information e.g. [ id:'test', single_end:false ] - reads: - type: list + type: file description: | List of input FastQ files to be concatenated. output: diff --git a/modules/nf-core/custom/dumpsoftwareversions/main.nf b/modules/nf-core/custom/dumpsoftwareversions/main.nf index 3df2176..800a609 100644 --- a/modules/nf-core/custom/dumpsoftwareversions/main.nf +++ b/modules/nf-core/custom/dumpsoftwareversions/main.nf @@ -2,10 +2,10 @@ process CUSTOM_DUMPSOFTWAREVERSIONS { label 'process_single' // Requires `pyyaml` which does not have a dedicated container but is in the MultiQC container - conda "bioconda::multiqc=1.13" + conda "bioconda::multiqc=1.14" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/multiqc:1.13--pyhdfd78af_0' : - 'quay.io/biocontainers/multiqc:1.13--pyhdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/multiqc:1.14--pyhdfd78af_0' : + 'quay.io/biocontainers/multiqc:1.14--pyhdfd78af_0' }" input: path versions diff --git a/modules/nf-core/custom/dumpsoftwareversions/meta.yml b/modules/nf-core/custom/dumpsoftwareversions/meta.yml index 60b546a..c32657d 100644 --- a/modules/nf-core/custom/dumpsoftwareversions/meta.yml +++ b/modules/nf-core/custom/dumpsoftwareversions/meta.yml @@ -1,7 +1,9 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/yaml-schema.json name: custom_dumpsoftwareversions description: Custom module used to dump software versions within the nf-core pipeline template keywords: - custom + - dump - version tools: - custom: diff --git a/modules/nf-core/gunzip/main.nf b/modules/nf-core/gunzip/main.nf index d906034..194dfc3 100644 --- a/modules/nf-core/gunzip/main.nf +++ b/modules/nf-core/gunzip/main.nf @@ -5,7 +5,7 @@ process GUNZIP { conda "conda-forge::sed=4.7" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/ubuntu:20.04' : - 'ubuntu:20.04' }" + 'docker.io/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 4d2ebc8..4cdcdf4 100644 --- a/modules/nf-core/gunzip/meta.yml +++ b/modules/nf-core/gunzip/meta.yml @@ -3,31 +3,32 @@ description: Compresses and decompresses files. keywords: - gunzip - compression + - decompression tools: - gunzip: - description: | - gzip is a file format and a software application used for file compression and decompression. - documentation: https://www.gnu.org/software/gzip/manual/gzip.html - licence: ["GPL-3.0-or-later"] + description: | + gzip is a file format and a software application used for file compression and decompression. + documentation: https://www.gnu.org/software/gzip/manual/gzip.html + licence: ["GPL-3.0-or-later"] input: - meta: - type: map - description: | - Optional groovy Map containing meta information - e.g. [ id:'test', single_end:false ] + type: map + description: | + Optional groovy Map containing meta information + e.g. [ id:'test', single_end:false ] - archive: - type: file - description: File to be compressed/uncompressed - pattern: "*.*" + type: file + description: File to be compressed/uncompressed + pattern: "*.*" output: - gunzip: - type: file - description: Compressed/uncompressed file - pattern: "*.*" + type: file + description: Compressed/uncompressed file + pattern: "*.*" - versions: - type: file - description: File containing software versions - pattern: "versions.yml" + type: file + description: File containing software versions + pattern: "versions.yml" authors: - "@joseespinosa" - "@drpatelh" diff --git a/modules/nf-core/multiqc/meta.yml b/modules/nf-core/multiqc/meta.yml index ebc29b2..f93b5ee 100644 --- a/modules/nf-core/multiqc/meta.yml +++ b/modules/nf-core/multiqc/meta.yml @@ -1,3 +1,4 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/yaml-schema.json name: MultiQC description: Aggregate results from bioinformatics analyses across many samples into a single report keywords: @@ -37,7 +38,7 @@ output: description: MultiQC report file pattern: "multiqc_report.html" - data: - type: dir + type: directory description: MultiQC data dir pattern: "multiqc_data" - plots: diff --git a/modules/nf-core/untar/main.nf b/modules/nf-core/untar/main.nf index 16bccc9..67f497e 100644 --- a/modules/nf-core/untar/main.nf +++ b/modules/nf-core/untar/main.nf @@ -2,17 +2,17 @@ process UNTAR { tag "$archive" label 'process_single' - conda "conda-forge::sed=4.7" + conda "conda-forge::sed=4.7 bioconda::grep=3.4 conda-forge::tar=1.34" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/ubuntu:20.04' : - 'ubuntu:20.04' }" + 'docker.io/ubuntu:20.04' }" input: tuple val(meta), path(archive) output: - tuple val(meta), path("$untar"), emit: untar - path "versions.yml" , emit: versions + tuple val(meta), path("$prefix"), emit: untar + path "versions.yml" , emit: versions when: task.ext.when == null || task.ext.when @@ -20,31 +20,29 @@ process UNTAR { script: def args = task.ext.args ?: '' def args2 = task.ext.args2 ?: '' - untar = archive.toString() - '.tar.gz' + prefix = task.ext.prefix ?: ( meta.id ? "${meta.id}" : archive.baseName.toString().replaceFirst(/\.tar$/, "")) """ - mkdir output + mkdir $prefix ## Ensures --strip-components only applied when top level of tar contents is a directory - ## If just files or multiple directories, place all in output - if [[ \$(tar -tzf ${archive} | grep -o -P "^.*?\\/" | uniq | wc -l) -eq 1 ]]; then + ## If just files or multiple directories, place all in prefix + if [[ \$(tar -taf ${archive} | grep -o -P "^.*?\\/" | uniq | wc -l) -eq 1 ]]; then tar \\ - -C output --strip-components 1 \\ - -xzvf \\ + -C $prefix --strip-components 1 \\ + -xavf \\ $args \\ $archive \\ $args2 else tar \\ - -C output \\ - -xzvf \\ + -C $prefix \\ + -xavf \\ $args \\ $archive \\ $args2 fi - mv output ${untar} - cat <<-END_VERSIONS > versions.yml "${task.process}": untar: \$(echo \$(tar --version 2>&1) | sed 's/^.*(GNU tar) //; s/ Copyright.*\$//') @@ -52,9 +50,10 @@ process UNTAR { """ stub: - untar = archive.toString() - '.tar.gz' + prefix = task.ext.prefix ?: ( meta.id ? "${meta.id}" : archive.toString().replaceFirst(/\.[^\.]+(.gz)?$/, "")) """ - touch $untar + mkdir $prefix + touch ${prefix}/file.txt cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/nf-core/untar/meta.yml b/modules/nf-core/untar/meta.yml index ea7a3f3..db241a6 100644 --- a/modules/nf-core/untar/meta.yml +++ b/modules/nf-core/untar/meta.yml @@ -3,6 +3,7 @@ description: Extract files. keywords: - untar - uncompress + - extract tools: - untar: description: | diff --git a/nextflow.config b/nextflow.config index ba1ff0f..9fa1882 100644 --- a/nextflow.config +++ b/nextflow.config @@ -187,7 +187,11 @@ try { profiles { - debug { process.beforeScript = 'echo $HOSTNAME' } + debug { + dumpHashes = true + process.beforeScript = 'echo $HOSTNAME' + cleanup = false + } conda { conda.enabled = true docker.enabled = false @@ -195,6 +199,7 @@ profiles { podman.enabled = false shifter.enabled = false charliecloud.enabled = false + apptainer.enabled = false } mamba { conda.enabled = true @@ -204,14 +209,18 @@ profiles { podman.enabled = false shifter.enabled = false charliecloud.enabled = false + apptainer.enabled = false } docker { docker.enabled = true + docker.registry = 'quay.io' docker.userEmulation = true + conda.enabled = false singularity.enabled = false podman.enabled = false shifter.enabled = false charliecloud.enabled = false + apptainer.enabled = false } arm { docker.runOptions = '-u $(id -u):$(id -g) --platform=linux/amd64' @@ -219,31 +228,49 @@ profiles { singularity { singularity.enabled = true singularity.autoMounts = true + conda.enabled = false docker.enabled = false podman.enabled = false shifter.enabled = false charliecloud.enabled = false + apptainer.enabled = false } podman { podman.enabled = true + podman.registry = 'quay.io' + conda.enabled = false docker.enabled = false singularity.enabled = false shifter.enabled = false charliecloud.enabled = false + apptainer.enabled = false } shifter { shifter.enabled = true + conda.enabled = false docker.enabled = false singularity.enabled = false podman.enabled = false charliecloud.enabled = false + apptainer.enabled = false } charliecloud { charliecloud.enabled = true + conda.enabled = false docker.enabled = false singularity.enabled = false podman.enabled = false shifter.enabled = false + apptainer.enabled = false + } + apptainer { + apptainer.enabled = true + conda.enabled = false + docker.enabled = false + singularity.enabled = false + podman.enabled = false + shifter.enabled = false + charliecloud.enabled = false } gitpod { executor.name = 'local' @@ -305,7 +332,7 @@ manifest { name = 'nf-core/taxprofiler' author = """James A. Fellows Yates, Sofia Stamouli, Moritz E. Beber, and the nf-core/taxprofiler team""" homePage = 'https://github.com/nf-core/taxprofiler' - description = """Taxonomic classification and profiling of shotgun metagenomic data""" + description = """Taxonomic classification and profiling of shotgun and long-read metagenomic data""" mainScript = 'main.nf' nextflowVersion = '!>=22.10.1' version = '1.1.0dev' diff --git a/nextflow_schema.json b/nextflow_schema.json index 60c22df..e5ece87 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -2,7 +2,7 @@ "$schema": "http://json-schema.org/draft-07/schema", "$id": "https://raw.githubusercontent.com/nf-core/taxprofiler/master/nextflow_schema.json", "title": "nf-core/taxprofiler pipeline parameters", - "description": "Taxonomic profiling of shotgun metagenomic data", + "description": "Taxonomic classification and profiling of shotgun metagenomic data", "type": "object", "definitions": { "input_output_options": { diff --git a/tower.yml b/tower.yml new file mode 100644 index 0000000..787aedf --- /dev/null +++ b/tower.yml @@ -0,0 +1,5 @@ +reports: + multiqc_report.html: + display: "MultiQC HTML report" + samplesheet.csv: + display: "Auto-created samplesheet with collated metadata and FASTQ paths"