Add Universc

.github/workflows/pytest-workflow.yml

@@ -81,6 +81,10 @@ jobs:
             tags: merquryfk/merquryfk
           - profile: "conda"
             tags: merquryfk/ploidyplot
+          - profile: "conda"
+            tags: universc
+          - profile: "singularity"
+            tags: universc
           - profile: "conda"
             tags: subworkflows/vcf_annotate_ensemblvep
     env:

modules/nf-core/universc/CITATION.cff

@@ -0,0 +1,51 @@
+cff-version: 1.2.0
+message: "If you use this software, please cite it as below."
+authors:
+  - given-names: "S. Thomas"
+    family-names: "Kelly"
+    email: "[email protected]"
+    affiliation: "Center for Integrative Medical Sciences, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan"
+    orcid: "https://orcid.org/0000-0003-3904-6690"
+  - family-names: "Battenberg"
+    given-names: "Kai"
+    email: "[email protected]"
+    affiliation: "Center for Sustainable Resource Science, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan"
+    orcid: "http://orcid.org/0000-0001-7517-2657"
+version: 1.2.5.1
+doi: 10.1101/2021.01.19.427209
+date-released: 2021-02-14
+url: "https://github.com/minoda-lab/universc"
+preferred-citation:
+  type: article
+  authors:
+    - given-names: "S. Thomas"
+      family-names: "Kelly"
+      email: "[email protected]"
+      affiliation: "Center for Integrative Medical Sciences, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan"
+      orcid: "https://orcid.org/0000-0003-3904-6690"
+    - family-names: "Battenberg"
+      given-names: "Kai"
+      email: "[email protected]"
+      affiliation: "Center for Sustainable Resource Science, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan"
+      orcid: "https://orcid.org/http://orcid.org/0000-0001-7517-2657"
+    - family-names: "Hetherington"
+      given-names: "Nicola A."
+      affiliation: "Center for Integrative Medical Sciences, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan"
+      orcid: "http://orcid.org/0000-0001-8802-2906"
+    - family-names: "Hayashi"
+      given-names: "Makoto"
+      affiliation: "Center for Sustainable Resource Science, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan"
+      orcid: "http://orcid.org/0000-0001-6389-4265"
+    - given-names: "Aki"
+      family-names: "Minoda"
+      email: "[email protected]"
+      affiliation: Center for Integrative Medical Sciences, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan"
+      orcid: "http://orcid.org/0000-0002-2927-5791"
+  doi: "10.1101/2021.01.19.427209"
+  title: "UniverSC: a flexible cross-platform single-cell data processing pipeline"
+  year: "2021"
+  journal: "bioRxiv"
+  start: 2021.01.19.427209
+  volume:
+  issue:
+  month: 1

modules/nf-core/universc/CITATION.md

@@ -0,0 +1,37 @@
+### Citation <span id="Citation"><span>
+
+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},
+  }
+```

modules/nf-core/universc/README.md

@@ -0,0 +1,116 @@
+# UniverSC
+
+## Single-cell processing across technologies
+
+UniverSC is an open-source single-cell pipeline that runs across platforms on various technologies.
+
+## Maintainers
+
+Tom Kelly (RIKEN, IMS)
+
+Kai Battenberg (RIKEN CSRS/IMS)
+
+Contact: <first name>.<family name>[at]riken.jp
+
+## Implementation
+
+This container runs Cell Ranger v3.0.2 installed from source on MIT License on GitHub with
+modifications for compatibility with updated dependencies. All software is installed from
+open-source repositories and available for reuse.
+
+It is _not_ subject to the 10X Genomics End User License Agreement (EULA).
+This version allows running Cell Ranger v3.0.2 on data generated from any experimental platform
+without restrictions. However, updating to newer versions on Cell Ranger subject to the
+10X EULA is not possible without the agreement of 10X Genomics.
+
+To comply with licensing and respect 10X Genomics Trademarks, the 10X Genomics logo
+has been removed from HTML reports, the tool has been renamed, and proprietary
+closed-source tools to build Cloupe files are disabled.
+
+It is still suffient to generate summary reports and count matrices compatible with
+single-cell analysis tools available for 10X Genomics and Cell Ranger output format
+in Python and R packages.
+
+## Usage
+
+### Generating References
+
+The Cell Ranger modules can be used to generate reference indexes to run UniverSC.
+Note that UniverSC requires the Open Source version v3.0.2 of Cell Ranger included
+in the nf-core/universc Docker image. The same module parameters can be run provided
+that the container is changed in process configurations (modify nextflow.config).
+
+```
+process {
+
+...
+    withName: CELLRANGER_MKGTF {
+        container = "nfcore/universc:1.2.5.1"
+    }
+    withName: CELLRANGER_MKREF{
+       container = "nfcore/universc:1.2.5.1"
+    }
+...
+}
+```
+
+This will generate a compatible index for UniverSC using the same version of the
+STAR aligner and a permissive software license without and EULA.
+
+### Container settings
+
+The cellranger install directory must have write permissions to run UniverSC.
+To run in docker or podman use the `--user root` option in container parameters
+and for singularity use the `--writeable` parameter.
+
+These are set as default in universc/main.nf:
+
+```
+    container "nfcore/universc:1.2.5.1"
+    if (workflow.containerEngine == 'docker'){
+        containerOptions = "--privileged"
+    }
+    if (workflow.containerEngine == 'podman'){
+        containerOptions = "--runtime /usr/bin/crun --userns=keep-id --user root --systemd=always"
+    }
+    if (workflow.containerEngine == 'singularity'){
+        containerOptions = "--writable"
+    }
+```
+
+Select the container engine with `nextflow --profile "docker"` or set the environment variable
+as one of the following before running nextflow.
+
+```
+export PROFILE="docker"
+export PROFILE="podman"
+export PROFILE="singularity"
+```
+
+Note that due to dependencies installed in a docker image, it is not possible to use conda environments.
+
+## Disclaimer
+
+We are third party developers not affiliated with 10X Genomics or any other vendor of
+single-cell technologies. We are releasing this code on an open-source license which calls Cell Ranger
+as an external dependency.
+
+## Licensing
+
+This package is provided open-source on a GPL-3 license. This means that you are free to use and
+modify this code provided that they also contain this license.
+
+## Updating the package
+
+The tomkellygenetics/universc:<VERSION> container is automatically updated with tomkellygenetics/universc:latest.
+
+A stable release is mirrored at nfcore/universc:1.2.5.1 and will be updated as needed.
+
+To build an updated container use the Dockerfile provided here:
+
+[https://github.com/minoda-lab/universc/blob/master/Dockerfile](https://github.com/minoda-lab/universc/blob/master/Dockerfile)
+
+Note that this uses a custom base image which is built with an open-source implementation of
+Cell Ranger v3.0.2 on MIT License and relies of Python 2. The build file can be found here:
+
+[https://github.com/TomKellyGenetics/cellranger_clean/blob/master/Dockerfile](https://github.com/TomKellyGenetics/cellranger_clean/blob/master/Dockerfile)

modules/nf-core/universc/main.nf

@@ -0,0 +1,76 @@
+process UNIVERSC {
+    tag "$meta.id"
+    label 'process_medium'
+
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        exit 1, "UNIVERSC module does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
+    container "nfcore/universc:1.2.5.1"
+    if (workflow.containerEngine == 'docker'){
+        containerOptions = "--privileged"
+    }
+    if ( workflow.containerEngine == 'podman'){
+        containerOptions = "--runtime crun --userns=keep-id --systemd=always"
+    }
+    if (workflow.containerEngine == 'singularity'){
+        containerOptions = "-B /var/tmp --writable-tmpfs"
+        params.singularity_autoMounts = true
+    }
+
+    input:
+    tuple val(meta), path(reads)
+    path  reference
+
+
+    output:
+    tuple val(meta), path("sample-${meta.id}/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 reference_name = reference.name
+    def input_reads = meta.single_end ? "--file $reads" : "-R1 ${reads[0]} -R2 ${reads[1]}"
+    """
+    universc \\
+        --id 'sample-${meta.id}' \\
+        ${input_reads} \\
+        --technology '${meta.technology}' \\
+        --chemistry '${meta.chemistry}' \\
+        --reference ${reference_name} \\
+        --description ${sample_arg} \\
+        --jobmode "local" \\
+        --localcores ${task.cpus} \\
+        --localmem ${task.memory.toGiga()} \\
+        --per-cell-data \\
+        $args 1> _log 2> _err
+
+    # save log files
+    echo !! > sample-${meta.id}/outs/_invocation
+    cp _log sample-${meta.id}/outs/_log
+    cp _err sample-${meta.id}/outs/_err
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cellranger:  \$(echo \$(cellranger count --version 2>&1 | head -n 2 | tail -n 1 | sed 's/^.* //g' | sed 's/(//g' | sed 's/)//g' ))
+        universc:  \$(echo \$(bash /universc/launch_universc.sh --version | grep version | grep universc  | sed 's/^.* //g' ))
+    END_VERSIONS
+    """
+
+
+    stub:
+    """
+    mkdir -p "sample-${meta.id}/outs/"
+    touch sample-${meta.id}/outs/fake_file.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cellranger:  \$(echo \$(cellranger count --version 2>&1 | head -n 2 | tail -n 1 | sed 's/^.* //g' | sed 's/(//g' | sed 's/)//g' ))
+        universc:  \$(echo \$(bash /universc/launch_universc.sh --version | grep version | grep universc | sed 's/^.* //g' ))
+    END_VERSIONS
+    """
+}

modules/nf-core/universc/meta.yml

@@ -0,0 +1,42 @@
+name: "universc"
+description: Module to run UniverSC an open-source pipeline to demultiplex and process single-cell RNA-Seq data
+keywords:
+  - demultiplex
+  - align
+  - single-cell
+  - scRNA-Seq
+  - count
+  - umi
+tools:
+  - "universc":
+      description: "UniverSC: a flexible cross-platform single-cell data processing pipeline"
+      homepage: "https://hub.docker.com/r/tomkellygenetics/universc"
+      documentation: "https://raw.githubusercontent.com/minoda-lab/universc/master/man/launch_universc.sh"
+      tool_dev_url: "https://github.com/minoda-lab/universc"
+      doi: "https://doi.org/10.1101/2021.01.19.427209"
+      licence: ["GPL-3.0-or-later"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: FASTQ or FASTQ.GZ file, list of 2 files for paired-end data
+      pattern: "*.{fastq,fq,fastq.gz,fq.gz}"
+
+output:
+  - outs:
+      type: file
+      description: Files containing the outputs of Cell Ranger
+      pattern: "sample-${meta.id}/outs/*"
+  - versions:
+      type: file
+      description: File containing software version
+      pattern: "versions.yml"
+
+authors:
+  - "@kbattenb"
+  - "@tomkellygenetics"

tests/config/nextflow.config

@@ -19,6 +19,10 @@ if ("$PROFILE" == "singularity") {
 } else if ("$PROFILE" == "mamba") {
     conda.enabled  = true
     conda.useMamba = true
+} else if ("$PROFILE" == "podman") {
+    podman.enabled = true
+    podman.userEmulation = true
+    podman.runOptions = "--runtime crun --platform linux/x86_64 --systemd=always"
 } else {
     docker.enabled = true
     docker.userEmulation = true

tests/config/pytest_modules.yml

@@ -3236,6 +3236,10 @@ unicycler:
   - modules/nf-core/unicycler/**
   - tests/modules/nf-core/unicycler/**
 
+universc:
+  - modules/nf-core/universc/**
+  - tests/modules/nf-core/universc/**
+
 untar:
   - modules/nf-core/untar/**
   - tests/modules/nf-core/untar/**

tests/modules/nf-core/universc/main.nf

@@ -0,0 +1,33 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CELLRANGER_MKGTF } from '../../../../modules/nf-core/cellranger/mkgtf/main.nf'
+include { CELLRANGER_MKREF } from '../../../../modules/nf-core/cellranger/mkref/main.nf'
+include { UNIVERSC } from '../../../../modules/nf-core/universc//main.nf'
+
+workflow test_universc_10x {
+
+    input = [ [ id:'123', technology:'10x', chemistry:'SC3Pv3', single_end:false, strandedness:'forward', samples: ["test_10x"] ], // meta map
+             [ file(params.test_data['homo_sapiens']['illumina']['test_10x_1_fastq_gz'], checkIfExists: true),
+              file(params.test_data['homo_sapiens']['illumina']['test_10x_2_fastq_gz'], checkIfExists: true)
+        ]
+    ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    gtf = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true)
+    reference_name = "homo_sapiens_chr22_reference"
+
+    CELLRANGER_MKGTF ( gtf )
+
+    CELLRANGER_MKREF (
+        fasta,
+        CELLRANGER_MKGTF.out.gtf,
+        reference_name
+    )
+
+    UNIVERSC (
+        input,
+        CELLRANGER_MKREF.out.reference
+    )
+}