new module cellranger mkref (#896)

* add cellranger mkref module

* add cellranger mkref tests

* update test yml chksum

* fix module linting

* fix test yml

* fix getprocessname

* fix versions typo

* fix cellranger test.yml

* fix versions.yml

* test versions.yml

* fix grep version

* fix cellranger version

* add dockerfile and readme

* review container statement

* Update modules/cellranger/mkref/meta.yml

Co-authored-by: Gregor Sturm <mail@gregor-sturm.de>

* add disclaimers

* change location dockerfile

Co-authored-by: Gregor Sturm <mail@gregor-sturm.de>

modules/cellranger/Dockerfile

@@ -0,0 +1,21 @@
+FROM continuumio/miniconda3:4.8.2
+LABEL authors="Gisela Gabernet <gisela.gabernet@gmail.com>" \
+    description="Docker image containing Cell Ranger"
+# Disclaimer: this container is not provided nor supported by 10x Genomics.
+
+# Install procps and clean apt cache
+RUN apt-get update \
+    && apt-get install -y procps \
+    && apt-get clean -y && rm -rf /var/lib/apt/lists/*
+
+# Copy pre-downloaded cellranger file
+ENV CELLRANGER_VER 6.0.2
+COPY cellranger-$CELLRANGER_VER.tar.gz /opt/cellranger-$CELLRANGER_VER.tar.gz
+
+# Install cellranger
+RUN \
+    cd /opt && \
+    tar -xzvf cellranger-$CELLRANGER_VER.tar.gz && \
+    export PATH=/opt/cellranger-$CELLRANGER_VER:$PATH && \
+    ln -s /opt/cellranger-$CELLRANGER_VER/cellranger /usr/bin/cellranger && \
+    rm -rf /opt/cellranger-$CELLRANGER_VER.tar.gz

modules/cellranger/mkref/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/cellranger/mkref/main.nf

@@ -0,0 +1,40 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process CELLRANGER_MKREF {
+    tag 'mkref'
+    label 'process_high'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:[:], publish_by_meta:[]) }
+
+    if (params.enable_conda) {
+        exit 1, "Conda environments cannot be used when using the Cell Ranger tool. Please use docker or singularity containers."
+    }
+    container "nfcore/cellranger:6.0.2"
+
+    input:
+    path fasta
+    path gtf
+    val(reference_name)
+
+    output:
+    path "versions.yml"     , emit: versions
+    path "${reference_name}", emit: reference
+
+    script:
+    """
+    cellranger mkref \\
+        --genome=${reference_name} \\
+        --fasta=${fasta} \\
+        --genes=${gtf}
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$(echo \$( cellranger --version 2>&1) | sed 's/^.*[^0-9]\\([0-9]*\\.[0-9]*\\.[0-9]*\\).*\$/\\1/' )
+    END_VERSIONS
+    """
+}

modules/cellranger/mkref/meta.yml

@@ -0,0 +1,39 @@
+name: cellranger_mkref
+description: Module to build the reference needed by the 10x Genomics Cell Ranger tool. Uses the cellranger mkref command.
+keywords:
+  - reference
+  - mkref
+  - index
+tools:
+  - cellranger:
+      description: Cell Ranger by 10x Genomics is a set of analysis pipelines that process Chromium single-cell data to align reads, generate feature-barcode matrices, perform clustering and other secondary analysis, and more.
+      homepage: https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/what-is-cell-ranger
+      documentation: https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/using/tutorial_ov
+      tool_dev_url: https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/using/tutorial_ov
+      doi: ""
+      licence: 10x Genomics EULA
+
+input:
+  - fasta:
+      type: file
+      description: fasta genome file
+      pattern: "*.{fasta,fa}"
+  - gtf:
+      type: file
+      description: gtf transcriptome file
+      pattern: "*.gtf"
+  - reference_name:
+      type: val
+      description: name to give the reference folder
+      pattern: str
+
+output:
+  - versions:
+      type: file
+      description: File containing software version
+      pattern: "versions.yml"
+  - reference:
+      type: folder
+      description: Folder containing all the reference indices needed by Cell Ranger
+authors:
+  - "@ggabernet"

modules/cellranger/readme.md

@@ -0,0 +1,18 @@
+# Updating the docker container and making a new module release
+
+Cell Ranger is a commercial tool by 10X Genomics. The container provided for the cellranger nf-core module is not provided nor supported by 10x Genomics. Updating the Cell Ranger version in the container and pushing the update to Dockerhub needs to be done manually.
+
+1. Navigate to the [Cell Ranger download page](https://support.10xgenomics.com/single-cell-gene-expression/software/downloads/latest) and download the tar ball of the desired Cell Ranger version with `curl` or `wget`. Place this file in the same folder where the Dockerfile lies.
+
+2. Edit the Dockerfile: update the Cell Ranger version in this line:
+
+    ```bash
+    ENV CELLRANGER_VER <VERSION>
+    ```
+
+3. Create the container:
+
+    ```bash
+    docker build . -t nfcore/cellranger:<VERSION>
+    docker push nfcore/cellranger:<VERSION>
+    ```

tests/config/pytest_modules.yml

@@ -254,6 +254,10 @@ cat/fastq:
   - modules/cat/fastq/**
   - tests/modules/cat/fastq/**
 
+cellranger/mkref:
+  - modules/cellranger/mkref/**
+  - tests/modules/cellranger/mkref/**
+
 checkm/lineagewf:
   - modules/checkm/lineagewf/**
   - tests/modules/checkm/lineagewf/**

tests/modules/cellranger/mkref/main.nf

@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CELLRANGER_MKREF } from '../../../../modules/cellranger/mkref/main.nf' addParams( options: [:] )
+
+workflow test_cellranger_mkref {
+
+    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_MKREF ( fasta,
+                        gtf,
+                        reference_name )
+}

tests/modules/cellranger/mkref/test.yml

@@ -0,0 +1,43 @@
+- name: cellranger mkref test_cellranger_mkref
+  command: nextflow run tests/modules/cellranger/mkref -entry test_cellranger_mkref -c tests/config/nextflow.config
+  tags:
+    - cellranger
+    - cellranger/mkref
+  files:
+    - path: output/cellranger/homo_sapiens_chr22_reference/fasta/genome.fa
+      md5sum: f315020d899597c1b57e5fe9f60f4c3e
+    - path: output/cellranger/homo_sapiens_chr22_reference/fasta/genome.fa.fai
+      md5sum: 3520cd30e1b100e55f578db9c855f685
+    - path: output/cellranger/homo_sapiens_chr22_reference/genes/genes.gtf.gz
+      md5sum: 6d9b5f409bfea95022bc25b9590e194e
+    - path: output/cellranger/homo_sapiens_chr22_reference/reference.json
+      md5sum: a4e2b9bbf016c55b0d4d7bc1fa53896f
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/Genome
+      md5sum: 22102926fadf5890e905ca71b2da3f35
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/SA
+      md5sum: bcf3e1a855783105150b46c905465333
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/SAindex
+      md5sum: b93fb07d342e6c32a00ebc4311c0ad38
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/chrLength.txt
+      md5sum: c81f40f27e72606d7d07097c1d56a5b5
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/chrName.txt
+      md5sum: 5ae68a67b70976ee95342a7451cb5af1
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/chrNameLength.txt
+      md5sum: b190587cae0531f3cf25552d8aa674db
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/chrStart.txt
+      md5sum: bc73df776dd3d5bb9cfcbcba60880519
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/exonGeTrInfo.tab
+      md5sum: d04497f69d6ef889efd4d34fe63edcc4
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/exonInfo.tab
+      md5sum: 0d560290fab688b7268d88d5494bf9fe
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/geneInfo.tab
+      md5sum: 8b608537307443ffaee4927d2b428805
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/genomeParameters.txt
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/sjdbInfo.txt
+      md5sum: 5690ea9d9f09f7ff85b7fd47bd234903
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/sjdbList.fromGTF.out.tab
+      md5sum: 8760c33e966dad0b39f440301ebbdee4
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/sjdbList.out.tab
+      md5sum: 9e4f991abbbfeb3935a2bb21b9e258f1
+    - path: output/cellranger/homo_sapiens_chr22_reference/star/transcriptInfo.tab
+      md5sum: 0c3a5adb49d15e5feff81db8e29f2e36