added cellranger vdj/mkvdjref modules, with module test for vdj

.github/workflows/pytest-workflow.yml

@@ -64,6 +64,10 @@ jobs:
             tags: cellranger/mkgtf
           - profile: "conda"
             tags: cellranger/mkref
+          - profile: "conda"
+            tags: cellranger/mkvdjref
+          - profile: "conda"
+            tags: cellranger/vdj
           - profile: "conda"
             tags: coreograph
           - profile: "conda"

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}":

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

modules/nf-core/cellranger/mkfastq/main.nf

@@ -2,7 +2,7 @@ process CELLRANGER_MKFASTQ {
     tag "mkfastq"
     label 'process_medium'
 
-    container "nfcore/cellrangermkfastq:7.1.0"
+    container "docker.io/nfcore/cellrangermkfastq:7.1.0"
 
     // Exit if running this module with -profile conda / -profile mamba
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
@@ -14,18 +14,21 @@ process CELLRANGER_MKFASTQ {
     path csv
 
     output:
-    path "versions.yml", emit: versions
-    path "${bcl.getSimpleName()}/outs/fastq_path/*.fastq.gz"  , emit: fastq
+    path "**/outs/fastq_path/*.fastq.gz", emit: fastq
+    path "versions.yml"                 , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
     def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${bcl.getSimpleName()}"
     """
-    cellranger mkfastq --id=${bcl.getSimpleName()} \
-        --run=$bcl \
-        --csv=$csv \
+    cellranger \\
+        mkfastq \\
+        --id=${prefix} \\
+        --run=$bcl \\
+        --csv=$csv \\
         $args
 
     cat <<-END_VERSIONS > versions.yml
@@ -35,9 +38,10 @@ process CELLRANGER_MKFASTQ {
     """
 
     stub:
+    def prefix = task.ext.prefix ?: "${bcl.getSimpleName()}"
     """
-    mkdir -p "${bcl.getSimpleName()}/outs/fastq_path/"
-    touch ${bcl.getSimpleName()}/outs/fastq_path/fake_file.fastq.gz
+    mkdir -p "${prefix}/outs/fastq_path/"
+    touch ${prefix}/outs/fastq_path/fake_file.fastq.gz
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

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) {
@@ -13,19 +13,20 @@ process CELLRANGER_MKGTF {
     path gtf
 
     output:
-    path "*.filtered.gtf", emit: gtf
+    path "*.gtf"         , emit: gtf
     path "versions.yml"  , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     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

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) {

modules/nf-core/cellranger/mkvdjref/main.nf

@@ -0,0 +1,39 @@
+process CELLRANGER_MKVDJREF {
+    tag "$fasta"
+    label 'process_high'
+
+    container "docker.io/nfcore/cellranger:7.1.0"
+
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        exit 1, "CELLRANGER_MKREF module does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
+
+    input:
+    path fasta
+    path gtf
+    val reference_name
+
+    output:
+    path "${reference_name}", emit: reference
+    path "versions.yml"     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    cellranger \\
+        mkvdjref \\
+        --genome=$reference_name \\
+        --fasta=$fasta \\
+        --genes=$gtf \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cellranger: \$(echo \$( cellranger --version 2>&1) | sed 's/^.*[^0-9]\\([0-9]*\\.[0-9]*\\.[0-9]*\\).*\$/\\1/' )
+    END_VERSIONS
+    """
+}

modules/nf-core/cellranger/mkvdjref/meta.yml

@@ -0,0 +1,40 @@
+name: cellranger_mkvdjref
+description: Module to build the VDJ reference needed by the 10x Genomics Cell Ranger tool. Uses the cellranger mkvdjref command.
+keywords:
+  - reference
+  - mkvdjref
+  - index
+  - immunoprofiling
+  - single-cell
+  - cellranger
+tools:
+  - cellranger:
+      description: Cell Ranger processes data from 10X Genomics Chromium kits. `cellranger vdj` takes FASTQ files from `cellranger mkfastq` or `bcl2fastq` for V(D)J libraries and performs sequence assembly and paired clonotype calling. It uses the Chromium cellular barcodes and UMIs to assemble V(D)J transcripts per cell. Clonotypes and CDR3 sequences are output as a `.vloupe` file which can be loaded into Loupe V(D)J Browser.
+      homepage: https://support.10xgenomics.com/single-cell-vdj/software/pipelines/latest/what-is-cell-ranger
+      documentation: https://support.10xgenomics.com/single-cell-vdj/software/pipelines/latest/advanced/references
+      tool_dev_url: https://support.10xgenomics.com/single-cell-vdj/software/pipelines/latest/advanced/references
+      licence: 10x Genomics EULA
+input:
+  - fasta:
+      type: file
+      description: Reference genome FASTA file
+      pattern: "*.{fasta,fa}"
+  - genes:
+      type: file
+      description: Reference transcriptome GTF file
+      pattern: "*.gtf"
+  - genome:
+      type: val
+      description: The name to give the new reference folder, e.g. `my_vdj_ref`
+      pattern: str
+output:
+  - reference:
+      type: directory
+      description: Folder containing all the reference indices needed by Cell Ranger
+  - versions:
+      type: file
+      description: File containing software version
+      pattern: "versions.yml"
+authors:
+  - "@ggabernet"
+  - "@klkeys"

modules/nf-core/cellranger/vdj/main.nf

@@ -0,0 +1,54 @@
+process CELLRANGER_VDJ {
+    tag "${meta.id}"
+    label 'process_high'
+
+    container "docker.io/nfcore/cellranger:7.1.0"
+
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        exit 1, "CELLRANGER_VDJ module does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
+
+    input:
+    tuple val(meta), path(reads)
+    path  reference
+
+    output:
+    tuple val(meta), path("**/outs/**"), emit: outs
+    path "versions.yml"                , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def reference_name = reference.name
+    """
+    cellranger \\
+        vdj \\
+        --id='${prefix}' \\
+        --fastqs=. \\
+        --reference=$reference_name \\
+        --localcores=${task.cpus} \\
+        --localmem=${task.memory.toGiga()} \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cellranger: \$(echo \$( cellranger --version 2>&1) | sed 's/^.*[^0-9]\\([0-9]*\\.[0-9]*\\.[0-9]*\\).*\$/\\1/' )
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    mkdir -p "${meta.id}/outs/"
+    touch ${meta.id}/outs/fake_file.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cellranger: \$(echo \$( cellranger --version 2>&1) | sed 's/^.*[^0-9]\\([0-9]*\\.[0-9]*\\.[0-9]*\\).*\$/\\1/' )
+    END_VERSIONS
+    """
+}

modules/nf-core/cellranger/vdj/meta.yml

@@ -0,0 +1,44 @@
+name: cellranger_vdj
+description: Module to use Cell Ranger's pipelines analyze sequencing data produced from Chromium Single Cell Immune Profiling.
+keywords:
+  - align
+  - vdj
+  - reference
+  - immunoprofiling
+  - single-cell
+  - cellranger
+tools:
+  - cellranger:
+      description: Cell Ranger processes data from 10X Genomics Chromium kits. `cellranger vdj` takes FASTQ files from `cellranger mkfastq` or `bcl2fastq` for V(D)J libraries and performs sequence assembly and paired clonotype calling. It uses the Chromium cellular barcodes and UMIs to assemble V(D)J transcripts per cell. Clonotypes and CDR3 sequences are output as a `.vloupe` file which can be loaded into Loupe V(D)J Browser.
+      homepage: https://support.10xgenomics.com/single-cell-vdj/software/pipelines/latest/what-is-cell-ranger
+      documentation: https://support.10xgenomics.com/single-cell-vdj/software/pipelines/latest/tutorial/tutorial-vdj
+      tool_dev_url: https://support.10xgenomics.com/single-cell-vdj/software/pipelines/latest/tutorial/tutorial-vdj
+      licence: 10x Genomics EULA
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      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}_${I1,I2,R1,R2}_001.fastq.gz"
+  - reference:
+      type: directory
+      description: Folder containing all the reference indices needed by Cell Ranger
+output:
+  - outs:
+      type: file
+      description: Files containing the outputs of Cell Ranger, see official 10X Genomics documentation for a complete list
+      pattern: "${meta.id}/outs/*"
+  - versions:
+      type: file
+      description: File containing software version
+      pattern: "versions.yml"
+authors:
+  - "@ggabernet"
+  - "@Emiller88"
+  - "@klkeys"

tests/config/pytest_modules.yml

@@ -625,12 +625,8 @@ cellranger/count:
   - tests/modules/nf-core/cellranger/count/**
   - modules/nf-core/cellranger/mkref/**
   - tests/modules/nf-core/cellranger/mkref/**
-  - modules/nf-core/cellranger/gtf/**
-  - tests/modules/nf-core/cellranger/gtf/**
-
-cellranger/gtf:
-  - modules/nf-core/cellranger/gtf/**
-  - tests/modules/nf-core/cellranger/gtf/**
+  - modules/nf-core/cellranger/mkgtf/**
+  - tests/modules/nf-core/cellranger/mkgtf/**
 
 cellranger/mkfastq:
   - modules/nf-core/cellranger/mkfastq/**
@@ -643,8 +639,16 @@ cellranger/mkgtf:
 cellranger/mkref:
   - modules/nf-core/cellranger/mkref/**
   - tests/modules/nf-core/cellranger/mkref/**
-  - modules/nf-core/cellranger/gtf/**
-  - tests/modules/nf-core/cellranger/gtf/**
+  - modules/nf-core/cellranger/mkgtf/**
+  - tests/modules/nf-core/cellranger/mkgtf/**
+
+cellranger/mkvdjref:
+  - modules/nf-core/cellranger/mkvdjref/**
+  - tests/modules/nf-core/cellranger/mkvdjref/**
+
+cellranger/vdj:
+  - modules/nf-core/cellranger/vdj/**
+  - tests/modules/nf-core/cellranger/vdj/**
 
 centrifuge/centrifuge:
   - modules/nf-core/centrifuge/centrifuge/**