Add Cell Ranger mkfastq, mkgtf, and count (#979)

* feat(cellranger): Add initial count module

Co-authored-by: Gisela Gabernet <gisela.gabernet@gmail.com>

* feat(cellranger): Add mkgtf module

* test(cellranger): Fix count test with mkgtf

* fix(cellranger): Generalize gtf attribute filters

* chore: Add .gitignore for cellranger tar

* build(cellranger): Update dockerfile

https://joshtronic.com/2021/09/12/fixed-repository-debian-security-buster-updates-changed-suite-from-stable-to-oldstable/

* Apply suggestions from code review

Co-authored-by: Gisela Gabernet <gisela.gabernet@gmail.com>

* Apply suggestions from code review

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update modules/cellranger/mkgtf/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* style: Capitalize README

* test(cellranger): Update pytest_modules

* feat(cellranger): Add initial mkfastq module

* ci: Update pytest modules

* refactor(cellranger): Update modules to new syntax

* docs(cellranger): Update meta files

There is some terrible copy-pasting going on.

* fix(cellranger): Add args

Co-authored-by: Gisela Gabernet <gisela.gabernet@gmail.com>
Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

modules/cellranger/.gitignore

@@ -0,0 +1 @@
+cellranger-*.tar.gz

modules/cellranger/Dockerfile

@@ -4,7 +4,7 @@ LABEL authors="Gisela Gabernet <gisela.gabernet@gmail.com>" \
 # Disclaimer: this container is not provided nor supported by 10x Genomics.
 
 # Install procps and clean apt cache
-RUN apt-get update \
+RUN apt-get update --allow-releaseinfo-change \
     && apt-get install -y procps \
     && apt-get clean -y && rm -rf /var/lib/apt/lists/*
 

modules/cellranger/count/main.nf

@@ -0,0 +1,49 @@
+process CELLRANGER_COUNT {
+    tag "$meta.gem"
+    label 'process_high'
+
+    if (params.enable_conda) {
+        exit 1, "Conda environments cannot be used when using the Cell Ranger tool. Please use docker or singularity containers."
+    }
+    container "nfcore/cellranger:6.0.2"
+
+    input:
+    tuple val(meta), path(reads)
+    path  reference
+
+    output:
+    path("sample-${meta.gem}/outs/*"), emit: outs
+    path "versions.yml"              , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    def sample_arg = meta.samples.unique().join(",")
+    def reference_name = reference.name
+    """
+    cellranger \\
+        count \\
+        --id='sample-${meta.gem}' \\
+        --fastqs=. \\
+        --transcriptome=$reference_name \\
+        --sample=$sample_arg \\
+        --localcores=$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:
+    """
+    mkdir -p "sample-${meta.gem}/outs/"
+    touch sample-${meta.gem}/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/cellranger/count/meta.yml

@@ -0,0 +1,40 @@
+name: cellranger_count
+description: Module to use Cell Ranger's pipelines analyze sequencing data produced from Chromium Single Cell Gene Expression.
+keywords:
+    - align
+    - count
+    - reference
+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:
+    - 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.
+    - reference:
+        type: folder
+        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/*"
+    - versions:
+        type: file
+        description: File containing software version
+        pattern: "versions.yml"
+authors:
+  - "@ggabernet"
+  - "@Emiller88"

modules/cellranger/mkfastq/main.nf

@@ -0,0 +1,31 @@
+process CELLRANGER_MKFASTQ {
+    tag "mkfastq"
+    label 'process_medium'
+
+    if (params.enable_conda) {
+        exit 1, "Conda environments cannot be used when using the Cell Ranger tool. Please use docker or singularity containers."
+    }
+    container "litd/docker-cellranger:v6.1.1" // FIXME Add bcl2fastq to nf-core docker image
+
+    input:
+    path bcl
+    path csv
+
+    output:
+    path "versions.yml", emit: versions
+    path "*.fastq.gz"  , emit: fastq
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    cellranger mkfastq --id=${bcl.getSimpleName()} \
+        --run=$bcl \
+        --csv=$csv
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cellranger: \$(echo \$( cellranger --version 2>&1) | sed 's/^.*[^0-9]\\([0-9]*\\.[0-9]*\\.[0-9]*\\).*\$/\\1/' )
+    END_VERSIONS
+    """
+}

modules/cellranger/mkfastq/meta.yml

@@ -0,0 +1,38 @@
+name: cellranger_mkfastq
+description: Module to create fastqs needed by the 10x Genomics Cell Ranger tool. Uses the cellranger mkfastq command.
+keywords:
+  - reference
+  - mkfastq
+  - fastq
+  - illumina
+  - bcl2fastq
+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:
+    - bcl:
+        type: file
+        description: Base call files
+        pattern: "*.bcl.bgzf"
+    - csv:
+        type: file
+        description: Sample sheet
+        pattern: "*.csv"
+output:
+    - fastq:
+          type: file
+          description: Unaligned FastQ files
+          pattern: "*.fastq.gz"
+    - versions:
+        type: file
+        description: File containing software version
+        pattern: "versions.yml"
+authors:
+  - "@ggabernet"
+  - "@Emiller88"
+  - "@RHReynolds"

modules/cellranger/mkgtf/main.nf

@@ -0,0 +1,31 @@
+process CELLRANGER_MKGTF {
+    tag "$gtf"
+    label 'process_low'
+
+    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 gtf
+
+    output:
+    path "*.filtered.gtf", emit: gtf
+    path "versions.yml"  , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    cellranger \\
+        mkgtf \\
+        $gtf \\
+        ${gtf.baseName}.filtered.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/cellranger/mkgtf/meta.yml

@@ -0,0 +1,31 @@
+name: cellranger_mkgtf
+description: Module to build a filtered gtf needed by the 10x Genomics Cell Ranger tool. Uses the cellranger mkgtf 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:
+    - gtf:
+        type: file
+        description:
+        pattern: "*.gtf"
+output:
+    - gtf:
+        type: folder
+        description: gtf transcriptome file
+        pattern: "*.filtered.gtf"
+    - versions:
+        type: file
+        description: File containing software version
+        pattern: "versions.yml"
+authors:
+  - "@ggabernet"
+  - "@Emiller88"

modules/cellranger/mkref/meta.yml

@@ -12,7 +12,6 @@ tools:
         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
@@ -26,14 +25,13 @@ input:
         type: val
         description: name to give the reference folder
         pattern: str
-
 output:
+    - reference:
+        type: folder
+        description: Folder containing all the reference indices needed by Cell Ranger
     - 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"

tests/config/pytest_modules.yml

@@ -270,9 +270,25 @@ cat/fastq:
   - modules/cat/fastq/**
   - tests/modules/cat/fastq/**
 
-cellranger/mkref:
+cellranger/gtf: # &cellranger/gtf
+  - modules/cellranger/gtf/**
+  - tests/modules/cellranger/gtf/**
+
+cellranger/mkref: # &cellranger/mkref
   - modules/cellranger/mkref/**
   - tests/modules/cellranger/mkref/**
+  # - *cellranger/gtf
+  - modules/cellranger/gtf/**
+  - tests/modules/cellranger/gtf/**
+
+cellranger/count:
+  - modules/cellranger/count/**
+  - tests/modules/cellranger/count/**
+  # - *cellranger/mkref
+  - modules/cellranger/mkref/**
+  - tests/modules/cellranger/mkref/**
+  - modules/cellranger/gtf/**
+  - tests/modules/cellranger/gtf/**
 
 checkm/lineagewf:
   - modules/checkm/lineagewf/**

tests/modules/cellranger/count/main.nf

@@ -0,0 +1,33 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CELLRANGER_MKGTF } from '../../../../modules/cellranger/mkgtf/main.nf'
+include { CELLRANGER_MKREF } from '../../../../modules/cellranger/mkref/main.nf'
+include { CELLRANGER_COUNT } from '../../../../modules/cellranger/count/main.nf'
+
+workflow test_cellranger_count {
+
+    input = [ [ id:'test', single_end:true, strandedness:'forward', gem: '123', 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
+    )
+
+    CELLRANGER_COUNT(
+        input,
+        CELLRANGER_MKREF.out.reference
+    )
+}

tests/modules/cellranger/count/nextflow.config

@@ -0,0 +1,31 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: CELLRANGER_MKGTF {
+        ext.args = '--attribute=gene_biotype:protein_coding \
+            --attribute=gene_biotype:lincRNA \
+            --attribute=gene_biotype:antisense \
+            --attribute=gene_biotype:IG_LV_gene \
+            --attribute=gene_biotype:IG_V_gene \
+            --attribute=gene_biotype:IG_V_pseudogene \
+            --attribute=gene_biotype:IG_D_gene \
+            --attribute=gene_biotype:IG_J_gene \
+            --attribute=gene_biotype:IG_J_pseudogene \
+            --attribute=gene_biotype:IG_C_gene \
+            --attribute=gene_biotype:IG_C_pseudogene \
+            --attribute=gene_biotype:TR_V_gene \
+            --attribute=gene_biotype:TR_V_pseudogene \
+            --attribute=gene_biotype:TR_D_gene \
+            --attribute=gene_biotype:TR_J_gene \
+            --attribute=gene_biotype:TR_J_pseudogene \
+            --attribute=gene_biotype:TR_C_gene'
+
+
+    }
+
+    withName: CELLRANGER_COUNT {
+        ext.args = '--chemistry SC3Pv3'
+    }
+
+}

tests/modules/cellranger/count/test.yml

@@ -0,0 +1,19 @@
+- name: cellranger count test_cellranger_count
+  command: nextflow run tests/modules/cellranger/count -entry test_cellranger_count -c tests/config/nextflow.config -c tests/modules/cellranger/count/nextflow.config
+  tags:
+    - cellranger
+    - cellranger/count
+  files:
+    - path: output/cellranger/sample-123/outs/filtered_feature_bc_matrix.h5
+    - path: output/cellranger/sample-123/outs/metrics_summary.csv
+      md5sum: 707df0f101d479d93f412ca74f9c4131
+    - path: output/cellranger/sample-123/outs/molecule_info.h5
+      md5sum: cf03b2b3ca776a1c37aa3518e91268ba
+    - path: output/cellranger/sample-123/outs/possorted_genome_bam.bam
+      md5sum: 15441da9cfceea0bb48c8b66b1b860df
+    - path: output/cellranger/sample-123/outs/possorted_genome_bam.bam.bai
+      md5sum: 7c3d49c77016a09535aff61a027f750c
+    - path: output/cellranger/sample-123/outs/raw_feature_bc_matrix
+    - path: output/cellranger/sample-123/outs/raw_feature_bc_matrix.h5
+      md5sum: 40c8df814eb8723b7317b234dc8222e9
+    - path: output/cellranger/sample-123/outs/web_summary.html

tests/modules/cellranger/mkfastq/main.nf

@@ -0,0 +1,26 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { UNTAR          } from '../../../../modules/untar/main.nf'
+include { CELLRANGER_MKFASTQ } from '../../../../modules/cellranger/mkfastq/main.nf'
+
+workflow test_cellranger_mkfastq_simple {
+
+    simple_csv = file("https://cf.10xgenomics.com/supp/cell-exp/cellranger-tiny-bcl-simple-1.2.0.csv", checkIfExists: true)
+    tiny_bcl = file("https://cf.10xgenomics.com/supp/cell-exp/cellranger-tiny-bcl-1.2.0.tar.gz", checkIfExists: true)
+
+    UNTAR ( tiny_bcl )
+
+    CELLRANGER_MKFASTQ ( UNTAR.out.untar, simple_csv)
+}
+
+workflow test_cellranger_mkfastq_illumina {
+
+    samplesheet_csv = file("https://cf.10xgenomics.com/supp/cell-exp/cellranger-tiny-bcl-samplesheet-1.2.0.csv", checkIfExists: true)
+    tiny_bcl = file("https://cf.10xgenomics.com/supp/cell-exp/cellranger-tiny-bcl-1.2.0.tar.gz", checkIfExists: true)
+
+    UNTAR ( tiny_bcl )
+
+    CELLRANGER_MKFASTQ ( UNTAR.out.untar, samplesheet_csv)
+}

tests/modules/cellranger/mkfastq/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+}

tests/modules/cellranger/mkfastq/test.yml

@@ -0,0 +1,13 @@
+- name: cellranger mkfastq test_cellranger_mkfastq_simple
+  command: nextflow run tests/modules/cellranger/mkfastq -entry test_cellranger_mkfastq_simple -c tests/config/nextflow.config -c ./tests/modules/cellranger/mkfastq/nextflow.config
+  tags:
+    - cellranger
+    - cellranger/mkfastq
+  # files:
+  #   - path: output/cellranger/genome.filtered.gtf
+  #     md5sum: a8b8a7b5039e05d3a9cf9151ea138b5b
+- name: cellranger mkfastq test_cellranger_mkfastq_illumina
+  command: nextflow run tests/modules/cellranger/mkfastq -entry test_cellranger_mkfastq_illumina -c tests/config/nextflow.config -c ./tests/modules/cellranger/mkfastq/nextflow.config
+  tags:
+    - cellranger
+    - cellranger/mkfastq

tests/modules/cellranger/mkgtf/main.nf

@@ -0,0 +1,11 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CELLRANGER_MKGTF } from '../../../../modules/cellranger/mkgtf/main.nf'
+
+workflow test_cellranger_mkgtf {
+    gtf = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true)
+
+    CELLRANGER_MKGTF ( gtf )
+}

tests/modules/cellranger/mkgtf/nextflow.config

@@ -0,0 +1,27 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: CELLRANGER_MKGTF {
+        ext.args = '--attribute=gene_biotype:protein_coding \
+            --attribute=gene_biotype:lincRNA \
+            --attribute=gene_biotype:antisense \
+            --attribute=gene_biotype:IG_LV_gene \
+            --attribute=gene_biotype:IG_V_gene \
+            --attribute=gene_biotype:IG_V_pseudogene \
+            --attribute=gene_biotype:IG_D_gene \
+            --attribute=gene_biotype:IG_J_gene \
+            --attribute=gene_biotype:IG_J_pseudogene \
+            --attribute=gene_biotype:IG_C_gene \
+            --attribute=gene_biotype:IG_C_pseudogene \
+            --attribute=gene_biotype:TR_V_gene \
+            --attribute=gene_biotype:TR_V_pseudogene \
+            --attribute=gene_biotype:TR_D_gene \
+            --attribute=gene_biotype:TR_J_gene \
+            --attribute=gene_biotype:TR_J_pseudogene \
+            --attribute=gene_biotype:TR_C_gene'
+
+
+    }
+
+}

tests/modules/cellranger/mkgtf/test.yml

@@ -0,0 +1,8 @@
+- name: cellranger mkgtf test_cellranger_mkgtf
+  command: nextflow run tests/modules/cellranger/mkgtf -entry test_cellranger_mkgtf -c tests/config/nextflow.config -c tests/modules/cellranger/mkgtf/nextflow.config
+  tags:
+    - cellranger
+    - cellranger/mkgtf
+  files:
+    - path: output/cellranger/genome.filtered.gtf
+      md5sum: a8b8a7b5039e05d3a9cf9151ea138b5b