Add Cellsnp to modules

modules/nf-core/cellsnp/environment.yml

@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "cellsnp"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::cellsnp-lite=1.2.3"

modules/nf-core/cellsnp/main.nf

@@ -0,0 +1,67 @@
+process CELLSNP {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/cellsnp-lite:1.2.3--h6141fd1_2' :
+        'biocontainers/cellsnp-lite:1.2.3--h6141fd1_2' }"
+
+    input:
+    tuple val(meta), path(bam), path(bai), path(region_vcf), path(barcode), path(sample_list)
+
+    output:
+    tuple val(meta), path('*/cellSNP.base.vcf.gz')     , emit: base
+    tuple val(meta), path('*/cellSNP.cells.vcf.gz')    , emit: cell,          optional: true
+    tuple val(meta), path('*/cellSNP.samples.tsv')     , emit: sample
+    tuple val(meta), path('*/cellSNP.tag.AD.mtx')      , emit: allele_depth
+    tuple val(meta), path('*/cellSNP.tag.DP.mtx')      , emit: depth_coverage
+    tuple val(meta), path('*/cellSNP.tag.OTH.mtx')     , emit: depth_other
+    path 'versions.yml'                                , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def barcode_file = barcode ? "-b $barcode" : ''
+    def region_file = region_vcf ? "-R $region_vcf" : ''
+    def sample = sample_list ? "-I $sample_list" : ''
+
+    """
+    cellsnp-lite -s $bam \\
+        $barcode_file \\
+        $region_file \\
+        $sample \\
+        -O $prefix --gzip \\
+        --nproc $task.cpus \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cellsnp: \$(cellsnp-lite --v | awk '{print \$2}')
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def barcode_file = barcode ? "-b $barcode" : ''
+    def region_file = region_vcf ? "-R $region_vcf" : ''
+    def sample = sample_list ? "-I $sample_list" : ''
+
+    """
+    mkdir $prefix
+    touch $prefix/cellSNP.base.vcf.gz
+    touch $prefix/cellSNP.samples.tsv
+    touch $prefix/cellSNP.tag.AD.mtx
+    touch $prefix/cellSNP.tag.DP.mtx
+    touch $prefix/cellSNP.tag.OTH.mtx
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cellsnp: \$(cellsnp-lite --v | awk '{print \$2}')
+    END_VERSIONS
+    """
+}

modules/nf-core/cellsnp/meta.yml

@@ -0,0 +1,85 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "cellsnp"
+description: Cellsnp-lite is a C/C++ tool for efficient genotyping bi-allelic SNPs on single cells. You can use cellsnp-lite after read alignment to obtain the snp x cell pileup UMI or read count matrices for each alleles of given or detected SNPs.
+keywords:
+  - genotyping
+  - single cell
+  - SNP
+tools:
+  - "cellsnp":
+      description: "Efficient genotyping bi-allelic SNPs on single cells"
+      homepage: "https://github.com/single-cell-genetics/cellsnp-lite"
+      documentation: "https://cellsnp-lite.readthedocs.io"
+      tool_dev_url: "https://github.com/single-cell-genetics/cellsnp-lite"
+      doi: "10.1093/bioinformatics/btab358"
+      licence: ["Apache-2.0"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+
+  - bam:
+      type: file
+      description: Indexed BAM/CRAM file(s), comma separated multiple samples.
+      pattern: "*.{bam,cram,sam}"
+  - bai:
+      type: file
+      description: Index of the BAM/CRAM file.
+      pattern: "*.{bai,crai}"
+  - region_vcf:
+      type: file
+      description: A vcf file listing all candidate SNPs, for fetch each variants.
+      pattern: "*.{vcf, vcf.gz}"
+  - barcode:
+      type: file
+      description: A plain file listing all effective cell barcodes.
+      pattern: "*.tsv"
+  - sample_list:
+      type: file
+      description: A list file containing sample IDs, each per line.
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1']`
+
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+  - base:
+      type: file
+      description: A VCF file listing genotyped SNPs and aggregated AD & DP infomation (without GT).
+      pattern: "*.base.vcf.gz"
+  - cell:
+      type: file
+      description: A VCF file listing genotyped SNPs and aggregated AD & DP infomation & genotype (GT) information for each cell or sample.
+      pattern: "*.cells.vcf.gz"
+  - sample:
+      type: file
+      description: A TSV file listing cell barcodes or sample IDs.
+      pattern: "*.tsv"
+  - allele_depth:
+      type: file
+      description: A file in “Matrix Market exchange formats”, containing the allele depths of the alternative (ALT) alleles.
+      pattern: "*.tag.AD.mtx"
+  - depth_coverage:
+      type: file
+      description: A file in “Matrix Market exchange formats”, containing the sum of allele depths of the reference and alternative alleles (REF + ALT).
+      pattern: "*.tag.DP.mtx"
+  - depth_other:
+      type: file
+      description: A file in “Matrix Market exchange formats”, containing the sum of allele depths of all the alleles other than REF and ALT.
+      pattern: "*.tag.OTH.mtx"
+
+authors:
+  - "@wxicu"
+maintainers:
+  - "@wxicu"

modules/nf-core/cellsnp/tests/main.nf.test

@@ -0,0 +1,90 @@
+// nf-core modules test cellsnp
+nextflow_process {
+
+    name "Test Process CELLSNP"
+    script "../main.nf"
+    process "CELLSNP"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "cellsnp"
+    tag "samtools/index"
+
+    test("genotyping") {
+        setup { 
+            run("SAMTOOLS_INDEX") {
+                script "../../samtools/index/main.nf"
+                process {
+                    """
+                    input[0] = [
+                    [ id:'sample1' ],
+                    file(params.modules_testdata_base_path + '/genomics/homo_sapiens/demultiplexing/chr21.bam', checkIfExists: true) ]
+                    """
+                }
+            }
+        }
+
+        when {
+            process {
+                """ 
+                input[0] = SAMTOOLS_INDEX.out.bai.collect{ meta, bai -> bai }.map{ 
+                            bai -> [[ id: 'sample1'], 
+                                    file(params.modules_testdata_base_path + '/genomics/homo_sapiens/demultiplexing/chr21.bam', checkIfExists: true),
+                                    bai,
+                                    file(params.modules_testdata_base_path + '/genomics/homo_sapiens/demultiplexing/donor_genotype_chr21.vcf', checkIfExists: true),
+                                    file(params.modules_testdata_base_path + '/genomics/homo_sapiens/demultiplexing/barcodes.tsv', checkIfExists: true),
+                                    []
+                                    ]}
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match("versions") },
+	        { assert path(process.out.base.get(0).get(1)).exists() },
+                { assert path(process.out.sample.get(0).get(1)).exists() },
+                { assert path(process.out.allele_depth.get(0).get(1)).exists() },
+                { assert path(process.out.depth_coverage.get(0).get(1)).exists() },
+                { assert path(process.out.depth_other.get(0).get(1)).exists() }           
+	    )
+        }
+
+    }
+
+    test("genotyping - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+
+                input[0] = [
+                    [ id:'sample1'], // meta map
+                    file(params.modules_testdata_base_path + '/genomics/homo_sapiens/demultiplexing/chr21.bam', checkIfExists: true),
+                    [],
+                    file(params.modules_testdata_base_path + '/genomics/homo_sapiens/demultiplexing/donor_genotype_chr21.vcf', checkIfExists: true),
+                    file(params.modules_testdata_base_path + '/genomics/homo_sapiens/demultiplexing/barcodes.tsv', checkIfExists: true),
+                    []
+                    ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match("versions-stub") },
+	        { assert path(process.out.base.get(0).get(1)).exists() },
+                { assert path(process.out.sample.get(0).get(1)).exists() },
+                { assert path(process.out.allele_depth.get(0).get(1)).exists() },
+                { assert path(process.out.depth_coverage.get(0).get(1)).exists() },
+                { assert path(process.out.depth_other.get(0).get(1)).exists() }
+            )
+        }
+
+    }
+
+}

modules/nf-core/cellsnp/tests/main.nf.test.snap

@@ -0,0 +1,26 @@
+{
+    "versions": {
+        "content": [
+            [
+                "versions.yml:md5,89366928a2dbfad795438e38c7ef8695"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-04-24T10:01:10.254512578"
+    },
+    "versions-stub": {
+        "content": [
+            [
+                "versions.yml:md5,89366928a2dbfad795438e38c7ef8695"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-04-24T10:01:50.522835434"
+    }
+}

modules/nf-core/cellsnp/tests/tags.yml

@@ -0,0 +1,2 @@
+cellsnp:
+  - "modules/nf-core/cellsnp/**"