dysgu_updated

modules/nf-core/dysgu/environment.yml

@@ -0,0 +1,11 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "dysgu"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - pip
+  - pip:
+      - dysgu==1.6.4

modules/nf-core/dysgu/main.nf

@@ -0,0 +1,58 @@
+process DYSGU {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'oras://community.wave.seqera.io/library/pip_dysgu:8b321eca2aa251f4' :
+        'community.wave.seqera.io/library/pip_dysgu:8b321eca2aa251f4' }"
+
+    input:
+    tuple val(meta), path(input_bam), path(input_bam_index)
+    tuple val(meta2), path(fasta), path(fai)
+
+    output:
+    tuple val(meta), path('*.vcf.gz')       , emit: vcf
+    tuple val(meta), path('*.vcf.gz.tbi')   , emit: tbi
+    path 'versions.yml'                     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def args2 = task.ext.args2 ?: ''
+    def args3 = task.ext.args3 ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+
+    dysgu run \\
+        -p ${task.cpus} \\
+        -x \\
+        $fasta \\
+        . \\
+        $input_bam \\
+        | bgzip ${args2} --threads ${task.cpus} --stdout > ${prefix}.vcf.gz
+    tabix ${args3} ${prefix}.vcf.gz
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        dysgu: \$(dysgu --version 2>&1)
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    echo "" | gzip > ${prefix}.vcf.gz
+    touch ${prefix}.vcf.gz.tbi
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        dysgu: \$(dysgu --version 2>&1)
+    END_VERSIONS
+    """
+}

modules/nf-core/dysgu/meta.yml

@@ -0,0 +1,73 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "dysgu"
+
+description: Dysgu calls structural variants (SVs) from mapped sequencing reads. It is designed for accurate and efficient detection of structural variations.
+keywords:
+  - structural variants
+  - sv
+  - vcf
+tools:
+  - dysgu:
+      description: Structural variant caller for mapped sequencing data
+      homepage: https://github.com/kcleal/dysgu
+      documentation: https://github.com/kcleal/dysgu/blob/master/README.rst
+      tool_dev_url: https://github.com/kcleal/dysgu
+      doi: "10.1093/nar/gkac039"
+      licence: ["GPL-3.0-or-later"]
+
+input:
+  # Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1' ]`
+
+  - input_bam:
+      type: file
+      description: Input BAM file
+      pattern: "*.bam"
+  - input_bam_index:
+      type: file
+      description: BAM index file
+      pattern: "*.bai"
+  - fasta:
+      type: file
+      description: Genome reference FASTA file
+      pattern: "*.{fa,fasta}"
+  - meta2:
+      type: map
+      description: |
+        Groovy Map containing reference information
+        e.g. [ id:'genome' ]
+  - fai:
+      type: file
+      description: Genome reference FASTA index file
+      pattern: "*.{fa.fai,fasta.fai}"
+
+output:
+  #Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'sample1'  ]
+  - vcf:
+      type: file
+      description: VCF file with identified structural variants
+      pattern: "*.{vcf.gz}"
+  - tbi:
+      type: file
+      description: The index of the BCF/VCF file
+      pattern: "*.{vcf.gz.tbi}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@kcleal"
+  - "@famosab"
+maintainers:
+  - "@kcleal"

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

@@ -0,0 +1,96 @@
+nextflow_process {
+
+    name "Test Process DYSGU"
+    script "../main.nf"
+    process "DYSGU"
+    config "./nextflow.config"
+    tag "modules"
+    tag "modules_nfcore"
+    tag "dysgu"
+
+
+    test("human - bam") {
+
+        when {
+            process {
+                """
+                input[0] = [ [ id:'test'], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test.paired_end.recalibrated.sorted.bam', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test.paired_end.recalibrated.sorted.bam.bai', checkIfExists: true)
+                ]
+                input[1] = [ [ id:'reference'], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/chr21/sequence/genome.fasta', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/chr21/sequence/genome.fasta.fai', checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match("bam") },
+                { assert path(process.out.vcf.get(0).get(1)).linesGzip.contains("##fileformat=VCFv4.2") }
+            )
+        }
+
+    }
+
+
+    test("human - cram") {
+
+        when {
+            process {
+                """
+                input[0] = [ [ id:'test'], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/cram/test.paired_end.recalibrated.sorted.cram', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/cram/test.paired_end.recalibrated.sorted.cram.crai', checkIfExists: true)
+                ]
+                input[1] = [ [ id:'reference'], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/chr21/sequence/genome.fasta', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/chr21/sequence/genome.fasta.fai', checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match("cram") },
+                { assert path(process.out.vcf.get(0).get(1)).linesGzip.contains("##fileformat=VCFv4.2") }
+            )
+        }
+
+    }
+
+
+    test("human - bam - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [ [ id:'test'], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test.paired_end.recalibrated.sorted.bam', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test.paired_end.recalibrated.sorted.bam.bai', checkIfExists: true)
+                ]
+                input[1] = [ [ id:'reference'], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/chr21/sequence/genome.fasta', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/chr21/sequence/genome.fasta.fai', checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}