Merge pull request #1652 from lmtani/haplocheck

Add Haplocheck

modules/haplocheck/main.nf

@@ -0,0 +1,44 @@
+process HAPLOCHECK {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::haplocheck=1.3.3" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/haplocheck:1.3.3--h4a94de4_0':
+        'quay.io/biocontainers/haplocheck:1.3.3--h4a94de4_0' }"
+
+    input:
+    tuple val(meta), path(vcf)
+
+    output:
+    tuple val(meta), path("*.txt") , emit: txt
+    tuple val(meta), path("*.html"), emit: html
+    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}"
+    """
+    haplocheck --raw --out $prefix $vcf
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        haplocheck: \$(echo \$(haplocheck --version 2>&1) | cut -f 2 -d " " )
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.raw.txt
+    touch ${prefix}.html
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        haplocheck: \$(echo \$(haplocheck --version 2>&1) | cut -f 2 -d " " )
+    END_VERSIONS
+    """
+}

modules/haplocheck/meta.yml

@@ -0,0 +1,55 @@
+name: "haplocheck"
+description: |
+  Haplocheck detects contamination patterns in mtDNA AND WGS sequencing studies by analyzing
+  the mitochondrial DNA. Haplocheck also works as a proxy tool for nDNA studies and provides
+  users a graphical report to investigate the contamination further. Internally, it uses the
+  Haplogrep tool, that supports rCRS and RSRS mitochondrial versions.
+keywords:
+  - mitochondrial
+  - mtDNA
+  - contamination
+tools:
+  - "haplocheck":
+      description: "Detects in-sample contamination in mtDNA or WGS sequencing studies by analyzing the mitochondrial content."
+      homepage: "https://github.com/genepi/haplocheck"
+      documentation: "https://github.com/genepi/haplocheck"
+      tool_dev_url: "https://github.com/genepi/haplocheck"
+      doi: 10.1101/gr.256545.119
+      licence: "['MIT']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+
+  - vcf:
+      type: file
+      description: VCF file
+      pattern: "*.{vcf.gz}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+  - txt:
+      type: file
+      description: Raw report in txt format
+      pattern: "*.{txt}"
+
+  - html:
+      type: file
+      description: Haplocheck HTML report
+      pattern: "*.{html}"
+
+authors:
+  - "@lmtani"

tests/config/pytest_modules.yml

@@ -967,6 +967,10 @@ hamronization/summarize:
   - modules/hamronization/summarize/**
   - tests/modules/hamronization/summarize/**
 
+haplocheck:
+  - modules/haplocheck/**
+  - tests/modules/haplocheck/**
+
 happy/happy:
   - modules/happy/happy/**
   - tests/modules/happy/happy/**

tests/config/test_data.config

@@ -329,6 +329,8 @@ params {
                 test_rnaseq_vcf                               =  "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/test.rnaseq.vcf"
                 test_sv_vcf                                   =  "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/sv_query.vcf.gz"
 
+                test_mito_vcf                                 = "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/NA12878_chrM.vcf.gz"
+
                 test_pytor                                    = "${test_data_dir}/genomics/homo_sapiens/illumina/pytor/test.pytor"
 
                 test_flowcell                                 = "${test_data_dir}/genomics/homo_sapiens/illumina/bcl/flowcell.tar.gz"

tests/modules/haplocheck/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { HAPLOCHECK } from '../../../modules/haplocheck/main.nf'
+
+workflow test_haplocheck {
+
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_mito_vcf'], checkIfExists: true)
+    ]
+
+    HAPLOCHECK ( input )
+}

tests/modules/haplocheck/nextflow.config

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

tests/modules/haplocheck/test.yml

@@ -0,0 +1,20 @@
+- name: haplocheck test_haplocheck
+  command: nextflow run ./tests/modules/haplocheck -entry test_haplocheck -c ./tests/config/nextflow.config -c ./tests/modules/haplocheck/nextflow.config
+  tags:
+    - haplocheck
+  files:
+    - path: output/haplocheck/test.html
+      md5sum: 59d69052c86edff0301816956eaf4d5f
+    - path: output/haplocheck/test.raw.txt
+      md5sum: 69f4e5b28a59b97fc19eb8e8b650d9d5
+    - path: output/haplocheck/versions.yml
+      md5sum: 94e2fa3ceb3946487319f92cea08c942
+
+- name: haplocheck test_haplocheck using stubs
+  command: nextflow run ./tests/modules/haplocheck -entry test_haplocheck -c ./tests/config/nextflow.config -c ./tests/modules/haplocheck/nextflow.config -stub-run
+  tags:
+    - haplocheck
+  files:
+    - path: output/haplocheck/test.html
+    - path: output/haplocheck/test.raw.txt
+    - path: output/haplocheck/versions.yml