New module: NGSCheckMate (#1290)

NGSCheckMate ncm mode, working on bam files and vcf files to check that (human) samples match as expected 

Co-authored-by: Simon Pearce <simon.pearce@cruk.manchester.ac.uk>
Co-authored-by: Mahesh Binzer-Panchal <mahesh.binzer-panchal@nbis.se>

modules/ngscheckmate/ncm/main.nf

@@ -0,0 +1,49 @@
+process NGSCHECKMATE_NCM {
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::ngscheckmate=1.0.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/ngscheckmate:1.0.0--py27r41hdfd78af_3':
+        'quay.io/biocontainers/ngscheckmate:1.0.0--py27r41hdfd78af_3' }"
+
+    input:
+    path files
+    path snp_bed
+    path fasta
+
+    output:
+    path "*.pdf"            , emit: pdf
+    path "*_corr_matrix.txt", emit: corr_matrix
+    path "*_matched.txt"    , emit: matched
+    path "*_all.txt"        , emit: all
+    path "*.vcf"            , emit: vcfs, optional: true
+    path "versions.yml"     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "output"
+    def unzip = files.any { it.toString().endsWith(".vcf.gz") }
+    """
+    if $unzip
+    then
+        for VCFGZ in *.vcf.gz; do
+            gunzip -cdf \$VCFGZ > \$( basename \$VCFGZ .gz );
+        done
+    fi
+
+    NCM_REF="./"${fasta} ncm.py -d . -bed ${snp_bed} -O . -N ${prefix} $args
+
+    if $unzip
+    then
+        rm -f *.vcf  # clean up decompressed vcfs
+    fi
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        ngscheckmate: \$(ncm.py --help | sed "7!d;s/ *Ensuring Sample Identity v//g")
+    END_VERSIONS
+    """
+}

modules/ngscheckmate/ncm/meta.yml

@@ -0,0 +1,64 @@
+name: ngscheckmate_ncm
+description: Determining whether sequencing data comes from the same individual by using SNP matching. Designed for humans on vcf or bam files.
+keywords:
+  - ngscheckmate
+  - matching
+  - snp
+tools:
+  - ngscheckmate:
+      description: NGSCheckMate is a software package for identifying next generation sequencing (NGS) data files from the same individual, including matching between DNA and RNA.
+      homepage: https://github.com/parklab/NGSCheckMate
+      documentation: https://github.com/parklab/NGSCheckMate
+      tool_dev_url: https://github.com/parklab/NGSCheckMate
+      doi: "doi:/10.1093/nar/gkx193"
+      licence: ['MIT']
+
+input:
+  - files:
+      type: file
+      description: VCF or BAM files for each sample, in a merged channel (possibly gzipped). BAM files require an index too.
+      pattern: "*.{vcf,vcf.gz,bam,bai}"
+
+  - snp_bed:
+      type: file
+      description: BED file containing the SNPs to analyse
+      pattern: "*.{bed}"
+
+  - fasta:
+      type: file
+      description: fasta file for the genome, only used in the bam mode
+      pattern: "*.{bed}"
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+  - pdf:
+      type: file
+      description: A pdf containing a dendrogram showing how the samples match up
+      pattern: "*.{pdf}"
+
+  - corr_matrix:
+      type: file
+      description: A text file containing the correlation matrix between each sample
+      pattern: "*corr_matrix.txt"
+
+  - matched:
+      type: file
+      description: A txt file containing only the samples that match with each other
+      pattern: "*matched.txt"
+
+  - all:
+      type: file
+      description: A txt file containing all the sample comparisons, whether they match or not
+      pattern: "*all.txt"
+
+  - vcfs:
+      type: file
+      description: If ran in bam mode, vcf files for each sample giving the SNP calls
+      pattern: "*.vcf"
+
+authors:
+  - "@sppearce"

tests/config/pytest_modules.yml

@@ -1145,6 +1145,10 @@ ngmaster:
   - modules/ngmaster/**
   - tests/modules/ngmaster/**
 
+ngscheckmate/ncm:
+  - modules/ngscheckmate/ncm/**
+  - tests/modules/ngscheckmate/ncm/**
+
 nucmer:
   - modules/nucmer/**
   - tests/modules/nucmer/**

tests/modules/ngscheckmate/ncm/main.nf

@@ -0,0 +1,63 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { NGSCHECKMATE_NCM as NGSCHECKMATE_NCM_BAM} from '../../../../modules/ngscheckmate/ncm/main.nf'
+include { NGSCHECKMATE_NCM as NGSCHECKMATE_NCM_VCF} from '../../../../modules/ngscheckmate/ncm/main.nf'
+
+include { BEDTOOLS_MAKEWINDOWS } from '../../../../modules/bedtools/makewindows/main.nf'
+
+include { BCFTOOLS_MPILEUP } from '../../../../modules/bcftools/mpileup/main.nf'
+include { BCFTOOLS_MPILEUP as BCFTOOLS_MPILEUP2 } from '../../../../modules/bcftools/mpileup/main.nf'
+
+workflow test_ngscheckmate_ncm_bam {
+    input    = [ file(params.test_data['sarscov2']['illumina']['test_paired_end_methylated_sorted_bam'], checkIfExists: true),
+                 file(params.test_data['sarscov2']['illumina']['test_paired_end_methylated_sorted_bam_bai'], checkIfExists: true),
+                 file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                 file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true)]
+
+    fasta    = [ file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ]
+
+    inputBed = [ [ id:'test'],
+                 file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true)]
+
+    BEDTOOLS_MAKEWINDOWS(inputBed, true).
+    tab.
+    map{it[1]}.
+    view().
+    set{snp_channel}
+
+    NGSCHECKMATE_NCM_BAM(input, snp_channel, fasta)
+}
+
+workflow test_ngscheckmate_ncm_vcf {
+    input1   = [ [ id:'test1' ], // meta map
+                 [ file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) ]
+               ]
+
+    input2   = [ [ id:'test2' ], // meta map
+                 [ file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) ]
+               ]
+
+    fasta    = [ file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ]
+
+    inputBed = [ [ id:'test'],
+                 file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true)]
+
+    BCFTOOLS_MPILEUP ( input1, fasta, false )
+    BCFTOOLS_MPILEUP2 ( input2, fasta, false )
+
+    BCFTOOLS_MPILEUP2.out.vcf.
+        combine( BCFTOOLS_MPILEUP.out.vcf ).
+        map { [ it[1], it[3] ] }.
+        set { vcf_channel }
+
+    BEDTOOLS_MAKEWINDOWS( inputBed, true ).tab.
+        map { it[1] }.
+        view().
+        set { snp_channel }
+
+    NGSCHECKMATE_NCM_VCF(vcf_channel, snp_channel, fasta)
+}
+
+

tests/modules/ngscheckmate/ncm/nextflow.config

@@ -0,0 +1,27 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: BEDTOOLS_MAKEWINDOWS {
+        ext.args = '-w 1'
+    }
+
+    withName: BCFTOOLS_MPILEUP {
+        ext.args2 = '--no-version --ploidy 1 --multiallelic-caller'
+        ext.args3 = '--no-version'
+    }
+
+    withName: BCFTOOLS_MPILEUP2 {
+        ext.args2 = '--no-version --ploidy 1 --multiallelic-caller'
+        ext.args3 = '--no-version'
+    }
+
+    withName: NGSCHECKMATE_NCM_VCF {
+        ext.args = '-V'
+    }
+
+    withName: NGSCHECKMATE_NCM_BAM {
+        ext.args = '-B'
+    }
+
+}

tests/modules/ngscheckmate/ncm/test.yml

@@ -0,0 +1,29 @@
+- name: ngscheckmate ncm test_ngscheckmate_ncm_bam
+  command: nextflow run tests/modules/ngscheckmate/ncm -entry test_ngscheckmate_ncm_bam -c tests/config/nextflow.config
+  tags:
+    - ngscheckmate/ncm
+    - ngscheckmate
+  files:
+    - path: output/ngscheckmate/output_all.txt
+      md5sum: f71a712c3f6ecf64dd526365212f1b7c
+    - path: output/ngscheckmate/output_corr_matrix.txt
+      md5sum: 6777377aa9ae3d57f841b12896318db0
+    - path: output/ngscheckmate/output_matched.txt
+      md5sum: f71a712c3f6ecf64dd526365212f1b7c
+    - path: output/ngscheckmate/versions.yml
+      md5sum: fbb2bebd65b4f4e1e93c6bf5c08a6829
+
+- name: ngscheckmate ncm test_ngscheckmate_ncm_vcf
+  command: nextflow run tests/modules/ngscheckmate/ncm -entry test_ngscheckmate_ncm_vcf -c tests/config/nextflow.config
+  tags:
+    - ngscheckmate/ncm
+    - ngscheckmate
+  files:
+    - path: output/ngscheckmate/output_all.txt
+      md5sum: fd74956dcac279b6f58e82ea73e344f8
+    - path: output/ngscheckmate/output_corr_matrix.txt
+      md5sum: 0c86bdad2721c470fe6be119f291c8e5
+    - path: output/ngscheckmate/output_matched.txt
+      md5sum: fd74956dcac279b6f58e82ea73e344f8
+    - path: output/ngscheckmate/versions.yml
+      md5sum: f06910b83dde194a47870c553cefe193