cnvkit module (#173)

* Normal bam file added

* Normal bam.bai file added

* Tumour bam bai files added

* human dir added

* annotation dir added

* cnvkit dir added

* cnvkit dir added

* Update software/cnvkit/main.nf

Co-authored-by: Maxime Garcia <maxime.garcia@scilifelab.se>

* Update software/cnvkit/main.nf

Co-authored-by: Maxime Garcia <maxime.garcia@scilifelab.se>

* Update software/cnvkit/main.nf

Co-authored-by: Maxime Garcia <maxime.garcia@scilifelab.se>

* changed input filenames

* edited main.nf

* edited main.nf

* edited meta.nf

* edited test.yml

* filters.yml

* edited main

* edited main

* edited meta

* edited meta

* edited main

* removed unwanted lines

* edited the path to the main.nf

* removed function.nf

* added functions.nf

* deleted 2 workflows and craeted a common workflow

* deleted paths for 2 workflows and created paths for a common workflow

* Deleted annotation dir

* deleted params.modules

* Edited meta.with_normal

* deleted normal_280_sub_chr21.bam

* deleted normal_280_sub_chr21.bam.bai

* deleted tumour_278_sub_chr21.bam

* deleted tumour_278_sub_chr21.bam.bai

* Edited input and script parts

* Edited input part

* Added

* Edited args

* Edited script

* Edited input

* Changed annotation to annotationfile

* Changed description of the tool

* edited singularuty container

* edited input

* line 44 removed trailing whitespace

* Edited addParams

* Deleted pdf output

* Deleted pdf output

* edited the path to main.nf

* edited path to the main.nf

* Added docker image version

* Removed extra ../

* added md5sums

* added md5sums

* Update software/cnvkit/main.nf

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

* Update software/cnvkit/main.nf

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

* Edited the script

* Edited the input

* Edited main.nf

* Edited main.nf

* edited md5sum for reference.cnn

* removed human fasta

* removed human fasta.fai

* added GRCh38 fasta

* added GRCh38 fasta.fai

* added hg19 fasta.fai

* added hg19 fasta

* Edited fasta file name

* Edited bed file names and md5sums

* Edited md5sums

* edited the input and script section

* edited input section

* added targetfile

* changed the files

* changed the output files

* added bam files

* added bam files

* remove files

* added md5sums

* replace file

* added files

* edited tests/software/cnvkit files

* edited tests/software/cnvkit files

* edited authors list

* removed files

* added files

* added files

* added files

* added files

* added file

* added file

* added file

* added file

* edited files

* edited files

* edited files

* edited files

* edited files

* edited files

* added new module

* added new module

* edited files

* edited file

* edited file

* edited file

* removed files

Co-authored-by: kaurravneet4123 <kaurravneet4123@yahoo.com@users.noreply.github.com>
Co-authored-by: Maxime Garcia <maxime.garcia@scilifelab.se>
Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

software/cnvkit/functions.nf

@@ -0,0 +1,59 @@
+/*
+ * -----------------------------------------------------
+ *  Utility functions used in nf-core DSL2 module files
+ * -----------------------------------------------------
+ */
+
+/*
+ * Extract name of software tool from process name using $task.process
+ */
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+/*
+ * Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+ */
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args          = args.args ?: ''
+    options.args2         = args.args2 ?: ''
+    options.publish_by_id = args.publish_by_id ?: false
+    options.publish_dir   = args.publish_dir ?: ''
+    options.publish_files = args.publish_files
+    options.suffix        = args.suffix ?: ''
+    return options
+}
+
+/*
+ * Tidy up and join elements of a list to return a path string
+ */
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }  // Remove empty entries
+    paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+/*
+ * Function to save/publish module results
+ */
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_id) {
+            path_list.add(args.publish_id)
+        }
+        if (ioptions.publish_files instanceof Map) {
+            for (ext in ioptions.publish_files) {
+                if (args.filename.endsWith(ext.key)) {
+                    def ext_list = path_list.collect()
+                    ext_list.add(ext.value)
+                    return "${getPathFromList(ext_list)}/$args.filename"
+                }
+            }
+        } else if (ioptions.publish_files == null) {
+            return "${getPathFromList(path_list)}/$args.filename"
+        }
+    }
+}

software/cnvkit/main.nf

@@ -0,0 +1,46 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+def options    = initOptions(params.options)
+
+process CNVKIT {
+    tag "$meta.id"
+    label 'process_low'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }
+
+    conda (params.enable_conda ? "bioconda::cnvkit=0.9.8" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/cnvkit:0.9.8--py_0"
+    } else {
+        container "quay.io/biocontainers/cnvkit:0.9.8--py_0"
+    }
+
+    input:
+    tuple val(meta), path(tumourbam), path(normalbam)
+    path fasta
+    path targetfile
+
+    output:
+    tuple val(meta), path("*.bed"), emit: bed
+    tuple val(meta), path("*.cnn"), emit: cnn
+    tuple val(meta), path("*.cnr"), emit: cnr
+    tuple val(meta), path("*.cns"), emit: cns
+    path "*.version.txt"          , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}.${options.suffix}" : "${meta.id}"
+    """
+    cnvkit.py batch \\
+        $tumourbam \\
+        --normal $normalbam\\
+        --fasta $fasta \\
+        --targets $targetfile \\
+        $options.args
+
+    cnvkit.py version | sed -e "s/cnvkit v//g" > ${software}.version.txt
+    """
+}

software/cnvkit/meta.yml

@@ -0,0 +1,87 @@
+name: cnvkit
+description: Copy number variant detection from high-throughput sequencing data
+keywords:
+  - bam
+  - fasta
+  - copy number
+tools:
+  - cnvkit:
+      description: |
+        CNVkit is a Python library and command-line software toolkit to infer and visualize copy number from high-throughput DNA sequencing data. It is designed for use with hybrid capture, including both whole-exome and custom target panels, and short-read sequencing platforms such as Illumina and Ion Torrent.
+      homepage: https://cnvkit.readthedocs.io/en/stable/index.html
+      documentation: https://cnvkit.readthedocs.io/en/stable/index.html
+params:
+  - outdir:
+      type: string
+      description: |
+        The pipeline's output directory. By default, the module will
+        output files into `$params.outdir/<SOFTWARE>`
+  - publish_dir_mode:
+      type: string
+      description: |
+        Value for the Nextflow `publishDir` mode parameter.
+        Available: symlink, rellink, link, copy, copyNoFollow, move.
+  - enable_conda:
+      type: boolean
+      description: |
+        Run the module with Conda using the software specified
+        via the `conda` directive
+  - singularity_pull_docker_container:
+      type: boolean
+      description: |
+        Instead of directly downloading Singularity images for use with Singularity,
+        force the workflow to pull and convert Docker containers instead.
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - tumourbam:
+      type: file
+      description: |
+        Input tumour sample bam file
+  - normalbam:
+      type: file
+      description: |
+        Input normal sample bam file
+  - fasta:
+      type: file
+      description: |
+        Input reference genome fasta file
+  - targetfile:
+      type: file
+      description: |
+        Input target bed file
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bed:
+      type: file
+      description: File containing genomic regions
+      pattern: "*.{bed}"
+  - cnn:
+      type: file
+      description: File containing coverage information
+      pattern: "*.{cnn}"
+  - cnr:
+      type: file
+      description: File containing copy number ratio information
+      pattern: "*.{cnr}"
+  - cns:
+      type: file
+      description: File containing copy number segment information
+      pattern: "*.{cns}"
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+authors:
+    - "@kaurravneet4123"
+    - "@KevinMenden"
+    - "@MaxUlysse"
+    - "@drpatelh"
+

tests/config/nextflow.config

@@ -7,7 +7,7 @@ params {
 
 process {
   cpus = 2
-  memory = 6.GB
+  memory = 3.GB
   time = 48.h
 }
 

tests/config/pytest_software.yml

@@ -150,6 +150,10 @@ cat_fastq:
   - software/cat/fastq/**
   - tests/software/cat/fastq/**
 
+cnvkit:
+  - software/cnvkit/**
+  - tests/software/cnvkit/**
+
 cutadapt:
   - software/cutadapt/**
   - tests/software/cutadapt/**
@@ -339,6 +343,10 @@ seqkit_split2:
   - software/seqkit/split2/**
   - tests/software/seqkit/split2/**
 
+sequenza_wiggle:
+  - software/sequenza/wiggle/**
+  - tests/software/sequenza/wiggle/**
+
 seqwish_induce:
   - software/seqwish/induce/**
   - tests/software/seqwish/induce/**

tests/data/genomics/sarscov2/bed/baits.bed

@@ -0,0 +1,5 @@
+MT192765.1	1098	1127
+MT192765.1	4190	4255
+MT192765.1	5697	5716
+MT192765.1	5798	5807
+MT192765.1	11217	11253

tests/software/cnvkit/main.nf

@@ -0,0 +1,20 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CNVKIT } from '../../../software/cnvkit/main.nf' addParams( options: [ 'args': '--output-reference reference.cnn' ] )
+
+workflow test_cnvkit {
+    
+    tumourbam = [ file("${launchDir}/tests/data/genomics/sarscov2/bam/test_paired_end.sorted.bam", checkIfExists: true) ]
+    normalbam = [ file("${launchDir}/tests/data/genomics/sarscov2/bam/test_single_end.sorted.bam", checkIfExists: true) ]   
+    
+    def input = []
+    input = [ [ id:'test' ], // meta map
+              tumourbam, normalbam ]
+    
+    fasta = [ file("${launchDir}/tests/data/genomics/sarscov2/fasta/test_genome.fasta", checkIfExists: true) ]
+    targetfile = [ file("${launchDir}/tests/data/genomics/sarscov2/bed/baits.bed", checkIfExists: true) ]
+
+    CNVKIT ( input, fasta, targetfile )
+}

tests/software/cnvkit/test.yml

@@ -0,0 +1,27 @@
+- name: cnvkit
+  command: nextflow run ./tests/software/cnvkit/ -entry test_cnvkit -c tests/config/nextflow.config
+  tags:
+    - cnvkit
+  files:
+    - path: output/cnvkit/baits.target.bed
+      md5sum: 26d25ff2d6c45b6d92169b3559c6acdb  
+    - path: output/cnvkit/baits.antitarget.bed
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/cnvkit/reference.cnn
+      md5sum: ac99c1ad8b917b96ae15119146c91ab9
+    - path: output/cnvkit/test_paired_end.sorted.targetcoverage.cnn
+      md5sum: 3fe80b6013ffc3e9968345e810158215
+    - path: output/cnvkit/test_paired_end.sorted.antitargetcoverage.cnn
+      md5sum: 203caf8cef6935bb50b4138097955cb8
+    - path: output/cnvkit/test_single_end.sorted.targetcoverage.cnn
+      md5sum: aa8a018b1d4d1e688c9f9f6ae01bf4d7
+    - path: output/cnvkit/test_single_end.sorted.antitargetcoverage.cnn
+      md5sum: 203caf8cef6935bb50b4138097955cb8
+    - path: output/cnvkit/test_paired_end.sorted.cnr
+      md5sum: 7e37d73ab604dbc3fe4ebb56aca9bdc3
+    - path: output/cnvkit/test_paired_end.sorted.cns
+      md5sum: 060af1aa637ed51812af19bcce24fcfe   
+    - path: output/cnvkit/test_paired_end.sorted.bintest.cns
+      md5sum: 6544d979475def8a9f69ba42a985668d
+    - path: output/cnvkit/test_paired_end.sorted.call.cns
+      md5sum: f2ca59b4d50b0c317adc526c1b99b622