New module: ichorCNA (#1182)

* hmmcopy/mapCounter

* update test

* Remove bam tag

* Remove /tmp/ path from test.yml

* Update modules/hmmcopy/mapcounter/meta.yml

Incorporate formatting changes

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* Update modules/hmmcopy/mapcounter/meta.yml

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* Update tests/modules/hmmcopy/mapcounter/main.nf

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* ichorCNA run

* Add panel of normals code

* Try and fix tests

* Edit string detection in tests

* Fix linting issues

* Just failing END_VERSIONS

* Fixed versions.yml

* Added DOI

* Optional name for file

* Add when command

* Updated when

* Update modules/ichorcna/createpon/main.nf

Co-authored-by: Simon Pearce <simon.pearce@cruk.manchester.ac.uk>
Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>
Co-authored-by: FriederikeHanssen <Friederike.hanssen@qbic.uni-tuebingen.de>

modules/ichorcna/createpon/main.nf

@@ -0,0 +1,48 @@
+def VERSION = '0.3.2' // Version information not provided by tool on CLI
+
+process ICHORCNA_CREATEPON {
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::r-ichorcna=0.3.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/r-ichorcna:0.3.2--r41hdfd78af_0' :
+        'quay.io/biocontainers/r-ichorcna:0.3.2--r41hdfd78af_0' }"
+
+    input:
+    path wigs
+    path gc_wig
+    path map_wig
+    path centromere
+
+    output:
+    path "*.rds"        , emit: rds
+    path "*.txt"        , emit: txt
+    path "versions.yml" , emit: versions
+
+    when:
+        task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def centro = centromere ? "--centromere ${centromere}" : ''
+    def prefix = task.ext.prefix ?: "PoN"
+
+    """
+    echo ${wigs} | tr " " "\\n" > wig_files.txt
+
+    createPanelOfNormals.R \\
+        --filelist wig_files.txt \\
+        --gcWig ${gc_wig} \\
+        --mapWig ${map_wig} \\
+        ${centro} \\
+        ${args} \\
+        --outfile ${prefix}
+
+    rm wig_files.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        ichorcna: $VERSION
+    END_VERSIONS
+    """
+}

modules/ichorcna/createpon/meta.yml

@@ -0,0 +1,57 @@
+name: ichorcna_createpon
+description: ichorCNA is an R package for calculating copy number alteration from (low-pass) whole genome sequencing, particularly for use in cell-free DNA. This module generates a panel of normals
+keywords:
+  - ichorcna
+  - cnv
+  - cna
+  - cfDNA
+  - wgs
+  - panel_of_normals
+tools:
+  - ichorcna:
+      description: Estimating tumor fraction in cell-free DNA from ultra-low-pass whole genome sequencing.
+      homepage: https://github.com/broadinstitute/ichorCNA
+      documentation: https://github.com/broadinstitute/ichorCNA/wiki
+      tool_dev_url: https://github.com/broadinstitute/ichorCNA
+      doi: "10.1038/s41467-017-00965-y"
+      licence: ['GPL v3']
+
+input:
+  - wigs:
+      type: file
+      description: Any number of hmmcopy/readCounter processed .wig files giving the number of reads in the sample, in each genomic window. These will be averaged over to generate the panel of normals.
+      pattern: "*.{wig}"
+
+  - gc_wig:
+      type: file
+      description: hmmcopy/gcCounter processed .wig file giving the gc content in the reference fasta, in each genomic window
+      pattern: "*.{wig}"
+
+  - map_wig:
+      type: file
+      description: hmmcopy/mapCounter processed .wig file giving the mapability in the reference fasta, in each genomic window
+      pattern: "*.{wig}"
+
+  - centromere:
+      type: file
+      description: Text file giving centromere locations of each genome, to exclude these windows
+      pattern: "*.{txt}"
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+  - rds:
+      type: file
+      description: R data file (.rds) containing panel of normals data, medians of each bin.
+      pattern: "*.rds"
+
+  - txt:
+      type: file
+      description: Text file containing panel of normals data, medians of each bin.
+      pattern: "*.txt"
+
+authors:
+  - "@sppearce"

modules/ichorcna/run/main.nf

@@ -0,0 +1,50 @@
+def VERSION = '0.3.2' // Version information not provided by tool on CLI
+
+process ICHORCNA_RUN {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::r-ichorcna=0.3.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/r-ichorcna:0.3.2--r41hdfd78af_0' :
+        'quay.io/biocontainers/r-ichorcna:0.3.2--r41hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(wig)
+    path gc_wig
+    path map_wig
+    path panel_of_normals
+    path centromere
+
+    output:
+    tuple val(meta), path("*.cna.seg")    , emit: cna_seg
+    tuple val(meta), path("*.params.txt") , emit: ichorcna_params
+    path "**/*genomeWide.pdf"             , emit: genome_plot
+    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 pon = panel_of_normals ? "--normalPanel ${panel_of_normals}" : ''
+    def centro = centromere ? "--centromere ${centromere}" : ''
+
+    """
+    runIchorCNA.R --id ${prefix} \\
+        $args \\
+        --WIG ${wig} \\
+        --id ${meta.id} \\
+        --gcWig ${gc_wig} \\
+        --mapWig ${map_wig} \\
+        ${pon} \\
+        ${centro} \\
+        --outDir .
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        ichorcna: $VERSION
+    END_VERSIONS
+    """
+}

modules/ichorcna/run/meta.yml

@@ -0,0 +1,72 @@
+name: ichorcna_run
+description: ichorCNA is an R package for calculating copy number alteration from (low-pass) whole genome sequencing, particularly for use in cell-free DNA
+keywords:
+  - ichorcna
+  - cnv
+  - cna
+  - cfDNA
+  - wgs
+tools:
+  - ichorcna:
+      description: Estimating tumor fraction in cell-free DNA from ultra-low-pass whole genome sequencing.
+      homepage: https://github.com/broadinstitute/ichorCNA
+      documentation: https://github.com/broadinstitute/ichorCNA/wiki
+      tool_dev_url: https://github.com/broadinstitute/ichorCNA
+      doi: "10.1038/s41467-017-00965-y"
+      licence: ['GPL v3']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test']
+  - wig:
+      type: file
+      description: hmmcopy/readCounter processed .wig file giving the number of reads in the sample, in each genomic window
+      pattern: "*.{wig}"
+
+  - gc_wig:
+      type: file
+      description: hmmcopy/gcCounter processed .wig file giving the gc content in the reference fasta, in each genomic window
+      pattern: "*.{wig}"
+
+  - map_wig:
+      type: file
+      description: hmmcopy/mapCounter processed .wig file giving the mapability in the reference fasta, in each genomic window
+      pattern: "*.{wig}"
+
+  - panel_of_normals:
+      type: file
+      description: Panel of normals data, generated by calling ichorCNA on a set of normal samples with the same window size etc.
+      pattern: "*.{rds}"
+
+  - centromere:
+      type: file
+      description: Text file giving centromere locations of each genome, to exclude these windows
+      pattern: "*.{txt}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test']
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - cna_seg:
+      type: file
+      description: Predicted copy number variation per segment
+      pattern: "*.{cng.seg}"
+  - ichorcna_params:
+      type: file
+      description: A text file showing the values that ichorCNA has estimated for tumour fraction, ploidy etc
+      pattern: "*.{params.txt}"
+  - genome_plot:
+      type: file
+      description: A plot with the best-fit genome-wide CNV data
+      pattern: "*.{genomeWide.pdf}"
+authors:
+  - "@sppearce"

tests/config/pytest_modules.yml

@@ -755,6 +755,14 @@ homer/makeucscfile:
   - modules/homer/makeucscfile/**
   - tests/modules/homer/makeucscfile/**
 
+ichorcna/createpon:
+  - modules/ichorcna/createpon/**
+  - tests/modules/ichorcna/createpon/**
+
+ichorcna/run:
+  - modules/ichorcna/run/**
+  - tests/modules/ichorcna/run/**
+
 idr:
   - modules/idr/**
   - tests/modules/idr/**

tests/modules/ichorcna/createpon/main.nf

@@ -0,0 +1,30 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { ICHORCNA_CREATEPON } from '../../../../modules/ichorcna/createpon/main.nf'
+
+workflow test_ichorcna_createpon {
+
+    input = file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/MBC_315.ctDNA.reads.wig", checkIfExists: true)
+
+    gcwig   = file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/gc_hg19_1000kb.wig", checkIfExists: true)
+    mapwig  = file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/map_hg19_1000kb.wig", checkIfExists: true)
+
+    centromere = file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/GRCh37.p13_centromere_UCSC-gapTable.txt", checkIfExists: true)
+
+    ICHORCNA_CREATEPON ( input, gcwig, mapwig, centromere )
+}
+
+workflow test_ichorcna_createpon2 {
+
+    input = [file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/MBC_315.ctDNA.reads.wig", checkIfExists: true),
+             file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/MBC_315_T2.ctDNA.reads.wig", checkIfExists: true)]
+
+    gcwig   = file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/gc_hg19_1000kb.wig", checkIfExists: true)
+    mapwig  = file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/map_hg19_1000kb.wig", checkIfExists: true)
+
+    centromere = file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/GRCh37.p13_centromere_UCSC-gapTable.txt", checkIfExists: true)
+
+    ICHORCNA_CREATEPON ( input, gcwig, mapwig, centromere )
+}

tests/modules/ichorcna/createpon/nextflow.config

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

tests/modules/ichorcna/createpon/test.yml

@@ -0,0 +1,21 @@
+- name: ichorcna createpon test_ichorcna_createpon
+  command: nextflow run tests/modules/ichorcna/createpon -entry test_ichorcna_createpon -c tests/config/nextflow.config
+  tags:
+    - ichorcna/createpon
+    - ichorcna
+  files:
+    - path: output/ichorcna/PoN_median.txt
+      contains: ['seqnames']
+    - path: output/ichorcna/versions.yml
+      md5sum: 59a2121301113cc013bfae65935e07f1
+
+- name: ichorcna createpon test_ichorcna_createpon2
+  command: nextflow run tests/modules/ichorcna/createpon -entry test_ichorcna_createpon2 -c tests/config/nextflow.config
+  tags:
+    - ichorcna/createpon
+    - ichorcna
+  files:
+    - path: output/ichorcna/PoN_median.txt
+      contains: ['seqnames']
+    - path: output/ichorcna/versions.yml
+      md5sum: 31a5fcc0075dbe747f7736efbdb99644

tests/modules/ichorcna/run/main.nf

@@ -0,0 +1,40 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { ICHORCNA_RUN } from '../../../../modules/ichorcna/run/main.nf'
+include { HMMCOPY_READCOUNTER } from '../../../../modules/hmmcopy/readcounter/main.nf'
+include { HMMCOPY_GCCOUNTER } from '../../../../modules/hmmcopy/gccounter/main.nf'
+include { HMMCOPY_MAPCOUNTER } from '../../../../modules/hmmcopy/mapcounter/main.nf'
+include { HMMCOPY_GENERATEMAP } from '../../../../modules/hmmcopy/generatemap/main.nf'
+
+workflow test_ichorcna_run_no_panel {
+
+    input = [ [ id:'test'], // meta map
+              file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/MBC_315.ctDNA.reads.wig", checkIfExists: true)
+            ]
+
+    gcwig   = file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/gc_hg19_1000kb.wig", checkIfExists: true)
+    mapwig  = file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/map_hg19_1000kb.wig", checkIfExists: true)
+
+    panel_of_normals = []
+    centromere = []
+
+    ICHORCNA_RUN ( input, gcwig, mapwig, panel_of_normals, centromere)
+}
+
+workflow test_ichorcna_run_inc_panel {
+
+    input = [ [ id:'test'], // meta map
+              file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/MBC_315.ctDNA.reads.wig", checkIfExists: true)
+            ]
+
+    gcwig   = file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/gc_hg19_1000kb.wig", checkIfExists: true)
+    mapwig  = file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/map_hg19_1000kb.wig", checkIfExists: true)
+
+    panel_of_normals = file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/HD_ULP_PoN_1Mb_median_normAutosome_mapScoreFiltered_median.rds", checkIfExists: true)
+
+    centromere = file("https://raw.githubusercontent.com/broadinstitute/ichorCNA/master/inst/extdata/GRCh37.p13_centromere_UCSC-gapTable.txt", checkIfExists: true)
+
+    ICHORCNA_RUN ( input, gcwig, mapwig, panel_of_normals, centromere)
+}

tests/modules/ichorcna/run/nextflow.config

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

tests/modules/ichorcna/run/test.yml

@@ -0,0 +1,25 @@
+- name: ichorcna run test_ichorcna_run_no_panel
+  command: nextflow run tests/modules/ichorcna/run -entry test_ichorcna_run_no_panel -c tests/config/nextflow.config
+  tags:
+    - ichorcna
+    - ichorcna/run
+  files:
+    - path: output/ichorcna/test.cna.seg
+      contains: ['Corrected_Copy_Number']
+    - path: output/ichorcna/test.params.txt
+      md5sum: e39a579cdcc9576679f06dc5c22605a7
+    - path: output/ichorcna/versions.yml
+      md5sum: effb37e19bec3609417aaccad4b6a294
+
+- name: ichorcna run test_ichorcna_run_inc_panel
+  command: nextflow run tests/modules/ichorcna/run -entry test_ichorcna_run_inc_panel -c tests/config/nextflow.config
+  tags:
+    - ichorcna
+    - ichorcna/run
+  files:
+    - path: output/ichorcna/test.cna.seg
+      contains: ['Corrected_Copy_Number']
+    - path: output/ichorcna/test.params.txt
+      md5sum: 0b97e0269cd0b571f5a85890f6ddb181
+    - path: output/ichorcna/versions.yml
+      md5sum: fc9d96de0a1c15cea59208305b14e535