Cnvpytor (#1297)

* Added cnvpytor/importreaddepth module

* Corrected process name in meta.yml file

* added -chrom argument

* space correction

* Added complementary info

* fixed typo

* md5sum added

* modified the module to work on cram files as well

* Added cnvpytor/histogram module and test files

* Added cnvpytor/partition module and test files

* added cnvpytor/callcnvs module and tests

* modified by new modules

* Added test file and fixed input path in modules

* added when block

* little fixes

* skip tracking test.yml

* removed changes to test if conflicts get resolved

* updated outfile name

* corrected the version.yml content

modules/cnvpytor/callcnvs/main.nf

@@ -0,0 +1,33 @@
+process CNVPYTOR_CALLCNVS {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::cnvpytor=1.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/cnvpytor:A1.0--py39h6a678da_2':
+        'quay.io/biocontainers/cnvpytor:1.0--py39h6a678da_2' }"
+
+    input:
+    tuple val(meta), path(pytor)
+
+    output:
+    tuple val(meta), path("*.tsv"), emit: cnvs
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: '1000'
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    cnvpytor \\
+        -root $pytor \\
+        -call $args > ${prefix}.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/^.*pyCNVnator //; s/Using.*\$//' ))
+    END_VERSIONS
+    """
+}

modules/cnvpytor/callcnvs/meta.yml

@@ -0,0 +1,40 @@
+name: cnvpytor_callcnvs
+description: command line tool for calling CNVs in whole genome sequencing data
+  - CNV calling
+tools:
+  - cnvpytor:
+      description: calling CNVs using read depth
+      homepage: https://github.com/abyzovlab/CNVpytor
+      documentation: https://github.com/abyzovlab/CNVpytor
+      tool_dev_url: https://github.com/abyzovlab/CNVpytor
+      doi: "10.1101/2021.01.27.428472v1"
+      licence: ['MIT']
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test']
+  - pytor:
+      type: file
+      description: cnvpytor root file
+      pattern: "*.{pytor}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - cnvs:
+      type: file
+      description: file containing identified copy numer variations
+      pattern: "*.{tsv}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+
+authors:
+  - "@sima-r"

modules/cnvpytor/histogram/main.nf

@@ -0,0 +1,32 @@
+process CNVPYTOR_HISTOGRAM {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::cnvpytor=1.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/cnvpytor:A1.0--py39h6a678da_2':
+        'quay.io/biocontainers/cnvpytor:1.0--py39h6a678da_2' }"
+
+    input:
+    tuple val(meta), path(pytor)
+
+    output:
+    tuple val(meta), path("${pytor.baseName}.pytor")	, emit: pytor
+    path "versions.yml"                                 , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: '1000'
+    """
+    cnvpytor \\
+        -root $pytor \\
+        -his $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/^.*pyCNVnator //; s/Using.*\$//' ))
+    END_VERSIONS
+    """
+}

modules/cnvpytor/histogram/meta.yml

@@ -0,0 +1,42 @@
+name: cnvpytor_histogram
+description: calculates read depth histograms
+keywords:
+  - cnv calling
+  - histogram
+tools:
+  - cnvpytor:
+      description: calling CNVs using read depth
+      homepage: https://github.com/abyzovlab/CNVpytor
+      documentation: https://github.com/abyzovlab/CNVpytor
+      tool_dev_url: https://github.com/abyzovlab/CNVpytor
+      doi: "10.1101/2021.01.27.428472v1"
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - pytor:
+      type: file
+      description: pytor file containing read depth data
+      pattern: "*.{pytor}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - pytor:
+      type: file
+      description: pytor file containing read depth histograms binned based on given bin size(s)
+      pattern: "*.{pytor}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@sima-r"

modules/cnvpytor/importreaddepth/main.nf

@@ -0,0 +1,38 @@
+process CNVPYTOR_IMPORTREADDEPTH {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::cnvpytor=1.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/cnvpytor:A1.0--py39h6a678da_2':
+        'quay.io/biocontainers/cnvpytor:1.0--py39h6a678da_2' }"
+
+    input:
+    tuple val(meta), path(input_file), path(index)
+    path fasta
+    path fai
+
+    output:
+    tuple val(meta), path("*.pytor")	, emit: pytor
+    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 reference = fasta ? "-T ${fasta}" : ''
+    """
+    cnvpytor \\
+        -root ${prefix}.pytor \\
+        -rd $input_file \\
+        $args \\
+        $reference
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/^.*pyCNVnator //; s/Using.*\$//' ))
+    END_VERSIONS
+    """
+}

modules/cnvpytor/importreaddepth/meta.yml

@@ -0,0 +1,55 @@
+name: cnvpytor_importreaddepth
+description: command line tool for CNV/CNA analysis. This step imports the read depth data into a root pytor file.
+keywords:
+  - read depth
+  - cnv calling
+tools:
+  - cnvpytor -rd:
+      description: calling CNVs using read depth
+      homepage: https://github.com/abyzovlab/CNVpytor
+      documentation: https://github.com/abyzovlab/CNVpytor
+      tool_dev_url: https://github.com/abyzovlab/CNVpytor
+      doi: "10.1101/2021.01.27.428472v1"
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - input_file:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram}"
+  - index:
+      type: file
+      description: bam file index
+      pattern: "*.{bai,crai}"
+  - fasta:
+      type: file
+      description: specifies reference genome file (only for cram file without reference genome)
+      pattern: "*.{fasta,fasta.gz,fa,fa.gz}"
+  - fai:
+    type: file
+    description: Index of reference fasta file
+    pattern: "*.fai"
+
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - pytor:
+      type: file
+      description: read depth root file in which read depth data binned to 100 base pair bins will be stored.
+      pattern: "*.{pytor}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@sima-r"

modules/cnvpytor/partition/main.nf

@@ -0,0 +1,32 @@
+process CNVPYTOR_PARTITION {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::cnvpytor=1.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/cnvpytor:A1.0--py39h6a678da_2':
+        'quay.io/biocontainers/cnvpytor:1.0--py39h6a678da_2' }"
+
+    input:
+    tuple val(meta), path(pytor)
+
+    output:
+    tuple val(meta), path("${pytor.baseName}.pytor"), emit: pytor
+    path "versions.yml"                             , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: '1000'
+    """
+    cnvpytor \\
+        -root $pytor \\
+        -partition $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/^.*pyCNVnator //; s/Using.*\$//' ))
+    END_VERSIONS
+    """
+}

modules/cnvpytor/partition/meta.yml

@@ -0,0 +1,42 @@
+name: cnvpytor_partition
+description: partitioning read depth histograms
+keywords:
+  - cnv calling
+  - partition histograms
+tools:
+  - cnvpytor:
+      description: calling CNVs using read depth
+      homepage: https://github.com/abyzovlab/CNVpytor
+      documentation: https://github.com/abyzovlab/CNVpytor
+      tool_dev_url: https://github.com/abyzovlab/CNVpytor
+      doi: "10.1101/2021.01.27.428472v1"
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - pytor:
+      type: file
+      description: pytor file containing read depth data
+      pattern: "*.{pytor}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - partitions:
+      type: file
+      description: pytor file containing partitions of read depth histograms using mean-shift method
+      pattern: "*.{pytor}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@sima-r"

tests/config/test_data.config

@@ -295,6 +295,8 @@ 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_pytor                                    = "${test_data_dir}/genomics/homo_sapiens/illumina/pytor/test.pytor"
             }
             'pacbio' {
                 primers                                       = "${test_data_dir}/genomics/homo_sapiens/pacbio/fasta/primers.fasta"

tests/modules/cnvpytor/callcnvs/main.nf

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

tests/modules/cnvpytor/callcnvs/nextflow.config

@@ -0,0 +1,7 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    withName: CNVPYTOR_CALLCNVS {
+        ext.args = '10000'
+    }
+}

tests/modules/cnvpytor/callcnvs/test.yml

@@ -0,0 +1,10 @@
+- name: cnvpytor callcnvs test_cnvpytor_callcnvs
+  command: nextflow run tests/modules/cnvpytor/callcnvs -entry test_cnvpytor_callcnvs -c tests/config/nextflow.config
+  tags:
+    - cnvpytor
+    - cnvpytor/callcnvs
+  files:
+    - path: output/cnvpytor/calls.10000.tsv
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/cnvpytor/versions.yml
+      md5sum: 5fe6ca3ef5c40f9dbf487f28db237821

tests/modules/cnvpytor/histogram/main.nf

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

tests/modules/cnvpytor/histogram/nextflow.config

@@ -0,0 +1,7 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    withName: CNVPYTOR_HISTOGRAM {
+        ext.args = '10000 100000'
+    }
+}

tests/modules/cnvpytor/histogram/test.yml

@@ -0,0 +1,10 @@
+- name: cnvpytor histogram test_cnvpytor_histogram
+  command: nextflow run tests/modules/cnvpytor/histogram -entry test_cnvpytor_histogram -c tests/config/nextflow.config
+  tags:
+    - cnvpytor
+    - cnvpytor/histogram
+  files:
+    - path: output/cnvpytor/test.pytor
+      md5sum: aa03a8fa15b39f77816705a48e10312a
+    - path: output/cnvpytor/versions.yml
+      md5sum: 9a4b176afd5f1a3edeb37eeb301cf464

tests/modules/cnvpytor/importreaddepth/main.nf

@@ -0,0 +1,32 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CNVPYTOR_IMPORTREADDEPTH } from '../../../../modules/cnvpytor/importreaddepth/main.nf'
+
+
+workflow test_cnvpytor_importreaddepth {
+
+    input = [
+        [ id: 'test' ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam_bai'], checkIfExists: true)
+    ]
+
+    CNVPYTOR_IMPORTREADDEPTH (input, [], [])
+}
+
+workflow test_cnvpytor_importreaddepth_cram {
+
+    input = [
+        [ id: 'test' ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram_crai'], checkIfExists: true)
+    ]
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+
+    fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+
+    CNVPYTOR_IMPORTREADDEPTH (input, fasta, fai)
+}

tests/modules/cnvpytor/importreaddepth/nextflow.config

@@ -0,0 +1,12 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: CNVPYTOR_IMPORTREADDEPTH {
+        ext.args = {params.cnvpytor_chr ? "-chrom ${params.cnvpytor_chr}" : '' }
+            }
+}
+
+params {
+    cnvpytor_chr = '' // specifies chromosome name(s) the same way as they are described in the sam/bam/cram header e.g. '1 2' or 'chr1 chr2'.
+    }

tests/modules/cnvpytor/partition/main.nf

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

tests/modules/cnvpytor/partition/nextflow.config

@@ -0,0 +1,7 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    withName: CNVPYTOR_PARTITION {
+        ext.args = '10000 100000'
+    }
+}

tests/modules/cnvpytor/partition/test.yml

@@ -0,0 +1,10 @@
+- name: cnvpytor partition test_cnvpytor_partition
+  command: nextflow run tests/modules/cnvpytor/partition -entry test_cnvpytor_partition -c tests/config/nextflow.config
+  tags:
+    - cnvpytor
+    - cnvpytor/partition
+  files:
+    - path: output/cnvpytor/test.pytor
+      md5sum: aa03a8fa15b39f77816705a48e10312a
+    - path: output/cnvpytor/versions.yml
+      md5sum: 8a04506554c58cd170cc050fd9904c6f