PR for sequenzautils/bam2seqz (#395)

* added files

* edited files

* removed file

* README.md edited

Co-authored-by: kaurravneet4123 <kaurravneet4123@yahoo.com@users.noreply.github.com>

README.md

@@ -540,4 +540,6 @@ nextflow run /path/to/pipeline/ -c /path/to/custom_module.conf
 > Note that the nf-core/tools helper package has a `download` command to download all required pipeline
 > files + singularity containers + institutional configs + modules in one go for you, to make this process easier.
 
+# New test data created for the module- sequenzautils/bam2seqz
+The new test data is an output from another module- sequenzautils/bcwiggle- (which uses sarscov2 genome fasta file as an input). 
 -->

software/sequenzautils/bam2seqz/functions.nf

@@ -0,0 +1,60 @@
+/*
+ * -----------------------------------------------------
+ *  Utility functions used in nf-core DSL2 module files
+ * -----------------------------------------------------
+ */
+
+/*
+ * Extract name of software tool from process name using $task.process
+ */
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+/*
+ * Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+ */
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args          = args.args ?: ''
+    options.args2         = args.args2 ?: ''
+    options.args3         = args.args3 ?: ''
+    options.publish_by_id = args.publish_by_id ?: false
+    options.publish_dir   = args.publish_dir ?: ''
+    options.publish_files = args.publish_files
+    options.suffix        = args.suffix ?: ''
+    return options
+}
+
+/*
+ * Tidy up and join elements of a list to return a path string
+ */
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }  // Remove empty entries
+    paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+/*
+ * Function to save/publish module results
+ */
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_id) {
+            path_list.add(args.publish_id)
+        }
+        if (ioptions.publish_files instanceof Map) {
+            for (ext in ioptions.publish_files) {
+                if (args.filename.endsWith(ext.key)) {
+                    def ext_list = path_list.collect()
+                    ext_list.add(ext.value)
+                    return "${getPathFromList(ext_list)}/$args.filename"
+                }
+            }
+        } else if (ioptions.publish_files == null) {
+            return "${getPathFromList(path_list)}/$args.filename"
+        }
+    }
+}

software/sequenzautils/bam2seqz/main.nf

@@ -0,0 +1,45 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process SEQUENZAUTILS_BAM2SEQZ {
+    tag "$meta.id"
+    label 'process_medium'
+    publishDir "${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::sequenza-utils=3.0.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/sequenza-utils:3.0.0--py38h6ed170a_2"
+    } else {
+        container "quay.io/biocontainers/sequenza-utils:3.0.0--py38h6ed170a_2"
+    }
+
+    input:
+    tuple val(meta), path(normalbam), path(tumourbam)
+    path fasta
+    path wigfile
+
+    output:
+    tuple val(meta), path("*.seqz.gz"), emit: seqz
+    path "*.version.txt"          , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    sequenza-utils \\
+        bam2seqz \\
+        $options.args \\
+        -n $normalbam \\
+        -t $tumourbam \\
+        --fasta $fasta \\
+        -gc $wigfile \\
+        -o ${prefix}.seqz.gz
+
+    echo \$(sequenzautils --version 2>&1) | sed 's/^.*sequenzautils //; s/Using.*\$//' > ${software}.version.txt
+    """
+}

software/sequenzautils/bam2seqz/meta.yml

@@ -0,0 +1,50 @@
+name: sequenzautils_bam2seqz
+description: Sequenza-utils bam2seqz process BAM and Wiggle files to produce a seqz file
+keywords:
+  - bam2seqz
+tools:
+  - sequenzautils:
+      description: Sequenza-utils provides 3 main command line programs to transform common NGS file format - such as FASTA, BAM - to input files for the Sequenza R package. The program - bam2seqz - process a paired set of BAM/pileup files (tumour and matching normal), and GC-content genome-wide information, to extract the common positions with A and B alleles frequencies.
+      homepage: https://sequenza-utils.readthedocs.io/en/latest/index.html
+      documentation: https://sequenza-utils.readthedocs.io/en/latest/index.html
+      doi: 10.1093/annonc/mdu479
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - normalbam:
+      type: file
+      description: BAM file from the reference/normal sample
+      pattern: "*.{bam}"
+  - tumourbam:
+      type: file
+      description: BAM file from the tumour sample
+      pattern: "*.{bam}"
+  - fasta:
+      type: file
+      description: Reference FASTA file
+      pattern: "*.{fasta}"
+  - wigfile:
+      type: file
+      description: GC content wiggle file
+      pattern: "*.{wig.gz}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+  - seqz:
+      type: file
+      description: Seqz file
+      pattern: "*.{seqz.gz}"
+
+authors:
+  - "@kaurravneet4123"

tests/config/pytest_software.yml

@@ -206,9 +206,6 @@ gatk4_createsequencedictionary:
   - software/gatk4/createsequencedictionary/**
   - tests/software/gatk4/createsequencedictionary/**
 
-gatk4_markduplicates:
-  - software/gatk4/markduplicates/**
-  - tests/software/gatk4/markduplicates/**
 gatk4_fastqtosam:
   - software/gatk4/fastqtosam/**
   - tests/software/gatk4/fastqtosam/**
@@ -217,6 +214,10 @@ gatk4_haplotypecaller:
   - software/gatk4/haplotypecaller/**
   - tests/software/gatk4/haplotypecaller/**
 
+gatk4_markduplicates:
+  - software/gatk4/markduplicates/**
+  - tests/software/gatk4/markduplicates/**
+
 gatk4_mergebamalignment:
   - software/gatk4/mergebamalignment/**
   - tests/software/gatk4/mergebamalignment/**
@@ -308,14 +309,14 @@ mosdepth:
   - software/mosdepth/**
   - tests/software/mosdepth/**
 
-msisensor_scan:
-  - software/msisensor/scan/**
-  - tests/software/msisensor/scan/**
-
 msisensor_msi:
   - software/msisensor/msi/**
   - tests/software/msisensor/msi/**
 
+msisensor_scan:
+  - software/msisensor/scan/**
+  - tests/software/msisensor/scan/**
+
 multiqc:
   - software/fastqc/**
   - software/multiqc/**
@@ -429,6 +430,10 @@ sequenza_wiggle:
   - software/sequenza/wiggle/**
   - tests/software/sequenza/wiggle/**
 
+sequenzautils_bam2seqz:
+  - software/sequenzautils/bam2seqz/**
+  - tests/software/sequenzautils/bam2seqz/**
+
 sequenzautils_gcwiggle:
   - software/sequenzautils/gcwiggle/**
   - tests/software/sequenzautils/gcwiggle/**

tests/config/test_data.config

@@ -22,6 +22,8 @@ params {
 
                 kraken2                                   = "${test_data_dir}/genomics/sarscov2/genome/db/kraken2"
                 kraken2_tar_gz                            = "${test_data_dir}/genomics/sarscov2/genome/db/kraken2.tar.gz"
+                
+                test_wig_gz                               = "${test_data_dir}/genomics/sarscov2/genome/gcwiggle/test.wig.gz"
             }
             'illumina' {
                 test_single_end_bam                       = "${test_data_dir}/genomics/sarscov2/illumina/bam/test_single_end.bam"
@@ -67,4 +69,4 @@ params {
             }
         }
     }
-}
+}

tests/software/sequenzautils/bam2seqz/main.nf

@@ -0,0 +1,20 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SEQUENZAUTILS_BAM2SEQZ } from '../../../../software/sequenzautils/bam2seqz/main.nf' addParams( options: [:] )
+
+workflow test_sequenzautils_bam2seqz {
+    
+    tumourbam = file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true)
+    normalbam = file(params.test_data['sarscov2']['illumina']['test_single_end_sorted_bam'], checkIfExists: true)
+
+    input = [ [ id:'test' ], // meta map
+              tumourbam,
+              normalbam
+            ]
+    fasta   = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    wigfile = file(params.test_data['sarscov2']['genome']['test_wig_gz'], checkIfExists: true)
+
+    SEQUENZAUTILS_BAM2SEQZ ( input, fasta, wigfile )
+}

tests/software/sequenzautils/bam2seqz/test.yml

@@ -0,0 +1,7 @@
+- name: sequenzautils bam2seqz
+  command: nextflow run ./tests/software/sequenzautils/bam2seqz -entry test_sequenzautils_bam2seqz -c tests/config/nextflow.config
+  tags:
+    - sequenzautils
+    - sequenzautils_bam2seqz
+  files:
+    - path: output/sequenzautils/test.seqz.gz