Merge pull request #46 from icgc-argo-workflows/seqz-preprocess@0.3.0

[release]

Author: lDesiree

seqz-preprocess/main.nf

@@ -29,7 +29,7 @@
 /* this block is auto-generated based on info from pkg.json where   */
 /* changes can be made if needed, do NOT modify this block manually */
 nextflow.enable.dsl = 2
-version = '0.2.5.1'
+version = '0.3.0'
 
 container = [
     'ghcr.io': 'ghcr.io/icgc-argo-workflows/icgc-argo-sv-copy-number.seqz-preprocess'
@@ -45,15 +45,18 @@ params.container = ""
 
 params.cpus = 1
 params.mem = 1  // GB
-params.publish_dir = "output_dir/"  // set to empty string will disable publishDir
+params.publish_dir = ""  // set to empty string will disable publishDir
 
 
 // tool specific parmas go here, add / change as needed
 params.tumor_bam      = ""
 params.normal_bam     = ""
 params.fasta          = ""
 params.gcwiggle       = "${baseDir}/resources/hg38.gc50Base.wig.gz"
-params.output_pattern = "*bin50.seqz.gz"  // output file name pattern
+params.chromosomes    = ["chr1", "chr2", "chr3", "chr4", "chr5", "chr6", "chr7", "chr8", "chr9", "chr10", "chr11", "chr12", "chr13", "chr14", "chr15", "chr16", "chr17", "chr18", "chr19", "chr20", "chr21", "chr22", "chrX", "chrY"]
+params.output_pattern = "*.seqz.gz"  // output file name pattern
+
+include { getSecondaryFiles } from './wfpr_modules/github.com/icgc-argo-workflows/data-processing-utility-tools/helper-functions@1.0.1.1/main.nf'
 
 process seqzPreprocess {
   container "${params.container ?: container[params.container_registry ?: default_container_registry]}:${params.container_version ?: version}"
@@ -64,20 +67,49 @@ process seqzPreprocess {
 
   input:  // input, make update as needed
     path tumor_bam
+    path tumour_bai
     path normal_bam
+    path normal_bai
     path fasta
+    path fasta_fai
     path gcwiggle
+    each chrom
 
   output:  // output, make update as needed
-    path "${params.output_pattern}", emit: seqz
+    path "${params.output_pattern}", emit: seqzperchromosome
+  
+  shell:
+  // add and initialize variables here as needed
+  '''
+  sequenza-utils bam2seqz --chromosome !{chrom} -n !{normal_bam} -t !{tumor_bam} --fasta !{fasta} -gc !{gcwiggle} -o "!{chrom}.seqz.gz"
+  '''
+
+
+}
+
+process seqzPreprocessMerge {
+  container "${params.container ?: container[params.container_registry ?: default_container_registry]}:${params.container_version ?: version}"
+  publishDir "${params.publish_dir}/${task.process.replaceAll(':', '_')}", mode: "copy", enabled: params.publish_dir
+
+  cpus params.cpus
+  memory "${params.mem} GB"
+
+  input:  // input, make update as needed
+    file seqzperchromosome
+
+  output:  // output, make update as needed
+    path "sample_bin50.seqz.gz", emit: seqz
+  
+  shell:
+  // add and initialize variables here as needed
+  seqzfiles = params.chromosomes.join('.seqz.gz ')
+  '''
+  zcat !{seqzfiles}.seqz.gz | awk '{if (NR!=1 && $1 != "chromosome") {print $0}}' | bgzip > sample.seqz.gz
+  tabix -f -s 1 -b 2 -e 2 -S 1 sample.seqz.gz
+  sequenza-utils seqz_binning --seqz sample.seqz.gz --window 50 -o sample_bin50.seqz.gz
+  '''
 
-  script:
-    // add and initialize variables here as needed
 
-    """
-    sequenza-utils bam2seqz --normal ${normal_bam} --tumor ${tumor_bam} --fasta ${fasta} -gc ${gcwiggle} --output sample.seqz.gz;
-    sequenza-utils seqz_binning --seqz sample.seqz.gz --window 50 -o sample_bin50.seqz.gz
-    """
 }
 
 
@@ -86,8 +118,15 @@ process seqzPreprocess {
 workflow {
   seqzPreprocess(
     file(params.tumor_bam),
+    Channel.fromPath(getSecondaryFiles(params.tumor_bam,['{b,cr}ai']), checkIfExists: true).collect(),
     file(params.normal_bam),
+    Channel.fromPath(getSecondaryFiles(params.normal_bam,['{b,cr}ai']), checkIfExists: true).collect(),
     file(params.fasta),
-    file(params.gcwiggle)
+    Channel.fromPath(getSecondaryFiles(params.fasta,['fai']), checkIfExists: true).collect(),
+    file(params.gcwiggle),
+    params.chromosomes.flatten()
+  )
+  seqzPreprocessMerge(
+    seqzPreprocess.out.seqzperchromosome.collect()
   )
 }

seqz-preprocess/pkg.json

@@ -1,6 +1,6 @@
 {
     "name": "seqz-preprocess",
-    "version": "0.2.5.1",
+    "version": "0.3.0",
     "description": "Sequenza preprocessing",
     "main": "main.nf",
     "deprecated": false,

seqz-preprocess/resources/readme

@@ -1 +1,2 @@
-"# File 'hg38.gc50Base.wig.gz' is >100mb. Please download it from ''https://object.cancercollaboratory.org:9080/swift/v1/genomics-public-data/sequenza_references/hg38.gc50Base.wig.gz"" and compare it to the md5sum in this folder."
+"File 'hg38.gc50Base.wig.gz' is >100mb. Please download it from 'https://object.cancercollaboratory.org:9080/swift/v1/genomics-public-data/sequenza_references/hg38.gc50Base.wig.gz' and compare 
+it to the md5sum in this folder."

seqz-preprocess/tests/checker.nf

@@ -34,7 +34,7 @@
 /* this block is auto-generated based on info from pkg.json where   */
 /* changes can be made if needed, do NOT modify this block manually */
 nextflow.enable.dsl = 2
-version = '0.2.5.1'
+version = '0.3.0'
 
 container = [
     'ghcr.io': 'ghcr.io/icgc-argo-workflows/icgc-argo-sv-copy-number.seqz-preprocess'
@@ -52,10 +52,12 @@ params.tumor_bam      = ""
 params.normal_bam     = ""
 params.gcwiggle       = ""
 params.fasta           = ""
+params.chromosomes    = ["chr11"]
 params.expected_output = ""
 
+include { getSecondaryFiles } from '../wfpr_modules/github.com/icgc-argo-workflows/data-processing-utility-tools/helper-functions@1.0.1.1/main.nf'
 include { seqzPreprocess } from '../main'
-
+include { seqzPreprocessMerge } from '../main'
 
 process file_smart_diff {
   container "${params.container ?: container[params.container_registry ?: default_container_registry]}:${params.container_version ?: version}"
@@ -78,21 +80,33 @@ process file_smart_diff {
 workflow checker {
   take:
     tumor_bam
+    tumor_bai
     normal_bam
-    gcwiggle
+    normal_bai
     fasta
+    fasta_fai
+    gcwiggle
+    chrom
     expected_output
 
   main:
     seqzPreprocess(
       tumor_bam,
+      tumor_bai,
       normal_bam,
+      normal_bai,
+      fasta,
+      fasta_fai,
       gcwiggle,
-      fasta
+      chrom
+    )
+
+    seqzPreprocessMerge(
+      seqzPreprocess.out.seqzperchromosome
     )
 
     file_smart_diff(
-      seqzPreprocess.out.seqz,
+      seqzPreprocessMerge.out.seqz,
       expected_output
     )
 }
@@ -101,9 +115,13 @@ workflow checker {
 workflow {
   checker(
     file(params.tumor_bam),
+    Channel.fromPath(getSecondaryFiles(params.tumor_bam,['{b,cr}ai']), checkIfExists: true).collect(),
     file(params.normal_bam),
+    Channel.fromPath(getSecondaryFiles(params.normal_bam,['{b,cr}ai']), checkIfExists: true).collect(),
     file(params.fasta),
+    Channel.fromPath(getSecondaryFiles(params.fasta,['fai']), checkIfExists: true).collect(),
     file(params.gcwiggle),
+    params.chromosomes.flatten(),
     file(params.expected_output)
   )
 }

seqz-preprocess/tests/expected/expected_bin50.seqz.gz

@@ -0,0 +1 @@
+chr11	537000	40	50	51