Update PipeVal (#81)

* add sub-module pipeline-Nextflow-module

* add pipeval 3.0.0 in default.config

* add pipeval submodule from pipeline-Nextflow-module and modify input validation channel in main.nf

* Update CHANGELOG.md

* update pipeval version logging in main.nf

* udpate validation output dir naming convention in main.nf

* udpate validation output dir naming convention in main.nf

* Update CHANGELOG.md

* update main.nf

* update sub-module pipeline-Nextflow-module

* fix sha512sum command in sha512.nf

* change run_validate to run_validate_PipeVal in node configs

Co-authored-by: Mootor <mmootor@ip-0A125238.rhxrlfvjyzbupc03cc22jkch3c.xx.internal.cloudapp.net>

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "external/pipeline-Nextflow-module"]
+	path = external/pipeline-Nextflow-module
+	url = [email protected]:uclahs-cds/pipeline-Nextflow-module.git

CHANGELOG.md

@@ -4,10 +4,16 @@ All notable changes to the call-gSV pipeline.
 ---
 
 ## [Unreleased]
-## Changed
+### Changed
 - Parameterize Docker registry
 - Use `ghcr.io/uclahs-cds` as default registry
 
+### Added
+- Add PipeVal using `pipeline-Nextflow-module` to validate the input CSV file
+
+### Removed
+- Remove `module/validation.nf` as PipeVal sub-module is used
+
 ---
 
 ## [4.0.0] - 2022-08-17

config/F16.config

@@ -1,5 +1,5 @@
 process {
-    withName: run_validate {
+    withName: run_validate_PipeVal {
         cpus = 1
         memory = 1.GB
     }

config/F2.config

@@ -1,5 +1,5 @@
 process {
-    withName: run_validate {
+    withName: run_validate_PipeVal {
         cpus = 1
         memory = 1.GB
     }

config/F32.config

@@ -1,5 +1,5 @@
 process {
-    withName: run_validate {
+    withName: run_validate_PipeVal {
         cpus = 1
         memory = 1.GB
     }

config/F72.config

@@ -1,5 +1,5 @@
 process {
-    withName: run_validate {
+    withName: run_validate_PipeVal {
         cpus = 1
         memory = 1.GB
     }

config/M64.config

@@ -1,5 +1,5 @@
 process {
-    withName: run_validate {
+    withName: run_validate_PipeVal {
         cpus = 1
         memory = 1.GB
     }

config/default.config

@@ -25,16 +25,15 @@ params {
     bcftools_version = "1.15.1"
     vcftools_version = "0.1.16"
     rtgtools_version = "3.12"
-    validate_version = "2.1.5"
+    pipeval_version = "3.0.0"
 
     // Docker tool versions
     docker_image_delly = "${-> params.docker_container_registry}/delly:${params.delly_version}"
     docker_image_bcftools = "${-> params.docker_container_registry}/bcftools:${params.bcftools_version}"
     docker_image_manta = "${-> params.docker_container_registry}/manta:${params.manta_version}"
     docker_image_rtgtools = "${-> params.docker_container_registry}/rtg-tools:${params.rtgtools_version}"
     docker_image_vcftools = "${-> params.docker_container_registry}/vcftools:${params.vcftools_version}"
-    docker_image_validate = "${-> params.docker_container_registry}/validate:${params.validate_version}"
-
+    docker_image_validate = "${-> params.docker_container_registry}/pipeval:${params.pipeval_version}"
     }
 
 process {

main.nf

@@ -39,15 +39,17 @@ Current Configuration:
     bcftools: ${params.bcftools_version}
     vcftools: ${params.vcftools_version}
     rtgtools: ${params.rtgtools_version}
-    validation tool: ${params.validate_version}
+    validation tool: ${params.pipeval_version}
 
 ------------------------------------
 Starting workflow...
 ------------------------------------
 """
 .stripIndent()
 
-include { run_validate } from './module/validation'
+include { run_validate_PipeVal } from './external/pipeline-Nextflow-module/modules/PipeVal/validate/main.nf' addParams(
+    options: [ docker_image_version: params.pipeval_version ]
+    )
 include { call_gSV_Delly; call_gCNV_Delly; regenotype_gSV_Delly; regenotype_gCNV_Delly } from './module/delly'
 include { call_gSV_Manta } from './module/manta'
 include { convert_BCF2VCF_BCFtools as convert_gSV_BCF2VCF_BCFtools; convert_BCF2VCF_BCFtools as convert_gCNV_BCF2VCF_BCFtools } from './module/bcftools'
@@ -101,14 +103,31 @@ if (!params.run_delly && !params.run_manta) {
 
 reference_fasta_index = "${params.reference_fasta}.fai"
 
-validation_channel = Channel
+/**
+* Create input_validation to validate the input bams
+*/
+validation_mode = Channel.of("file-input")
+
+input_files = Channel
     .fromPath(params.input_csv, checkIfExists:true)
     .splitCsv(header:true)
     .map{ row -> [row.input_bam, "${row.input_bam}.bai"]}
     .flatten()
 
+validation_mode
+     .combine(input_files)
+     .set { input_validation }
+
 workflow {
-    run_validate(validation_channel)
+    /**
+    * Validate the input bams
+    */
+    run_validate_PipeVal(input_validation)
+    // Collect and store input validation output
+    run_validate_PipeVal.out.validation_result.collectFile(
+        name: 'input_validation.txt',
+        storeDir: "${params.output_dir}/validation/run_validate_PipeVal"
+        )
 
     if (params.run_discovery) {
         if (params.run_manta) {

module/sha512.nf

@@ -29,6 +29,6 @@ process run_sha512sum {
 
     """
         set -euo pipefail
-        python -m validate -t sha512-gen $input_checksum_file > ${input_checksum_file}.sha512
+        sha512sum ${input_checksum_file} > ${input_checksum_file}.sha512
     """
     }