Add panel of normals subworkflow (#1044)

* commiting changes to switch branch

* commit to setup remote branch

* first draft of the sompon workflow

* keep branch in line with gendb bugfixing

* Update test.yml

* tidy up main.nf

* fixed md5sum

Co-authored-by: GCJMackenzie <gavin.mackenzie@nibsc.org>

subworkflows/nf-core/gatk_create_som_pon/main.nf

@@ -0,0 +1,58 @@
+//
+// Run GATK mutect2, genomicsdbimport and createsomaticpanelofnormals
+//
+
+params.mutect2_options      = [args: '--max-mnp-distance 0']
+params.gendbimport_options  = [:]
+params.createsompon_options = [:]
+
+include { GATK4_MUTECT2                     } from '../../../modules/gatk4/mutect2/main'                     addParams( options: params.mutect2_options )
+include { GATK4_GENOMICSDBIMPORT            } from '../../../modules/gatk4/genomicsdbimport/main'            addParams( options: params.gendbimport_options )
+include { GATK4_CREATESOMATICPANELOFNORMALS } from '../../../modules/gatk4/createsomaticpanelofnormals/main' addParams( options: params.createsompon_options )
+
+workflow GATK_CREATE_SOM_PON {
+    take:
+    ch_mutect2_in       // channel: [ val(meta), [ input ], [ input_index ], [] ]
+    fasta               // channel: /path/to/reference/fasta
+    fastaidx            // channel: /path/to/reference/fasta/index
+    dict                // channel: /path/to/reference/fasta/dictionary
+    pon_name            // channel: name for panel of normals
+    interval_file       // channel: /path/to/interval/file
+
+    main:
+    ch_versions      = Channel.empty()
+    input = channel.from(ch_mutect2_in)
+    //
+    //Perform variant calling for each sample using mutect2 module in panel of normals mode.
+    //
+    GATK4_MUTECT2 ( input , false , true, false , [] , fasta , fastaidx , dict , [], [] , [] , [] )
+    ch_versions = ch_versions.mix(GATK4_MUTECT2.out.versions.first())
+
+    //
+    //Convert all sample vcfs into a genomicsdb workspace using genomicsdbimport.
+    //
+    ch_vcf = GATK4_MUTECT2.out.vcf.collect{it[1]}.toList()
+    ch_index = GATK4_MUTECT2.out.tbi.collect{it[1]}.toList()
+    gendb_input = Channel.of([[ id:pon_name ]]).combine(ch_vcf).combine(ch_index).combine([interval_file]).combine(['']).combine([dict])
+    GATK4_GENOMICSDBIMPORT ( gendb_input, false, false, false )
+    ch_versions = ch_versions.mix(GATK4_GENOMICSDBIMPORT.out.versions.first())
+
+    //
+    //Panel of normals made from genomicsdb workspace using createsomaticpanelofnormals.
+    //
+    GATK4_GENOMICSDBIMPORT.out.genomicsdb.view()
+    GATK4_CREATESOMATICPANELOFNORMALS ( GATK4_GENOMICSDBIMPORT.out.genomicsdb, fasta, fastaidx, dict )
+    ch_versions = ch_versions.mix(GATK4_CREATESOMATICPANELOFNORMALS.out.versions.first())
+
+    emit:
+    mutect2_vcf      = GATK4_MUTECT2.out.vcf.collect()                     // channel: [ val(meta), [ vcf ] ]
+    mutect2_index    = GATK4_MUTECT2.out.tbi.collect()                     // channel: [ val(meta), [ tbi ] ]
+    mutect2_stats    = GATK4_MUTECT2.out.stats.collect()                   // channel: [ val(meta), [ stats ] ]
+
+    genomicsdb       = GATK4_GENOMICSDBIMPORT.out.genomicsdb               // channel: [ val(meta), [ genomicsdb ] ]
+
+    pon_vcf          = GATK4_CREATESOMATICPANELOFNORMALS.out.vcf           // channel: [ val(meta), [ vcf.gz ] ]
+    pon_index        = GATK4_CREATESOMATICPANELOFNORMALS.out.tbi           // channel: [ val(meta), [ tbi ] ]
+
+    versions         = ch_versions                                         // channel: [ versions.yml ]
+}

subworkflows/nf-core/gatk_create_som_pon/meta.yml

@@ -0,0 +1,75 @@
+name: gatk_create_som_pon
+description: Perform variant calling on a set of normal samples using mutect2 panel of normals mode. Group them into a genomicsdbworkspace using genomicsdbimport, then use this to create a panel of normals using createsomaticpanelofnormals.
+keywords:
+  - gatk4
+  - mutect2
+  - genomicsdbimport
+  - createsomaticpanelofnormals
+  - variant_calling
+  - genomicsdb_workspace
+  - panel_of_normals
+modules:
+  - gatk4/mutect2
+  - gatk4/genomicsdbimport
+  - gatk4/createsomaticpanelofnormals
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - input:
+      type: list
+      description: list of BAM files, also able to take CRAM as an input
+      pattern: "[ *.{bam/cram} ]"
+  - input_index:
+      type: list
+      description: list of BAM file indexes, also able to take CRAM indexes as an input
+      pattern: "[ *.{bam.bai/cram.crai} ]"
+  - fasta:
+      type: file
+      description: The reference fasta file
+      pattern: "*.fasta"
+  - fastaidx:
+      type: file
+      description: Index of reference fasta file
+      pattern: "fasta.fai"
+  - dict:
+      type: file
+      description: GATK sequence dictionary
+      pattern: "*.dict"
+  - pon_name:
+      type: String
+      Description: name to be used for the genomicsdb workspace and panel of normals as meta_id has the individual sample names and a name for the combined files is reuired here.
+      pattern: "example_name"
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: 'versions.yml'
+  - mutect2_vcf:
+      type: list
+      description: List of compressed vcf files to be used to make the gendb workspace
+      pattern: "[ *.vcf.gz ]"
+  - mutect2_index:
+      type: list
+      description: List of indexes of mutect2_vcf files
+      pattern: "[ *vcf.gz.tbi ]"
+  - mutect2_stats:
+      type: list
+      description: List of stats files that pair with mutect2_vcf files
+      pattern: "[ *vcf.gz.stats ]"
+  - genomicsdb:
+      type: directory
+      description: Directory containing the files that compose the genomicsdb workspace.
+      pattern: "path/name_of_workspace"
+  - pon_vcf:
+      type: file
+      description: Panel of normal as compressed vcf file
+      pattern: "*.vcf.gz"
+  - pon_index:
+      type: file
+      description: Index of pon_vcf file
+      pattern: "*vcf.gz.tbi"
+authors:
+  - '@GCJMackenzie'

subworkflows/nf-core/gatk_create_som_pon/nextflow.config

@@ -0,0 +1,3 @@
+params.mutect2_options      = [:]
+params.gendbimport_options  = [:]
+params.createsompon_options = [:]

tests/config/pytest_subworkflows.yml

@@ -14,3 +14,8 @@ subworkflows/sra_fastq:
   - subworkflows/nf-core/sra_fastq/**
   - tests/subworkflows/nf-core/sra_fastq/**
 
+subworkflows/gatk_create_som_pon:
+  - subworkflows/nf-core/gatk_create_som_pon/**
+  - tests/subworkflows/nf-core/gatk_create_som_pon/**
+  
+  

tests/subworkflows/nf-core/gatk_create_som_pon/main.nf

@@ -0,0 +1,26 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK_CREATE_SOM_PON } from '../../../../subworkflows/nf-core/gatk_create_som_pon/main' addParams( [:]  )
+
+workflow test_gatk_create_som_pon {
+    ch_mutect2_in = [
+                    [[ id:'test1' ], // meta map
+                    [file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam'], checkIfExists: true)],
+                    [file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam_bai'], checkIfExists: true)],
+                    [] ],
+                    [[ id:'test2' ], // meta map
+                    [file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_bam'], checkIfExists: true)],
+                    [file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_bam_bai'], checkIfExists: true)],
+                    [] ]
+                    ]
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    fastaidx = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+    dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
+    pon_name = "test_panel"
+    interval_file = file(params.test_data['homo_sapiens']['genome']['genome_interval_list'], checkIfExists: true)
+
+    GATK_CREATE_SOM_PON ( ch_mutect2_in, fasta, fastaidx, dict, pon_name, interval_file )
+
+}

tests/subworkflows/nf-core/gatk_create_som_pon/test.yml

@@ -0,0 +1,38 @@
+- name: gatk_create_som_pon
+  command: nextflow run ./tests/subworkflows/nf-core/gatk_create_som_pon -entry test_gatk_create_som_pon -c tests/config/nextflow.config
+  tags:
+    - subworkflows/gatk_create_som_pon
+    # Modules
+    - gatk4
+    - gatk4
+    - gatk4/genomicsdbimport
+    - gatk4/createsomaticpanelofnormals
+  files:
+      # gatk4 mutect2
+    - path: output/gatk4/test1.vcf.gz
+    - path: output/gatk4/test1.vcf.gz.stats
+      md5sum: 4f77301a125913170b8e9e7828b4ca3f
+    - path: output/gatk4/test1.vcf.gz.tbi
+    - path: output/gatk4/test2.vcf.gz
+    - path: output/gatk4/test2.vcf.gz.stats
+      md5sum: 106c5828b02b906c97922618b6072169
+    - path: output/gatk4/test2.vcf.gz.tbi
+      # gatk4 genomicsdbimport
+    - path: output/gatk4/test_panel/__tiledb_workspace.tdb
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/gatk4/test_panel/callset.json
+      md5sum: 2ab411773b7267de61f8c04939de2a99
+    - path: output/gatk4/test_panel/chr22$1$40001/.__consolidation_lock
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/gatk4/test_panel/chr22$1$40001/__array_schema.tdb
+    - path: output/gatk4/test_panel/chr22$1$40001/genomicsdb_meta_dir/genomicsdb_column_bounds.json
+      md5sum: 2502f79658bc000578ebcfddfc1194c0
+    - path: output/gatk4/test_panel/vcfheader.vcf
+      contains:
+        - "FORMAT=<ID=AD,Number=R,Type=Integer,Description="
+    - path: output/gatk4/test_panel/vidmap.json
+      md5sum: ee4f6815c433caa8ab101ec45ff328a6
+      # gatk4 createsomaticpanelofnormals
+    - path: output/gatk4/test_panel.vcf.gz
+    - path: output/gatk4/test_panel.vcf.gz.tbi
+      md5sum: d7e2524ba4bf7538dbee3e225a74b0da