Sentieon haplotyper refactored

.github/workflows/pytest-workflow.yml

@@ -2,7 +2,7 @@ name: pytest-workflow
 # This workflow runs the pipeline with the minimal test dataset to check that it completes without any syntax errors
 on:
   pull_request:
-    branches: [dev, master]
+    branches: [dev, master, sentieon]
 
 # Cancel if a newer run is started
 concurrency:

conf/modules/sentieon_haplotyper.config

@@ -16,8 +16,6 @@
 process {
 
     withName: 'SENTIEON_HAPLOTYPER' {
-        // ext.args         = { params.joint_germline ? "-ERC GVCF" : "" }  // TO-DO: Change that
-        // ext.prefix       = { meta.num_intervals <= 1 ? ( params.joint_germline ? "${meta.id}.haplotyper.g" : "${meta.id}.haplotyper" ) : ( params.joint_germline ? "${meta.id}.haplotyper.${intervals.simpleName}.g" :"${meta.id}.haplotyper.${intervals.simpleName}" ) }  // old value
         ext.prefix       = { meta.num_intervals <= 1 ? "${meta.id}.haplotyper" : "${meta.id}.haplotyper.${intervals.simpleName}" }
         ext.when         = { params.tools && params.tools.split(',').contains('sentieon_haplotyper') }
         publishDir       = [
@@ -30,7 +28,7 @@ process {
     }
 
     withName: 'MERGE_SENTIEON_HAPLOTYPER_VCFS' {
-        ext.prefix       = { params.joint_germline ? "${meta.id}.haplotyper.g" : "${meta.id}.haplotyper.unfiltered" }  // TO-DO:  This shouldn't be relevant for gvcf. But check with the joint-germline flow.
+        ext.prefix       = { params.joint_germline ? "${meta.id}.haplotyper.g" : "${meta.id}.haplotyper.unfiltered" }
         publishDir       = [
             mode: params.publish_dir_mode,
             path: { "${params.outdir}/variant_calling/sentieon_haplotyper/${meta.id}/" },

nextflow.config

@@ -69,7 +69,7 @@ params {
     ignore_soft_clipped_bases   = false // no --dont-use-soft-clipped-bases for GATK Mutect2
     wes                         = false // Set to true, if data is exome/targeted sequencing data. Used to use correct models in various variant callers
     joint_germline              = false // g.vcf & joint germline calling are not run by default if HaplotypeCaller is selected
-    sentieon_haplotyper_out_format = "vcf"
+    sentieon_haplotyper_emit_mode = "variant"
 
     // Annotation
     vep_out_format      = 'vcf'

nextflow_schema.json

@@ -372,14 +372,13 @@
                     "help_text": "use the `--dont-use-soft-clipped-bases` params with GATK Mutect2.",
                     "hidden": true
                 },
-                "sentieon_haplotyper_out_format": {
+                "sentieon_haplotyper_emit_mode": {
                     "type": "string",
-                    "default": "vcf",
-                    "description": "Option for selecting Sentieon Haplotyper output format.",
-                    "enum": ["vcf", "gvcf", "both"],
-                    "help_text": "Sets the format of the output file or files from Sentieon's Haplotyper. Available formats: vcf, gvcf, or both",
-                    "fa_icon": "fas fa-table",
-                    "hidden": true
+                    "default": "variant",
+                    "fa_icon": "fas fa-toolbox",
+                    "description": "Option for selecting output and emit-mode of Sentieon's Haplotyper.",
+                    "help_text": "The option `--sentieon_haplotyper_emit_mode` can be set to the same string values as the Haplotyper's `--emit_mode`. To output both a vcf and a gvcf, specify both a vcf-option (currently, `all`, `confident` and `variant`) and `gvcf`. For example, to obtain a vcf and gvcf one could set `--sentieon_haplotyper_emit_mode` to `variant, gvcf`.",
+                    "pattern": "^(all|confident|gvcf|variant|gvcf,all|gvcf,confident|gvcf,variant|all,gvcf|confident,gvcf|variant,gvcf)(?<!,)$"
                 }
             }
         },

subworkflows/local/bam_variant_calling_germline_all/main.nf

@@ -38,7 +38,7 @@ workflow BAM_VARIANT_CALLING_GERMLINE_ALL {
     known_sites_snps_tbi
     known_snps_vqsr
     joint_germline                    // boolean: [mandatory] [default: false] joint calling of germline variants
-    sentieon_haplotyper_out_format    // channel: [mandatory] value channel with string
+    sentieon_haplotyper_emit_mode     // channel: [mandatory] value channel with string
 
     main:
     versions = Channel.empty()
@@ -174,7 +174,7 @@ workflow BAM_VARIANT_CALLING_GERMLINE_ALL {
             intervals_bed_combined_haplotypec,
             (skip_tools && skip_tools.split(',').contains('haplotyper_filter')),
             joint_germline,
-            sentieon_haplotyper_out_format)
+            sentieon_haplotyper_emit_mode)
 
         versions = versions.mix(BAM_VARIANT_CALLING_SENTIEON_HAPLOTYPER.out.versions)
 

subworkflows/local/bam_variant_calling_sentieon_haplotyper/main.nf

@@ -22,7 +22,7 @@ workflow BAM_VARIANT_CALLING_SENTIEON_HAPLOTYPER {
     intervals_bed_combined         // channel: [mandatory] intervals/target regions in one file unzipped, no_intervals.bed if no_intervals
     skip_haplotyper_filter         // boolean: [mandatory] [default: false] skip haplotyper filter
     joint_germline                 // boolean: [mandatory] [default: false] joint calling of germline variants
-    sentieon_haplotyper_out_format // channel: [mandatory] value channel with string
+    sentieon_haplotyper_emit_mode
 
     main:
     versions = Channel.empty()
@@ -45,13 +45,19 @@ workflow BAM_VARIANT_CALLING_SENTIEON_HAPLOTYPER {
             ]
         }
 
+
+    emit_mode_items = sentieon_haplotyper_emit_mode.split(',')
+    lst = emit_mode_items - 'gvcf'
+    emit_vcf = lst.size() > 0 ? lst[0] : ''
+
     SENTIEON_HAPLOTYPER(
         cram_intervals_for_sentieon,
         fasta,
         fasta_fai,
         dbsnp,
         dbsnp_tbi,
-        sentieon_haplotyper_out_format)
+        emit_vcf,
+        emit_mode_items.contains('gvcf'))
 
     versions = versions.mix(SENTIEON_HAPLOTYPER.out.versions)
 

tests/test_sentieon_haplotyper.yml

@@ -78,7 +78,7 @@
     - path: results/sentieon_haplotyper
       should_exist: false
 - name: Run variant calling on germline sample with sentieons haplotyper output gvcf
-  command: nextflow run main.nf -profile test,targeted --input ./tests/csv/3.0/mapped_single_bam.csv --tools sentieon_haplotyper --step variant_calling --outdir results --sentieon_haplotyper_out_format gvcf
+  command: nextflow run main.nf -profile test,targeted --input ./tests/csv/3.0/mapped_single_bam.csv --tools sentieon_haplotyper --step variant_calling --outdir results --sentieon_haplotyper_emit_mode gvcf
   tags:
     - germline
     - sentieon/haplotyper
@@ -115,8 +115,8 @@
       should_exist: false
     - path: results/haplotyper
       should_exist: false
-- name: Run variant calling on germline sample with sentieons haplotyper output both vcf and gvcf
-  command: nextflow run main.nf -profile test,targeted --input ./tests/csv/3.0/mapped_single_bam.csv --tools sentieon_haplotyper --step variant_calling --outdir results --sentieon_haplotyper_out_format both
+- name: Run variant calling on germline sample with sentieons haplotyper output both gvcf and vcf
+  command: nextflow run main.nf -profile test,targeted --input ./tests/csv/3.0/mapped_single_bam.csv --tools sentieon_haplotyper --step variant_calling --outdir results --sentieon_haplotyper_emit_mode variant,gvcf
   tags:
     - germline
     - sentieon/haplotyper

tests/test_sentieon_joint_germline.yml

@@ -1,5 +1,5 @@
 - name: Run joint germline variant calling with sentieon haplotyper
-  command: nextflow run main.nf -profile test,targeted --input ./tests/csv/3.0/mapped_joint_bam.csv --tools sentieon_haplotyper --step variant_calling --joint_germline --skip_tools haplotyper_filter --outdir results --sentieon_haplotyper_out_format gvcf
+  command: nextflow run main.nf -profile test,targeted --input ./tests/csv/3.0/mapped_joint_bam.csv --tools sentieon_haplotyper --step variant_calling --joint_germline --skip_tools haplotyper_filter --outdir results --sentieon_haplotyper_emit_mode gvcf
   tags:
     - germline
     - sentieon_joint_germline

workflows/sarek.nf

@@ -68,8 +68,8 @@ if (params.step == 'mapping' && params.aligner.contains("dragmap") && !(params.s
     log.warn("DragMap was specified as aligner. Base recalibration is not contained in --skip_tools. It is recommended to skip baserecalibration when using DragMap\nhttps://gatk.broadinstitute.org/hc/en-us/articles/4407897446939--How-to-Run-germline-single-sample-short-variant-discovery-in-DRAGEN-mode")
 }
 
-if (params.tools && params.tools.contains("sentieon_haplotyper") && params.joint_germline && (!params.sentieon_haplotyper_out_format || !(params.sentieon_haplotyper_out_format.contains('gvcf') || params.sentieon_haplotyper_out_format.contains('both')))) {
-    error("When setting the option `--joint_germline` and including `sentieon_haplotyper` among the requested tools, please set `--sentieon_haplotyper_out_format` to `gvcf` or `both`.")
+if (params.tools && params.tools.contains("sentieon_haplotyper") && params.joint_germline && (!params.sentieon_haplotyper_emit_mode || !(params.sentieon_haplotyper_emit_mode.contains('gvcf')))) {
+    error("When setting the option `--joint_germline` and including `sentieon_haplotyper` among the requested tools, please set `--sentieon_haplotyper_emit_mode` to include `gvcf`.")
 }
 
 // Fails or warns when missing files or params for ascat
@@ -962,7 +962,7 @@ workflow SAREK {
             known_sites_snps_tbi,
             known_snps_vqsr,
             params.joint_germline,
-            params.sentieon_haplotyper_out_format)
+            params.sentieon_haplotyper_emit_mode)
 
         // TUMOR ONLY VARIANT CALLING
         BAM_VARIANT_CALLING_TUMOR_ONLY_ALL(