Dnascope module and subworkflow in Sarek

CHANGELOG.md

@@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- [#1193](https://github.com/nf-core/sarek/pull/1193) - Adding support for Sentieon's DnaScope for germline variant-calling including joint-germline.
 - [#1271](https://github.com/nf-core/sarek/pull/1271) - Back to dev
 
 ### Changed

conf/modules/prepare_genome.config

@@ -76,7 +76,7 @@ process {
     }
 
     withName: 'TABIX_DBSNP' {
-        ext.when         = { !params.dbsnp_tbi && params.dbsnp && ((params.step == "mapping" || params.step == "markduplicates" || params.step == "prepare_recalibration") || params.tools && (params.tools.split(',').contains('controlfreec') || params.tools.split(',').contains('haplotypecaller') || params.tools.split(',').contains('sentieon_haplotyper') || params.tools.split(',').contains('mutect2'))) }
+        ext.when         = { !params.dbsnp_tbi && params.dbsnp && ((params.step == "mapping" || params.step == "markduplicates" || params.step == "prepare_recalibration") || params.tools && (params.tools.split(',').contains('controlfreec') || params.tools.split(',').contains('haplotypecaller') || params.tools.split(',').contains('sentieon_haplotyper') || params.tools.split(',').contains('sentieon_dnascope') || params.tools.split(',').contains('mutect2'))) }
         publishDir       = [
             enabled: (params.save_reference || params.build_only_index),
             mode: params.publish_dir_mode,
@@ -96,7 +96,7 @@ process {
     }
 
     withName: 'TABIX_KNOWN_INDELS' {
-        ext.when         = { !params.known_indels_tbi && params.known_indels && (params.step == 'mapping' || params.step == "markduplicates" || params.step == 'prepare_recalibration' || (params.tools && (params.tools.split(',').contains('haplotypecaller') || params.tools.split(',').contains('sentieon_haplotyper'))) ) }
+        ext.when         = { !params.known_indels_tbi && params.known_indels && (params.step == 'mapping' || params.step == "markduplicates" || params.step == 'prepare_recalibration' || (params.tools && (params.tools.split(',').contains('haplotypecaller') || params.tools.split(',').contains('sentieon_haplotyper') || params.tools.split(',').contains('sentieon_dnascope'))) ) }
         publishDir       = [
             enabled: (params.save_reference || params.build_only_index),
             mode: params.publish_dir_mode,
@@ -106,7 +106,7 @@ process {
     }
 
     withName: 'TABIX_KNOWN_SNPS' {
-        ext.when         = { !params.known_snps_tbi && params.known_snps && (params.step == 'mapping' || params.step == "markduplicates" || params.step == 'prepare_recalibration' || (params.tools && (params.tools.split(',').contains('haplotypecaller') || params.tools.split(',').contains('sentieon_haplotyper'))) ) }
+        ext.when         = { !params.known_snps_tbi && params.known_snps && (params.step == 'mapping' || params.step == "markduplicates" || params.step == 'prepare_recalibration' || (params.tools && (params.tools.split(',').contains('haplotypecaller') || params.tools.split(',').contains('sentieon_haplotyper') )) ) }
         publishDir       = [
             enabled: (params.save_reference || params.build_only_index),
             mode: params.publish_dir_mode,

conf/modules/sentieon_dnascope.config

@@ -0,0 +1,68 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Config file for defining DSL2 per module options and publishing paths
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Available keys to override module options:
+        ext.args   = Additional arguments appended to command in module.
+        ext.args2  = Second set of arguments appended to command in module (multi-tool modules).
+        ext.args3  = Third set of arguments appended to command in module (multi-tool modules).
+        ext.prefix = File name prefix for output files.
+        ext.when   = When to run the module.
+----------------------------------------------------------------------------------------
+*/
+
+// SENTIEON DNASCOPE
+
+process {
+
+    withName: 'SENTIEON_DNASCOPE' {
+        ext.prefix       = { meta.num_intervals <= 1 ? "${meta.id}.dnascope" : "${meta.id}.dnascope.${intervals.simpleName}" }
+        ext.when         = { params.tools && params.tools.split(',').contains('sentieon_dnascope') }
+        publishDir       = [
+            mode: params.publish_dir_mode,
+            path: { "${params.outdir}/variant_calling/"},
+            pattern: "*{vcf.gz,vcf.gz.tbi}",
+            saveAs: { meta.num_intervals > 1 ? null : "sentieon_dnascope/${meta.id}/${it}" }
+        ]
+    }
+
+    withName: 'MERGE_SENTIEON_DNASCOPE_VCFS' {
+        ext.prefix       = { params.joint_germline ? "${meta.id}.dnascope.g" : "${meta.id}.dnascope.unfiltered" }
+        publishDir       = [
+            mode: params.publish_dir_mode,
+            path: { "${params.outdir}/variant_calling/sentieon_dnascope/${meta.id}/" },
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: 'MERGE_SENTIEON_DNASCOPE_GVCFS' {
+        ext.prefix       = { "${meta.id}.dnascope.g" }
+        publishDir       = [
+            mode: params.publish_dir_mode,
+            path: { "${params.outdir}/variant_calling/sentieon_dnascope/${meta.id}/" },
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    if (params.tools && params.tools.contains('sentieon_dnascope')) {
+        withName: '.*FILTERVARIANTTRANCHES' {
+            ext.prefix       = {"${meta.id}.dnascope"}
+            ext.args         = { "--info-key CNN_1D" }
+            publishDir       = [
+                mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/sentieon_dnascope/${meta.id}/"},
+                pattern: "*{vcf.gz,vcf.gz.tbi}"
+            ]
+        }
+    }
+
+    withName: 'SENTIEON_DNAMODELAPPLY' {
+        ext.prefix       = {"${meta.id}.dnascope.filtered"}
+        publishDir       = [
+            mode: params.publish_dir_mode,
+            path: { "${params.outdir}/variant_calling/sentieon_dnascope/${meta.id}/"},
+            pattern: "*{vcf.gz,vcf.gz.tbi}"
+        ]
+    }
+
+}

conf/modules/sentieon_dnascope_joint_germline.config

@@ -0,0 +1,45 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Config file for defining DSL2 per module options and publishing paths
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Available keys to override module options:
+        ext.args   = Additional arguments appended to command in module.
+        ext.args2  = Second set of arguments appended to command in module (multi-tool modules).
+        ext.args3  = Third set of arguments appended to command in module (multi-tool modules).
+        ext.prefix = File name prefix for output files.
+        ext.when   = When to run the module.
+----------------------------------------------------------------------------------------
+*/
+
+// SENTIEON DNASCOPE JOINT_GERMLINE
+
+process {
+
+    // TO-DO: duplicate!!
+    withName: 'SENTIEON_GVCFTYPER' {
+        ext.args         = { "--allow-old-rms-mapping-quality-annotation-data" }
+        ext.prefix       = { meta.intervals_name }
+        publishDir       = [
+            enabled: false
+        ]
+    }
+
+    if (params.tools && params.tools.contains('sentieon_dnascope') && params.joint_germline) {
+        withName: 'NFCORE_SAREK:SAREK:BAM_VARIANT_CALLING_GERMLINE_ALL:BAM_JOINT_CALLING_GERMLINE_SENTIEON:BCFTOOLS_SORT' {
+            ext.prefix       = { vcf.baseName - ".vcf" + ".sort" }
+            publishDir       = [
+                enabled: false
+            ]
+        }
+
+        withName: 'NFCORE_SAREK:SAREK:BAM_VARIANT_CALLING_GERMLINE_ALL:BAM_JOINT_CALLING_GERMLINE_SENTIEON:MERGE_GENOTYPEGVCFS' {
+            ext.prefix       = "joint_germline"
+            publishDir       = [
+                mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/sentieon_dnascope/joint_variant_calling/" },
+                saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+                pattern: "*{vcf.gz,vcf.gz.tbi}"
+            ]
+        }
+    }
+}

docs/output.md

@@ -37,8 +37,10 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
       - [GATK Germline Single Sample Variant Calling](#gatk-germline-single-sample-variant-calling)
       - [GATK Joint Germline Variant Calling](#gatk-joint-germline-variant-calling)
     - [GATK Mutect2](#gatk-mutect2)
+    - [Sentieon DNAscope](#sentieon-dnascope)
+      - [Sentieon DNAscope joint germline variant calling](#sentieon-dnascope-joint-germline-variant-calling)
     - [Sentieon Haplotyper](#sentieon-haplotyper)
-      - [Sentieon Joint Germline Variant Calling](#sentieon-joint-germline-variant-calling)
+      - [Sentieon Haplotyper joint germline variant calling](#sentieon-haplotyper-joint-germline-variant-calling)
     - [Strelka2](#strelka2)
   - [Structural Variants](#structural-variants)
     - [Manta](#manta)
@@ -442,6 +444,53 @@ Files created:
 
 </details>
 
+#### Sentieon DNAscope
+
+[Sentieon DNAscope](https://support.sentieon.com/appnotes/dnascope_ml/#dnascope-germline-variant-calling-with-a-machine-learning-model) is a variant-caller which aims at outperforming GATK's Haplotypecaller in terms of both speed and accuracy. DNAscope allows you to use a machine learning model to perform variant calling with higher accuracy by improving the candidate detection and filtering.
+
+<details markdown="1">
+<summary>Unfiltered VCF-files for normal samples</summary>
+
+**Output directory: `{outdir}/variantcalling/sentieon_dnascope/<sample>/`**
+
+- `<sample>.dnascope.unfiltered.vcf.gz` and `<sample>.dnascope.unfiltered.vcf.gz.tbi`
+  - VCF with tabix index
+
+</details>
+
+The output from Sentieon's DNAscope can be controlled through the option `--sentieon_dnascope_emit_mode` for Sarek, see [Basic usage of Sentieon functions](#basic-usage-of-sentieon-functions).
+
+Unless `dnascope_filter` is listed under `--skip_tools` in the nextflow command, Sentieon's [DNAModelApply](https://support.sentieon.com/manual/usages/general/#dnamodelapply-algorithm) is applied to the unfiltered VCF-files in order to obtain filtered VCF-files.
+
+<details markdown="1">
+<summary>Filtered VCF-files for normal samples</summary>
+
+**Output directory: `{outdir}/variantcalling/sentieon_dnascope/<sample>/`**
+
+- `<sample>.dnascope.filtered.vcf.gz` and `<sample>.dnascope.filtered.vcf.gz.tbi`
+  - VCF with tabix index
+
+</details>
+
+##### Sentieon DNAscope joint germline variant calling
+
+In Sentieon's package DNAscope, joint germline variant calling is done by first running Sentieon's Dnacope in emit-mode `gvcf` for each sample and then running Sentieon's [GVCFtyper](https://support.sentieon.com/manual/usages/general/#gvcftyper-algorithm) on the set of gVCF-files. See [Basic usage of Sentieon functions](#basic-usage-of-sentieon-functions) for information on how joint germline variant calling can be done in Sarek using Sentieon's DNAscope.
+
+<details markdown="1">
+<summary>Output files from joint germline variant calling</summary>
+
+**Output directory: `{outdir}/variantcalling/sentieon_dnascope/<sample>/`**
+
+- `<sample>.dnascope.g.vcf.gz` and `<sample>.dnascope.g.vcf.gz.tbi`
+  - VCF with tabix index
+
+**Output directory: `{outdir}/variantcalling/sentieon_dnascope/joint_variant_calling/`**
+
+- `joint_germline.vcf.gz` and `joint_germline.vcf.gz.tbi`
+  - VCF with tabix index
+
+</details>
+
 #### Sentieon Haplotyper
 
 [Sentieon Haplotyper](https://support.sentieon.com/manual/usages/general/#haplotyper-algorithm) is Sention's speedup version of GATK's Haplotypecaller (see above).
@@ -456,7 +505,7 @@ Files created:
 
 </details>
 
-The output from Sentieon's Haplotyper can be controlled through the option `--sentieon_haplotyper_emit_mode` for Sarek, see [Basic usage of Sentieon functions in Sarek](#basic-usage-of-sentieon-functions-in-sarek).
+The output from Sentieon's Haplotyper can be controlled through the option `--sentieon_haplotyper_emit_mode` for Sarek, see [Basic usage of Sentieon functions](#basic-usage-of-sentieon-functions).
 
 Unless `haplotyper_filter` is listed under `--skip_tools` in the nextflow command, GATK's CNNScoreVariants and FilterVariantTranches (see above) is applied to the unfiltered VCF-files in order to obtain filtered VCF-files.
 
@@ -470,16 +519,16 @@ Unless `haplotyper_filter` is listed under `--skip_tools` in the nextflow comman
 
 </details>
 
-##### Sentieon Joint Germline Variant Calling
+##### Sentieon Haplotyper joint germline variant calling
 
-In Sentieon's package DNAseq, joint germline variant calling is done by first running Sentieon's Haplotyper in emit-mode `gvcf` for each sample and then running Sentieon's [GVCFtyper](https://support.sentieon.com/manual/usages/general/#gvcftyper-algorithm) on the set of gVCF-files. See [Basic usage of Sentieon functions in Sarek](#basic-usage-of-sentieon-functions-in-sarek) for information on how joint germline variant calling can be done in Sarek using Sentieon's DNAseq. After joint genotyping, Sentieon's version of VQSR ([VarCal](https://support.sentieon.com/manual/usages/general/#varcal-algorithm) and [ApplyVarCal](https://support.sentieon.com/manual/usages/general/#applyvarcal-algorithm)) is applied for filtering to produce the final multisample callset with the desired balance of precision and sensitivity.
+In Sentieon's package DNAseq, joint germline variant calling is done by first running Sentieon's Haplotyper in emit-mode `gvcf` for each sample and then running Sentieon's [GVCFtyper](https://support.sentieon.com/manual/usages/general/#gvcftyper-algorithm) on the set of gVCF-files. See [Basic usage of Sentieon functions](#basic-usage-of-sentieon-functions) for information on how joint germline variant calling can be done in Sarek using Sentieon's DNAseq. After joint genotyping, Sentieon's version of VQSR ([VarCal](https://support.sentieon.com/manual/usages/general/#varcal-algorithm) and [ApplyVarCal](https://support.sentieon.com/manual/usages/general/#applyvarcal-algorithm)) is applied for filtering to produce the final multisample callset with the desired balance of precision and sensitivity.
 
 <details markdown="1">
 <summary>Output files from joint germline variant calling</summary>
 
 **Output directory: `{outdir}/variantcalling/sentieon_haplotyper/<sample>/`**
 
-- `<sample>.haplotypecaller.g.vcf.gz` and `<sample>.haplotypecaller.g.vcf.gz.tbi`
+- `<sample>.haplotyper.g.vcf.gz` and `<sample>.haplotyper.g.vcf.gz.tbi`
   - VCF with tabix index
 
 **Output directory: `{outdir}/variantcalling/sentieon_haplotyper/joint_variant_calling/`**