Add found_in tag to SV-calling (#417)

genomic-medicine-sweden · Oct 8, 2024 · 7d187a6 · 7d187a6
1 parent 98ec9a1
commit 7d187a6
Show file tree

Hide file tree

Showing 8 changed files with 134 additions and 173 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -19,7 +19,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#388](https://github.com/genomic-medicine-sweden/nallo/pull/388) - Added longphase as the default phaser
 - [#388](https://github.com/genomic-medicine-sweden/nallo/pull/388) - Added single-sample tbi output to the short variant calling subworkflow
 - [#393](https://github.com/genomic-medicine-sweden/nallo/pull/393) - Added a new `--minimap2_read_mapping_preset` parameter
-- [#403](https://github.com/genomic-medicine-sweden/nallo/pull/403) - Added `FOUND_IN=hificnv` tags to CNV output
+- [#403](https://github.com/genomic-medicine-sweden/nallo/pull/403) - Added `FOUND_IN=hificnv` tags to CNV calling output
+- [#417](https://github.com/genomic-medicine-sweden/nallo/pull/417) - Added `FOUND_IN=deepvariant` tags to SNV calling output
 
 ### `Changed`
 
@@ -43,9 +44,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#403](https://github.com/genomic-medicine-sweden/nallo/pull/403) - Revert [#404](https://github.com/genomic-medicine-sweden/nallo/pull/404)
 - [#404](https://github.com/genomic-medicine-sweden/nallo/pull/404) - Changed to only run nf-tests where files have changes compared to the base branch
 - [#407](https://github.com/genomic-medicine-sweden/nallo/pull/407) - Changed echtvar example file in docs
-- [#406](https://github.com/genomic-medicine-sweden/nallo/issues/406) - Updated genmod to version 3.8.3
+- [#410](https://github.com/genomic-medicine-sweden/nallo/pull/410) - Updated genmod to version 3.8.3
 - [#411](https://github.com/genomic-medicine-sweden/nallo/pull/411) - Updated longphase module to most recent version. ([#409](https://github.com/genomic-medicine-sweden/nallo/issues/409)).
 - [#416](https://github.com/genomic-medicine-sweden/nallo/pull/416) - Updated WhatsHap to 2.3 and added the `--use-supplementary` flag to use supplementary reads for phasing by default. Changed modules to use biocontainers instead of custom containers. ([#296](https://github.com/genomic-medicine-sweden/nallo/issues/296))
+- [#417](https://github.com/genomic-medicine-sweden/nallo/pull/417) - Updated SNV annotation tests to use correct configuration, and snapshot the md5sum, and summary of the variants
 
 ### `Removed`
 

diff --git a/conf/modules/short_variant_calling.config b/conf/modules/short_variant_calling.config
@@ -24,6 +24,16 @@ process {
         ]
     }
 
+    withName: '.*:SHORT_VARIANT_CALLING:ADD_FOUND_IN_TAG' {
+        ext.prefix = { "${meta.id}_found_in" }
+        ext.args = '--no-version'
+        ext.args2 = [
+            '--output-type b',
+            '--no-version'
+        ].join(' ')
+    }
+
+
     withName: '.*:SHORT_VARIANT_CALLING:DEEPVARIANT' {
         ext.prefix = { intervals ? "${meta.id}_${intervals}_deepvariant" : "${meta.id}_deepvariant" }
         ext.args = { [

diff --git a/subworkflows/local/short_variant_calling/main.nf b/subworkflows/local/short_variant_calling/main.nf
@@ -1,6 +1,7 @@
 //
 // Workflow to call and merge SNVs
 //
+include { ADD_FOUND_IN_TAG                            } from '../../../modules/local/add_found_in_tag/main'
 include { BCFTOOLS_CONCAT                             } from '../../../modules/nf-core/bcftools/concat/main'
 include { BCFTOOLS_FILLTAGS                           } from '../../../modules/local/bcftools/filltags/main'
 include { BCFTOOLS_NORM as BCFTOOLS_NORM_MULTISAMPLE  } from '../../../modules/nf-core/bcftools/norm/main'
@@ -84,12 +85,18 @@ workflow SHORT_VARIANT_CALLING {
     BCFTOOLS_FILLTAGS ( GLNEXUS.out.bcf )
     ch_versions = ch_versions.mix(BCFTOOLS_FILLTAGS.out.versions)
 
-    BCFTOOLS_FILLTAGS.out.vcf
-        .map { meta, vcf -> [ meta, vcf, [] ] }
-        .set { bcftools_norm_in }
+    // Annotate with FOUND_IN tag
+    ADD_FOUND_IN_TAG (
+        BCFTOOLS_FILLTAGS.out.vcf.map { meta, vcf -> [ meta, vcf, [] ] },
+        "deepvariant"
+    )
+    ch_versions = ch_versions.mix(ADD_FOUND_IN_TAG.out.versions)
 
     // Decompose and normalize variants
-    BCFTOOLS_NORM_MULTISAMPLE ( bcftools_norm_in, ch_fasta )
+    BCFTOOLS_NORM_MULTISAMPLE (
+        ADD_FOUND_IN_TAG.out.vcf.map { meta, vcf -> [ meta, vcf, [] ] },
+        ch_fasta
+    )
     ch_versions = ch_versions.mix(BCFTOOLS_NORM_MULTISAMPLE.out.versions)
 
     emit:

diff --git a/subworkflows/local/short_variant_calling/tests/main.nf.test.snap b/subworkflows/local/short_variant_calling/tests/main.nf.test.snap
diff --git a/subworkflows/local/short_variant_calling/tests/nextflow.config b/subworkflows/local/short_variant_calling/tests/nextflow.config
@@ -1,5 +1,5 @@
 process {
-    withName: 'DEEPVARIANT' {
+    withName: 'SHORT_VARIANT_CALLING:DEEPVARIANT' {
         ext.prefix = { intervals ? "${meta.id}_${intervals}_deepvariant" : "${meta.id}_deepvariant" }
         ext.args = { [
             '--model_type WGS',
@@ -8,19 +8,19 @@ process {
         ].join(' ') }
     }
 
-    withName: 'GLNEXUS' {
+    withName: 'SHORT_VARIANT_CALLING:GLNEXUS' {
         ext.args = '--config DeepVariant_unfiltered'
     }
 
-    withName: 'BCFTOOLS_CONCAT' {
+    withName: 'SHORT_VARIANT_CALLING:BCFTOOLS_CONCAT' {
         ext.prefix = { "${meta.id}_concat" }
         ext.args = [
             '--no-version',
             '--allow-overlaps'
         ].join(' ')
     }
 
-    withName: 'BCFTOOLS_NORM_MULTISAMPLE' {
+    withName: 'SHORT_VARIANT_CALLING:BCFTOOLS_NORM_MULTISAMPLE' {
         ext.prefix = { "${meta.id}_norm_multisample" }
         ext.args = [
             '--no-version',
@@ -31,7 +31,7 @@ process {
         ].join(' ')
     }
 
-    withName: 'BCFTOOLS_NORM_SINGLESAMPLE' {
+    withName: 'SHORT_VARIANT_CALLING:BCFTOOLS_NORM_SINGLESAMPLE' {
         ext.prefix = { "${meta.id}_norm_singlesample" }
         ext.args = [
             '--no-version',
@@ -42,12 +42,21 @@ process {
         ].join(' ')
     }
 
-    withName: 'BCFTOOLS_FILLTAGS' {
+    withName: 'SHORT_VARIANT_CALLING:BCFTOOLS_FILLTAGS' {
         ext.prefix = { "${meta.id}_ac" }
         ext.args = [
             '--no-version',
             '--output-type u'
         ].join(' ')
     }
 
+    withName: 'SHORT_VARIANT_CALLING:ADD_FOUND_IN_TAG' {
+        ext.prefix = { "${meta.id}_found_in" }
+        ext.args = '--no-version'
+        ext.args2 = [
+            '--output-type z',
+            '--no-version'
+        ].join(' ')
+    }
+
 }
diff --git a/subworkflows/local/snv_annotation/tests/main.nf.test b/subworkflows/local/snv_annotation/tests/main.nf.test
@@ -107,8 +107,8 @@ nextflow_workflow {
                 { assert snapshot(
                     workflow.out.versions,
                     file(workflow.out.tbi.get(0).get(1)).name,
-                    path(workflow.out.vcf.get(0).get(1)).linesGzip[48..118], // Stable
-                    path(workflow.out.vcf.get(0).get(1)).linesGzip[121..150] // Stable
+                    path(workflow.out.vcf.get(0).get(1)).vcf.variantsMD5,
+                    path(workflow.out.vcf.get(0).get(1)).vcf.summary,
                 ).match() }
             )
         }