parallel snv-annotation

CHANGELOG.md

@@ -15,6 +15,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#245](https://github.com/genomic-medicine-sweden/nallo/pull/245) - Added repeat annotation with Stranger
 - [#252](https://github.com/genomic-medicine-sweden/nallo/pull/252) - Added a new `SCATTER_GENOME` subworkflow
 - [#255](https://github.com/genomic-medicine-sweden/nallo/pull/255) - Added a new `RANK_VARIANTS` subworkflow to rank SNVs using genmod
+- [#261](https://github.com/genomic-medicine-sweden/nallo/pull/261) - Added a `--skip_rank_variants` parameter to skip the rank_variants subworkflow
 
 ### `Changed`
 
@@ -35,6 +36,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#251](https://github.com/genomic-medicine-sweden/nallo/pull/251) - Switched from annotating single sample VCFs to annotating a multisample VCF, splitting the VCF per sample afterwards to keep outputs almost consistent
 - [#256](https://github.com/genomic-medicine-sweden/nallo/pull/256) - Changed Stranger to annotate single-sample VCFs instead of a multi-sample VCF
 - [#258](https://github.com/genomic-medicine-sweden/nallo/pull/258) - Updated test profile parameters to speed up tests
+- [#261](https://github.com/genomic-medicine-sweden/nallo/pull/261) - Changed SNV annotation to run in parallel
+- [#261](https://github.com/genomic-medicine-sweden/nallo/pull/261) - Changed SNV output file names and directory structure
 
 ### `Removed`
 
@@ -57,6 +60,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 | `--extra_gvcfs`    |                            |
 | `--skip_repeat_wf` | `--skip_repeat_calling`    |
 | `--skip_repeat_wf` | `--skip_repeat_annotation` |
+|                    | `--skip_rank_variants`     |
+
+> [!NOTE]
+> Parameter has been updated if both old and new parameter information is present.
+> Parameter has been added if just the new parameter information is present.
+> Parameter has been removed if new parameter information isn't present.
 
 ## v0.2.0 - [2024-06-26]
 

conf/modules/general.config

@@ -24,16 +24,40 @@ process {
     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     */
 
+    withName: '.*:NALLO:BCFTOOLS_CONCAT' {
+        ext.prefix = { params.skip_snv_annotation ? "${meta.id}_snv" : "${meta.id}_snv_annotated" }
+        ext.args = { [
+            '--allow-overlaps',
+            '--output-type z',
+            '--write-index=tbi'
+        ].join(' ') }
+        publishDir = [
+            path: { "${params.outdir}/snvs/multi_sample/${meta.id}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : (!params.skip_rank_variants && !params.skip_snv_annotation ? null : filename) }
+        ]
+    }
+
     withName: '.*:NALLO:BCFTOOLS_PLUGINSPLIT' {
-        ext.prefix = { "${meta.id}_vep" }
         ext.args = [
             '--output-type z',
             '--write-index=tbi'
         ].join(' ')
         publishDir = [
-            path: { "${params.outdir}/snv_annotation/vep/single_sample/" },
+            path: { "${params.outdir}/snvs/single_sample/" },
             mode: params.publish_dir_mode,
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+            // Can't use prefix as it would come from the original file
+            saveAs: { filename ->
+                if (filename.equals('versions.yml')) {
+                    null
+                } else {
+                    def matcher = filename =~ /(.+)(\.vcf\.gz(?:\.tbi)?)$/
+                    def sample = matcher[0][1]
+                    def extension = matcher[0][2]
+                    def annotated = params.skip_snv_annotation ? "" : (params.skip_rank_variants ? "_annotated" : "_annotated_ranked" )
+                    "${sample}/${sample}_snv${annotated}${extension}"
+                }
+            }
         ]
     }
     withName: '.*:NALLO:FASTQC' {
@@ -114,7 +138,7 @@ process {
 
     withName: '.*:NALLO:ECHTVAR_ENCODE' {
         publishDir = [
-            path: { "${params.outdir}/snv_annotation/echtvar/encode/${meta.id}" },
+            path: { "${params.outdir}/databases/echtvar/encode/${meta.id}" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]

conf/modules/rank_variants.config

@@ -46,17 +46,17 @@ process {
     }
 
     withName: '.*:RANK_VARIANTS_SNV:TABIX_BGZIP' {
-        ext.prefix = { "${meta.id}_snv_ranked" }
+        ext.prefix = { "${meta.id}_snv_annotated_ranked" }
         publishDir = [
-            path: { "${params.outdir}/ranked_variants" },
+            path: { "${params.outdir}/snvs/multi_sample/${meta.id}" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
     }
 
     withName: '.*:RANK_VARIANTS_SNV:TABIX_TABIX' {
         publishDir = [
-            path: { "${params.outdir}/ranked_variants" },
+            path: { "${params.outdir}/snvs/multi_sample/${meta.id}" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]

conf/modules/short_variant_calling.config

@@ -37,56 +37,30 @@ process {
         ext.args = '--config DeepVariant_unfiltered'
     }
 
-    withName: '.*:SHORT_VARIANT_CALLING:BCFTOOLS_CONCAT_GVCF' {
+    withName: '.*:SHORT_VARIANT_CALLING:BCFTOOLS_CONCAT' {
         ext.args = '--allow-overlaps'
     }
 
-    withName: '.*:SHORT_VARIANT_CALLING:BCFTOOLS_CONCAT_VCF' {
-        ext.args = '--allow-overlaps'
-    }
-
-    withName: '.*:SHORT_VARIANT_CALLING:BCFTOOLS_SORT_GVCF' {
-        ext.prefix = { "${vcf.simpleName}_sorted.g" }
-        ext.args = [
-            '--output-type z',
-            '--write-index=tbi'
-        ].join(' ')
-        publishDir = [
-            path: { "${params.outdir}/snv_calling/single_sample/deepvariant/gvcf/${meta.id}" },
-            mode: params.publish_dir_mode,
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
-        ]
-    }
-
-    withName: '.*:SHORT_VARIANT_CALLING:BCFTOOLS_SORT_VCF' {
-        ext.prefix = { "${vcf.simpleName}_sorted" }
+    withName: '.*:SHORT_VARIANT_CALLING:BCFTOOLS_NORM_SINGLESAMPLE' {
+        ext.prefix = { "${meta.id}_deepvariant_snv" }
         ext.args = [
-            '--output-type z',
-            '--write-index=tbi'
+            '-m -',
+            '-w 10000',
+            '--output-type u',
         ].join(' ')
-        publishDir = [
-            path: { "${params.outdir}/snv_calling/single_sample/deepvariant/vcf/${meta.id}" },
-            mode: params.publish_dir_mode,
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
-        ]
     }
 
     withName: '.*:SHORT_VARIANT_CALLING:BCFTOOLS_FILLTAGS' {
         ext.prefix = { "${meta.id}_ac" }
-        ext.args = '--output-type b'
+        ext.args = '--output-type u'
     }
 
-    withName: '.*:SHORT_VARIANT_CALLING:BCFTOOLS_NORM' {
+    withName: '.*:SHORT_VARIANT_CALLING:BCFTOOLS_NORM_MULTISAMPLE' {
         ext.args = [
             '-m -',
-            '--output-type b',
+            '--output-type u',
             '--write-index=csi',
             '-w 10000'
         ].join(' ')
-        publishDir = [
-            path: { "${params.outdir}/snv_calling/multi_sample/glnexus/${meta.id}" },
-            mode: params.publish_dir_mode,
-            saveAs: { filename -> filename.equals('versions.yml')? null : (meta.id == "multisample" ? filename : null)}
-        ]
     }
 }

conf/modules/snv_annotation.config

@@ -45,18 +45,6 @@ process {
             '--uniprot --vcf',
             '--no_stats'
         ].join(' ') }
-        publishDir = [
-            path: { "${params.outdir}/snv_annotation/vep/multi_sample/${meta.id}" },
-            mode: params.publish_dir_mode,
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
-        ]
     }
 
-    withName: '.*:SNV_ANNOTATION:TABIX_VEP' {
-        publishDir = [
-            path: { "${params.outdir}/snv_annotation/vep/multi_sample/${meta.id}" },
-            mode: params.publish_dir_mode,
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
-        ]
-    }
 }

docs/output.md

@@ -301,11 +301,11 @@ In case of affected samples, [echtvar](https://github.com/brentp/echtvar) and [V
 <details markdown="1">
 <summary>Output files from SNV Annotation</summary>
 
-- `{outputdir}/snv_annotation/echtvar/encode/multisample/`
+- `{outputdir}/databases/echtvar/encode/multisample/`
   - `*.zip`: Database with AF and AC for all samples run
-- `{outputdir}/snv_annotation/vep/{single_sample,multi_sample/multisample}/`
-  - `*.vcf.gz`: VCF with annotated variants
-  - `*.vcf.gz.tbi`: Index of the corresponding VCF file
+- `{outputdir}/snvs/{single_sample,multi_sample/multisample}/`
+  - `*_snvs_annotated*.vcf.gz`: VCF with annotated variants
+  - `*_snvs_annotated*.vcf.gz.tbi`: Index of the corresponding VCF file
   </details>
 
 ### Ranked variants
@@ -321,9 +321,10 @@ In case of affected samples, [echtvar](https://github.com/brentp/echtvar) and [V
 <details markdown="1">
 <summary>Output files</summary>
 
-- `{outputdir}ranked_variants/`
-  - `*_snv_ranked.vcf.gz`: file containing SNV annotations with their rank scores (does not include mitochondrial variants).
-  - `*_snv_ranked.vcf.gz.tbi`: index of the file containing SNV annotations with their rank scores.
+- `{outputdir}/snvs/{single_sample,multi_sample/multisample}/`
+  - `*_snvs_annotated_ranked.vcf.gz`: VCF with annotated and ranked variants
+  - `*_snvs_annotated_ranked.vcf.gz.tbi`: Index of the corresponding VCF file
+  </details>
 
 ### SNV Calling
 

modules.json

@@ -190,7 +190,7 @@
                     },
                     "sniffles": {
                         "branch": "master",
-                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "git_sha": "b50aa17b1b604c7b3cfe58a2472d1e7b990ae8bf",
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/sniffles/sniffles.diff"
                     },

nextflow.config

@@ -33,6 +33,7 @@ params {
     skip_assembly_wf           = params.preset == 'ONT_R10' ? true : false
     skip_mapping_wf            = false
     skip_methylation_wf        = params.preset == 'pacbio' ? true : false
+    skip_rank_variants         = false
     skip_repeat_calling        = params.preset == 'ONT_R10' ? true : false
     skip_repeat_annotation     = params.preset == 'ONT_R10' ? true : false
     skip_phasing_wf            = false

nextflow_schema.json

@@ -62,6 +62,10 @@
                 "skip_call_paralogs": {
                     "type": "boolean",
                     "description": "Skip call paralogs (Paraphase)"
+                },
+                "skip_rank_variants": {
+                    "type": "boolean",
+                    "description": "Skip rank variants workflow"
                 }
             },
             "fa_icon": "fas fa-american-sign-language-interpreting"

subworkflows/local/rank_variants/main.nf

@@ -46,6 +46,7 @@ workflow RANK_VARIANTS {
         ch_versions = ch_versions.mix(TABIX_TABIX.out.versions)
 
     emit:
-        vcf      = ch_vcf       // channel: [ val(meta), path(vcf) ]
-        versions = ch_versions  // channel: [ path(versions.yml) ]
+        vcf      = ch_vcf              // channel: [ val(meta), path(vcf) ]
+        tbi      = TABIX_TABIX.out.tbi // channel: [ val(meta), path(tbi) ]
+        versions = ch_versions         // channel: [ path(versions.yml) ]
 }