nf-core · ramprasadn · Aug 24, 2023 · Aug 23, 2023 · Aug 23, 2023 · Aug 23, 2023
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -8,6 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### `Added`
 
 - Use `nf-validation` plugin for parameter and samplesheet validation [#386](https://github.com/nf-core/raredisease/pull/386)
+- A new parameter to skip filtering based on vep results [#416](https://github.com/nf-core/raredisease/pull/416)
 
 ### `Changed`
 

diff --git a/conf/modules/raredisease.config b/conf/modules/raredisease.config
@@ -103,12 +103,23 @@ process {
 //
 
 process {
+    withName: '.*RANK_VARIANTS_SNV' {
+        publishDir = [
+            enabled: params.skip_vep_filter,
+            path: { "${params.outdir}/rank_and_filter" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: '.*FILTERVEP_SNV' {
+        ext.when   = !params.skip_vep_filter
         ext.prefix = { "${meta.id}_clinical_snv" }
         ext.args   = { "--filter \"HGNC_ID in ${feature_file}\"" }
     }
 
     withName: '.*BGZIPTABIX_SNV' {
+        ext.when   = !params.skip_vep_filter
         ext.prefix = { "${meta.id}_clinical_snv" }
         publishDir = [
             path: { "${params.outdir}/rank_and_filter" },
@@ -119,12 +130,23 @@ process {
 }
 
 process {
+    withName: '.*RANK_VARIANTS_SV' {
+        publishDir = [
+            enabled: params.skip_vep_filter,
+            path: { "${params.outdir}/rank_and_filter" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: '.*FILTERVEP_SV' {
+        ext.when   = !params.skip_vep_filter
         ext.prefix = { "${meta.id}_clinical_sv" }
         ext.args   = { "--filter \"HGNC_ID in ${feature_file}\"" }
     }
 
     withName: '.*BGZIPTABIX_SV' {
+        ext.when   = !params.skip_vep_filter
         ext.prefix = { "${meta.id}_clinical_sv" }
         publishDir = [
             path: { "${params.outdir}/rank_and_filter" },

diff --git a/docs/output.md b/docs/output.md
@@ -437,7 +437,7 @@ We recommend using vcfanno to annotate SNVs with precomputed CADD scores (files
 
 #### GENMOD
 
-[GENMOD](https://github.com/Clinical-Genomics/genmod) is a simple to use command line tool for annotating and analyzing genomic variations in the VCF file format. GENMOD can annotate genetic patterns of inheritance in vcf:s with single or multiple families of arbitrary size. VCF file annotated by GENMOD are further filtered using [filter_vep from VEP](https://www.ensembl.org/info/docs/tools/vep/script/vep_filter.html) to separate clinically relevant variants.
+[GENMOD](https://github.com/Clinical-Genomics/genmod) is a simple to use command line tool for annotating and analyzing genomic variations in the VCF file format. GENMOD can annotate genetic patterns of inheritance in vcf:s with single or multiple families of arbitrary size. VCF file annotated by GENMOD are further filtered using [filter_vep from VEP](https://www.ensembl.org/info/docs/tools/vep/script/vep_filter.html) to separate clinically relevant variants. You can skip the filtering step by setting --skip_vep_filter to true.
 
 <details markdown="1">
 <summary>Output files</summary>

diff --git a/docs/usage.md b/docs/usage.md
@@ -224,7 +224,7 @@ See example cache [here](https://raw.githubusercontent.com/nf-core/test-datasets
 no header and the following columns: `CHROM POS REF_ALLELE ALT_ALLELE AF`. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/gnomad_reformated.tab.gz).<br />
 <sup>6</sup>Used by GENMOD for ranking the variants. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/rank_model_snv.ini).<br />
 <sup>7</sup>Used by GENMOD while modeling the variants. Contains a list of loci that show [reduced penetrance](https://medlineplus.gov/genetics/understanding/inheritance/penetranceexpressivity/) in people. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/reduced_penetrance.tsv).<br />
-<sup>8</sup> This file contains a list of candidate genes (with [HGNC](https://www.genenames.org/) IDs) that is used to split the variants into canditate variants and research variants. Research variants contain all the variants, while candidate variants are a subset of research variants and are associated with candidate genes. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/hgnc.txt).<br />
+<sup>8</sup> This file contains a list of candidate genes (with [HGNC](https://www.genenames.org/) IDs) that is used to split the variants into canditate variants and research variants. Research variants contain all the variants, while candidate variants are a subset of research variants and are associated with candidate genes. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/hgnc.txt). Not required if --skip_vep_filter is set to true.<br />
 <sup>9</sup>Path to a folder containing cadd annotations. Equivalent of the data/annotations/ folder described [here](https://github.com/kircherlab/CADD-scripts/#manual-installation), and it is used to calculate CADD scores for small indels. <br />
 
 > NB: We use CADD only to annotate small indels. To annotate SNVs with precomputed CADD scores, pass the file containing CADD scores as a resource to vcfanno instead. Files containing the precomputed CADD scores for SNVs can be downloaded from [here](https://cadd.gs.washington.edu/download) (description: "All possible SNVs of GRCh3<7/8>/hg3<7/8>")

diff --git a/nextflow.config b/nextflow.config
@@ -27,6 +27,7 @@ params {
     skip_cnv_calling           = false
     skip_snv_annotation        = false
     skip_sv_annotation         = false
+    skip_vep_filter            = false
     skip_mt_analysis           = false
     gens_switch                = false
     cadd_resources             = null

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -386,7 +386,7 @@
                 "skip_cnv_calling": {
                     "type": "boolean",
                     "description": "Specifies whether or not to skip CNV calling.",
-                    "fa_icon": "fas fa-book"
+                    "fa_icon": "fas fa-toggle-on"
                 },
                 "skip_mt_analysis": {
                     "type": "boolean",
@@ -402,6 +402,11 @@
                     "type": "boolean",
                     "description": "Specifies whether or not to skip annotate structural variant subworkflow.",
                     "fa_icon": "fas fa-toggle-on"
+                },
+                "skip_vep_filter": {
+                    "type": "boolean",
+                    "description": "Specifies whether or not to filter results based on a list of candidate genes specified in 'vep_filters'.",
+                    "fa_icon": "fas fa-toggle-on"
                 }
             }
         },

diff --git a/workflows/raredisease.nf b/workflows/raredisease.nf
@@ -58,6 +58,10 @@ if (!params.skip_cnv_calling) {
     mandatoryParams += ["ploidy_model", "gcnvcaller_model"]
 }
 
+if (!params.skip_vep_filter) {
+    mandatoryParams += ["vep_filters"]
+}
+
 def missingParamsCount = 0
 for (param in mandatoryParams.unique()) {
     if (params[param] == null) {