nf-core · ramprasadn · Feb 5, 2024 · Feb 2, 2024 · Feb 2, 2024 · Feb 2, 2024
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -27,6 +27,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - New workflow for annotating mobile elements [#483](https://github.com/nf-core/raredisease/pull/483)
 - Added a functionality to subsample mitochondrial alignment, and a new parameter `skip_mt_subsample` to skip the subworkflow [#508](https://github.com/nf-core/raredisease/pull/508).
 - Chromograph to plot coverage across chromosomes [#507](https://github.com/nf-core/raredisease/pull/507)
+- Added two new parameters `variant_consequences_snv` and `variant_consequences_sv` to supply variant consequence files for annotating SNVs and SVs. [#509](https://github.com/nf-core/raredisease/pull/509)
 
 ### `Changed`
 

diff --git a/assets/variant_consequences_v2.txt b/assets/variant_consequences_v2.txt
diff --git a/conf/test.config b/conf/test.config
@@ -43,7 +43,7 @@ params {
     intervals_y          = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/targetY.interval_list"
     known_dbsnp          = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/dbsnp_-138-.vcf.gz"
     ml_model             = "https://s3.amazonaws.com/sentieon-release/other/SentieonDNAscopeModel1.0.model"
-    mobile_element_references = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/mobile_element_references.tsv"
+    mobile_element_references       = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/mobile_element_references.tsv"
     mobile_element_svdb_annotations = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/svdb_querydb_files.csv"
     reduced_penetrance   = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/reduced_penetrance.tsv"
     score_config_mt      = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/rank_model_snv.ini"
@@ -55,6 +55,8 @@ params {
     vcfanno_lua          = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/vcfanno_functions.lua"
     vcfanno_resources    = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/vcfanno_resources.txt"
     vcfanno_toml         = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/vcfanno_config.toml"
+    variant_consequences_snv = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/variant_consequences_v2.txt"
+    variant_consequences_sv  = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/variant_consequences_v2.txt"
     vep_cache            = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/vep_cache_and_plugins.tar.gz"
     vep_filters          = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/hgnc.txt"
     vep_cache_version    = 107

diff --git a/conf/test_one_sample.config b/conf/test_one_sample.config
@@ -43,7 +43,7 @@ params {
     intervals_y          = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/targetY.interval_list"
     known_dbsnp          = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/dbsnp_-138-.vcf.gz"
     ml_model             = "https://s3.amazonaws.com/sentieon-release/other/SentieonDNAscopeModel1.0.model"
-    mobile_element_references = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/mobile_element_references.tsv"
+    mobile_element_references       = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/mobile_element_references.tsv"
     mobile_element_svdb_annotations = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/svdb_querydb_files.csv"
     reduced_penetrance   = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/reduced_penetrance.tsv"
     score_config_mt      = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/rank_model_snv.ini"
@@ -55,6 +55,8 @@ params {
     vcfanno_lua          = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/vcfanno_functions.lua"
     vcfanno_resources    = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/vcfanno_resources.txt"
     vcfanno_toml         = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/vcfanno_config.toml"
+    variant_consequences_snv = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/variant_consequences_v2.txt"
+    variant_consequences_sv  = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/variant_consequences_v2.txt"
     vep_cache            = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/vep_cache_and_plugins.tar.gz"
     vep_filters          = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/hgnc.txt"
     vep_cache_version    = 107

diff --git a/docs/usage.md b/docs/usage.md
@@ -221,15 +221,16 @@ The mandatory and optional parameters for each category are tabulated below.
 
 ##### 7. SNV annotation & Ranking
 
-| Mandatory                     | Optional                       |
-| ----------------------------- | ------------------------------ |
-| genome<sup>1</sup>            | reduced_penetrance<sup>7</sup> |
-| vcfanno_resources<sup>2</sup> | vcfanno_lua                    |
-| vcfanno_toml<sup>3</sup>      | vep_filters<sup>8</sup>        |
-| vep_cache_version             | cadd_resources<sup>9</sup>     |
-| vep_cache<sup>4</sup>         | vep_plugin_files<sup>10</sup>  |
-| gnomad_af<sup>5</sup>         |                                |
-| score_config_snv<sup>6</sup>  |                                |
+| Mandatory                            | Optional                       |
+| ------------------------------------ | ------------------------------ |
+| genome<sup>1</sup>                   | reduced_penetrance<sup>8</sup> |
+| vcfanno_resources<sup>2</sup>        | vcfanno_lua                    |
+| vcfanno_toml<sup>3</sup>             | vep_filters<sup>9</sup>        |
+| vep_cache_version                    | cadd_resources<sup>10</sup>    |
+| vep_cache<sup>4</sup>                | vep_plugin_files<sup>11</sup>  |
+| gnomad_af<sup>5</sup>                |                                |
+| score_config_snv<sup>6</sup>         |                                |
+| variant_consequences_snv<sup>7</sup> |                                |
 
 <sup>1</sup>Genome version is used by VEP. You have the option to choose between GRCh37 and GRCh38.<br />
 <sup>2</sup>Path to VCF files and their indices used by vcfanno. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/vcfanno_resources.txt).<br />
@@ -240,10 +241,11 @@ See example cache [here](https://raw.githubusercontent.com/nf-core/test-datasets
 <sup>5</sup> GnomAD VCF files can be downloaded from [here](https://gnomad.broadinstitute.org/downloads). The option `gnomad_af` expects a tab-delimited file with
 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). 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 />
-<sup>10</sup>A CSV file that describes the files used by VEP's named and custom plugins. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/vep_files.csv). <br />
+<sup>7</sup>File containing list of SO terms listed in the order of severity from most severe to lease severe for annotating genomic and mitochondrial SNVs. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/variant_consequences_v2.txt). You can learn more about these terms [here](https://grch37.ensembl.org/info/genome/variation/prediction/predicted_data.html).
+<sup>8</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>9</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>10</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 />
+<sup>11</sup>A CSV file that describes the files used by VEP's named and custom plugins. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/vep_files.csv). <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>")
 
@@ -256,20 +258,23 @@ no header and the following columns: `CHROM POS REF_ALLELE ALT_ALLELE AF`. Sampl
 | vep_cache_version                              | vep_filters        |
 | vep_cache                                      | vep_plugin_files   |
 | score_config_sv                                |                    |
+| variant_consequences_sv<sup>2</sup>            |                    |
 
 <sup>1</sup> A CSV file that describes the databases (VCFs or BEDPEs) used by SVDB for annotating structural variants. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/svdb_querydb_files.csv). Information about the column headers can be found [here](https://github.com/J35P312/SVDB#Query).
+<sup>2</sup> File containing list of SO terms listed in the order of severity from most severe to lease severe for annotating genomic SVs. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/variant_consequences_v2.txt). You can learn more about these terms [here](https://grch37.ensembl.org/info/genome/variation/prediction/predicted_data.html).
 
 ##### 9. Mitochondrial annotation
 
-| Mandatory         | Optional         |
-| ----------------- | ---------------- |
-| genome            | vep_filters      |
-| mito_name         | vep_plugin_files |
-| vcfanno_resources |                  |
-| vcfanno_toml      |                  |
-| vep_cache_version |                  |
-| vep_cache         |                  |
-| score_config_mt   |                  |
+| Mandatory                | Optional         |
+| ------------------------ | ---------------- |
+| genome                   | vep_filters      |
+| mito_name                | vep_plugin_files |
+| vcfanno_resources        |                  |
+| vcfanno_toml             |                  |
+| vep_cache_version        |                  |
+| vep_cache                |                  |
+| score_config_mt          |                  |
+| variant_consequences_snv |                  |
 
 ##### 10. Mobile element annotation
 
@@ -279,6 +284,7 @@ no header and the following columns: `CHROM POS REF_ALLELE ALT_ALLELE AF`. Sampl
 | mobile_element_svdb_annotations<sup>1</sup> |             |
 | vep_cache_version                           |             |
 | vep_cache                                   |             |
+| variant_consequences_sv                     |             |
 
 <sup>1</sup> A CSV file that describes the databases (VCFs) used by SVDB for annotating mobile elements with allele frequencies. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/svdb_querydb_files.csv).
 

diff --git a/main.nf b/main.nf
@@ -47,6 +47,8 @@ params.sdf                            = WorkflowMain.getGenomeAttribute(params,
 params.svdb_query_dbs                 = WorkflowMain.getGenomeAttribute(params, 'svdb_query_dbs')
 params.target_bed                     = WorkflowMain.getGenomeAttribute(params, 'target_bed')
 params.variant_catalog                = WorkflowMain.getGenomeAttribute(params, 'variant_catalog')
+params.variant_consequences_snv       = WorkflowMain.getGenomeAttribute(params, 'variant_consequences_snv')
+params.variant_consequences_sv        = WorkflowMain.getGenomeAttribute(params, 'variant_consequences_sv')
 params.vep_filters                    = WorkflowMain.getGenomeAttribute(params, 'vep_filters')
 params.vcf2cytosure_blacklist         = WorkflowMain.getGenomeAttribute(params, 'vcf2cytosure_blacklist')
 params.vcfanno_resources              = WorkflowMain.getGenomeAttribute(params, 'vcfanno_resources')

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -625,6 +625,18 @@
             "fa_icon": "fas fa-user-cog",
             "description": "Options used to facilitate the annotation of the variants.",
             "properties": {
+                "variant_consequences_snv": {
+                    "type": "string",
+                    "description": "File containing list of SO terms listed in the order of severity from most severe to lease severe for annotating genomic and mitochondrial SNVs.",
+                    "help_text": "For more information check https://grch37.ensembl.org/info/genome/variation/prediction/predicted_data.html",
+                    "fa_icon": "fas fa-file-csv"
+                },
+                "variant_consequences_sv": {
+                    "type": "string",
+                    "description": "File containing list of SO terms listed in the order of severity from most severe to lease severe for annotating genomic SVs.",
+                    "help_text": "For more information check https://grch37.ensembl.org/info/genome/variation/prediction/predicted_data.html",
+                    "fa_icon": "fas fa-file-csv"
+                },
                 "vep_cache_version": {
                     "type": "integer",
                     "default": 110,

diff --git a/workflows/raredisease.nf b/workflows/raredisease.nf
@@ -40,19 +40,19 @@ if (params.run_rtgvcfeval) {
 
 if (!params.skip_snv_annotation) {
     mandatoryParams += ["genome", "vcfanno_resources", "vcfanno_toml", "vep_cache", "vep_cache_version",
-    "gnomad_af", "score_config_snv"]
+    "gnomad_af", "score_config_snv", "variant_consequences_snv"]
 }
 
 if (!params.skip_sv_annotation) {
-    mandatoryParams += ["genome", "vep_cache", "vep_cache_version", "score_config_sv"]
+    mandatoryParams += ["genome", "vep_cache", "vep_cache_version", "score_config_sv", "variant_consequences_sv"]
     if (!params.svdb_query_bedpedbs && !params.svdb_query_dbs) {
         println("params.svdb_query_bedpedbs or params.svdb_query_dbs should be set.")
         missingParamsCount += 1
     }
 }
 
 if (!params.skip_mt_annotation) {
-    mandatoryParams += ["genome", "mito_name", "vcfanno_resources", "vcfanno_toml", "vep_cache_version", "vep_cache"]
+    mandatoryParams += ["genome", "mito_name", "vcfanno_resources", "vcfanno_toml", "vep_cache_version", "vep_cache", "variant_consequences_snv"]
 }
 
 if (params.analysis_type.equals("wes")) {
@@ -72,7 +72,7 @@ if (!params.skip_vep_filter) {
 }
 
 if (!params.skip_me_annotation) {
-    mandatoryParams += ["mobile_element_svdb_annotations"]
+    mandatoryParams += ["mobile_element_svdb_annotations", "variant_consequences_snv"]
 }
 
 for (param in mandatoryParams.unique()) {
@@ -288,7 +288,10 @@ workflow RAREDISEASE {
     ch_target_intervals         = ch_references.target_intervals
     ch_variant_catalog          = params.variant_catalog                    ? Channel.fromPath(params.variant_catalog).map { it -> [[id:it[0].simpleName],it]}.collect()
                                                                             : Channel.value([[],[]])
-    ch_variant_consequences     = Channel.fromPath("$projectDir/assets/variant_consequences_v2.txt", checkIfExists: true).collect()
+    ch_variant_consequences_snv = params.variant_consequences_snv           ? Channel.fromPath(params.variant_consequences_snv).collect()
+                                                                            : Channel.value([])
+    ch_variant_consequences_sv  = params.variant_consequences_sv            ? Channel.fromPath(params.variant_consequences_sv).collect()
+                                                                            : Channel.value([])
     ch_vcfanno_resources        = params.vcfanno_resources                  ? Channel.fromPath(params.vcfanno_resources).splitText().map{it -> it.trim()}.collect()
                                                                             : Channel.value([])
     ch_vcf2cytosure_blacklist   = params.vcf2cytosure_blacklist             ? Channel.fromPath(params.vcf2cytosure_blacklist).collect()
@@ -490,7 +493,7 @@ workflow RAREDISEASE {
 
         ANN_CSQ_PLI_SV (
             GENERATE_CLINICAL_SET_SV.out.vcf,
-            ch_variant_consequences
+            ch_variant_consequences_sv
         )
         ch_versions = ch_versions.mix(ANN_CSQ_PLI_SV.out.versions)
 
@@ -535,7 +538,7 @@ workflow RAREDISEASE {
 
         ANN_CSQ_PLI_SNV (
             GENERATE_CLINICAL_SET_SNV.out.vcf,
-            ch_variant_consequences
+            ch_variant_consequences_snv
         )
         ch_versions = ch_versions.mix(ANN_CSQ_PLI_SNV.out.versions)
 
@@ -577,7 +580,7 @@ workflow RAREDISEASE {
 
         ANN_CSQ_PLI_MT(
             GENERATE_CLINICAL_SET_MT.out.vcf,
-            ch_variant_consequences
+            ch_variant_consequences_snv
         )
         ch_versions = ch_versions.mix(ANN_CSQ_PLI_MT.out.versions)
 
@@ -663,7 +666,7 @@ workflow RAREDISEASE {
             ch_genome_fasta,
             ch_genome_dictionary,
             ch_vep_cache,
-            ch_variant_consequences,
+            ch_variant_consequences_sv,
             ch_vep_filters,
             params.genome,
             params.vep_cache_version,