Vep update

CHANGELOG.md

@@ -23,6 +23,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - GATK CNVCaller uses segments instead of intervals, filters out "reference" segments between the calls, and fixes a bug with how `ch_readcount_intervals` was handled [#472](https://github.com/nf-core/raredisease/pull/472)
 - bwa aligner [#474](https://github.com/nf-core/raredisease/pull/474)
 - Add FOUND_IN tag, which mentions the variant caller that found the mutation, in the INFO column of the vcf files [#471](https://github.com/nf-core/raredisease/pull/471)
+- A new parameter `vep_plugin_files` to supply files required by vep plugins [#482](https://github.com/nf-core/raredisease/pull/482)
 - New workflow for annotating mobile elements [#483](https://github.com/nf-core/raredisease/pull/483)
 
 ### `Changed`
@@ -43,6 +44,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Changed the name of the parameter from `skip_cnv_calling` to `skip_germlinecnvcaller` [#435](https://github.com/nf-core/raredisease/pull/435)
 - Check SVDB query input files for existence and correct format [#476](https://github.com/nf-core/raredisease/pull/476)
 - Change hardcoded platform value to params.platform in align_MT.config [#475](https://github.com/nf-core/raredisease/pull/475)
+- Installed the nf-core version of ensemblvep/vep module [#482](https://github.com/nf-core/raredisease/pull/482)
 
 ### `Fixed`
 

assets/variant_consequences_v1.txt → assets/variant_consequences_v2.txt

@@ -6,12 +6,14 @@ frameshift_variant
 stop_lost
 start_lost
 transcript_amplification
+feature_elongation
+feature_truncation
 inframe_insertion
 inframe_deletion
 missense_variant
 protein_altering_variant
-splice_region_variant
 splice_donor_5th_base_variant
+splice_region_variant
 splice_donor_region_variant
 splice_polypyrimidine_tract_variant
 incomplete_terminal_codon_variant
@@ -26,14 +28,14 @@ non_coding_transcript_exon_variant
 intron_variant
 NMD_transcript_variant
 non_coding_transcript_variant
+coding_transcript_variant
 upstream_gene_variant
 downstream_gene_variant
 TFBS_ablation
 TFBS_amplification
 TF_binding_site_variant
 regulatory_region_ablation
 regulatory_region_amplification
-feature_elongation
 regulatory_region_variant
-feature_truncation
 intergenic_variant
+sequence_variant

assets/vep_plugin_files_schema.json

@@ -0,0 +1,19 @@
+{
+    "$schema": "http://json-schema.org/draft-07/schema",
+    "$id": "https://raw.githubusercontent.com/nf-core/raredisease/master/assets/mobile_element_references_schema.json",
+    "title": "Schema for VEP plugin files and their indices",
+    "description": "Schema for VEP plugin files and their indices",
+    "type": "array",
+    "items": {
+        "type": "object",
+        "properties": {
+            "vep_files": {
+                "type": "string",
+                "format": "file-path",
+                "exists": true,
+                "errorMessage": "Path to vep plugin files and their indices"
+            }
+        },
+        "required": ["vep_files"]
+    }
+}

conf/modules/annotate_genome_snvs.config

@@ -79,16 +79,15 @@ process {
             ext.prefix = { "${vcf.simpleName}_rohann_vcfanno_filter_vep" }
             ext.args   = [
                 '--dir_plugins vep_cache/Plugins',
-                '--plugin LoFtool,vep_cache/LoFtool_scores.txt',
-                '--plugin pLI,vep_cache/pLI_values_107.txt',
-                '--plugin SpliceAI,snv=vep_cache/spliceai_21_scores_raw_snv_-v1.3-.vcf.gz,indel=vep_cache/spliceai_21_scores_raw_snv_-v1.3-.vcf.gz',
-                '--plugin MaxEntScan,vep_cache/fordownload,SWA,NCSS',
+                '--plugin LoFtool,LoFtool_scores.txt',
+                '--plugin pLI,pLI_values_107.txt',
+                '--plugin SpliceAI,snv=spliceai_21_scores_raw_snv_-v1.3-.vcf.gz,indel=spliceai_21_scores_raw_snv_-v1.3-.vcf.gz',
                 '--distance 5000',
                 '--buffer_size 20000',
                 '--format vcf --max_sv_size 248956422',
                 '--appris --biotype --cache --canonical --ccds --compress_output bgzip',
                 '--domains --exclude_predicted --force_overwrite',
-                '--hgvs --humdiv --no_progress --no_stats --numbers',
+                '--hgvs --humdiv --no_progress --numbers',
                 '--merged --polyphen p --protein --offline --regulatory --sift p --symbol --tsl',
                 '--uniprot --vcf'
             ].join(' ')

conf/modules/annotate_mobile_elements.config

@@ -40,12 +40,12 @@ process {
         ext.args   = { [
             '--dir_cache vep_cache',
             '--dir_plugins vep_cache/Plugins',
-            '--plugin pLI,vep_cache/pLI_values_107.txt',
+            '--plugin pLI,pLI_values_107.txt',
             '--appris --biotype --buffer_size 100 --canonical --cache --ccds',
             '--compress_output bgzip --distance 5000 --domains',
             '--exclude_predicted --force_overwrite --format vcf',
             '--fork 4 --hgvs --humdiv --max_sv_size 248956422 --merged',
-            '--no_progress --no_stats --numbers --per_gene --polyphen p',
+            '--no_progress --numbers --per_gene --polyphen p',
             '--protein --offline --regulatory --sift p',
             '--symbol --tsl --uniprot --vcf'
         ].join(' ') }

conf/modules/annotate_mt_snvs.config

@@ -20,16 +20,15 @@ process {
         withName: '.*ANNOTATE_MT_SNVS:ENSEMBLVEP_MT' {
             ext.args   = [
                 '--dir_plugins vep_cache/Plugins',
-                '--plugin LoFtool,vep_cache/LoFtool_scores.txt',
-                '--plugin pLI,vep_cache/pLI_values_107.txt',
-                '--plugin SpliceAI,snv=vep_cache/spliceai_21_scores_raw_snv_-v1.3-.vcf.gz,indel=vep_cache/spliceai_21_scores_raw_snv_-v1.3-.vcf.gz',
-                '--plugin MaxEntScan,vep_cache/fordownload,SWA,NCSS',
+                '--plugin LoFtool,LoFtool_scores.txt',
+                '--plugin pLI,pLI_values_107.txt',
+                '--plugin SpliceAI,snv=spliceai_21_scores_raw_snv_-v1.3-.vcf.gz,indel=spliceai_21_scores_raw_snv_-v1.3-.vcf.gz',
                 '--distance 0',
                 '--buffer_size 20000',
                 '--format vcf --fork 4 --max_sv_size 248956422',
                 '--appris --biotype --cache --canonical --ccds --compress_output bgzip',
                 '--domains --exclude_predicted --force_overwrite',
-                '--hgvs --humdiv --no_progress --no_stats --numbers',
+                '--hgvs --humdiv --no_progress --numbers',
                 '--merged --polyphen p --protein --offline --regulatory --sift p --symbol --tsl --vcf',
                 '--uniprot'
             ].join(' ')

conf/modules/annotate_structural_variants.config

@@ -46,12 +46,12 @@ process {
             ext.args   = [
                 '--dir_cache vep_cache',
                 '--dir_plugins vep_cache/Plugins',
-                '--plugin pLI,vep_cache/pLI_values_107.txt',
+                '--plugin pLI,pLI_values_107.txt',
                 '--appris --biotype --buffer_size 100 --canonical --cache --ccds',
                 '--compress_output bgzip --distance 5000 --domains',
                 '--exclude_predicted --force_overwrite --format vcf',
                 '--fork 4 --hgvs --humdiv --max_sv_size 248956422 --merged',
-                '--no_progress --no_stats --numbers --per_gene --polyphen p',
+                '--no_progress --numbers --per_gene --polyphen p',
                 '--protein --offline --regulatory --sift p',
                 '--symbol --tsl --uniprot --vcf'
             ].join(' ')

conf/test.config

@@ -58,10 +58,5 @@ params {
     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
-}
-
-process {
-    withName: '.*FILTERVEP.*' {
-        container  = "docker.io/ensemblorg/ensembl-vep:release_107.0"
-    }
+    vep_plugin_files     = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/vep_files.csv"
 }

conf/test_one_sample.config

@@ -58,10 +58,5 @@ params {
     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
-}
-
-process {
-    withName: '.*FILTERVEP.*' {
-        container  = "docker.io/ensemblorg/ensembl-vep:release_107.0"
-    }
+    vep_plugin_files     = "https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/vep_files.csv"
 }

docs/usage.md

@@ -225,22 +225,23 @@ The mandatory and optional parameters for each category are tabulated below.
 | 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_cache<sup>4</sup>         | vep_plugin_files<sup>10</sup>  |
 | gnomad_af<sup>5</sup>         |                                |
 | score_config_snv<sup>6</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 />
 <sup>3</sup>Path to a vcfanno configuration file. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/vcfanno_config.toml).<br />
 <sup>4</sup> VEP caches can be downloaded [here](https://www.ensembl.org/info/docs/tools/vep/script/vep_cache.html#cache).
-VEP plugins and associated files may be installed in the cache directory, and the plugin pLI is mandatory to install.
+VEP plugins may be installed in the cache directory, and the plugin pLI is mandatory to install. To supply files required by VEP plugins, use `vep_plugin_files` parameter.
 See example cache [here](https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/reference/vep_cache_and_plugins.tar.gz).<br />
 <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 />
 
 > 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>")
 
@@ -251,22 +252,22 @@ no header and the following columns: `CHROM POS REF_ALLELE ALT_ALLELE AF`. Sampl
 | genome                                         | reduced_penetrance |
 | svdb_query_dbs/svdb_query_bedpedbs<sup>1</sup> |                    |
 | vep_cache_version                              | vep_filters        |
-| vep_cache                                      |                    |
+| vep_cache                                      | vep_plugin_files   |
 | score_config_sv                                |                    |
 
 <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).
 
 ##### 9. Mitochondrial annotation
 
-| Mandatory         | Optional    |
-| ----------------- | ----------- |
-| genome            | vep_filters |
-| mito_name         |             |
-| 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   |                  |
 
 ##### 10. Mobile element annotation
 

main.nf

@@ -54,7 +54,7 @@ params.vcfanno_toml                   = WorkflowMain.getGenomeAttribute(params,
 params.vcfanno_lua                    = WorkflowMain.getGenomeAttribute(params, 'vcfanno_lua')
 params.vep_cache                      = WorkflowMain.getGenomeAttribute(params, 'vep_cache')
 params.vep_cache_version              = WorkflowMain.getGenomeAttribute(params, 'vep_cache_version')
-
+params.vep_plugin_files               = WorkflowMain.getGenomeAttribute(params, 'vep_plugin_files')
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     VALIDATE & PRINT PARAMETER SUMMARY

modules.json

@@ -115,6 +115,11 @@
                         "git_sha": "29984d70aea47d06f0062a1785d76c357dd40ea9",
                         "installed_by": ["modules"]
                     },
+                    "ensemblvep/vep": {
+                        "branch": "master",
+                        "git_sha": "76a0696a60c41c57fc5f6040ac31b11ce5d4d8dd",
+                        "installed_by": ["modules"]
+                    },
                     "expansionhunter": {
                         "branch": "master",
                         "git_sha": "0260e5d22372eae434816d6970dedf3f5adc0053",