Rename vep option and patch dbs

Author: dglemos

modules/Bio/EnsEMBL/VEP/Config.pm

@@ -149,10 +149,10 @@ our @VEP_PARAMS = (
   'nearest=s',               # get nearest transcript, gene or symbol (for gene)
   'distance=s',              # set up/downstream distance
   'clin_sig_allele=i',       # use allele specific clinical significance data where it exists
-  'somatic_classification',  # report the somatic classification of a variant as reported by ClinVar
-  'overlaps',                # report length and percent of a transcript or regulatory feature overlaped with a SV
-  'max_sv_size=i',           # modify the size of structural variant to be handled (limited by default to reduce memory requirements)
-  'remove_hgvsp_version',    # removes translation version from hgvs_protein output
+  'clinvar_somatic_classification',  # report the somatic classification of a variant as reported by ClinVar
+  'overlaps',                        # report length and percent of a transcript or regulatory feature overlaped with a SV
+  'max_sv_size=i',                   # modify the size of structural variant to be handled (limited by default to reduce memory requirements)
+  'remove_hgvsp_version',            # removes translation version from hgvs_protein output
 
 
   # verbosity options

modules/Bio/EnsEMBL/VEP/Constants.pm

@@ -79,7 +79,7 @@ our @FLAG_FIELDS = (
   { flag => 'minimal',         fields => ['MINIMISED']},
   { flag => 'spdi',            fields => ['SPDI']},
   { flag => 'ga4gh_vrs',       fields => ['GA4GH_VRS']},
-  { flag => 'somatic_classification', fields => ['SOMATIC_CLASSIFICATION']},
+  { flag => 'clinvar_somatic_classification', fields => ['CLINVAR_SOMATIC_CLASSIFICATION']},
 
   # gene-related
   { flag => 'symbol',          fields => ['SYMBOL','SYMBOL_SOURCE','HGNC_ID'] },
@@ -237,7 +237,7 @@ our %FIELD_DESCRIPTIONS = (
   'MAX_AF_POPS'        => 'Populations in which maximum allele frequency was observed',
   'DISTANCE'           => 'Shortest distance from variant to transcript',
   'CLIN_SIG'           => 'ClinVar clinical significance of the dbSNP variant',
-  'SOMATIC_CLASSIFICATION' => 'ClinVar somatic classification of the dbSNP variant',
+  'CLINVAR_SOMATIC_CLASSIFICATION' => 'ClinVar somatic classification of the dbSNP variant',
   'BIOTYPE'            => 'Biotype of transcript or regulatory feature',
   'PUBMED'             => 'Pubmed ID(s) of publications that cite existing variant',
   'ALLELE_NUM'         => 'Allele number from input; 0 is reference, 1 is first alternate etc',

modules/Bio/EnsEMBL/VEP/OutputFactory.pm

@@ -84,8 +84,6 @@ use Bio::EnsEMBL::VEP::OutputFactory::VEP_output;
 use Bio::EnsEMBL::VEP::OutputFactory::VCF;
 use Bio::EnsEMBL::VEP::OutputFactory::Tab;
 
-use Data::Dumper;
-
 our $CAN_USE_JSON;
 
 BEGIN {
@@ -176,7 +174,7 @@ sub new {
     max_af
     pubmed
     clin_sig_allele
-    somatic_classification
+    clinvar_somatic_classification
 
     numbers
     domains
@@ -1047,8 +1045,8 @@ sub add_colocated_variant_info {
     push @{$hash->{VAR_SYNONYMS}}, $ex->{var_synonyms} if $self->{var_synonyms} && $ex->{var_synonyms} && !$self->{_config}->{_params}->{is_vr};
 
     # ClinVar somatic classification
-    if(defined($ex->{clinical_impact}) && $self->{somatic_classification}) {
-      $hash->{SOMATIC_CLASSIFICATION} = $ex->{clinical_impact};
+    if(defined($ex->{clinical_impact}) && $self->{clinvar_somatic_classification}) {
+      $hash->{CLINVAR_SOMATIC_CLASSIFICATION} = $ex->{clinical_impact};
     }
 
     if(defined($ex->{clin_sig_allele}) && $self->{clin_sig_allele} )

modules/Bio/EnsEMBL/VEP/OutputFactory/JSON.pm

@@ -108,7 +108,7 @@ my %RENAME_KEYS = (
   'chr' => 'seq_region_name',
   'variation_name' => 'id',
   'sv' => 'colocated_structural_variants',
-  'clinical_impact' => 'somatic_classification'
+  'clinical_impact' => 'clinvar_somatic_classification'
 );
 
 my %NUMBERIFY_EXEMPT = (

t/Runner.t

@@ -235,6 +235,7 @@ is_deeply($runner->get_OutputFactory, bless( {
   'clin_sig_allele' => 1,
   'var_synonyms' => undef,
   'ga4gh_vrs' => undef,
+  'clinvar_somatic_classification' => undef,
 }, 'Bio::EnsEMBL::VEP::OutputFactory::VEP_output' ), 'get_OutputFactory');
 
 

t/test-genome-DBs/homo_vepiens/variation/meta.txt

@@ -1,5 +1,5 @@
 1	\N	schema_type	variation
-2	\N	schema_version	114
+2	\N	schema_version	115
 3	\N	patch	patch_73_74_a.sql|schema version
 4	\N	patch	patch_73_74_b.sql|Add doi and UCSC id to publication table
 5	\N	patch	patch_73_74_c.sql|Add clinical_significance to variation_feature table
@@ -133,13 +133,9 @@
 164	\N	patch	patch_107_108_a.sql|schema version
 165	\N	patch	patch_107_108_b.sql|fix SAS population description
 166	\N	patch	patch_108_109_a.sql|schema version
-167 \N  patch   patch_109_110_a.sql|schema version
-168 \N  patch   patch_109_110_b.sql|Add DDG2P data_source_attrib to variation_citation
-169 \N  patch   patch_109_110_c.sql|Add new clinical_significance values to variation, variation_feature and structural_variation
-170 \N  patch   patch_110_111_a.sql|schema version
-171 \N  patch   patch_110_111_b.sql|Update transcript_variation primary key
-172 \N  patch   patch_111_112_a.sql|schema version
 173	\N	patch	patch_111_112_a.sql|schema version
 174	\N	patch	patch_112_113_a.sql|schema version
 175	\N	patch	patch_112_113_b.sql|Update meta_key length
 176	\N	patch	patch_113_114_a.sql|schema version
+177	\N	patch	patch_114_115_a.sql|schema version
+178	\N	patch	patch_114_115_b.sql|Add column DNA_type to phenotype_feature

t/test-genome-DBs/homo_vepiens/variation/table.sql

@@ -186,7 +186,7 @@ CREATE TABLE `meta` (
   PRIMARY KEY (`meta_id`),
   UNIQUE KEY `species_key_value_idx` (`species_id`,`meta_key`,`meta_value`),
   KEY `species_value_idx` (`species_id`,`meta_value`)
-) ENGINE=MyISAM AUTO_INCREMENT=177 DEFAULT CHARSET=latin1;
+) ENGINE=MyISAM AUTO_INCREMENT=179 DEFAULT CHARSET=latin1;
 
 CREATE TABLE `meta_coord` (
   `table_name` varchar(40) NOT NULL,
@@ -239,6 +239,7 @@ CREATE TABLE `phenotype_feature` (
   `seq_region_start` int(11) unsigned DEFAULT NULL,
   `seq_region_end` int(11) unsigned DEFAULT NULL,
   `seq_region_strand` tinyint(4) DEFAULT NULL,
+  `DNA_type` enum('Germline','Somatic') DEFAULT NULL,
   PRIMARY KEY (`phenotype_feature_id`),
   KEY `phenotype_idx` (`phenotype_id`),
   KEY `object_idx` (`object_id`,`type`),