Handle scRNA biotype; Add AR to uniprot isoforms

mskcc · Jul 20, 2020 · e1f5744 · e1f5744
1 parent cd51d65
commit e1f5744
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 3 deletions.
diff --git a/data/isoform_overrides_uniprot b/data/isoform_overrides_uniprot
@@ -874,6 +874,7 @@ ENST00000297988	AQP7	NM_001170.1	CCDS6541.1
 ENST00000219660	AQP8	NM_001169.2	CCDS10626.1
 ENST00000219919	AQP9	NM_020980.3	CCDS10165.1
 ENST00000156471	AQR	NM_014691.2	CCDS42013.1
+ENST00000374690	AR	NM_000044.3	CCDS14387.1
 ENST00000377045	ARAF	NM_001654.4	CCDS35232.1
 ENST00000393609	ARAP1	NM_001040118.2	CCDS41687.1
 ENST00000303965	ARAP2	NM_015230.3	CCDS3441.1

diff --git a/data/isoform_overrides_uniprot_from_biomart_91 b/data/isoform_overrides_uniprot_from_biomart_91
@@ -874,6 +874,7 @@ ENST00000297988	AQP7	NM_001170.1	CCDS6541.1
 ENST00000219660	AQP8	NM_001169.2	CCDS10626.1
 ENST00000219919	AQP9	NM_020980.3	CCDS10165.1
 ENST00000156471	AQR	NM_014691.2	CCDS42013.1
+ENST00000374690	AR	NM_000044.3	CCDS14387.1
 ENST00000377045	ARAF	NM_001654.4	CCDS35232.1
 ENST00000393609	ARAP1	NM_001040118.2	CCDS41687.1
 ENST00000303965	ARAP2	NM_015230.3	CCDS3441.1

diff --git a/vcf2maf.pl b/vcf2maf.pl
@@ -29,7 +29,7 @@
     Lys K Met M Phe F Pro P Ser S Thr T Trp W Tyr Y Val V Xxx X Ter * );
 
 # Prioritize Sequence Ontology terms in order of severity, as estimated by Ensembl:
-# http://useast.ensembl.org/info/genome/variation/predicted_data.html#consequences
+# https://ensembl.org/info/genome/variation/prediction/predicted_data.html
 sub GetEffectPriority {
     my ( $effect ) = @_;
     $effect = '' unless( defined $effect );
@@ -93,7 +93,7 @@ sub GetEffectPriority {
 }
 
 # Prioritize the transcript biotypes that variants are annotated to, based on disease significance:
-# All possible biotypes are defined here: http://www.gencodegenes.org/gencode_biotypes.html
+# All possible biotypes are defined here: https://www.gencodegenes.org/pages/biotypes.html
 sub GetBiotypePriority {
     my ( $biotype ) = @_;
     $biotype = '' unless( defined $biotype );
@@ -117,8 +117,9 @@ sub GetBiotypePriority {
         'sRNA' => 3, # Non-coding RNA predicted using sequences from RFAM and miRBase
         'scaRNA' => 3, # Non-coding RNA predicted using sequences from RFAM and miRBase
         'rRNA' => 3, # Non-coding RNA predicted using sequences from RFAM and miRBase
+        'scRNA' => 3, # Non-coding RNA predicted using sequences from Rfam and miRBase
         'lincRNA' => 3, # Long, intervening noncoding (linc) RNAs, that can be found in evolutionarily conserved, intergenic regions
-        'lncRNA' => 3, # Long, noncoding (lnc) RNAs  
+        'lncRNA' => 3, # Replaces 3prime_overlapping_ncRNA, antisense, bidirectional_promoter_lncRNA, lincRNA, macro_lncRNA, non_coding, processed_transcript, sense_intronic and sense_overlapping
         'bidirectional_promoter_lncrna' => 3, # A non-coding locus that originates from within the promoter region of a protein-coding gene, with transcription proceeding in the opposite direction on the other strand
         'bidirectional_promoter_lncRNA' => 3, # A non-coding locus that originates from within the promoter region of a protein-coding gene, with transcription proceeding in the opposite direction on the other strand
         'known_ncrna' => 4,