Fixing bug charite#248 for ENSEMBL that used gene_id for gene_name

closes charite#248
holtgrewe · Aug 26, 2016 · 23ab36a · 23ab36a
1 parent 73621d3
commit 23ab36a
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 1 deletion.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,6 +2,10 @@
 
 ## develop
 
+### jannovar-core
+
+* fixing bug #248 for ENSEMBL that used `gene_id` for `gene_name`
+
 ## v0.17
 
 ### jped-cli

diff --git a/...ovar-core/src/main/java/de/charite/compbio/jannovar/impl/parse/ensembl/EnsemblParser.java b/...ovar-core/src/main/java/de/charite/compbio/jannovar/impl/parse/ensembl/EnsemblParser.java
@@ -185,6 +185,7 @@ private Map<String, TranscriptModelBuilder> processGeneGFFRecords(ArrayList<Feat
 			final List<FeatureRecord> featureRecords = txEntry.getValue();
 
 			final FeatureRecord first = featureRecords.get(0);
+			final String geneName = first.getAttributes().get("gene_name");
 			final String geneID = first.getAttributes().get("gene_id");
 			final String txID = first.getAttributes().get("transcript_id");
 
@@ -194,7 +195,8 @@ private Map<String, TranscriptModelBuilder> processGeneGFFRecords(ArrayList<Feat
 			final Strand strand = (first.getStrand() == FeatureRecord.Strand.FORWARD) ? Strand.FWD : Strand.REV;
 			builder.setStrand(strand);
 			builder.setAccession(txID);
-			builder.setGeneSymbol(geneID);
+			builder.setGeneID(geneID);
+			builder.setGeneSymbol(geneName);
 			builder.setSequence(txID);
 
 			// Iterate over the features, interpreting "exon" and "CDS"/"stop_codon" entries