Merge pull request #6754 from thehyve/gene_info_parser_fix

Gene info parser fix
cBioPortal · Nov 27, 2019 · 8a953f7 · 8a953f7
2 parents d20782c + cb50b7e
commit 8a953f7
Showing 1 changed file with 18 additions and 2 deletions.
diff --git a/core/src/main/java/org/mskcc/cbio/portal/scripts/ImportGeneData.java b/core/src/main/java/org/mskcc/cbio/portal/scripts/ImportGeneData.java
@@ -96,13 +96,21 @@ public static void importData(File geneFile, String genomeBuild) throws IOExcept
                     String strAliases = parts[4];
                     String strXrefs = parts[5];
                     String cytoband = parts[7];
-                    String chr = cytoband.split("p|q")[0];
+                    String chr = cytoband.split("p|q|;|c")[0]; // various strange characters were found in this column
                     int referenceGenomeId = DaoReferenceGenome.getReferenceGenomeByBuildName(genomeBuild).getReferenceGenomeId();
                     String desc = parts[8];
                     String type = parts[9];
                     String mainSymbol = parts[10]; // use 10 instead of 2 since column 2 may have duplication
                     Set<String> aliases = new HashSet<String>();
 
+                    // try to get chr from other column if needed
+                    if (chr.equals("-")) {
+                        if (!parts[6].equals("-")) {
+                            chr = parts[6];
+                        } else { 
+                            continue; // skip if both columns are absent
+                        }
+                    }
                     if (!locusTag.equals("-")) {
                         aliases.add(locusTag);
                     }
@@ -504,9 +512,17 @@ else if (i.contains("gene_name")) {
     public static boolean updateLength(String symbol, String chromosome, List<long[]> loci, int refreneceGenomeId) throws IOException, DaoException {
         DaoGeneOptimized daoGeneOptimized = DaoGeneOptimized.getInstance();
         CanonicalGene gene = daoGeneOptimized.getNonAmbiguousGene(symbol);
+
+        boolean lengthUpdated = false;
+
+        if (gene == null) {
+            ProgressMonitor.logWarning("Unable to retrieve gene by symbol: " +symbol);
+            return lengthUpdated;
+        }
+
         System.out.println(" --> update reference genome gene:  " + gene.getHugoGeneSymbolAllCaps());
         DaoReferenceGenomeGene daoReferenceGenomeGene = DaoReferenceGenomeGene.getInstance();
-        boolean lengthUpdated = false;
+
         /// Check if the gene is in the database
         ReferenceGenomeGene refGene = daoReferenceGenomeGene.getGene(gene.getEntrezGeneId(), refreneceGenomeId);
         /// If it's not in the database, don't add it