acfbaec13c08b80dc3c5138821a23ef4f905d573
max
  Mon Jan 20 09:17:30 2025 -0800
fixing color coding of CNVs in clinvar, refs #35062

diff --git src/hg/utils/otto/clinvar/clinVarToBed src/hg/utils/otto/clinvar/clinVarToBed
index 959a831..6135470 100755
--- src/hg/utils/otto/clinvar/clinVarToBed
+++ src/hg/utils/otto/clinvar/clinVarToBed
@@ -170,30 +170,32 @@
         # GRCh37/hg19 15q14-15.1 chr15:34638237..42057083 complex variant
         print(name)
         assert False # name that starts with GRCh but does not match our regex should not happen
     elif "." in name:
         # many names look like NM_000274.3(OAT):c.550_552delGCT (p.Ala184del)
         # so we remove the gene and the protein description
         if ":" in name:
             name = name.split(":")[1]
             longName = name.split(" ")[0]
 
         # handle genomic HGVS NC_000010.11:g.(?_87925503)_(87965482_?)del
         if name.startswith("NC_") and "g." in name and ")" in name:
             shortName = name
         else:
             # strip away the final description like " (p.Ala184del)"
+            if not name.startswith("g.("):
+                # do not strip anything anymore is all we have the g. notation as we would end up with just g.
                 name = name.split(" ")[0].split("[")[0].split("(")[0]
             shortName = name
 
         if name.endswith("del"):
             shortName = "del"
         elif name.endswith("ins"):
             shortName = "ins"
         elif name.endswith("dup"):
             shortName = "dup"
         else:
             posMatch = posRe.match(name)
             if posMatch!=None:
                 pos, dupDelIns, change = posMatch.groups()
                 if dupDelIns==None:
                     dupDelIns= ""