Add gene_id as a 2nd option to get GTF names

thanks @AlexandraBomane
lpantano · Aug 5, 2016 · e167c54 · e167c54
1 parent 13eb826
commit e167c54
Showing 1 changed file with 3 additions and 0 deletions.
diff --git a/seqcluster/libs/annotation.py b/seqcluster/libs/annotation.py
@@ -12,6 +12,9 @@ def read_gtf_line(cols):
         group = cols[2]
         attrs = cols[8].split(";")
         name = [attr.strip().split(" ")[1] for attr in attrs if attr.strip().split(" ")[0].lower().endswith("name")]
+        if not name:
+            name = [attr.strip().split(" ")[1] for attr in attrs if attr.strip().split(" ")[0].lower().endswith("gene_id")]
+
         biotype = [attr.strip().split(" ")[1] for attr in attrs if attr.strip().split(" ")[0].lower().endswith("biotype")]
         if biotype:
             group = biotype[0]