grep ensembl transcript with ENS*T instead of ENST, to include non-hu…

…man transcripts
griffithlab · Feb 7, 2025 · 5396e98 · 5396e98
1 parent 0eea407
commit 5396e98
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/pvactools/lib/combine_inputs.py b/pvactools/lib/combine_inputs.py
@@ -15,7 +15,7 @@ def add_junction_coordinates_to_variants(self):
 
         # remove version number in annotated to compare with filtered junctions file
         var_df[['transcript_id', 'transcript_version']] = var_df['transcript_name'].str.split('.', expand=True)
-        var_df = var_df.loc[var_df['transcript_id'].str.startswith('ENST') == True]
+        var_df = var_df.loc[var_df['transcript_id'].str.contains(r'^ENS.*T', regex=True)]
         var_df['transcript_version'] = var_df['transcript_version'].astype('int64')
 
         # create new cols