remove protein_id qualifier if already present in another CDS

Author: Luis Figueiredo

deepbgc/util.py

@@ -48,7 +48,7 @@ def get_protein_features(record):
 
 
 def get_proteins_by_id(protein_features):
-    return {get_protein_id(feature): feature for feature in protein_features}
+    return {protein_id: feature for feature in protein_features for protein_id in get_protein_ids(feature)}
 
 
 def get_features_of_type(record, feature_type):
@@ -502,6 +502,8 @@ def fix_duplicate_cds(record):
 
         if protein_id != new_protein_id:
             logging.warning('Setting new unique_protein_id %s for CDS %s', new_protein_id, protein_id)
+            filtered_qualifiers = {k: v for k, v in feature.qualifiers.items() if k != "protein_id"}
+            feature.qualifiers = collections.OrderedDict(filtered_qualifiers)
             feature.qualifiers['unique_protein_id'] = [new_protein_id]
 
         protein_ids.add(new_protein_id)

test/unit/test_pfam.py

@@ -3,6 +3,7 @@
 from io import StringIO
 import pandas as pd
 from copy import deepcopy
+from collections import OrderedDict
 from Bio import SearchIO
 from Bio.SeqRecord import SeqRecord
 from Bio.Seq import Seq
@@ -188,6 +189,8 @@ def test_same_protein_id(mock_find_exe, mock_popen, mock_searchio, mock_read_csv
     )
 
     expected_record = deepcopy(record)
+    filtered_qualifiers = {k: v for k, v in expected_record.features[-1].qualifiers.items() if k != "protein_id"}
+    expected_record.features[-1].qualifiers = OrderedDict(filtered_qualifiers)
     expected_record.features[-1].qualifiers['unique_protein_id'] = 'AAK73500.1_1'
     expected_record.features += [
             SeqFeature(