fix

cas9on.py

@@ -146,21 +146,30 @@ def process_gene(gene_symbol, model_path):
     # Return the sorted output, combined gene sequences, and all exons
     return results, all_gene_sequences, all_exons
 
-def create_genbank_features(formatted_data):
+
+def create_genbank_features(df):
     features = []
-    for data in formatted_data:
-        strand = 1 if data[3] == '+' else -1
-        location = FeatureLocation(start=int(data[1]), end=int(data[2]), strand=strand)
+    for index, row in df.iterrows():
+        # Convert strand from '+/-' to 1/-1 for Biopython
+        strand = 1 if row['Strand'] == '+' else -1 if row['Strand'] == '-' else 0
+
+        # Create feature location using the 'Start Pos' and 'End Pos'
+        location = FeatureLocation(start=int(row['Start Pos']), end=int(row['End Pos']), strand=strand)
+
+        # Create a SeqFeature
         feature = SeqFeature(location=location, type="misc_feature", qualifiers={
-            'label': data[7],  # Use gRNA as the label
-            'target': data[6],  # Include the target sequence
-            'note': f"Prediction: {data[8]:.4f}"  # Include the prediction score
+            'label': row['gRNA'],  # Use gRNA as the label
+            'target': row['Target'],  # Include the target sequence
+            'note': f"Prediction: {row['Prediction']:.4f}",  # Include the prediction score
+            'transcript_id': row['Transcript'],
+            'exon_id': row['Exon']
         })
         features.append(feature)
     return features
 
+
 def generate_genbank_file_from_df(df, gene_sequence, gene_symbol, output_path):
-    features = create_genbank_features(df.values.tolist())
+    features = create_genbank_features(df)
     record = SeqRecord(Seq(gene_sequence), id=gene_symbol, name=gene_symbol,
                        description=f'CRISPR Cas9 predicted targets for {gene_symbol}', features=features)
     record.annotations["molecule_type"] = "DNA"