Update app.py

app.py

@@ -15,7 +15,6 @@ uploaded_file = st.file_uploader("Upload a GenBank file", type=['gb', 'gbk'])
 
 def extract_features_from_genbank(genbank_content, feature_types=['CDS', 'tRNA', 'gene']):
     """Extracts specified features from GenBank content."""
-    # Convert binary stream (if present) to a StringIO object for text handling
     text_stream = StringIO(genbank_content.decode("utf-8")) if isinstance(genbank_content, bytes) else genbank_content
     record = SeqIO.read(text_stream, "genbank")
     features = {ftype: [] for ftype in feature_types}
@@ -48,51 +47,40 @@ if uploaded_file is not None:
     features, record = extract_features_from_genbank(genbank_content)
     feature_type = st.selectbox('Select feature type:', ['CDS', 'tRNA', 'gene'])
 
-    # Enhanced selection box to show names and locations
-    feature_options = [f"{feature.qualifiers.get('gene', [''])[0]} ({feature.location})" for feature in features[feature_type]]
+    feature_options = [f"{feature.qualifiers.get('locus_tag', [''])[0]} ({feature.location})" for feature in features[feature_type]]
     selected_index = st.selectbox(f'Select a {feature_type}:', options=range(len(feature_options)), format_func=lambda x: feature_options[x])
     selected_feature = features[feature_type][selected_index]
 
-    feature_sequence = selected_feature.extract(record.seq)  # Extract the sequence of the selected feature
+    feature_sequence = selected_feature.extract(record.seq)
     st.write(f"Selected {feature_type} sequence (length: {len(feature_sequence)} bp):")
-    st.text(str(feature_sequence))  # Display the sequence
+    st.text(str(feature_sequence))
 
     product_size_range = st.text_input("Enter desired PCR product size range (e.g., 150-500):", value="150-500")
 
     if st.button(f'Design Primers for selected {feature_type}'):
-        # Design primers directly for the extracted sequence
         primers = design_primers_for_region(feature_sequence, num_to_return=5)
-        
-        # Lists to hold primer details, initializing with placeholders if keys are missing
-        sequences, tm_values, lengths, gc_percents = [], [], [], []
-        
-        # Gather primer details if available
-        for i in range(5):  # We expect 5 primer pairs
-            left_key_seq, right_key_seq = f'PRIMER_LEFT_{i}_SEQUENCE', f'PRIMER_RIGHT_{i}_SEQUENCE'
-            left_key_tm, right_key_tm = f'PRIMER_LEFT_{i}_TM', f'PRIMER_RIGHT_{i}_TM'
-            left_key_size, right_key_size = f'PRIMER_LEFT_{i}_SIZE', f'PRIMER_RIGHT_{i}_SIZE'
-            left_key_gc, right_key_gc = f'PRIMER_LEFT_{i}_GC_PERCENT', f'PRIMER_RIGHT_{i}_GC_PERCENT'
 
-            # Append primer information if available, else append 'N/A' or another placeholder
-            sequences.append(primers.get(left_key_seq, 'N/A'))
-            sequences.append(primers.get(right_key_seq, 'N/A'))
-            tm_values.append(primers.get(left_key_tm, 'N/A'))
-            tm_values.append(primers.get(right_key_tm, 'N/A'))
-            lengths.append(primers.get(left_key_size, 'N/A'))
-            lengths.append(primers.get(right_key_size, 'N/A'))
-            gc_percents.append(primers.get(left_key_gc, 'N/A'))
-            gc_percents.append(primers.get(right_key_gc, 'N/A'))
+        primer_data = []
+        for i in range(5):
+            for direction in ['LEFT', 'RIGHT']:
+                seq_key = f'PRIMER_{direction}_{i}_SEQUENCE'
+                tm_key = f'PRIMER_{direction}_{i}_TM'
+                size_key = f'PRIMER_{direction}_{i}_SIZE'
+                gc_key = f'PRIMER_{direction}_{i}_GC_PERCENT'
+                product_size_key = f'PRIMER_PAIR_{i}_PRODUCT_SIZE'
 
-        # Construct the DataFrame only if we found some primers
-        if any(seq != 'N/A' for seq in sequences):  # Check if we added any real sequences
-            primer_df = pd.DataFrame({
-                'Primer': ['Left Primer', 'Right Primer'] * (len(sequences) // 2),
-                'Sequence': sequences,
-                'Tm (°C)': tm_values,
-                'Length': lengths,
-                'GC%': gc_percents,
-            })
+                if seq_key in primers:
+                    primer_data.append({
+                        'Primer': f'{direction.capitalize()} Primer {i+1}',
+                        'Sequence': primers.get(seq_key, 'N/A'),
+                        'Tm (°C)': primers.get(tm_key, 'N/A'),
+                        'Primer Length': primers.get(size_key, 'N/A'),
+                        'GC%': primers.get(gc_key, 'N/A'),
+                        'PCR Product Size (bp)': primers.get(product_size_key, 'N/A'),
+                    })
 
+        if primer_data:
+            primer_df = pd.DataFrame(primer_data)
             st.write('### Designed Primers')
             st.dataframe(primer_df)
             csv = primer_df.to_csv(index=False).encode('utf-8')