Update app.py

app.py

@@ -16,10 +16,7 @@ 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
-    if isinstance(genbank_content, bytes):
-        text_stream = StringIO(genbank_content.decode("utf-8"))
-    else:
-        text_stream = genbank_content
+    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}
     for feature in record.features:
@@ -27,13 +24,11 @@ def extract_features_from_genbank(genbank_content, feature_types=['CDS', 'tRNA',
             features[feature.type].append(feature)
     return features, record
 
-def design_primers_for_region(sequence, start, end, num_to_return=5):
-    """Design primers for a specific region within a sequence."""
-    target = [start, end - start]
+def design_primers_for_region(sequence, num_to_return=5):
+    """Design primers for a specific sequence."""
     return primer3.bindings.designPrimers(
         {
             'SEQUENCE_TEMPLATE': str(sequence),
-            'SEQUENCE_TARGET': target,
         },
         {
             'PRIMER_OPT_SIZE': 20,
@@ -53,42 +48,38 @@ if uploaded_file is not None:
     features, record = extract_features_from_genbank(genbank_content)
     feature_type = st.selectbox('Select feature type:', ['CDS', 'tRNA', 'gene'])
 
-    # Create a selection box for genes based on chosen feature
-    feature_options = [f"{feature.qualifiers.get('locus_tag', [''])[0]}: {feature.location}" for feature in features[feature_type]]
-    selected_feature_option = st.selectbox(f'Select a {feature_type}:', feature_options)
-    selected_feature = features[feature_type][feature_options.index(selected_feature_option)]
+    # Enhanced selection box to show names and locations
+    feature_options = [f"{feature.qualifiers.get('gene', [''])[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]
 
-    start, end = int(selected_feature.location.start), int(selected_feature.location.end)
-    st.write(f"Selected {feature_type} size: {end - start} bp")
+    feature_sequence = selected_feature.extract(record.seq)  # Extract the sequence of the selected feature
+    st.write(f"Selected {feature_type} sequence (length: {len(feature_sequence)} bp):")
+    st.text(str(feature_sequence))  # Display the 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 {feature_type}'):
-        size_range = [tuple(map(int, r.split('-'))) for r in product_size_range.split(',')]
-        primers = design_primers_for_region(record.seq, start, end, num_to_return=5)
+    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)
         
         # Initialize lists to hold primer details
         sequences, tm_values, lengths, gc_percents = [], [], [], []
         
         # Check if primer keys exist and add their details to the lists
         for i in range(5):  # Assuming we are looking for 5 primer pairs
-            left_key = f'PRIMER_LEFT_{i}_SEQUENCE'
-            right_key = f'PRIMER_RIGHT_{i}_SEQUENCE'
+            left_key, right_key = f'PRIMER_LEFT_{i}_SEQUENCE', f'PRIMER_RIGHT_{i}_SEQUENCE'
             if left_key in primers and right_key in primers:
-                sequences.append(primers[left_key])
-                sequences.append(primers[right_key])
-                tm_values.append(primers[f'PRIMER_LEFT_{i}_TM'])
-                tm_values.append(primers[f'PRIMER_RIGHT_{i}_TM'])
-                lengths.append(primers[f'PRIMER_LEFT_{i}_SIZE'])
-                lengths.append(primers[f'PRIMER_RIGHT_{i}_SIZE'])
-                gc_percents.append(primers[f'PRIMER_LEFT_{i}_GC_PERCENT'])
-                gc_percents.append(primers[f'PRIMER_RIGHT_{i}_GC_PERCENT'])
+                sequences += [primers[left_key], primers[right_key]]
+                tm_values += [primers[f'PRIMER_LEFT_{i}_TM'], primers[f'PRIMER_RIGHT_{i}_TM']]
+                lengths += [primers[f'PRIMER_LEFT_{i}_SIZE'], primers[f'PRIMER_RIGHT_{i}_SIZE']]
+                gc_percents += [primers[f'PRIMER_LEFT_{i}_GC_PERCENT'], primers[f'PRIMER_RIGHT_{i}_GC_PERCENT']]
         
         # Check if any primers were found
         if sequences:
             # Construct the DataFrame using the collected primer details
             primer_df = pd.DataFrame({
-                'Primer': ['Left Primer'] * len(sequences) // 2 + ['Right Primer'] * len(sequences) // 2,
+                'Primer': ['Left Primer', 'Right Primer'] * (len(sequences) // 2),
                 'Sequence': sequences,
                 'Tm (°C)': tm_values,
                 'Length': lengths,
@@ -106,4 +97,4 @@ if uploaded_file is not None:
                 key='download-csv'
             )
         else:
-            st.error('No primers were found. Please adjust your parameters and try again.')
+            st.error('No primers were found. Please adjust your parameters and try again.')