Update app.py

app.py

@@ -4,6 +4,7 @@ import primer3
 from Bio import SeqIO
 import os
 from io import StringIO
+import matplotlib.pyplot as plt
 
 # Ensure the 'temp' directory exists for saving temporary files
 temp_dir = "temp"
@@ -15,7 +16,6 @@ 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}
@@ -24,11 +24,14 @@ 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, num_to_return=5):
+def design_primers_for_region(sequence, product_size_range, num_to_return=5):
     """Design primers for a specific sequence."""
+    # Parse the product size range
+    size_min, size_max = map(int, product_size_range.split('-'))
     return primer3.bindings.designPrimers(
         {
             'SEQUENCE_TEMPLATE': str(sequence),
+            'PRIMER_PRODUCT_SIZE_RANGE': [[size_min, size_max]]
         },
         {
             'PRIMER_OPT_SIZE': 20,
@@ -43,56 +46,56 @@ def design_primers_for_region(sequence, num_to_return=5):
         }
     )
 
+def plot_pcr_product(sequence, primers, num_pairs=5):
+    """Visualize the PCR product based on primer locations."""
+    plt.figure(figsize=(10, 2))
+    plt.plot([0, len(sequence)], [0, 0], 'k-')  # Draw the sequence line
+    for i in range(num_pairs):
+        left_pos = primers.get(f'PRIMER_LEFT_{i}', {}).get('position', -1)
+        right_pos = primers.get(f'PRIMER_RIGHT_{i}', {}).get('position', -1)
+        if left_pos != -1 and right_pos != -1:
+            plt.plot([left_pos, right_pos], [i, i], 'r-')  # Draw the PCR product line
+            plt.text(left_pos, i, f'{i+1}', va='bottom', ha='right')
+    plt.yticks([])
+    plt.title('PCR Products')
+    plt.xlabel('Nucleotide position')
+    plt.show()
+
 if uploaded_file is not None:
     genbank_content = StringIO(uploaded_file.getvalue().decode("utf-8"))
     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]]
     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 = [], [], [], []
+        primers = design_primers_for_region(feature_sequence, product_size_range, num_to_return=5)
         
-        # 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'))
-
-        # 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,
-            })
+        primer_data = []
+        for i in range(5):  # Collect data for 5 primer pairs
+            primer_info = {
+                'Primer Pair': i + 1,
+                'Left Sequence': primers.get(f'PRIMER_LEFT_{i}_SEQUENCE', 'N/A'),
+                'Right Sequence': primers.get(f'PRIMER_RIGHT_{i}_SEQUENCE', 'N/A'),
+                'Left TM (°C)': primers.get(f'PRIMER_LEFT_{i}_TM', 'N/A'),
+                'Right TM (°C)': primers.get(f'PRIMER_RIGHT_{i}_TM', 'N/A'),
+                'Left Length': primers.get(f'PRIMER_LEFT_{i}_SIZE', 'N/A'),
+                'Right Length': primers.get(f'PRIMER_RIGHT_{i}_SIZE', 'N/A'),
+                'PCR Product Size (bp)': primers.get(f'PRIMER_PAIR_{i}_PRODUCT_SIZE', 'N/A')
+            }
+            if primer_info['Left Sequence'] != 'N/A' and primer_info['Right Sequence'] != 'N/A':
+                primer_data.append(primer_info)
 
+        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')
@@ -103,5 +106,8 @@ if uploaded_file is not None:
                 "text/csv",
                 key='download-csv'
             )
+            # Plotting PCR products
+            st.write("### Visualization of PCR Products")
+            plot_pcr_product(feature_sequence, primers, num_pairs=5)
         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.')