Update app.py

app.py

@@ -1,10 +1,8 @@
 import streamlit as st
 import pandas as pd
-from Bio import SeqIO
-from Bio.SeqFeature import SeqFeature, FeatureLocation
 import primer3
+from Bio import SeqIO
 import os
-from collections import Counter
 
 # Ensure the 'temp' directory exists for saving temporary files
 temp_dir = "temp"
@@ -14,22 +12,21 @@ os.makedirs(temp_dir, exist_ok=True)
 st.set_page_config(page_title="PCR Primer Design", page_icon="🧬", layout="wide")
 uploaded_file = st.file_uploader("Upload a GenBank file", type=['gb', 'gbk'])
 
-def extract_features(genbank_path, feature_type='CDS'):
-    """Extracts features from a GenBank file."""
-    with open(genbank_path, 'r') as file:
-        record = SeqIO.read(file, "genbank")
-        features = [feature for feature in record.features if feature.type == feature_type]
-        return features, record
+def extract_features_from_genbank(genbank_content, feature_types=['CDS', 'tRNA', 'gene']):
+    """Extracts specified features from a GenBank content."""
+    record = SeqIO.read(genbank_content, "genbank")
+    features = {ftype: [] for ftype in feature_types}
+    for feature in record.features:
+        if feature.type in feature_types:
+            features[feature.type].append(feature)
+    return features, record
 
-def design_primers_for_feature(feature, sequence, num_to_return=5):
-    """Design primers for a specific feature."""
-    start, end = int(feature.location.start), int(feature.location.end)
-    sequence_template = str(sequence)
+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]
-    primer_design_results = primer3.bindings.designPrimers(
+    return primer3.bindings.designPrimers(
         {
-            'SEQUENCE_ID': feature.qualifiers.get('gene', [''])[0],
-            'SEQUENCE_TEMPLATE': sequence_template,
+            'SEQUENCE_TEMPLATE': str(sequence),
             'SEQUENCE_TARGET': target,
         },
         {
@@ -44,30 +41,34 @@ def design_primers_for_feature(feature, sequence, num_to_return=5):
             'PRIMER_NUM_RETURN': num_to_return,
         }
     )
-    return primer_design_results
 
 if uploaded_file is not None:
-    temp_gb_path = os.path.join(temp_dir, uploaded_file.name)
-    with open(temp_gb_path, 'wb') as f:
-        f.write(uploaded_file.getvalue())
+    features, record = extract_features_from_genbank(uploaded_file)
+    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)]
+
+    start, end = int(selected_feature.location.start), int(selected_feature.location.end)
+    st.write(f"Selected {feature_type} size: {end - start} bp")
 
-    features, record = extract_features(temp_gb_path)
-    gene_names = [feature.qualifiers.get('gene', ['N/A'])[0] for feature in features]
-    selected_gene = st.selectbox('Select a gene to design primers for:', gene_names)
+    product_size_range = st.text_input("Enter desired PCR product size range (e.g., 150-500):", value="150-500")
 
-    if st.button('Design Primers'):
-        selected_feature = next(feature for feature in features if feature.qualifiers.get('gene', [''])[0] == selected_gene)
-        primers = design_primers_for_feature(selected_feature, record.seq)
+    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)
         primer_df = pd.DataFrame({
-            'Primer': ['Left Primer', 'Right Primer'] * len(primers) // 2,
-            'Sequence': [primers[f'PRIMER_LEFT_{i}_SEQUENCE'] for i in range(len(primers) // 2)] +
-                        [primers[f'PRIMER_RIGHT_{i}_SEQUENCE'] for i in range(len(primers) // 2)],
-            'Tm (°C)': [primers[f'PRIMER_LEFT_{i}_TM'] for i in range(len(primers) // 2)] +
-                       [primers[f'PRIMER_RIGHT_{i}_TM'] for i in range(len(primers) // 2)],
-            'Length': [primers[f'PRIMER_LEFT_{i}_SIZE'] for i in range(len(primers) // 2)] +
-                      [primers[f'PRIMER_RIGHT_{i}_SIZE'] for i in range(len(primers) // 2)],
-            'GC%': [primers[f'PRIMER_LEFT_{i}_GC_PERCENT'] for i in range(len(primers) // 2)] +
-                   [primers[f'PRIMER_RIGHT_{i}_GC_PERCENT'] for i in range(len(primers) // 2)],
+            'Primer': ['Left Primer'] * 5 + ['Right Primer'] * 5,
+            'Sequence': [primers[f'PRIMER_LEFT_{i}_SEQUENCE'] for i in range(5)] + 
+                        [primers[f'PRIMER_RIGHT_{i}_SEQUENCE'] for i in range(5)],
+            'Tm (°C)': [primers[f'PRIMER_LEFT_{i}_TM'] for i in range(5)] + 
+                       [primers[f'PRIMER_RIGHT_{i}_TM'] for i in range(5)],
+            'Length': [primers[f'PRIMER_LEFT_{i}_SIZE'] for i in range(5)] +
+                      [primers[f'PRIMER_RIGHT_{i}_SIZE'] for i in range(5)],
+            'GC%': [primers[f'PRIMER_LEFT_{i}_GC_PERCENT'] for i in range(5)] +
+                   [primers[f'PRIMER_RIGHT_{i}_GC_PERCENT'] for i in range(5)],
         })
 
         st.write('### Designed Primers')