Update app.py

app.py

@@ -5,7 +5,7 @@ from Bio import SeqIO
 import os
 from io import StringIO
 
-# Ensure the 'temp' directory exists
+# Ensure temp directory exists
 temp_dir = "temp"
 os.makedirs(temp_dir, exist_ok=True)
 
@@ -16,37 +16,24 @@ st.set_page_config(page_title="PCR Primer Design", page_icon="🧬", layout="wid
 st.sidebar.header("User Guide")
 st.sidebar.info(
     """
-    This application allows you to design PCR primers for specific features within a GenBank file. 
-    Follow these steps:
-    1. Upload a GenBank file.
-    2. Select a feature type and then a specific feature.
-    3. Adjust the desired PCR product size range and the number of primer pairs.
-    4. Click 'Design Primers' to generate your primers.
+    This app allows you to design PCR primers from GenBank or FASTA files.
+
+    1. Upload a GenBank or FASTA file.
+    2. If GenBank: choose a feature (CDS, gene, tRNA).
+    3. Adjust product size range and primer count.
+    4. Click to generate primers.
     """
 )
 
 # File uploader
 uploaded_file = st.file_uploader(
-    "Upload a GenBank file", 
-    type=['gb', 'gbk'],
-    help="Upload a GenBank (.gb or .gbk) file containing the DNA sequence from which to design primers."
+    "Upload a GenBank or FASTA file",
+    type=['gb', 'gbk', 'fa', 'fasta'],
+    help="Supported formats: .gb, .gbk (GenBank); .fa, .fasta (FASTA)"
 )
 
-# Custom CSS
-st.markdown("""
-<style>
-h1, h2, h3 {
-    color: #1f77b4;
-    font-weight: bold;
-}
-.stProgress {
-    margin-top: 20px;
-}
-</style>
-""", unsafe_allow_html=True)
-
+# Helper functions
 def extract_features_from_genbank(genbank_content, feature_types=['CDS', 'tRNA', 'gene']):
-    """Extracts specified features from 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}
@@ -55,8 +42,12 @@ def extract_features_from_genbank(genbank_content, feature_types=['CDS', 'tRNA',
             features[feature.type].append(feature)
     return features, record
 
+def parse_fasta(fasta_content):
+    text_stream = StringIO(fasta_content.decode("utf-8"))
+    record = SeqIO.read(text_stream, "fasta")
+    return record
+
 def design_primers_for_region(sequence, product_size_range, num_to_return=10):
-    """Design primers for a specific sequence."""
     size_min, size_max = map(int, product_size_range.split('-'))
     return primer3.bindings.designPrimers(
         {
@@ -76,95 +67,99 @@ def design_primers_for_region(sequence, product_size_range, num_to_return=10):
         }
     )
 
+# File processing logic
 if uploaded_file is not None:
-    genbank_content = StringIO(uploaded_file.getvalue().decode("utf-8"))
-    features, record = extract_features_from_genbank(genbank_content)
-    
-    st.write("## Feature Selection")
-    feature_type = st.selectbox(
-        'Select feature type:', 
-        ['CDS', 'tRNA', 'gene'],
-        help="Choose the type of genomic feature for which you want to design primers."
-    )
-
-    if features[feature_type]:
-        feature_options = [
-            f"{feature.qualifiers.get('gene', [''])[0]} ({feature.location}) [length: {len(feature.location)} bp]"
-            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],
-            help="Select a specific feature based on its gene name and location."
-        )
-        selected_feature = features[feature_type][selected_index]
-
-        feature_sequence = selected_feature.extract(record.seq)
-        st.write(f"Selected {feature_type} sequence (length: {len(feature_sequence)} bp):")
-        st.code(str(feature_sequence), language="text")
+    file_ext = os.path.splitext(uploaded_file.name)[-1].lower()
 
-        st.write("## Primer Design Parameters")
+    if file_ext in ['.gb', '.gbk']:
+        genbank_content = StringIO(uploaded_file.getvalue().decode("utf-8"))
+        features, record = extract_features_from_genbank(genbank_content)
 
-        product_size_range = st.slider(
-            "Select desired PCR product size range:",
-            min_value=100,
-            max_value=len(feature_sequence),
-            value=(100, min(500, len(feature_sequence))),
-            step=10,
-            help="Adjust the desired PCR product size range (min 100 bp, max = feature length)."
+        st.write("## Feature Selection")
+        feature_type = st.selectbox(
+            'Select feature type:',
+            ['CDS', 'tRNA', 'gene'],
+            help="Choose the feature type for primer design."
         )
 
-        min_num_primers = st.number_input(
-            "Enter minimum number of primer pairs to return:", 
-            min_value=1, value=5, step=1,
-            help="Determine the number of primer pairs to generate."
-        )
+        if features[feature_type]:
+            feature_options = [
+                f"{f.qualifiers.get('gene', [''])[0]} ({f.location}) [length: {len(f.location)} bp]"
+                for f 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],
+                help="Choose a specific feature."
+            )
+            selected_feature = features[feature_type][selected_index]
+            sequence = selected_feature.extract(record.seq)
+            st.code(str(sequence), language="text")
+
+    elif file_ext in ['.fa', '.fasta']:
+        record = parse_fasta(uploaded_file.getvalue())
+        sequence = record.seq
+        st.write(f"FASTA sequence loaded (length: {len(sequence)} bp):")
+        st.code(str(sequence), language="text")
+    else:
+        st.error("Unsupported file format.")
+        st.stop()
+
+    st.write("## Primer Design Parameters")
+
+    product_size_range = st.slider(
+        "Select PCR product size range:",
+        min_value=100,
+        max_value=len(sequence),
+        value=(100, min(500, len(sequence))),
+        step=10,
+        help="Range of the desired PCR product size."
+    )
 
-        if st.button(f'Design Primers for selected {feature_type}'):
-            with st.spinner('Designing primers...'):
-                primers = design_primers_for_region(
-                    feature_sequence,
-                    f"{product_size_range[0]}-{product_size_range[1]}",
-                    num_to_return=min_num_primers
-                )
-
-            primer_data = []
-            for i in range(min_num_primers):
-                left_sequence = primers.get(f'PRIMER_LEFT_{i}_SEQUENCE', 'N/A')
-                right_sequence = primers.get(f'PRIMER_RIGHT_{i}_SEQUENCE', 'N/A')
-                if left_sequence != 'N/A' and right_sequence != 'N/A':
-                    primer_info = {
-                        'Primer Pair': i + 1,
-                        'Left Sequence': left_sequence,
-                        'Right Sequence': right_sequence,
-                        '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': len(left_sequence),
-                        'Right Length': len(right_sequence),
-                        'PCR Product Size (bp)': primers.get(f'PRIMER_PAIR_{i}_PRODUCT_SIZE', 'N/A')
-                    }
-                    primer_data.append(primer_info)
-
-            if primer_data:
-                st.subheader('Designed Primers')
-                primer_df = pd.DataFrame(primer_data)
-                st.table(primer_df)
-
-                csv = primer_df.to_csv(index=False).encode('utf-8')
-                st.download_button(
-                    "Download Primers as CSV",
-                    csv,
-                    "primers.csv",
-                    "text/csv",
-                    key='download-csv'
-                )
-            else:
-                st.error('No primers were found. Please adjust your parameters and try again.')
+    min_num_primers = st.number_input(
+        "Number of primer pairs to return:",
+        min_value=1, value=5, step=1,
+        help="How many primer pairs to return."
+    )
+
+    if st.button("Design Primers"):
+        with st.spinner("Designing primers..."):
+            primers = design_primers_for_region(
+                sequence,
+                f"{product_size_range[0]}-{product_size_range[1]}",
+                num_to_return=min_num_primers
+            )
+
+        primer_data = []
+        for i in range(min_num_primers):
+            left = primers.get(f'PRIMER_LEFT_{i}_SEQUENCE', 'N/A')
+            right = primers.get(f'PRIMER_RIGHT_{i}_SEQUENCE', 'N/A')
+            if left != 'N/A' and right != 'N/A':
+                primer_data.append({
+                    'Primer Pair': i + 1,
+                    'Left Sequence': left,
+                    'Right Sequence': right,
+                    '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': len(left),
+                    'Right Length': len(right),
+                    'PCR Product Size (bp)': primers.get(f'PRIMER_PAIR_{i}_PRODUCT_SIZE', 'N/A')
+                })
+
+        if primer_data:
+            st.subheader('Designed Primers')
+            df = pd.DataFrame(primer_data)
+            st.table(df)
+
+            csv = df.to_csv(index=False).encode('utf-8')
+            st.download_button("Download Primers as CSV", csv, "primers.csv", "text/csv")
+        else:
+            st.error("No primers found. Try adjusting your parameters.")
 
 # Footer
 st.markdown("""
 ---
 **© 2024 Yash Munnalal Gupta**  
-For inquiries or permissions, contact: [yash.610@live.com](mailto:yash.610@live.com)
-""", unsafe_allow_html=True)
+Contact: [yash.610@live.com](mailto:yash.610@live.com)
+""", unsafe_allow_html=True)