Update app.py

app.py

@@ -475,16 +475,6 @@ def build_maximum_likelihood_tree(f_gene_sequence):
 
 # --- NEW Tree Analysis Function (Using the new analyzer API) ---
 def analyze_sequence_for_tree(sequence: str, matching_percentage: float) -> tuple:
-    """
-    Analyze sequence and create phylogenetic tree using the new analyzer API
-    
-    Args:
-        sequence (str): DNA sequence to analyze
-        matching_percentage (float): Similarity threshold percentage
-        
-    Returns:
-        tuple: (status_message, html_file_path)
-    """
     try:
         if not analyzer:
             return "❌ Error: Tree analyzer not initialized. Please check if the CSV data file is available.", None
@@ -495,16 +485,13 @@ def analyze_sequence_for_tree(sequence: str, matching_percentage: float) -> tupl
         if not (1 <= matching_percentage <= 99):
             return "❌ Error: Matching percentage must be between 1 and 99.", None
         
-        # Validate inputs
         sequence = sequence.strip()
         if len(sequence) < 10:
             return "❌ Error: Invalid or missing sequence. Must be ≥10 nucleotides.", None
         
-        # Find query sequence
         if not analyzer.find_query_sequence(sequence):
             return "❌ Error: Sequence not accepted.", None
         
-        # Find similar sequences
         matched_ids, actual_percentage = analyzer.find_similar_sequences(matching_percentage)
         
         if not matched_ids:
@@ -512,13 +499,10 @@ def analyze_sequence_for_tree(sequence: str, matching_percentage: float) -> tupl
         
         logging.info(f"Found {len(matched_ids)} similar sequences at {actual_percentage:.2f}% similarity")
         
-        # Build tree structure
         analyzer.build_tree_structure_with_ml_safe(matched_ids)
         
-        # Create interactive tree
         fig = analyzer.create_interactive_tree(matched_ids, actual_percentage)
         
-        # Save to temporary file that Gradio can access
         temp_dir = tempfile.gettempdir()
         output_path = os.path.join(temp_dir, 'phylogenetic_tree_interactive.html')
         fig.write_html(output_path)
@@ -669,47 +653,41 @@ def run_pipeline(dna_input, similarity_score=95.0, build_ml_tree=False):
         html_file = None
         tree_html_content = "No tree generated"
         simplified_ml_output = ""
-        
+
         if analyzer and processed_sequence and len(processed_sequence) >= 10:
-            try:
-                logging.info(f"Starting simplified ML tree analysis with F gene sequence length: {len(processed_sequence)}")
-                
-                # Use the new analyze_sequence_for_tree function
-                tree_result, html_path = analyze_sequence_for_tree(processed_sequence, similarity_score)
-                
-                if html_path and os.path.exists(html_path):
-                    # Success - copy the HTML file to a location Gradio can serve
-                    output_dir = "output"
-                    os.makedirs(output_dir, exist_ok=True)
-
-                    # Create a safe filename
-                    safe_seq_name = re.sub(r'[^a-zA-Z0-9]', '_', processed_sequence[:20])
-                    html_filename = os.path.join(output_dir, f"tree_{safe_seq_name}_{uuid.uuid4().hex[:8]}.html")
-                    
-                    # Copy the HTML file
-                    shutil.copy2(html_path, html_filename)
-                    html_file = html_filename
-                    
-                    # Read HTML content for display
-                    with open(html_filename, 'r', encoding='utf-8') as f:
-                        tree_html_content = f.read()
-                    
-                    simplified_ml_output = tree_result
-                    logging.info(f"Tree analysis completed successfully. HTML saved to: {html_filename}")
-                else:
-                    simplified_ml_output = tree_result or "❌ Failed to generate tree visualization"
-                    logging.warning("Tree analysis failed or no HTML output generated")
-                    
+           try:
+               logging.info(f"Starting simplified ML tree analysis with F gene sequence length: {len(processed_sequence)}")
+        
+               tree_result, html_path = analyze_sequence_for_tree(processed_sequence, similarity_score)
+        
+               if html_path and os.path.exists(html_path):
+                   output_dir = "output"
+                   os.makedirs(output_dir, exist_ok=True)
+
+                   safe_seq_name = re.sub(r'[^a-zA-Z0-9]', '_', processed_sequence[:20])
+                   html_filename = os.path.join(output_dir, f"tree_{safe_seq_name}_{uuid.uuid4().hex[:8]}.html")
+            
+                   shutil.copy2(html_path, html_filename)
+                   html_file = html_filename
+            
+                   with open(html_filename, 'r', encoding='utf-8') as f:
+                       tree_html_content = f.read()
+            
+                  simplified_ml_output = tree_result
+                  logging.info(f"Tree analysis completed successfully. HTML saved to: {html_filename}")
+               else:
+                 simplified_ml_output = tree_result or "❌ Failed to generate tree visualization"
+                 logging.warning("Tree analysis failed or no HTML output generated")
+            
             except Exception as e:
                 simplified_ml_output = f"❌ Simplified ML tree analysis failed: {str(e)}"
                 logging.error(f"Simplified ML tree analysis failed: {e}")
         elif not analyzer:
-            simplified_ml_output = "❌ Tree analyzer not available (CSV data not loaded)"
+                simplified_ml_output = "❌ Tree analyzer not available (CSV data not loaded)"
         elif len(processed_sequence) < 10:
-            simplified_ml_output = "❌ Sequence too short for tree analysis (minimum 10 bp)"
+             simplified_ml_output = "❌ Sequence too short for tree analysis (minimum 10 bp)"
         else:
-            simplified_ml_output = "Tree analysis skipped"
-
+             simplified_ml_output = "Tree analysis skipped"
         # Prepare final outputs
         final_boundary_output = f"F gene sequence ({len(processed_sequence)} bp):\n{boundary_output}"
         final_keras_output = f"F gene validation: {keras_output}"
@@ -831,13 +809,7 @@ def create_gradio_interface():
                                 elem_classes=["output-html"]
                             )
                         
-                        with gr.Tab("Sequence Output"):
-                            extracted_sequence = gr.Textbox(
-                                label="Extracted F Gene Sequence",
-                                lines=10,
-                                interactive=False,
-                                info="The F gene sequence extracted by the boundary model"
-                            )
+                      
                         
                         with gr.Tab("Download Files"):
                             tree_file = gr.File(