Update app.py

app.py

@@ -466,39 +466,39 @@ 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
+    Analyze sequence and create phylogenetic tree and detailed report 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)
+        tuple: (status_message, tree_html_path, report_html_path)
     """
     try:
         if not analyzer:
-            return "❌ Error: Tree analyzer not initialized. Please check if the CSV data file is available.", None
+            return "❌ Error: Tree analyzer not initialized. Please check if the CSV data file is available.", None, None
             
         if not sequence:
-            return "❌ Error: Please provide a sequence.", None
+            return "❌ Error: Please provide a sequence.", None, None
             
         if not (1 <= matching_percentage <= 99):
-            return "❌ Error: Matching percentage must be between 1 and 99.", None
+            return "❌ Error: Matching percentage must be between 1 and 99.", None, None
         
         # Validate inputs
         sequence = sequence.strip()
         if len(sequence) < 10:
-            return "❌ Error: Invalid or missing sequence. Must be ≥10 nucleotides.", None
+            return "❌ Error: Invalid or missing sequence. Must be ≥10 nucleotides.", None, None
         
         # Find query sequence
         if not analyzer.find_query_sequence(sequence):
-            return "❌ Error: Sequence not accepted.", None
+            return "❌ Error: Sequence not accepted.", None, None
         
         # Find similar sequences
         matched_ids, actual_percentage = analyzer.find_similar_sequences(matching_percentage)
         
         if not matched_ids:
-            return f"❌ Error: No similar sequences found at {matching_percentage}% similarity threshold.", None
+            return f"❌ Error: No similar sequences found at {matching_percentage}% similarity threshold.", None, None
         
         logging.info(f"Found {len(matched_ids)} similar sequences at {actual_percentage:.2f}% similarity")
         
@@ -508,22 +508,28 @@ def analyze_sequence_for_tree(sequence: str, matching_percentage: float) -> tupl
         # Create interactive tree
         fig = analyzer.create_interactive_tree(matched_ids, actual_percentage)
         
-        # Save to temporary file that Gradio can access
+        # Save tree to temporary file
         temp_dir = tempfile.gettempdir()
-        output_path = os.path.join(temp_dir, 'phylogenetic_tree_interactive.html')
-        fig.write_html(output_path)
+        query_id = analyzer.query_id or f"query_{int(time.time())}"
+        tree_html_path = os.path.join(temp_dir, f'phylogenetic_tree_interactive_{query_id}.html')
+        fig.write_html(tree_html_path)
+        
+        # Generate and save detailed report
+        report_html_content = analyzer.generate_detailed_report(matched_ids, actual_percentage)
+        report_html_path = os.path.join(temp_dir, f'detailed_report_{query_id}.html')
+        with open(report_html_path, 'w', encoding='utf-8') as f:
+            f.write(report_html_content)
         
         success_msg = f"✅ Analysis complete! Found {len(matched_ids)} similar sequences with {actual_percentage:.2f}% average similarity."
         
-        return success_msg, output_path
+        return success_msg, tree_html_path, report_html_path
         
     except Exception as e:
         error_msg = f"❌ Error during analysis: {str(e)}"
         logging.error(error_msg)
         import traceback
         logging.error(f"Full traceback: {traceback.format_exc()}")
-        return error_msg, None
-
+        return error_msg, None, None
 # --- Keras Prediction ---
 def predict_with_keras(sequence):
     try:
@@ -577,19 +583,19 @@ def run_pipeline_from_file(fasta_file_obj, similarity_score, build_ml_tree):
     try:
         dna_input = read_fasta_file(fasta_file_obj)
         if not dna_input:
-            return "Failed to read FASTA file", "", "", "", "", None, None, None, "No input sequence"
+            return "Failed to read FASTA file", "", "", "", "", None, None, None, None, "No input sequence", "No input sequence"
         return run_pipeline(dna_input, similarity_score, build_ml_tree)
     except Exception as e:
         error_msg = f"Pipeline error: {str(e)}"
         logging.error(error_msg)
-        return error_msg, "", "", "", "", None, None, None, error_msg
+        return error_msg, "", "", "", "", None, None, None, None, error_msg, error_msg
 
 def run_pipeline(dna_input, similarity_score=95.0, build_ml_tree=False):
     try:
         # Clean input
         dna_input = dna_input.upper().strip()
         if not dna_input:
-            return "Empty input", "", "", "", "", None, None, None, "No input provided"
+            return "Empty input", "", "", "", "", None, None, None, None, "No input provided"
         
         # Sanitize DNA sequence
         if not re.match('^[ACTGN]+$', dna_input):
@@ -602,7 +608,7 @@ def run_pipeline(dna_input, similarity_score=95.0, build_ml_tree=False):
         
         if boundary_model:
             try:
-                result = boundary_model.predict_sequence(dna_input)  # Updated to use predict_sequence
+                result = boundary_model.predict_sequence(dna_input)
                 predictions = result['predictions']
                 probs = result['probabilities']['gene']
                 confidence = result['confidence']
@@ -628,12 +634,11 @@ def run_pipeline(dna_input, similarity_score=95.0, build_ml_tree=False):
         keras_output = ""
         if processed_sequence and len(processed_sequence) >= 6:
             keras_prediction = predict_with_keras(processed_sequence)
-            # Use the prediction directly as it's now a percentage
             keras_output = keras_prediction
         else:
             keras_output = "Skipped: sequence too short for F gene validation"
 
-        # Step 3: Maximum Likelihood Tree (Phylogenetic Placement) - Using improved API
+        # Step 3: Maximum Likelihood Tree (Phylogenetic Placement)
         aligned_file = None
         phy_file = None
         ml_tree_output = ""
@@ -648,7 +653,7 @@ def run_pipeline(dna_input, similarity_score=95.0, build_ml_tree=False):
                     aligned_file = ml_aligned
                     phy_file = ml_tree
                 else:
-                    ml_tree_output = ml_message  # This now includes detailed error information
+                    ml_tree_output = ml_message
                     
             except Exception as e:
                 ml_tree_output = f"❌ Phylogenetic placement failed: {str(e)}"
@@ -658,54 +663,71 @@ def run_pipeline(dna_input, similarity_score=95.0, build_ml_tree=False):
         else:
             ml_tree_output = "Phylogenetic placement skipped (not requested)"
 
-# Step 4: NEW Simplified Tree Analysis (using the new analyzer API)
-        html_file = None
+        # Step 4: Simplified Tree Analysis
+        tree_html_file = None
+        report_html_file = None
         tree_html_content = "No tree generated"
+        report_html_content = "No report 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)
+                # Updated call to analyze_sequence_for_tree
+                tree_result, tree_html_path, report_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
+                if tree_html_path and os.path.exists(tree_html_path):
+                    # Copy tree HTML to output directory
                     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])
                     timestamp = str(int(time.time()))
-                    html_filename = f"tree_{safe_seq_name}_{timestamp}.html"
-                    final_html_path = os.path.join(output_dir, html_filename)
-                    
-                    # Copy the HTML file
-                    shutil.copy2(html_path, final_html_path)
-                    html_file = final_html_path
+                    tree_html_filename = f"tree_{safe_seq_name}_{timestamp}.html"
+                    tree_html_final_path = os.path.join(output_dir, tree_html_filename)
+                    shutil.copy2(tree_html_path, tree_html_final_path)
+                    tree_html_file = tree_html_final_path
                     
-                    # Read HTML content for display
-                    with open(html_path, 'r', encoding='utf-8') as f:
+                    # Read tree HTML content for display
+                    with open(tree_html_path, 'r', encoding='utf-8') as f:
                         tree_html_content = f.read()
                     
-                    simplified_ml_output = tree_result
-                    logging.info(f"Tree analysis completed successfully: {html_filename}")
+                    # Clean up temporary tree file
+                    try:
+                        os.unlink(tree_html_path)
+                    except:
+                        pass
+                
+                if report_html_path and os.path.exists(report_html_path):
+                    # Copy report HTML to output directory
+                    report_html_filename = f"report_{safe_seq_name}_{timestamp}.html"
+                    report_html_final_path = os.path.join(output_dir, report_html_filename)
+                    shutil.copy2(report_html_path, report_html_final_path)
+                    report_html_file = report_html_final_path
+                    
+                    # Read report HTML content for display
+                    with open(report_html_path, 'r', encoding='utf-8') as f:
+                        report_html_content = f.read()
                     
-                    # Clean up temporary file
+                    # Clean up temporary report file
                     try:
-                        os.unlink(html_path)
+                        os.unlink(report_html_path)
                     except:
                         pass
-                        
-                else:
-                    simplified_ml_output = tree_result  # Error message
+                
+                simplified_ml_output = tree_result
+                if not tree_html_file:
                     tree_html_content = f"<div style='color: red;'>{tree_result}</div>"
-                    
+                if not report_html_file:
+                    report_html_content = f"<div style='color: red;'>{tree_result}</div>"
+                
+                logging.info(f"Tree analysis completed successfully: {tree_html_filename}")
+                
             except Exception as e:
                 error_msg = f"❌ Tree analysis failed: {str(e)}"
                 simplified_ml_output = error_msg
                 tree_html_content = f"<div style='color: red;'>{error_msg}</div>"
+                report_html_content = f"<div style='color: red;'>{error_msg}</div>"
                 logging.error(f"Tree analysis failed: {e}")
         else:
             if not analyzer:
@@ -716,6 +738,7 @@ def run_pipeline(dna_input, similarity_score=95.0, build_ml_tree=False):
                 simplified_ml_output = "❌ No processed sequence available for tree analysis"
             
             tree_html_content = f"<div style='color: orange;'>{simplified_ml_output}</div>"
+            report_html_content = f"<div style='color: orange;'>{simplified_ml_output}</div>"
 
         # Final summary
         summary_output = f"""
@@ -726,19 +749,22 @@ def run_pipeline(dna_input, similarity_score=95.0, build_ml_tree=False):
 ✅ F GENE VALIDATION: {keras_output}
 🌳 PHYLOGENETIC PLACEMENT: {'✅ Completed' if 'successfully' in ml_tree_output else '❌ ' + ('Skipped' if 'skipped' in ml_tree_output else 'Failed')}
 🔬 TREE ANALYSIS: {'✅ Completed' if '✅' in simplified_ml_output else '❌ ' + ('Not available' if 'not available' in simplified_ml_output else 'Failed')}
+📝 DETAILED REPORT: {'✅ Generated' if report_html_file else '❌ Not generated'}
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 """
 
         return (
-            boundary_output,  # F gene sequence
-            keras_output,     # F gene validation
-            ml_tree_output,   # Phylogenetic placement
-            simplified_ml_output,  # Tree analysis
-            summary_output,   # Summary
-            aligned_file,     # Alignment file
-            phy_file,         # Tree file
-            html_file,        # HTML tree file
-            tree_html_content # HTML content for display
+            boundary_output,
+            keras_output,
+            ml_tree_output,
+            simplified_ml_output,
+            summary_output,
+            aligned_file,
+            phy_file,
+            tree_html_file,
+            report_html_file,
+            tree_html_content,
+            report_html_content
         )
         
     except Exception as e:
@@ -746,14 +772,13 @@ def run_pipeline(dna_input, similarity_score=95.0, build_ml_tree=False):
         logging.error(error_msg)
         import traceback
         logging.error(f"Full traceback: {traceback.format_exc()}")
-        return error_msg, "", "", "", "", None, None, None, error_msg
+        return error_msg, "", "", "", "", None, None, None, None, error_msg, error_msg
 
 
 # --- Gradio Interface ---
 def create_interface():
     """Create and configure the Gradio interface"""
     
-    # Custom CSS for better styling
     custom_css = """
     .gradio-container {
         font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
@@ -802,7 +827,6 @@ def create_interface():
     
     with gr.Blocks(css=custom_css, title="🧬 Advanced Gene Analysis Pipeline", theme=gr.themes.Soft()) as iface:
         
-        # Header
         gr.HTML("""
         <div style="text-align: center; padding: 20px; background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); border-radius: 15px; margin-bottom: 20px;">
             <h1 style="color: white; margin: 0; font-size: 2.5em; font-weight: 700;">🧬 Advanced Gene Analysis Pipeline</h1>
@@ -810,7 +834,6 @@ def create_interface():
         </div>
         """)
         
-        # Instructions
         with gr.Accordion("📋 Instructions & Information", open=False):
             gr.HTML("""
             <div style="background: #f8fafc; padding: 20px; border-radius: 10px; border-left: 4px solid #3b82f6;">
@@ -820,6 +843,7 @@ def create_interface():
                     <li><strong>Gene Validation:</strong> Validates extracted sequence as F gene using deep learning</li>
                     <li><strong>Phylogenetic Placement:</strong> Places sequence in reference phylogenetic tree (MAFFT + IQ-TREE)</li>
                     <li><strong>Interactive Tree Analysis:</strong> Creates interactive phylogenetic tree with similar sequences</li>
+                    <li><strong>Detailed Report:</strong> Provides comprehensive analysis details</li>
                 </ol>
                 
                 <h3 style="color: #1e40af;">📁 Input Requirements</h3>
@@ -837,20 +861,17 @@ def create_interface():
             </div>
             """)
         
-        # Main input section
         with gr.Row():
             with gr.Column(scale=2):
                 gr.HTML("<h3 style='color: #1e40af; margin-bottom: 10px;'>📝 Sequence Input</h3>")
                 
-                # Input tabs
                 with gr.Tabs():
                     with gr.TabItem("✍️ Text Input"):
                         dna_input = gr.Textbox(
                             label="DNA Sequence",
                             placeholder="Enter your DNA sequence here (A, T, C, G, N)...",
                             lines=6,
-                            value="",
-                            info="Paste your DNA sequence or enter it manually"
+                            value=""
                         )
                     
                     with gr.TabItem("📁 File Upload"):
@@ -868,17 +889,14 @@ def create_interface():
                     maximum=99.0,
                     value=95.0,
                     step=1.0,
-                    label="Similarity Threshold (%)",
-                    info="Minimum similarity for tree analysis"
+                    label="Similarity Threshold (%)"
                 )
                 
                 build_ml_tree = gr.Checkbox(
                     label="🌳 Enable Phylogenetic Placement",
-                    value=False,
-                    info="Requires MAFFT and IQ-TREE (slower but more accurate)"
+                    value=False
                 )
                 
-                # Action buttons
                 with gr.Row():
                     analyze_text_btn = gr.Button(
                         "🚀 Analyze Text Input",
@@ -891,52 +909,50 @@ def create_interface():
                         size="lg"
                     )
         
-        # Results section
         gr.HTML("<hr style='margin: 30px 0; border: none; height: 2px; background: linear-gradient(to right, #3b82f6, #8b5cf6);'>")
         gr.HTML("<h2 style='color: #1e40af; text-align: center; margin-bottom: 20px;'>📊 Analysis Results</h2>")
         
-        # Output tabs
         with gr.Tabs():
             with gr.TabItem("🎯 F Gene Extraction"):
                 f_gene_output = gr.Textbox(
                     label="Extracted F Gene Sequence",
-                    lines=8,
-                    info="Boundary-detected F gene region"
+                    lines=8
                 )
             
             with gr.TabItem("✅ Gene Validation"):
                 keras_output = gr.Textbox(
                     label="F Gene Validation Result",
-                    lines=3,
-                    info="Deep learning validation of F gene"
+                    lines=3
                 )
             
             with gr.TabItem("🌳 Phylogenetic Placement"):
                 ml_tree_output = gr.Textbox(
                     label="Phylogenetic Placement Results",
-                    lines=10,
-                    info="MAFFT alignment + IQ-TREE placement results"
+                    lines=10
                 )
             
             with gr.TabItem("🔬 Interactive Tree"):
                 tree_analysis_output = gr.Textbox(
                     label="Tree Analysis Status",
-                    lines=5,
-                    info="Interactive phylogenetic tree generation"
+                    lines=5
                 )
                 tree_html_display = gr.HTML(
                     label="Interactive Phylogenetic Tree",
                     value="<div style='text-align: center; color: #6b7280; padding: 40px;'>No tree generated yet. Run analysis to create interactive tree.</div>"
                 )
             
+            with gr.TabItem("📝 Detailed Report"):
+                report_html_display = gr.HTML(
+                    label="Detailed Analysis Report",
+                    value="<div style='text-align: center; color: #6b7280; padding: 40px;'>No report generated yet. Run analysis to create detailed report.</div>"
+                )
+            
             with gr.TabItem("📋 Summary"):
                 summary_output = gr.Textbox(
                     label="Analysis Summary",
-                    lines=12,
-                    info="Complete pipeline summary"
+                    lines=12
                 )
         
-        # Download section
         with gr.Accordion("💾 Download Results", open=False):
             with gr.Row():
                 alignment_file = gr.File(
@@ -951,8 +967,11 @@ def create_interface():
                     label="🌐 Download Interactive Tree (HTML)",
                     visible=True
                 )
+                report_file = gr.File(
+                    label="📝 Download Detailed Report (HTML)",
+                    visible=True
+                )
         
-        # Footer
         gr.HTML("""
         <div style="text-align: center; padding: 20px; margin-top: 30px; border-top: 2px solid #e5e7eb; color: #6b7280;">
             <p style="margin: 0;">🧬 Advanced Gene Analysis Pipeline | Powered by Deep Learning & Phylogenetics</p>
@@ -960,7 +979,6 @@ def create_interface():
         </div>
         """)
         
-        # Event handlers
         analyze_text_btn.click(
             fn=run_pipeline,
             inputs=[dna_input, similarity_score, build_ml_tree],
@@ -973,7 +991,9 @@ def create_interface():
                 alignment_file,
                 tree_file,
                 html_tree_file,
-                tree_html_display
+                report_file,
+                tree_html_display,
+                report_html_display
             ]
         )
         
@@ -989,12 +1009,13 @@ def create_interface():
                 alignment_file,
                 tree_file,
                 html_tree_file,
-                tree_html_display
+                report_file,
+                tree_html_display,
+                report_html_display
             ]
         )
     
     return iface
-
 # --- Main Execution ---
 if __name__ == "__main__":
     try: