Update app.py

app.py

@@ -866,7 +866,6 @@ def create_interface():
             )
             with gr.Row():
                 show_tree_link = gr.HTML()
-                debug_output = gr.Textbox(label="Debug Info", interactive=False)
 
             # File downloads
             gr.Markdown("### 📁 Download Results")
@@ -886,40 +885,91 @@ def create_interface():
                     interactive=False
                 )
         
-        
+        with gr.Tab("ℹ️ Help & Info"):
+            gr.Markdown("""
+            ## About This Tool
+            
+            ### F Gene Analysis Pipeline
+            This comprehensive pipeline analyzes F genes through multiple computational approaches:
+            
+            #### 🎯 Gene Boundary Detection
+            - Uses deep learning to identify and extract F gene sequences from larger genomic sequences
+            - Provides confidence scores for detected boundaries
+            - Automatically trims sequences to focus on the F gene region
+            
+            #### 🔍 Gene Validation
+            - Employs k-mer based machine learning models to validate extracted sequences
+            - Provides probability scores indicating likelihood of being a genuine F gene
+            - Uses 6-mer frequency patterns for classification
+            
+            #### 🌳 Phylogenetic Analysis
+            
+            **Maximum Likelihood Trees:**
+            - Requires MAFFT (sequence alignment) and IQ-TREE (phylogenetic reconstruction)
+            - Performs model selection and bootstrap analysis
+            - Generates publication-quality phylogenetic trees
+            - Provides detailed evolutionary analysis
+            
+            **Simplified Trees:**
+            - Uses built-in algorithms for quick phylogenetic analysis
+            - Interactive visualization with similarity-based clustering
+            - Faster alternative when external tools are not available
+            
+            ### Input Requirements
+            - **DNA Sequences**: ATCG format, minimum 50 bp for meaningful analysis
+            - **FASTA Files**: Standard FASTA format with single or multiple sequences
+            - **Similarity Threshold**: 1-99% for controlling phylogenetic analysis sensitivity
+            
+            ### Dependencies
+            
+            **Required for ML Trees:**
+            ```bash
+            # Ubuntu/Debian
+            sudo apt-get install mafft iqtree
+            
+            # macOS
+            brew install mafft iqtree
+            
+            # Conda
+            conda install -c bioconda mafft iqtree
+            ```
+            
+            ### Output Files
+            - **Aligned FASTA**: Multiple sequence alignment in FASTA format
+            - **Tree File**: Newick format phylogenetic tree
+            - **HTML Tree**: Interactive visualization for web browsers (ML Simplified Tree)
+            
+            ### Troubleshooting
+            
+            **Common Issues:**
+            - *"No similar sequences found"*: Lower the similarity threshold
+            - *"Sequence too short"*: Provide sequences longer than 50 bp
+            - *"MAFFT/IQ-TREE not found"*: Install required dependencies
+            - *"Model not available"*: Check model files are properly downloaded
+            
+            **Performance Tips:**
+            - Use sequences between 100-2000 bp for optimal performance  
+            - Limit to <50 sequences for faster tree construction
+            - Lower similarity thresholds find more distant relatives
+            - Higher thresholds focus on closely related sequences
+            
+            ### Citation
+            If you use this tool in your research, please cite the appropriate methods and tools used.
+            """)
         
         # Event handlers
         def run_analysis_text(dna_seq, sim_score, build_tree):
-            results = run_pipeline(dna_seq, sim_score, build_tree)
-            html_file_path = results.get('html_file', None)  # Fallback to check dictionary
-            return (results.get('boundary_output', ''),
-                    results.get('keras_output', ''),
-                    results.get('ml_tree_output', ''),
-                    results.get('simplified_ml_output', ''),
-                    tree_html,
-                    results.get('aligned_file', None),
-                    results.get('phy_file', None),
-                    html_file_path if html_file_path and os.path.exists(html_file_path) else None,
-                    "Analysis complete")
-
+            return run_pipeline(dna_seq, sim_score, build_tree)
+        
         def run_analysis_file(file_obj, sim_score, build_tree):
-            results = run_pipeline_from_file(file_obj, sim_score, build_tree)
-            html_file_path = results.get('html_file', None)
-            return (results.get('boundary_output', ''),
-                    results.get('keras_output', ''),
-                    results.get('ml_tree_output', ''),
-                    results.get('simplified_ml_output', ''),
-                    tree_html,
-                    results.get('aligned_file', None),
-                    results.get('phy_file', None),
-                    html_file_path if html_file_path and os.path.exists(html_file_path) else None,
-                    "Analysis complete")
-
+            return run_pipeline_from_file(file_obj, sim_score, build_tree)
+        
         def run_analysis_combined(dna_seq, file_obj, sim_score, build_tree):
+            # Priority: file upload over text input
             if file_obj is not None:
-                return run_analysis_file(file_obj, sim_score, build_tree)
+                return run_pipeline_from_file(file_obj, sim_score, build_tree)
             else:
-                return run_analysis_text(dna_seq, sim_score, build_tree)
+                return run_pipeline(dna_seq, sim_score, build_tree)
         
         def clear_inputs():
             return "", None, 95.0, False, "Ready to analyze"
@@ -927,13 +977,14 @@ def create_interface():
         def show_tree(html_file):
             if html_file and os.path.exists(html_file):
                 try:
+                    # Convert to relative path for Gradio file serving
                     relative_path = os.path.relpath(html_file, os.getcwd())
                     file_url = f"/file={relative_path}"
                     link_html = f'<a href="{file_url}" target="_blank">View ML Simplified Tree</a>'
-                    return gr.update(value=link_html), f"File found: {relative_path}"
+                    return gr.update(value=link_html)
                 except Exception as e:
-                    return gr.update(value=f"<p>Error generating link: {str(e)}</p>"), f"Error: {str(e)}"
-            return gr.update(value="<p>No tree file available</p>"), "No file available"
+                    return gr.update(value=f"<p>Error generating link: {str(e)}. Please download and open the file manually.</p>")
+            return gr.update(value="<p>No tree file available. Run analysis to generate one.</p>")
         
         # Connect events
         run_btn.click(
@@ -954,7 +1005,7 @@ def create_interface():
         show_tree_link.click(
             fn=show_tree,
             inputs=[html_file],
-            outputs=[show_tree_link, debug_output]
+            outputs=[show_tree_link]
         )
         
         # Example data loading