Update app.py

app.py

@@ -862,10 +862,10 @@ def create_interface():
             gr.Markdown("### 🌲 Phylogenetic Tree Visualization (ML Simplified Tree)")
             tree_html = gr.HTML(
                 label="Interactive Tree",
-                value="<p>Click 'Show Tree' to view the ML Simplified Tree in a new tab.</p>"
+                value="<p>Click the link below to view the ML Simplified Tree in a new tab.</p>"
             )
             with gr.Row():
-                show_tree_btn = gr.Button("👁️ Show Tree", variant="secondary")
+                show_tree_link = gr.HTML()
 
             # File downloads
             gr.Markdown("### 📁 Download Results")
@@ -885,6 +885,78 @@ 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):
             return run_pipeline(dna_seq, sim_score, build_tree)
@@ -907,9 +979,10 @@ def create_interface():
                 try:
                     # Use the same file-serving URL as the download link
                     file_url = f"/file={html_file}"
-                    return gr.update(value=f"<script>window.open('{file_url}', '_blank');</script>")
+                    link_html = f'<a href="{file_url}" target="_blank">View ML Simplified Tree</a>'
+                    return gr.update(value=link_html)
                 except Exception as e:
-                    return gr.update(value=f"<p>Error showing tree: {str(e)}. Please download and open the file manually.</p>")
+                    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
@@ -928,10 +1001,10 @@ def create_interface():
             outputs=[dna_input, fasta_file, similarity_score, build_ml_tree, status_display]
         )
         
-        show_tree_btn.click(
+        show_tree_link.click(
             fn=show_tree,
             inputs=[html_file],
-            outputs=[tree_html]
+            outputs=[show_tree_link]
         )
         
         # Example data loading