Update app.py

app.py

@@ -96,7 +96,7 @@ except Exception as e:
     analyzer = None
 
 # --- Tree Analysis Function (Based on old Gradio API) ---
-def analyze_sequence_for_tree(sequence: str, matching_percentage: float = 95.0) -> str:
+def analyze_sequence_for_tree(sequence: str, matching_percentage: float) -> str:
     """
     Analyze sequence and create phylogenetic tree using the working Gradio API pattern
     """
@@ -205,18 +205,18 @@ def read_fasta_file(file_obj):
         return ""
 
 # --- Full Pipeline ---
-def run_pipeline_from_file(fasta_file_obj):
+def run_pipeline_from_file(fasta_file_obj, similarity_score):
     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 run_pipeline(dna_input)
+        return run_pipeline(dna_input, similarity_score)
     except Exception as e:
         error_msg = f"Pipeline error: {str(e)}"
         logging.error(error_msg)
         return error_msg, "", "", "", None, None, None, error_msg
 
-def run_pipeline(dna_input):
+def run_pipeline(dna_input, similarity_score=95.0):
     try:
         # Clean input
         dna_input = dna_input.upper().strip()
@@ -283,8 +283,8 @@ def run_pipeline(dna_input):
             try:
                 logging.info(f"Starting ML tree analysis with F gene sequence length: {len(processed_sequence)}")
                 
-                # Use the new tree analysis function
-                tree_result = analyze_sequence_for_tree(processed_sequence, matching_percentage=95.0)
+                # Use the new tree analysis function with user-specified similarity
+                tree_result = analyze_sequence_for_tree(processed_sequence, matching_percentage=similarity_score)
                 
                 if tree_result and not tree_result.startswith("Error:"):
                     # Success - we have HTML content
@@ -301,7 +301,7 @@ def run_pipeline(dna_input):
                     
                     # Count sequences analyzed
                     if analyzer.find_query_sequence(processed_sequence):
-                        matched_ids, perc = analyzer.find_similar_sequences(95.0)
+                        matched_ids, perc = analyzer.find_similar_sequences(similarity_score)
                         ml_output += f"\n- {len(matched_ids)} sequences analyzed"
                         ml_output += f"\n- Similarity threshold: {perc:.1f}%"
                 else:
@@ -345,18 +345,40 @@ with gr.Blocks(title="Viral Gene Phylogenetic Pipeline", theme=gr.themes.Soft())
     gr.Markdown("This pipeline processes DNA sequences through boundary detection, k-mer analysis, and phylogenetic tree construction.")
 
     with gr.Tab("📝 Paste DNA Sequence"):
-        inp = gr.Textbox(
-            label="DNA Input", 
-            placeholder="Paste your DNA sequence here (ACTG format)",
-            lines=5
-        )
+        with gr.Row():
+            with gr.Column(scale=3):
+                inp = gr.Textbox(
+                    label="DNA Input", 
+                    placeholder="Paste your DNA sequence here (ACTG format)",
+                    lines=5
+                )
+            with gr.Column(scale=1):
+                similarity_input = gr.Slider(
+                    minimum=50, 
+                    maximum=99, 
+                    step=1, 
+                    value=95, 
+                    label="Similarity Threshold (%)",
+                    info="Higher values = more similar sequences"
+                )
         btn1 = gr.Button("🚀 Run Pipeline", variant="primary", size="lg")
 
     with gr.Tab("📁 Upload FASTA File"):
-        file_input = gr.File(
-            label="FASTA File", 
-            file_types=['.fasta', '.fa', '.txt']
-        )
+        with gr.Row():
+            with gr.Column(scale=3):
+                file_input = gr.File(
+                    label="FASTA File", 
+                    file_types=['.fasta', '.fa', '.txt']
+                )
+            with gr.Column(scale=1):
+                similarity_input_file = gr.Slider(
+                    minimum=50, 
+                    maximum=99, 
+                    step=1, 
+                    value=95, 
+                    label="Similarity Threshold (%)",
+                    info="Higher values = more similar sequences"
+                )
         btn2 = gr.Button("🚀 Run on FASTA", variant="primary", size="lg")
 
     # Outputs
@@ -381,12 +403,12 @@ with gr.Blocks(title="Viral Gene Phylogenetic Pipeline", theme=gr.themes.Soft())
     # Event handlers
     btn1.click(
         fn=run_pipeline, 
-        inputs=inp, 
+        inputs=[inp, similarity_input], 
         outputs=[out1, out2, out3, out4, html, fasta, phy, tree_html]
     )
     btn2.click(
         fn=run_pipeline_from_file, 
-        inputs=file_input, 
+        inputs=[file_input, similarity_input_file], 
         outputs=[out1, out2, out3, out4, html, fasta, phy, tree_html]
     )