Update app.py

app.py

@@ -7,7 +7,7 @@ import os
 import re
 import logging
 import numpy as np
-from predictor import GenePredictor
+from predictor import EnhancedGenePredictor
 from tensorflow.keras.models import load_model
 # Import the new analyzer
 from analyzer import PhylogeneticTreeAnalyzer
@@ -56,7 +56,7 @@ try:
         token=hf_token
     )
     if os.path.exists(boundary_path):
-        boundary_model = GenePredictor(boundary_path)
+        boundary_model = EnhancedGenePredictor(boundary_path)
         logging.info("Boundary model loaded successfully from Hugging Face Hub.")
     else:
         logging.warning(f"Boundary model file not found after download")
@@ -597,16 +597,19 @@ def run_pipeline(dna_input, similarity_score=95.0, build_ml_tree=False):
             logging.info("DNA sequence sanitized")
 
         # Step 1: Boundary Prediction - Extract F gene sequence
-        processed_sequence = dna_input  # This will be the sequence used for downstream analysis
+        processed_sequence = dna_input
         boundary_output = ""
         
         if boundary_model:
             try:
-                predictions, probs, confidence = boundary_model.predict(dna_input)
-                regions = boundary_model.extract_gene_regions(predictions, dna_input)
+                result = boundary_model.predict_sequence(dna_input)  # Updated to use predict_sequence
+                predictions = result['predictions']
+                probs = result['probabilities']['gene']
+                confidence = result['confidence']
+                regions = result['gene_regions']
                 if regions:
-                    processed_sequence = regions[0]["sequence"]  # Use the extracted gene region
-                    boundary_output = processed_sequence  # Output the actual F gene sequence
+                    processed_sequence = regions[0]["sequence"]
+                    boundary_output = processed_sequence
                     logging.info(f"F gene extracted: {len(processed_sequence)} bp (confidence: {confidence:.3f})")
                 else:
                     boundary_output = f"No F gene regions found in input sequence"
@@ -616,7 +619,7 @@ def run_pipeline(dna_input, similarity_score=95.0, build_ml_tree=False):
             except Exception as e:
                 logging.error(f"Boundary model failed: {e}")
                 boundary_output = f"Boundary model error: {str(e)}"
-                processed_sequence = dna_input  # Fall back to original sequence
+                processed_sequence = dna_input
         else:
             boundary_output = f"Boundary model not available. Using original input: {len(dna_input)} bp"
             processed_sequence = dna_input