Update app.py

app.py

@@ -31,13 +31,23 @@ keras_model = None
 kmer_to_index = None
 
 if os.path.exists(boundary_path):
-    boundary_model = GenePredictor(boundary_path)
-    logging.info("Boundary model loaded.")
+    try:
+        boundary_model = GenePredictor(boundary_path)
+        logging.info(f"Boundary model loaded successfully from {boundary_path}")
+    except Exception as e:
+        logging.error(f"Failed to load Boundary model from {boundary_path}: {e}")
+else:
+    logging.error(f"Boundary model file not found at {boundary_path}")
 if os.path.exists(keras_path) and os.path.exists(kmer_path):
-    keras_model = load_model(keras_path)
-    with open(kmer_path, "rb") as f:
-        kmer_to_index = pickle.load(f)
-    logging.info("Keras model and k-mer index loaded.")
+    try:
+        keras_model = load_model(keras_path)
+        with open(kmer_path, "rb") as f:
+            kmer_to_index = pickle.load(f)
+        logging.info(f"Keras model and k-mer index loaded successfully from {keras_path} and {kmer_path}")
+    except Exception as e:
+        logging.error(f"Failed to load Keras model or kmer_to_index from {keras_path} or {kmer_path}: {e}")
+else:
+    logging.error(f"Keras model or kmer_to_index file not found at {keras_path} or {kmer_path}")
 
 # --- Keras Prediction ---
 def predict_with_keras(sequence):
@@ -65,19 +75,35 @@ def run_pipeline(dna_input):
     dna_input = dna_input.upper()
     if not re.match('^[ACTGN]+$', dna_input):
         dna_input = ''.join(c if c in 'ACTGN' else 'N' for c in dna_input)
+        logging.warning("Invalid DNA sequence characters replaced with 'N'.")
 
     # Step 1: Boundary Prediction
     if boundary_model:
-        predictions, probs, confidence = boundary_model.predict(dna_input)
-        regions = boundary_model.extract_gene_regions(predictions, dna_input)
-        step1_out = regions[0]["sequence"] if regions else dna_input
+        try:
+            predictions, probs, confidence = boundary_model.predict(dna_input)
+            regions = boundary_model.extract_gene_regions(predictions, dna_input)
+            step1_out = regions[0]["sequence"] if regions else dna_input
+            logging.info(f"Boundary model output: {step1_out[:50]}... (truncated)")
+        except Exception as e:
+            logging.error(f"Boundary model prediction failed: {e}")
+            step1_out = dna_input
     else:
         step1_out = dna_input
+        logging.info("Boundary model skipped due to loading failure or missing file")
 
     # Step 2: Keras Prediction
-    step2_out = predict_with_keras(step1_out) if keras_model and kmer_to_index else step1_out
+    if keras_model and kmer_to_index:
+        try:
+            step2_out = predict_with_keras(step1_out)
+            logging.info(f"Keras model output: {step2_out[:50]}... (truncated)")
+        except Exception as e:
+            logging.error(f"Keras prediction failed: {e}")
+            step2_out = step1_out
+    else:
+        step2_out = step1_out
+        logging.info("Keras model skipped due to loading failure or missing file")
 
-    # Save to FASTA for MAFFT/IQTREE
+    # Save to FASTA for MAFFT/IQTREE (optional, can be skipped if ML tree is independent)
     fasta_file = "input_sequence.fasta"
     with open(fasta_file, "w") as f:
         f.write(">query\n" + step2_out + "\n")
@@ -91,37 +117,46 @@ def run_pipeline(dna_input):
         aligned_file = None
         logging.error(f"MAFFT failed: {e}")
 
-    # Run IQ-TREE
+    # Run IQ-TREE (only if alignment exists)
     phy_file = "input_sequence.phy"
-    try:
-        subprocess.run(["iqtree2", "-s", aligned_file, "-nt", "AUTO"], check=True)
-    except Exception as e:
-        logging.error(f"IQ-TREE failed: {e}")
+    if aligned_file is not None:
+        try:
+            subprocess.run(["iqtree2", "-s", aligned_file, "-nt", "AUTO"], check=True)
+        except Exception as e:
+            logging.error(f"IQ-TREE failed: {e}")
+    else:
+        logging.warning("Skipping IQ-TREE due to missing alignment file")
 
-    # Step 3: ML Simplified Tree
+    # Step 3: ML Simplified Tree (independent of MAFFT/IQ-TREE)
     html_file = "phylogenetic_tree_normalized_horizontal.html"
     ml_output = ""
+    tree_html_content = "No tree generated."
     if os.path.exists(csv_path):
         analyzer = ml_simplified_tree.PhylogeneticTreeAnalyzer()
         if analyzer.load_data(csv_path):
             if analyzer.find_query_sequence(step2_out):
                 matched_ids, perc = analyzer.find_similar_sequences(analyzer.matching_percentage)
-                analyzer.create_interactive_tree(matched_ids, perc)
-                ml_output = "Tree generated."
-                if os.path.exists(html_file):
-                    with open(html_file, "r") as f:
-                        tree_html_content = f.read()
-                else:
-                    tree_html_content = "Tree HTML file not generated."
+                try:
+                    analyzer.create_interactive_tree(matched_ids, perc)
+                    ml_output = "Tree generated."
+                    if os.path.exists(html_file):
+                        with open(html_file, "r") as f:
+                            tree_html_content = f.read()
+                    else:
+                        ml_output += " (HTML file not generated)"
+                        logging.error("HTML file not created after tree generation")
+                except Exception as e:
+                    ml_output = f"Error creating tree: {e}"
+                    logging.error(f"Tree creation failed: {e}")
             else:
-                ml_output = "Query sequence not found."
-                tree_html_content = "No tree generated."
+                ml_output = "Query sequence not found in CSV."
+                logging.warning(f"Query sequence {step2_out[:50]}... not found")
         else:
             ml_output = "Failed to load CSV."
-            tree_html_content = "No tree generated."
+            logging.error("CSV loading failed")
     else:
         ml_output = "CSV file missing."
-        tree_html_content = "No tree generated."
+        logging.error(f"CSV file not found at {csv_path}")
 
     return step1_out, step2_out, csv_path, ml_output, html_file, aligned_file, phy_file, tree_html_content