Update app.py

app.py

@@ -46,27 +46,36 @@ selected_features =  [
 
 
 def extract_features(sequence):
-    """Extract selected features and normalize them."""
-    
-    # Extract features from different methods
-    aa_features = AAComposition.CalculateAADipeptideComposition(sequence)
-    auto_features = Autocorrelation.CalculateAutoTotal(sequence)
-    ctd_features = CTD.CalculateCTD(sequence)
-    pseaac_features = PseudoAAC.GetAPseudoAAC(sequence, lamda=9)
+    try:
+        comp_features = AAComposition.CalculateAAComposition(sequence)
+        auto_features = Autocorrelation.CalculateAutoTotal(sequence)
+        ctd_features = CTD.CalculateCTD(sequence)
+        pseudo_features = PseudoAAC.GetAPseudoAAC(sequence)
+        
+        # Combine all features into a dictionary
+        all_features = {**comp_features, **auto_features, **ctd_features, **pseudo_features}
+        
+        # Convert to DataFrame
+        all_features_df = pd.DataFrame([all_features])
+        
+        # Select only required features
+        all_features_df = all_features_df[selected_features]
+
+        # Ensure correct shape
+        if all_features_df.shape[0] == 0:
+            raise ValueError("No features extracted. Check the input sequence.")
 
-    # Combine all extracted features
-    all_features = {**aa_features, **auto_features, **ctd_features, **pseaac_features}
-    all_features = list(all_features.values())
-    normalized_features = scaler.transform(all_features.T)
-    normalized_features = normalized_features.flatten()  
+        # Normalize the features
+        normalized_features = scaler.transform(all_features_df)
 
-    # Select features that match training data
-    selected_feature_dict = {feature: normalized_features[i] for i, feature in enumerate(selected_features)
-                             if feature in all_features}
-    selected_feature_df = pd.DataFrame([selected_feature_dict])
-    selected_feature_array = selected_feature_df.T.to_numpy()
+        return normalized_features
+    except ZeroDivisionError:
+        print("Error: Division by zero encountered in Moran autocorrelation calculation.")
+        return None
+    except Exception as e:
+        print(f"Feature extraction error: {e}")
+        return None
 
-    return selected_feature_array