Update app.py

app.py

@@ -43,6 +43,23 @@ selected_features =  [
     "APAAC24"
 ]
 
+def extract_features(sequence):
+    """Extract selected features and normalize them."""
+    all_features = AAComposition.CalculateAADipeptideComposition(sequence)  
+    feature_values = list(all_features.values())  
+    feature_array = np.array(feature_values).reshape(-1, 1)
+    feature_array = feature_array[: 420]  # Ensure we only use 420 features
+    normalized_features = scaler.transform(feature_array.T)
+    normalized_features = normalized_features.flatten()  
+
+    # 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 selected_feature_array
+
 def extract_features(sequence):
     """Extract selected features and normalize them."""
     
@@ -54,18 +71,14 @@ def extract_features(sequence):
 
     # Combine all extracted features
     all_features = {**aa_features, **auto_features, **ctd_features, **pseaac_features}
+    normalized_features = scaler.transform(all_features.T)
+    normalized_features = normalized_features.flatten()  
 
-    # Ensure all selected features are present
-    feature_dict = {feature: all_features.get(feature, 0) for feature in selected_features}
-    
-    # Convert to DataFrame
-    feature_df = pd.DataFrame([feature_dict])
-
-    # Normalize the features
-    normalized_features = scaler.transform(feature_df)
-
-    # Convert to a NumPy array in the expected format
-    selected_feature_array = normalized_features.flatten().reshape(1, -1)
+    # 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 selected_feature_array