Update app.py

app.py

@@ -51,9 +51,14 @@ def extract_features(sequence):
         return "Error: Protein sequence must be longer than 9 amino acids to extract features (for lamda=9)."
 
     all_features_dict = {}
-
+    
+    # Calculate all dipeptide features
     dipeptide_features = AAComposition.CalculateAADipeptideComposition(sequence)
-    all_features_dict.update(dipeptide_features)
+    
+    first_420_keys = list(dipeptide_features.keys())[:420] 
+    filtered_dipeptide_features = {key: dipeptide_features[key] for key in first_420_keys}
+    
+    all_features_dict.update(filtered_dipeptide_features)
 
     auto_features = Autocorrelation.CalculateAutoTotal(sequence)
     all_features_dict.update(auto_features)
@@ -64,26 +69,20 @@ def extract_features(sequence):
     pseudo_features = PseudoAAC.GetAPseudoAAC(sequence, lamda=9)
     all_features_dict.update(pseudo_features)
 
-    # Create an ordered list of feature values based on selected_features
-    ordered_feature_values = []
-    missing_features = []
-    for feature_name in selected_features:
-        if feature_name in all_features_dict:
-            ordered_feature_values.append(all_features_dict[feature_name])
-        else:
-            missing_features.append(feature_name)
-            ordered_feature_values.append(0) # Pad with 0 for missing features - important for consistent input size
-
-    if missing_features:
-        print(f"Warning: The following features were missing from extraction and padded with 0: {missing_features}")
-
-
-    feature_array = np.array(ordered_feature_values).reshape(1, -1) # Reshape to (1, n_features) for single sample
+    feature_values = list(all_features_dict.values())
+    feature_array = np.array(feature_values).reshape(-1, 1)
+    normalized_features = scaler.transform(feature_array.T)
+    normalized_features = normalized_features.flatten()
 
-    normalized_features = scaler.transform(feature_array) # Normalize the ordered feature array
+    selected_feature_dict = {}
+    for i, feature in enumerate(selected_features):
+        if feature in all_features_dict:
+            selected_feature_dict[feature] = normalized_features[i]
 
+    selected_feature_df = pd.DataFrame([selected_feature_dict])
+    selected_feature_array = selected_feature_df.T.to_numpy()
 
-    return normalized_features # Return the normalized features as a 2D numpy array
+    return selected_feature_array
 
 
 def predict(sequence):