Update app.py

app.py

@@ -51,14 +51,9 @@ 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)
-    
-    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)
+    all_features_dict.update(dipeptide_features)
 
     auto_features = Autocorrelation.CalculateAutoTotal(sequence)
     all_features_dict.update(auto_features)
@@ -70,9 +65,12 @@ def extract_features(sequence):
     all_features_dict.update(pseudo_features)
 
     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()
+    feature_array = np.array(feature_values).reshape(1, -1) # Reshape to (1, n_features) - CORRECT SHAPE
+    print(f"Shape of feature_array before normalization: {feature_array.shape}") # Debug print
+
+    normalized_features = scaler.transform(feature_array) # Normalize - NO TRANSPOSE
+    normalized_features = normalized_features.flatten() # Flatten AFTER normalization if needed
+
 
     selected_feature_dict = {}
     for i, feature in enumerate(selected_features):