Update app.py

app.py

@@ -45,11 +45,8 @@ selected_features =  [
 
 def extract_features(sequence):
     aa_features = AAComposition.CalculateAADipeptideComposition(sequence)
-
     auto_features = Autocorrelation.CalculateAutoTotal(sequence)
-
     ctd_features = CTD.CalculateCTD(sequence)
-
     pseaac_features = PseudoAAC.GetAPseudoAAC(sequence, lamda=9)
 
     all_features = {**aa_features, **auto_features, **ctd_features, **pseaac_features}
@@ -57,7 +54,23 @@ def extract_features(sequence):
     # Convert to DataFrame
     feature_df = pd.DataFrame([all_features])
 
-    # Select features that match training data
+    print("Extracted Features:", feature_df.columns.tolist())  # Debugging line
+
+    # Ensure all selected features are present
+    missing_features = [f for f in selected_features if f not in feature_df.columns]
+    extra_features = [f for f in feature_df.columns if f not in selected_features]
+
+    if missing_features:
+        print(f"Missing Features ({len(missing_features)}):", missing_features)
+    
+    if extra_features:
+        print(f"Extra Features ({len(extra_features)}):", extra_features)
+
+    # Fix missing columns by adding them with default values (0)
+    for feature in missing_features:
+        feature_df[feature] = 0
+
+    # Select only the required features
     feature_df = feature_df[selected_features]
 
     # Normalize
@@ -65,6 +78,7 @@ def extract_features(sequence):
 
     return normalized_features
 
+
 def predict(sequence):
     """Predict if the sequence is an AMP or not."""
     features = extract_features(sequence)