Update app.py

app.py

@@ -46,24 +46,36 @@ selected_features = [
 ]
 
 def extract_features(sequence):
- 
-    dipeptide_features = AAComposition.CalculateAADipeptideComposition(sequence)
+    if len(sequence) < 2:  # Ensure sequence is long enough
+        return None  
 
-    # 2. Calculate other features
-    auto_features = Autocorrelation.CalculateAutoTotal(sequence)
-    ctd_features = CTD.CalculateCTD(sequence)
-    pseudo_features = PseudoAAC.GetAPseudoAAC(sequence)
-    all_features = {**auto_features, **ctd_features, **pseudo_features,**dipeptide_features}
-    all_features = list(all_features.values())
-    all_features = np.array(all_features).reshape(-1, 1) #Correct shape
-    normalized_features = scaler.transform(all_features.T)
-    normalized_features = normalized_features.flatten()  
+    try:
+        dipeptide_features = AAComposition.CalculateAADipeptideComposition(sequence)
+        auto_features = Autocorrelation.CalculateAutoTotal(sequence)
+        ctd_features = CTD.CalculateCTD(sequence)
+        
+        # Check sequence length before APAAC
+        if len(sequence) > 2:  # APAAC requires a longer sequence
+            pseudo_features = PseudoAAC.GetAPseudoAAC(sequence)
+        else:
+            pseudo_features = {}
 
-    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()
+        all_features = {**auto_features, **ctd_features, **pseudo_features, **dipeptide_features}
+        all_features = list(all_features.values())
+        all_features = np.array(all_features).reshape(-1, 1)  # Correct shape
+        normalized_features = scaler.transform(all_features.T)
+        normalized_features = normalized_features.flatten()
+
+        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
+
+    except Exception as e:
+        print(f"Feature extraction error: {e}")
+        return None  # Return None if extraction fails
 
-    return selected_feature_array