Update app.py

app.py

@@ -5,12 +5,10 @@ import pandas as pd
 from propy import AAComposition
 from sklearn.preprocessing import MinMaxScaler
 
-# Load trained SVM model and scaler (Ensure both files exist in the Space)
 model = joblib.load("SVM.joblib")
 scaler = joblib.load("norm.joblib")
 
 
-# List of features used in your model
 selected_features = [
     "A", "R", "N", "D", "C", "E", "Q", "G", "H", "I", "L", "K", "M", "F", "P", "S", "T", "W", "Y", "V",
     "AA", "AR", "AN", "AD", "AC", "AE", "AQ", "AG", "AI", "AL", "AK", "AF", "AP", "AS", "AT", "AY", "AV",
@@ -37,27 +35,19 @@ selected_features = [
 
 def extract_features(sequence):
     """Extract only the required features and normalize them."""
-    # Compute all possible features
-    all_features = AAComposition.CalculateAADipeptideComposition(sequence)  # Amino Acid Composition
-    # Extract the values from the dictionary
-    feature_values = list(all_features.values())  # Extract values only
-    # Convert to NumPy array for normalization
+    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]
-    # Min-Max Normalization
     normalized_features = scaler.transform(feature_array.T)
 
-    # Reshape normalized_features back to a single dimension
-    normalized_features = normalized_features.flatten()  # Flatten array
+    normalized_features = normalized_features.flatten()  
 
-    # Create a dictionary with selected features
     selected_feature_dict = {feature: normalized_features[i] for i, feature in enumerate(selected_features)
                                if feature in all_features}
 
-    # Convert dictionary to dataframe
     selected_feature_df = pd.DataFrame([selected_feature_dict])
 
-    # Convert dataframe to numpy array
     selected_feature_array = selected_feature_df.T.to_numpy()
 
     return selected_feature_array
@@ -68,11 +58,18 @@ def predict(sequence):
     """Predict AMP vs Non-AMP"""
     features = extract_features(sequence)
     prediction = model.predict(features.T)[0]
-    probabilities = model.predict_proba(features.T)
+    probability_amp = model.predict_proba(features.T)
+    
+    if prediction == 0:
+        prediction_label = "Potential Bioactive Peptide with Antimicrobial Properties (P-AMP)"
+        probability_amp = probabilities[0] 
+    else:
+        prediction_label = "Likely Non-Antimicrobial Peptide"
+        probability_amp = probabilities[0]
+
+    return prediction_label, probability_amp 
 
-    return "Potential Bioactive Peptide with Antimicrobial Properties (P-AMP)" if prediction == 0 else "Likely Non-Antimicrobial Peptide", probabilities[0]
 
-# Create Gradio interface
 iface = gr.Interface(
     fn=predict,
     inputs=gr.Textbox(label="Enter Protein Sequence"),
@@ -81,5 +78,4 @@ iface = gr.Interface(
     description="Enter an amino acid sequence to predict whether it's an antimicrobial peptide (AMP) or not."
 )
 
-# Launch app
 iface.launch(share=True)