Update app.py

app.py

@@ -5,10 +5,11 @@ import pandas as pd
 from propy import AAComposition
 from sklearn.preprocessing import MinMaxScaler
 
+# Load trained model and scaler
 model = joblib.load("SVM.joblib")
 scaler = joblib.load("norm.joblib")
 
-
+# Selected features used in training
 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",
@@ -34,34 +35,33 @@ selected_features = [
 ]
 
 def extract_features(sequence):
-    """Extract only the required features and normalize them."""
+    """Extract selected features and normalize them."""
     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]
+    feature_array = feature_array[: 420]  # Ensure we only use 420 features
     normalized_features = scaler.transform(feature_array.T)
-
     normalized_features = normalized_features.flatten()  
 
+    # Select features that match training data
     selected_feature_dict = {feature: normalized_features[i] for i, feature in enumerate(selected_features)
-                               if feature in all_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
 
-
-
 def predict(sequence):
-    """Predict AMP vs Non-AMP"""
+    """Predict if the sequence is an AMP or not."""
     features = extract_features(sequence)
     prediction = model.predict(features.T)[0]
-    
-    return "Potential Bioactive Peptide with Antimicrobial Properties (P-AMP)" if prediction == 0 else "Likely Non-Antimicrobial Peptide"
+    probabilities = model.predict_proba(features.T)[0]  
+    prob_amp = probabilities[0]  
+    prob_non_amp = probabilities[1]  
 
+    return f"⚡ {prob_amp * 100:.2f}% chance of being an Antimicrobial Peptide (AMP)" if prediction == 0 else f"❌ {prob_non_amp * 100:.2f}% chance of being Non-AMP"
 
+# Gradio interface
 iface = gr.Interface(
     fn=predict,
     inputs=gr.Textbox(label="Enter Protein Sequence"),
@@ -70,4 +70,4 @@ iface = gr.Interface(
     description="Enter an amino acid sequence to predict whether it's an antimicrobial peptide (AMP) or not."
 )
 
-iface.launch(share=True)
+iface.launch(share=True)