Update app.py

app.py

@@ -75,18 +75,6 @@ def extract_features(sequence):
     selected_df = normalized_df[selected_features].fillna(0)
     return selected_df.values
 
-# AMP Classifier
-def predict(sequence):
-    features = extract_features(sequence)
-    if isinstance(features, str):
-        return features
-    prediction = model.predict(features)[0]
-    probabilities = model.predict_proba(features)[0]
-    if prediction == 0:
-        return f"{probabilities[0] * 100:.2f}% chance of being an Antimicrobial Peptide (AMP)"
-    else:
-        return f"{probabilities[1] * 100:.2f}% chance of being Non-AMP"
-
 # MIC Predictor
 def predictmic(sequence):
     sequence = ''.join([aa for aa in sequence.upper() if aa in "ACDEFGHIKLMNPQRSTVWY"])
@@ -99,37 +87,17 @@ def predictmic(sequence):
         outputs = protbert_model(**tokens)
         embedding = outputs.last_hidden_state.mean(dim=1).squeeze().cpu().numpy().reshape(1, -1)
     bacteria_config = {
-        "E.coli": {
-            "model": "coli_xgboost_model.pkl",
-            "scaler": "coli_scaler.pkl",
-            "pca": None
-        },
-        "S.aureus": {
-            "model": "aur_xgboost_model.pkl",
-            "scaler": "aur_scaler.pkl",
-            "pca": None
-        },
-        "P.aeruginosa": {
-            "model": "arg_xgboost_model.pkl",
-            "scaler": "arg_scaler.pkl",
-            "pca": None
-        },
-        "K.Pneumonia": {
-            "model": "pne_mlp_model.pkl",
-            "scaler": "pne_scaler.pkl",
-            "pca": "pne_pca.pkl"
-        }
+        "E.coli": {"model": "coli_xgboost_model.pkl", "scaler": "coli_scaler.pkl", "pca": None},
+        "S.aureus": {"model": "aur_xgboost_model.pkl", "scaler": "aur_scaler.pkl", "pca": None},
+        "P.aeruginosa": {"model": "arg_xgboost_model.pkl", "scaler": "arg_scaler.pkl", "pca": None},
+        "K.Pneumonia": {"model": "pne_mlp_model.pkl", "scaler": "pne_scaler.pkl", "pca": "pne_pca.pkl"}
     }
     mic_results = {}
     for bacterium, cfg in bacteria_config.items():
         try:
             scaler = joblib.load(cfg["scaler"])
             scaled = scaler.transform(embedding)
-            if cfg["pca"]:
-                pca = joblib.load(cfg["pca"])
-                transformed = pca.transform(scaled)
-            else:
-                transformed = scaled
+            transformed = joblib.load(cfg["pca"]).transform(scaled) if cfg["pca"] else scaled
             model = joblib.load(cfg["model"])
             mic_log = model.predict(transformed)[0]
             mic = round(expm1(mic_log), 3)
@@ -138,29 +106,29 @@ def predictmic(sequence):
             mic_results[bacterium] = f"Error: {str(e)}"
     return mic_results
 
-# Combined Prediction
+# Combined Output as Single String
 def full_prediction(sequence):
     features = extract_features(sequence)
     if isinstance(features, str):
-        return "Error", "0%", {}
+        return features
     prediction = model.predict(features)[0]
     probabilities = model.predict_proba(features)[0]
     amp_result = "Antimicrobial Peptide (AMP)" if prediction == 0 else "Non-AMP"
     confidence = round(probabilities[0 if prediction == 0 else 1] * 100, 2)
     mic_values = predictmic(sequence)
-    return amp_result, f"{confidence}%", mic_values
+    result = f"Prediction: {amp_result}\nConfidence: {confidence}%\n\nPredicted MIC Values (µM):\n"
+    for organism, mic in mic_values.items():
+        result += f"- {organism}: {mic}\n"
+    return result
 
-# Gradio Interface
+# Gradio Interface (Single Label Output)
 iface = gr.Interface(
     fn=full_prediction,
     inputs=gr.Textbox(label="Enter Protein Sequence"),
-    outputs=[
-        gr.Label(label="AMP Classification"),
-        gr.Label(label="Confidence"),
-        gr.JSON(label="Predicted MIC (µM) for Each Bacterium")
-    ],
+    outputs=gr.Textbox(label="AMP & MIC Prediction Summary"),
     title="AMP & MIC Predictor",
     description="Enter an amino acid sequence (≥10 valid letters) to predict AMP class and MIC values."
 )
 
 iface.launch(share=True)
+