Update app.py

app.py

@@ -6,55 +6,32 @@ from propy import AAComposition, Autocorrelation, CTD, PseudoAAC
 from sklearn.preprocessing import MinMaxScaler
 import torch
 from transformers import BertTokenizer, BertModel
+from lime.lime_tabular import LimeTabularExplainer
 from math import expm1
 
 # Load AMP Classifier
 model = joblib.load("RF.joblib")
 scaler = joblib.load("norm (4).joblib")
 
-# Load ProtBert Globally
+# Load ProtBert
 tokenizer = BertTokenizer.from_pretrained("Rostlab/prot_bert", do_lower_case=False)
 protbert_model = BertModel.from_pretrained("Rostlab/prot_bert")
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 protbert_model = protbert_model.to(device).eval()
 
 # Selected Features
-selected_features = [
-    "_SolventAccessibilityC3", "_SecondaryStrC1", "_SecondaryStrC3", "_ChargeC1", "_PolarityC1",
-    "_NormalizedVDWVC1", "_HydrophobicityC3", "_SecondaryStrT23", "_PolarizabilityD1001",
-    "_PolarizabilityD2001", "_PolarizabilityD3001", "_SolventAccessibilityD1001",
-    "_SolventAccessibilityD2001", "_SolventAccessibilityD3001", "_SecondaryStrD1001",
-    "_SecondaryStrD1075", "_SecondaryStrD2001", "_SecondaryStrD3001", "_ChargeD1001",
-    "_ChargeD1025", "_ChargeD2001", "_ChargeD3075", "_ChargeD3100", "_PolarityD1001",
-    "_PolarityD1050", "_PolarityD2001", "_PolarityD3001", "_NormalizedVDWVD1001",
-    "_NormalizedVDWVD2001", "_NormalizedVDWVD2025", "_NormalizedVDWVD2050", "_NormalizedVDWVD3001",
-    "_HydrophobicityD1001", "_HydrophobicityD2001", "_HydrophobicityD3001", "_HydrophobicityD3025",
-    "A", "R", "D", "C", "E", "Q", "H", "I", "M", "P", "Y", "V",
-    "AR", "AV", "RC", "RL", "RV", "CR", "CC", "CL", "CK", "EE", "EI", "EL",
-    "HC", "IA", "IL", "IV", "LA", "LC", "LE", "LI", "LT", "LV", "KC", "MA",
-    "MS", "SC", "TC", "TV", "YC", "VC", "VE", "VL", "VK", "VV",
-    "MoreauBrotoAuto_FreeEnergy30", "MoranAuto_Hydrophobicity2", "MoranAuto_Hydrophobicity4",
-    "GearyAuto_Hydrophobicity20", "GearyAuto_Hydrophobicity24", "GearyAuto_Hydrophobicity26",
-    "GearyAuto_Hydrophobicity27", "GearyAuto_Hydrophobicity28", "GearyAuto_Hydrophobicity29",
-    "GearyAuto_Hydrophobicity30", "GearyAuto_AvFlexibility22", "GearyAuto_AvFlexibility26",
-    "GearyAuto_AvFlexibility27", "GearyAuto_AvFlexibility28", "GearyAuto_AvFlexibility29",
-    "GearyAuto_AvFlexibility30", "GearyAuto_Polarizability22", "GearyAuto_Polarizability24",
-    "GearyAuto_Polarizability25", "GearyAuto_Polarizability27", "GearyAuto_Polarizability28",
-    "GearyAuto_Polarizability29", "GearyAuto_Polarizability30", "GearyAuto_FreeEnergy24",
-    "GearyAuto_FreeEnergy25", "GearyAuto_FreeEnergy30", "GearyAuto_ResidueASA21",
-    "GearyAuto_ResidueASA22", "GearyAuto_ResidueASA23", "GearyAuto_ResidueASA24",
-    "GearyAuto_ResidueASA30", "GearyAuto_ResidueVol21", "GearyAuto_ResidueVol24",
-    "GearyAuto_ResidueVol25", "GearyAuto_ResidueVol26", "GearyAuto_ResidueVol28",
-    "GearyAuto_ResidueVol29", "GearyAuto_ResidueVol30", "GearyAuto_Steric18",
-    "GearyAuto_Steric21", "GearyAuto_Steric26", "GearyAuto_Steric27", "GearyAuto_Steric28",
-    "GearyAuto_Steric29", "GearyAuto_Steric30", "GearyAuto_Mutability23", "GearyAuto_Mutability25",
-    "GearyAuto_Mutability26", "GearyAuto_Mutability27", "GearyAuto_Mutability28",
-    "GearyAuto_Mutability29", "GearyAuto_Mutability30", "APAAC1", "APAAC4", "APAAC5",
-    "APAAC6", "APAAC8", "APAAC9", "APAAC12", "APAAC13", "APAAC15", "APAAC18", "APAAC19",
-    "APAAC24"
-]
+selected_features = [ ... ]  # keep your full selected_features list here
 
-# AMP Feature Extractor
+# LIME Explainer Setup
+sample_data = np.random.rand(100, len(selected_features))
+explainer = LimeTabularExplainer(
+    training_data=sample_data,
+    feature_names=selected_features,
+    class_names=["AMP", "Non-AMP"],
+    mode="classification"
+)
+
+# Feature Extractor
 def extract_features(sequence):
     all_features_dict = {}
     sequence = ''.join([aa for aa in sequence.upper() if aa in "ACDEFGHIKLMNPQRSTVWY"])
@@ -79,7 +56,7 @@ def extract_features(sequence):
 def predictmic(sequence):
     sequence = ''.join([aa for aa in sequence.upper() if aa in "ACDEFGHIKLMNPQRSTVWY"])
     if len(sequence) < 10:
-        return {"Error": "Sequence too short or invalid. Must contain at least 10 valid amino acids."}
+        return {"Error": "Sequence too short or invalid."}
     seq_spaced = ' '.join(list(sequence))
     tokens = tokenizer(seq_spaced, return_tensors="pt", padding='max_length', truncation=True, max_length=512)
     tokens = {k: v.to(device) for k, v in tokens.items()}
@@ -106,37 +83,46 @@ def predictmic(sequence):
             mic_results[bacterium] = f"Error: {str(e)}"
     return mic_results
 
-# Combined Output as Single String
+# Full Prediction with LIME Explanation
 def full_prediction(sequence):
     features = extract_features(sequence)
-    if isinstance(features, str):  # error message returned
+    if isinstance(features, str):  # error
         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)
     
     result = f"Prediction: {amp_result}\nConfidence: {confidence}%\n"
-    
-    if prediction == 0:  # only predict MIC if AMP
+
+    if prediction == 0:
         mic_values = predictmic(sequence)
         result += "\nPredicted MIC Values (µM):\n"
-        for organism, mic in mic_values.items():
-            result += f"- {organism}: {mic}\n"
+        for org, mic in mic_values.items():
+            result += f"- {org}: {mic}\n"
     else:
-        result += "\nMIC prediction is not available because sequence is Non-AMP."
+        result += "\nMIC prediction skipped for Non-AMP sequences.\n"
     
-    return result
+    # LIME explanation
+    explanation = explainer.explain_instance(
+        data_row=features[0],
+        predict_fn=model.predict_proba,
+        num_features=10
+    )
+    result += "\nTop Features Influencing AMP Prediction:\n"
+    for feat, weight in explanation.as_list():
+        result += f"- {feat}: {round(weight, 4)}\n"
 
+    return result
 
-# Gradio Interface (Single Label Output)
+# Gradio UI
 iface = gr.Interface(
     fn=full_prediction,
     inputs=gr.Textbox(label="Enter Protein Sequence"),
-    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."
+    outputs=gr.Textbox(label="Prediction + MIC + LIME"),
+    title="AMP & MIC Predictor + LIME Explanation",
+    description="Paste an amino acid sequence (≥10 characters). Get AMP classification, MIC predictions, and LIME interpretability insights."
 )
 
 iface.launch(share=True)
-