Update app.py

app.py

@@ -1,147 +1,112 @@
 import gradio as gr
 import requests
-import json
+import time
 from inference import DDIPredictor
-import re
 
-# Initialize your trained model from the Hugging Face Hub
+# Initialize predictor with your Hugging Face repository
 try:
-    predictor = DDIPredictor(model_repo="Fredaaaaaa/drug_interaction_severity")
+    predictor = DDIPredictor("Fredaaaaaa/drug_interaction_severity")
+    MODEL_LOADED = True
+    print("✅ Model loaded successfully from Fredaaaaaa/drug_interaction_severity")
 except Exception as e:
-    print(f"Failed to initialize DDIPredictor: {e}")
-    raise
+    print(f"❌ Model loading failed: {e}")
+    MODEL_LOADED = False
 
 def fetch_pubchem_data(drug_name):
-    """Fetch comprehensive drug data from PubChem by name"""
+    """Fetch drug data from PubChem by name"""
     try:
+        if not drug_name or not drug_name.strip():
+            return None, "Please enter a valid drug name"
+        
         # First, search for the compound ID
         search_url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/name/{drug_name}/cids/JSON"
-        search_response = requests.get(search_url, timeout=10)
+        search_response = requests.get(search_url, timeout=15)
         
         if search_response.status_code != 200:
             return None, f"Drug '{drug_name}' not found in PubChem"
         
         cid = search_response.json()['IdentifierList']['CID'][0]
         
-        # Fetch comprehensive compound data
-        properties = [
-            'CanonicalSMILES', 'MolecularWeight', 'XLogP', 'TPSA',
-            'RotatableBondCount', 'HBondDonorCount', 'HBondAcceptorCount',
-            'Complexity', 'Charge', 'ExactMass'
-        ]
-        
+        # Fetch compound data
+        properties = ['CanonicalSMILES', 'MolecularWeight', 'IUPACName', 'XLogP', 'TPSA']
         compound_url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/{cid}/property/{','.join(properties)}/JSON"
-        compound_response = requests.get(compound_url, timeout=10)
+        compound_response = requests.get(compound_url, timeout=15)
         
         if compound_response.status_code != 200:
-            return None, "Failed to fetch compound properties"
+            return None, "Failed to fetch compound data from PubChem"
         
         data = compound_response.json()['PropertyTable']['Properties'][0]
         data['CID'] = cid
         
-        # Get IUPAC name for better identification
-        iupac_url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/{cid}/property/IUPACName/JSON"
-        iupac_response = requests.get(iupac_url, timeout=10)
-        if iupac_response.status_code == 200:
-            data['IUPACName'] = iupac_response.json()['PropertyTable']['Properties'][0]['IUPACName']
-        else:
-            data['IUPACName'] = drug_name
-        
         return data, None
         
     except requests.exceptions.Timeout:
         return None, "PubChem API timeout - please try again"
+    except requests.exceptions.RequestException:
+        return None, "Network error - please check your connection"
     except Exception as e:
         return None, f"Error fetching data: {str(e)}"
 
 def generate_interaction_description(drug1_data, drug2_data):
-    """Generate a clinical-style interaction description based on molecular properties"""
-    descriptions = []
-    
-    # Molecular weight analysis
-    mw1 = drug1_data.get('MolecularWeight', 0)
-    mw2 = drug2_data.get('MolecularWeight', 0)
-    mw_diff = abs(mw1 - mw2)
-    
-    if mw_diff > 500:
-        descriptions.append("Significant molecular size difference may affect metabolic pathways")
-    elif mw_diff > 200:
-        descriptions.append("Moderate molecular size difference could influence distribution")
-    
-    # Lipophilicity analysis (XLogP)
-    logp1 = drug1_data.get('XLogP', 0)
-    logp2 = drug2_data.get('XLogP', 0)
-    logp_diff = abs(logp1 - logp2)
-    
-    if logp_diff > 3:
-        descriptions.append("Differing lipophilicity may affect membrane permeability and clearance rates")
-    elif logp_diff > 1.5:
-        descriptions.append("Variation in lipophilicity could influence tissue distribution")
-    
-    # Polar surface area analysis
-    tpsa1 = drug1_data.get('TPSA', 0)
-    tpsa2 = drug2_data.get('TPSA', 0)
-    tpsa_diff = abs(tpsa1 - tpsa2)
-    
-    if tpsa_diff > 100:
-        descriptions.append("Significant difference in polar surface area suggests varying bioavailability")
-    elif tpsa_diff > 50:
-        descriptions.append("Moderate difference in polar surface area may affect absorption")
-    
-    # Hydrogen bonding analysis
-    h_donor1 = drug1_data.get('HBondDonorCount', 0)
-    h_donor2 = drug2_data.get('HBondDonorCount', 0)
-    h_acceptor1 = drug1_data.get('HBondAcceptorCount', 0)
-    h_acceptor2 = drug2_data.get('HBondAcceptorCount', 0)
-    
-    if abs(h_donor1 - h_donor2) > 3 or abs(h_acceptor1 - h_acceptor2) > 5:
-        descriptions.append("Differing hydrogen bonding capacity may affect protein binding and metabolism")
-    
-    # Rotatable bonds analysis
-    rotatable1 = drug1_data.get('RotatableBondCount', 0)
-    rotatable2 = drug2_data.get('RotatableBondCount', 0)
-    
-    if abs(rotatable1 - rotatable2) > 8:
-        descriptions.append("Significant difference in molecular flexibility may influence receptor binding")
-    
-    # Default description if no specific features stand out
-    if not descriptions:
-        descriptions.append("Potential pharmacokinetic interaction based on molecular properties - clinical evaluation recommended")
-    
-    return ". ".join(descriptions) + "."
+    """Generate clinical interaction description based on molecular properties"""
+    try:
+        descriptions = []
+        
+        # Molecular weight analysis
+        mw1 = drug1_data.get('MolecularWeight', 0)
+        mw2 = drug2_data.get('MolecularWeight', 0)
+        if mw1 and mw2:
+            mw_diff = abs(mw1 - mw2)
+            if mw_diff > 300:
+                descriptions.append("Significant molecular size difference may affect metabolic pathways")
+        
+        # Lipophilicity analysis
+        logp1 = drug1_data.get('XLogP', 0)
+        logp2 = drug2_data.get('XLogP', 0)
+        if logp1 is not None and logp2 is not None:
+            logp_diff = abs(logp1 - logp2)
+            if logp_diff > 2:
+                descriptions.append("Differing lipophilicity may affect membrane permeability")
+        
+        # Polar surface area analysis
+        tpsa1 = drug1_data.get('TPSA', 0)
+        tpsa2 = drug2_data.get('TPSA', 0)
+        if tpsa1 and tpsa2:
+            tpsa_diff = abs(tpsa1 - tpsa2)
+            if tpsa_diff > 80:
+                descriptions.append("Varying polar surface areas suggest different absorption characteristics")
+        
+        if not descriptions:
+            descriptions.append("Potential pharmacokinetic interaction based on molecular properties")
+        
+        return ". ".join(descriptions) + ". Clinical evaluation recommended."
+        
+    except Exception:
+        return "Potential drug interaction requiring clinical assessment."
 
 def check_drugbank_interaction(drug1_name, drug2_name):
-    """Mock function to simulate DrugBank interaction check"""
-    # Convert to lowercase for case-insensitive matching
+    """Mock function for DrugBank interaction check"""
     drug1_clean = drug1_name.lower().strip()
     drug2_clean = drug2_name.lower().strip()
     
-    # Expanded mock database of known interactions
     known_interactions = {
         ('warfarin', 'aspirin'): 'Severe: Increased risk of bleeding and hemorrhage',
         ('warfarin', 'ibuprofen'): 'Moderate: Increased risk of gastrointestinal bleeding',
-        ('warfarin', 'simvastatin'): 'Moderate: Increased anticoagulant effect',
         ('simvastatin', 'clarithromycin'): 'Severe: Increased risk of myopathy and rhabdomyolysis',
-        ('simvastatin', 'itraconazole'): 'Severe: Increased statin levels and toxicity risk',
         ('digoxin', 'quinine'): 'Moderate: Increased digoxin levels, risk of toxicity',
-        ('digoxin', 'verapamil'): 'Moderate: Increased digoxin concentrations',
-        ('lisinopril', 'ibuprofen'): 'Moderate: Reduced antihypertensive effect',
-        ('metformin', 'contrast'): 'Severe: Risk of lactic acidosis with contrast media',
-        ('phenytoin', 'warfarin'): 'Moderate: Altered anticoagulant effect',
     }
     
-    # Check both orders of drug names
     interaction = (known_interactions.get((drug1_clean, drug2_clean)) or 
                    known_interactions.get((drug2_clean, drug1_clean)))
     
-    if interaction:
-        return interaction
-    else:
-        return "No known severe interaction in database (mock data)"
+    return interaction or "No known severe interaction in mock database"
 
 def predict_ddi(drug1_name, drug2_name):
     """Main prediction function"""
     try:
+        if not MODEL_LOADED:
+            return "Model not loaded properly. Please check the deployment.", "", "", "", ""
+        
         if not drug1_name or not drug2_name:
             return "Please enter both drug names", "", "", "", ""
         
@@ -157,50 +122,41 @@ def predict_ddi(drug1_name, drug2_name):
         # Generate interaction description
         interaction_description = generate_interaction_description(drug1_data, drug2_data)
         
-        # Make prediction
+        # Make prediction using your hosted model
         result = predictor.predict(interaction_description)
         
         # Check DrugBank (mock)
         drugbank_result = check_drugbank_interaction(drug1_name, drug2_name)
         
-        # Prepare detailed output
+        # Prepare output
         drug1_info = f"""
         **{drug1_name}** (PubChem CID: {drug1_data.get('CID', 'N/A')})
         - **IUPAC Name:** {drug1_data.get('IUPACName', 'N/A')}
-        - **SMILES:** {drug1_data.get('CanonicalSMILES', 'N/A')}
         - **Molecular Weight:** {drug1_data.get('MolecularWeight', 'N/A')} g/mol
-        - **LogP (XLogP):** {drug1_data.get('XLogP', 'N/A')}
+        - **LogP:** {drug1_data.get('XLogP', 'N/A')}
         - **TPSA:** {drug1_data.get('TPSA', 'N/A')} Ų
-        - **H-Bond Donors:** {drug1_data.get('HBondDonorCount', 'N/A')}
-        - **H-Bond Acceptors:** {drug1_data.get('HBondAcceptorCount', 'N/A')}
-        - **Rotatable Bonds:** {drug1_data.get('RotatableBondCount', 'N/A')}
-        - **Complexity:** {drug1_data.get('Complexity', 'N/A')}
+        - **SMILES:** {drug1_data.get('CanonicalSMILES', 'N/A')}
         """
         
         drug2_info = f"""
         **{drug2_name}** (PubChem CID: {drug2_data.get('CID', 'N/A')})
         - **IUPAC Name:** {drug2_data.get('IUPACName', 'N/A')}
-        - **SMILES:** {drug2_data.get('CanonicalSMILES', 'N/A')}
         - **Molecular Weight:** {drug2_data.get('MolecularWeight', 'N/A')} g/mol
-        - **LogP (XLogP):** {drug2_data.get('XLogP', 'N/A')}
+        - **LogP:** {drug2_data.get('XLogP', 'N/A')}
         - **TPSA:** {drug2_data.get('TPSA', 'N/A')} Ų
-        - **H-Bond Donors:** {drug2_data.get('HBondDonorCount', 'N/A')}
-        - **H-Bond Acceptors:** {drug2_data.get('HBondAcceptorCount', 'N/A')}
-        - **Rotatable Bonds:** {drug2_data.get('RotatableBondCount', 'N/A')}
-        - **Complexity:** {drug2_data.get('Complexity', 'N/A')}
+        - **SMILES:** {drug2_data.get('CanonicalSMILES', 'N/A')}
         """
         
         prediction_output = f"""
         ## 🔍 AI Prediction Results
         
-        **Generated Interaction Description:**
-        *"{interaction_description}"*
+        **Model Source:** Fredaaaaaa/drug_interaction_severity
+        **Generated Description:** {interaction_description}
         
-        **Prediction:**
-        - **Severity:** **{result['prediction']}**
-        - **Confidence:** {result['confidence']:.1%}
+        **Prediction:** **{result['prediction']}**
+        **Confidence:** {result['confidence']:.1%}
         
-        **Probability Distribution:**
+        **Probabilities:**
         {', '.join([f'{k}: {v:.1%}' for k, v in result['probabilities'].items()])}
         """
         
@@ -211,54 +167,40 @@ def predict_ddi(drug1_name, drug2_name):
 
 # Create Gradio interface
 with gr.Blocks(title="Drug Interaction Severity Predictor", theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🧪 Drug Interaction Severity Predictor")
-    gr.Markdown("Predict potential drug-drug interaction severity using molecular properties from PubChem and AI")
+    gr.Markdown("# 💊 Drug Interaction Severity Predictor")
+    gr.Markdown("Powered by AI model from: [Fredaaaaaa/drug_interaction_severity](https://huggingface.co/Fredaaaaaa/drug_interaction_severity)")
     
     with gr.Row():
-        with gr.Column(scale=1):
-            gr.Markdown("## 💊 Input Drug Names")
-            drug1 = gr.Textbox(label="First Drug Name", placeholder="e.g., Warfarin, Aspirin, Simvastatin...")
-            drug2 = gr.Textbox(label="Second Drug Name", placeholder="e.g., Ibuprofen, Clarithromycin, Digoxin...")
-            predict_btn = gr.Button("🔬 Predict Interaction", variant="primary", size="lg")
-            
-            gr.Markdown("### 💡 Example Pairs")
-            gr.Examples(
-                examples=[
-                    ["Warfarin", "Aspirin"],
-                    ["Simvastatin", "Clarithromycin"],
-                    ["Digoxin", "Quinine"],
-                    ["Lisinopril", "Ibuprofen"]
-                ],
-                inputs=[drug1, drug2],
-                label="Try these examples:"
-            )
+        drug1 = gr.Textbox(label="First Drug Name", placeholder="e.g., Warfarin, Aspirin...")
+        drug2 = gr.Textbox(label="Second Drug Name", placeholder="e.g., Ibuprofen, Clarithromycin...")
+    
+    predict_btn = gr.Button("🔬 Predict Interaction", variant="primary")
     
     with gr.Row():
-        with gr.Column(scale=2):
-            gr.Markdown("## 📊 Prediction Results")
-            prediction_output = gr.Markdown(label="AI Prediction")
-            
-        with gr.Column(scale=1):
-            gr.Markdown("## 🏥 DrugBank Check")
-            drugbank_result = gr.Textbox(label="Known Interaction (Mock Data)", interactive=False)
+        prediction_output = gr.Markdown("## 📊 Prediction Results will appear here")
     
     with gr.Row():
         with gr.Column():
-            gr.Markdown("## 🔍 Molecular Properties")
-            with gr.Tab("Drug 1 Properties"):
-                drug1_info = gr.Markdown()
-            with gr.Tab("Drug 2 Properties"):
-                drug2_info = gr.Markdown()
+            drug1_info = gr.Markdown("### 💊 Drug 1 Properties")
+        with gr.Column():
+            drug2_info = gr.Markdown("### 💊 Drug 2 Properties")
     
     with gr.Row():
-        gr.Markdown("## 📝 Generated Description")
-        interaction_description = gr.Textbox(label="AI-Generated Interaction Description", interactive=False, lines=3)
+        drugbank_info = gr.Textbox(label="🏥 DrugBank Comparison (Mock Data)")
+        interaction_desc = gr.Textbox(label="📝 AI-Generated Description")
     
-    predict_btn.click(
-        fn=predict_ddi,
+    # Examples
+    gr.Examples(
+        examples=[["Warfarin", "Aspirin"], ["Simvastatin", "Clarithromycin"]],
         inputs=[drug1, drug2],
-        outputs=[prediction_output, drug1_info, drug2_info, drugbank_result, interaction_description]
+        label="💡 Try these examples:"
+    )
+    
+    predict_btn.click(
+        predict_ddi,
+        [drug1, drug2],
+        [prediction_output, drug1_info, drug2_info, drugbank_info, interaction_desc]
     )
 
 if __name__ == "__main__":
-    demo.launch(share=True)
+    demo.launch()