Create app.py

app.py

@@ -0,0 +1,69 @@
+import gradio as gr
+from rdkit import Chem
+from rdkit.Chem import Draw, Descriptors, AllChem
+from rdkit.DataStructs.cDataStructs import ConvertToNumpyArray
+import numpy as np
+import xgboost as xgb
+from PIL import Image
+
+
+# Load the XGBoost model
+model = xgb.XGBClassifier()
+model.load_model("xg3.json")
+
+# Function to convert SMILES string to descriptors and Lipinski features
+def predict_smiles(smiles):
+    mol = Chem.MolFromSmiles(smiles)
+    if mol is None:  # Check if the conversion was unsuccessful
+        return None, "Invalid SMILES string. Please enter a valid SMILES."
+
+    fp = AllChem.GetMorganFingerprintAsBitVect(mol, radius=2, nBits=2048)
+    fp_array = np.zeros((1,), dtype=int)
+    ConvertToNumpyArray(fp, fp_array)
+    lipinski_features = np.array([[Descriptors.MolWt(mol), Descriptors.MolLogP(mol), Descriptors.NumHAcceptors(mol), Descriptors.NumHDonors(mol)]])
+    
+    # Combine fingerprint and Lipinski features
+    features = np.concatenate([fp_array, lipinski_features.flatten()])
+    return features, lipinski_features
+
+# Updated function to predict from SMILES and visualize Lipinski's features
+def predict_and_visualize(smiles):
+    features, lipinski_features = predict_smiles(smiles)
+    if features is None:
+        # Return a clear message for invalid SMILES, a placeholder for the features, and None for the image
+        error_message = "Invalid SMILES string. Please enter a valid SMILES."
+        placeholder_features = "<b><u>RDKit estimates</u></b><br>Not applicable due to invalid SMILES input."
+        return error_message, placeholder_features, None
+    
+    # Process valid SMILES 
+    molecular_weight, alogp, hba, hbd = lipinski_features.flatten()
+    molecular_weight = round(molecular_weight, 1)
+    alogp = round(alogp, 1)
+    hba = int(hba)
+    hbd = int(hbd)
+
+    lipinski_features = np.array([[molecular_weight, alogp, hba, hbd]])
+
+    prediction = model.predict(features.reshape(1, -1))
+    result = "drug-like" if prediction == 1 else "not drug-like"
+    
+    mol = Chem.MolFromSmiles(smiles)
+    img = Draw.MolToImage(mol)
+    img = img.resize((800, 800), Image.Resampling.LANCZOS)  
+
+    features_names = ["Molecular Weight", "AlogP", "HBA", "HBD"]
+    lipinski_str = "<b><u>RDKit estimates</u></b><br>" + "<br>".join([f"{name}: {value}" for name, value in zip(features_names, [molecular_weight, alogp, hba, hbd])])
+    
+    return result, lipinski_str, img
+
+# Gradio interface
+iface = gr.Interface(fn=predict_and_visualize,
+                     inputs=gr.Textbox(lines=2, placeholder="Enter SMILES string here..."),
+                     outputs=[gr.Text(label="Prediction"),
+                              gr.HTML(label="Lipinski's Features"),
+                              gr.Image(label="Molecule Visualization")],
+                     title="XGBoost Drug-like Classifier",
+                     description="This application predicts whether a molecule is drug-like based on its SMILES representation.")
+
+if __name__ == "__main__":
+    iface.launch()