Upload 4 files

app.py

@@ -11,6 +11,7 @@ def run_diffdock_inference(protein_pdb_content, ligand_smiles_string):
     """
     Performs molecular docking analysis using RDKit for binding affinity estimation.
     This is a lightweight alternative to full DiffDock that works on free CPU tier.
+    Generates PDBQT format for compatibility with AutoDock Vina.
     Returns a JSON-serializable dictionary.
     """
     try:
@@ -23,7 +24,7 @@ def run_diffdock_inference(protein_pdb_content, ligand_smiles_string):
         
         # Import RDKit for molecular analysis
         from rdkit import Chem
-        from rdkit.Chem import Descriptors, Lipinski
+        from rdkit.Chem import Descriptors, Lipinski, AllChem
         
         # Parse SMILES string
         mol = Chem.MolFromSmiles(ligand_smiles_string)
@@ -78,6 +79,31 @@ def run_diffdock_inference(protein_pdb_content, ligand_smiles_string):
         # Clamp score between 0 and 1
         confidence_score = max(0.0, min(1.0, confidence_score))
         
+        # Generate 3D structure and PDBQT format for Vina compatibility
+        ligand_pdbqt = None
+        try:
+            # Add hydrogens and generate 3D coordinates
+            mol_3d = Chem.AddHs(mol)
+            AllChem.EmbedMolecule(mol_3d, randomSeed=42)
+            AllChem.MMFFOptimizeMolecule(mol_3d)
+            
+            # Convert to PDB format first
+            pdb_block = Chem.MolToPDBBlock(mol_3d)
+            
+            # Simple PDBQT conversion (add charges and atom types)
+            # This is a simplified version - full PDBQT requires proper charge calculation
+            pdbqt_lines = []
+            for line in pdb_block.split('\n'):
+                if line.startswith('HETATM') or line.startswith('ATOM'):
+                    # Add Gasteiger charges (simplified - just use 0.0 for now)
+                    pdbqt_line = line[:66] + "  0.00  0.00    0.000 " + line[77:78]
+                    pdbqt_lines.append(pdbqt_line)
+            
+            ligand_pdbqt = '\n'.join(pdbqt_lines) if pdbqt_lines else None
+        except Exception as pdbqt_error:
+            # If PDBQT generation fails, continue without it
+            ligand_pdbqt = None
+        
         # Build result with explicit JSON-serializable types
         result = {
             "success": True,
@@ -92,7 +118,8 @@ def run_diffdock_inference(protein_pdb_content, ligand_smiles_string):
                 "rotatable_bonds": int(rotatable_bonds),
                 "lipinski_compliant": bool(lipinski_pass)
             },
-            "note": str("RDKit-based drug-likeness scoring (lightweight alternative to DiffDock)")
+            "ligand_pdbqt": ligand_pdbqt,
+            "note": str("RDKit-based drug-likeness scoring with PDBQT generation")
         }
         
         # Return dict directly - Gradio will handle JSON serialization