Spaces:
Paused
Paused
| """ | |
| ADMET & In Silico Drug-Likeness Profiling Engine. | |
| Computes physicochemical descriptors, Lipinski Rule of 5, Veber, Ghose, Egan, | |
| QED, PAINS filter alerts, Brenk toxicophores, and Bioavailability Radar coordinates. | |
| """ | |
| from typing import Dict, Any, List, Tuple, Optional | |
| import numpy as np | |
| from rdkit import Chem | |
| from rdkit.Chem import Descriptors, Lipinski, Crippen, QED | |
| from rdkit.Chem.FilterCatalog import FilterCatalog, FilterCatalogParams | |
| # Initialize FilterCatalogs for PAINS and BRENK structural alerts | |
| _pains_params = FilterCatalogParams() | |
| _pains_params.AddCatalog(FilterCatalogParams.FilterCatalogs.PAINS) | |
| PAINS_CATALOG = FilterCatalog(_pains_params) | |
| _brenk_params = FilterCatalogParams() | |
| _brenk_params.AddCatalog(FilterCatalogParams.FilterCatalogs.BRENK) | |
| BRENK_CATALOG = FilterCatalog(_brenk_params) | |
| def compute_admet_profile(mol_or_smiles: Any) -> Dict[str, Any]: | |
| """ | |
| Compute comprehensive in silico ADMET and drug-likeness profile. | |
| Args: | |
| mol_or_smiles: RDKit Mol object or SMILES string. | |
| Returns: | |
| Dictionary containing descriptors, rule evaluations, alerts, and scores. | |
| """ | |
| if isinstance(mol_or_smiles, str): | |
| mol = Chem.MolFromSmiles(mol_or_smiles) | |
| else: | |
| mol = mol_or_smiles | |
| if mol is None: | |
| raise ValueError("Invalid molecule provided for ADMET calculation.") | |
| # 1. Fundamental Physicochemical Descriptors | |
| mw = float(Descriptors.MolWt(mol)) | |
| logp = float(Crippen.MolLogP(mol)) | |
| tpsa = float(Descriptors.TPSA(mol)) | |
| hbd = int(Lipinski.NumHDonors(mol)) | |
| hba = int(Lipinski.NumHAcceptors(mol)) | |
| rot_bonds = int(Lipinski.NumRotatableBonds(mol)) | |
| heavy_atoms = int(mol.GetNumHeavyAtoms()) | |
| aromatic_rings = int(Lipinski.NumAromaticRings(mol)) | |
| fraction_csp3 = float(Descriptors.FractionCSP3(mol)) | |
| molar_refractivity = float(Crippen.MolMR(mol)) | |
| qed_score = float(QED.qed(mol)) | |
| # Synthetic Accessibility Approximation (heuristic based on complexity, rings, chiral centers) | |
| num_chiral = len(Chem.FindMolChiralCenters(mol, includeUnassigned=True)) | |
| num_rings = Descriptors.RingCount(mol) | |
| bertz = Descriptors.BertzCT(mol) | |
| # Normalized complexity heuristic between 1.0 (very easy) and 10.0 (very hard) | |
| sascore_est = min(10.0, max(1.0, 1.0 + (bertz / 250.0) + (num_chiral * 0.4) + (max(0, num_rings - 2) * 0.5))) | |
| # 2. Rule of 5 (Lipinski) | |
| lipinski_violations = [] | |
| if mw > 500: | |
| lipinski_violations.append(f"MW > 500 ({mw:.1f} Da)") | |
| if logp > 5.0: | |
| lipinski_violations.append(f"LogP > 5.0 ({logp:.2f})") | |
| if hbd > 5: | |
| lipinski_violations.append(f"HBD > 5 ({hbd})") | |
| if hba > 10: | |
| lipinski_violations.append(f"HBA > 10 ({hba})") | |
| lipinski_pass = len(lipinski_violations) <= 1 | |
| # 3. Veber Rule (Oral Bioavailability) | |
| veber_violations = [] | |
| if rot_bonds > 10: | |
| veber_violations.append(f"Rotatable Bonds > 10 ({rot_bonds})") | |
| if tpsa > 140.0: | |
| veber_violations.append(f"TPSA > 140 Ų ({tpsa:.1f})") | |
| veber_pass = len(veber_violations) == 0 | |
| # 4. Ghose Filter | |
| ghose_violations = [] | |
| if not (160 <= mw <= 480): | |
| ghose_violations.append(f"MW not in [160, 480] ({mw:.1f})") | |
| if not (-0.4 <= logp <= 5.6): | |
| ghose_violations.append(f"LogP not in [-0.4, 5.6] ({logp:.2f})") | |
| if not (40 <= molar_refractivity <= 130): | |
| ghose_violations.append(f"MR not in [40, 130] ({molar_refractivity:.1f})") | |
| if not (20 <= heavy_atoms <= 70): | |
| ghose_violations.append(f"Heavy atoms not in [20, 70] ({heavy_atoms})") | |
| ghose_pass = len(ghose_violations) == 0 | |
| # 5. Egan Filter (Absorption) | |
| egan_violations = [] | |
| if logp > 5.88: | |
| egan_violations.append(f"LogP > 5.88 ({logp:.2f})") | |
| if tpsa > 131.6: | |
| egan_violations.append(f"TPSA > 131.6 ({tpsa:.1f})") | |
| egan_pass = len(egan_violations) == 0 | |
| # 6. PAINS Filter (Pan-Assay Interference Compounds) | |
| pains_matches = [] | |
| for entry in PAINS_CATALOG.GetMatches(mol): | |
| pains_matches.append(entry.GetDescription()) | |
| # 7. Brenk Filter (Toxicophores & Reactive Groups) | |
| brenk_matches = [] | |
| for entry in BRENK_CATALOG.GetMatches(mol): | |
| brenk_matches.append(entry.GetDescription()) | |
| # 8. Bioavailability Radar Coordinates (Normalized to [0, 1] relative to drug-like box) | |
| # Axes: LIPO (LogP), SIZE (MW), POLAR (TPSA), INSOLU (LogS proxy/LogP), INSATU (FractionCsp3), FLEX (RotBonds) | |
| # Optimal ranges: | |
| # LIPO: -0.7 to 5.0 | |
| # SIZE: 150 to 500 | |
| # POLAR: 20 to 130 | |
| # INSOLU: 0 to 6 | |
| # INSATU: 0.25 to 1.0 | |
| # FLEX: 0 to 9 | |
| radar_coords = { | |
| "LIPO": float(np.clip((logp - (-0.7)) / (5.0 - (-0.7)), 0.05, 1.2)), | |
| "SIZE": float(np.clip((mw - 150) / (500 - 150), 0.05, 1.2)), | |
| "POLAR": float(np.clip((tpsa - 20) / (130 - 20), 0.05, 1.2)), | |
| "INSOLU": float(np.clip(max(0, logp) / 6.0, 0.05, 1.2)), | |
| "INSATU": float(np.clip(fraction_csp3, 0.05, 1.2)), | |
| "FLEX": float(np.clip(rot_bonds / 9.0, 0.05, 1.2)) | |
| } | |
| return { | |
| "descriptors": { | |
| "Molecular Weight": mw, | |
| "LogP": logp, | |
| "TPSA": tpsa, | |
| "H-Bond Donors": hbd, | |
| "H-Bond Acceptors": hba, | |
| "Rotatable Bonds": rot_bonds, | |
| "Heavy Atoms": heavy_atoms, | |
| "Aromatic Rings": aromatic_rings, | |
| "Fraction Csp3": fraction_csp3, | |
| "Molar Refractivity": molar_refractivity, | |
| "QED": qed_score, | |
| "SA Score (est)": sascore_est | |
| }, | |
| "filters": { | |
| "Lipinski": { | |
| "passed": lipinski_pass, | |
| "num_violations": len(lipinski_violations), | |
| "violations": lipinski_violations | |
| }, | |
| "Veber": { | |
| "passed": veber_pass, | |
| "num_violations": len(veber_violations), | |
| "violations": veber_violations | |
| }, | |
| "Ghose": { | |
| "passed": ghose_pass, | |
| "num_violations": len(ghose_violations), | |
| "violations": ghose_violations | |
| }, | |
| "Egan": { | |
| "passed": egan_pass, | |
| "num_violations": len(egan_violations), | |
| "violations": egan_violations | |
| } | |
| }, | |
| "alerts": { | |
| "PAINS": { | |
| "has_alerts": len(pains_matches) > 0, | |
| "count": len(pains_matches), | |
| "descriptions": pains_matches | |
| }, | |
| "Brenk": { | |
| "has_alerts": len(brenk_matches) > 0, | |
| "count": len(brenk_matches), | |
| "descriptions": brenk_matches | |
| } | |
| }, | |
| "radar": radar_coords | |
| } | |