def test6Charge(self):
mol = Chem.MolFromSmiles("C1=C(C=CC(=C1)[S]([O-])=O)[S](O)(=O)=O")
# instantiate with default acid base pair library
reionizer = rdMolStandardize.Reionizer()
nm = reionizer.reionize(mol)
self.assertEqual(Chem.MolToSmiles(nm), "O=S(O)c1ccc(S(=O)(=O)[O-])cc1")
# try reionize with another acid base pair library without the right
# pairs
abfile = os.path.join(RDConfig.RDDataDir, 'MolStandardize',
'acid_base_pairs2.txt')
reionizer2 = rdMolStandardize.Reionizer(abfile)
nm2 = reionizer2.reionize(mol)
self.assertEqual(Chem.MolToSmiles(nm2),
"O=S([O-])c1ccc(S(=O)(=O)O)cc1")
# test Uncharger
uncharger = rdMolStandardize.Uncharger()
mol3 = Chem.MolFromSmiles("O=C([O-])c1ccccc1")
nm3 = uncharger.uncharge(mol3)
self.assertEqual(Chem.MolToSmiles(nm3), "O=C(O)c1ccccc1")
# test canonical Uncharger
uncharger = rdMolStandardize.Uncharger(canonicalOrder=False)
mol3 = Chem.MolFromSmiles("C[N+](C)(C)CC(C(=O)[O-])CC(=O)[O-]")
nm3 = uncharger.uncharge(mol3)
self.assertEqual(Chem.MolToSmiles(nm3),
"C[N+](C)(C)CC(CC(=O)[O-])C(=O)O")
uncharger = rdMolStandardize.Uncharger(canonicalOrder=True)
nm3 = uncharger.uncharge(mol3)
self.assertEqual(Chem.MolToSmiles(nm3),
"C[N+](C)(C)CC(CC(=O)O)C(=O)[O-]")
def reionize(mol):
"""Ensure the strongest acid groups ionize first in partially
ionized molecules.
Parameters
----------
mol: rdkit.Chem.Mol
The partially ionized molecule.
Returns
-------
mol: rdkit.Chem.Mol
Returns a molecule, with strongest acid groups ionized first.
"""
return rdMolStandardize.Reionizer().reionize(mol)
def standardize_mol(
mol: Chem.rdchem.Mol,
disconnect_metals: bool = False,
normalize: bool = True,
reionize: bool = True,
uncharge: bool = False,
stereo: bool = True,
):
r"""
This function returns a standardized version the given molecule, with or without disconnect the metals.
The process is apply in the order of the argument.
Arguments:
mol: The molecule to standardize.
disconnect_metals: Whether to disconnect the metallic atoms from non-metals
normalize: Whether to apply normalization (correct functional groups and recombine charges).
reionize: Whether to apply molecule reionization
uncharge: Whether to remove all charge from molecule
stereo: Whether to attempt to assign stereochemistry
Returns:
mol: The standardized molecule.
"""
mol = copy_mol(mol)
if disconnect_metals:
md = rdMolStandardize.MetalDisconnector()
mol = md.Disconnect(mol)
if normalize:
mol = rdMolStandardize.Normalize(mol)
if reionize:
reionizer = rdMolStandardize.Reionizer()
mol = reionizer.reionize(mol)
if uncharge:
uncharger = rdMolStandardize.Uncharger()
mol = uncharger.uncharge(mol)
if stereo:
Chem.AssignStereochemistry(mol, force=False, cleanIt=True)
return mol
def my_standardizer(mol: Chem.Mol) -> Chem.Mol:
"""
MolVS implementation of standardization
Args:
mol (Chem.Mol): non-standardized rdkit mol object
Returns:
Chem.Mol: stndardized rdkit mol object
"""
mol = copy.deepcopy(mol)
Chem.SanitizeMol(mol)
mol = Chem.RemoveHs(mol)
disconnector = rdMolStandardize.MetalDisconnector()
mol = disconnector.Disconnect(mol)
normalizer = rdMolStandardize.Normalizer()
mol = normalizer.normalize(mol)
reionizer = rdMolStandardize.Reionizer()
mol = reionizer.reionize(mol)
Chem.AssignStereochemistry(mol, force=True, cleanIt=True)
# TODO: Check this removes symmetric stereocenters
return mol
