def test3Parents(self):
mol = Chem.MolFromSmiles("[Na]OC(=O)c1ccccc1")
nmol = rdMolStandardize.FragmentParent(mol)
self.assertEqual(Chem.MolToSmiles(nmol), "O=C([O-])c1ccccc1")
mol = Chem.MolFromSmiles("C[NH+](C)(C).[Cl-]")
nmol = rdMolStandardize.ChargeParent(mol)
self.assertEqual(Chem.MolToSmiles(nmol), "CN(C)C")
mol = Chem.MolFromSmiles("[O-]CCCC=CO.[Na+]")
nmol = rdMolStandardize.TautomerParent(mol)
self.assertEqual(Chem.MolToSmiles(nmol), "O=CCCCC[O-].[Na+]")
nmol = rdMolStandardize.TautomerParent(mol, skipStandardize=True)
# same answer because of the standardization at the end
self.assertEqual(Chem.MolToSmiles(nmol), "O=CCCCC[O-].[Na+]")
mol = Chem.MolFromSmiles("C[C@](F)(Cl)C/C=C/[C@H](F)Cl")
nmol = rdMolStandardize.StereoParent(mol)
self.assertEqual(Chem.MolToSmiles(nmol), "CC(F)(Cl)CC=CC(F)Cl")
mol = Chem.MolFromSmiles("[12CH3][13CH3]")
nmol = rdMolStandardize.IsotopeParent(mol)
self.assertEqual(Chem.MolToSmiles(nmol), "CC")
mol = Chem.MolFromSmiles(
"[Na]Oc1c([12C@H](F)Cl)c(O[2H])c(C(=O)O)cc1CC=CO")
nmol = rdMolStandardize.SuperParent(mol)
self.assertEqual(Chem.MolToSmiles(nmol),
"O=CCCc1cc(C(=O)O)c(O)c(C(F)Cl)c1O")
mol = Chem.MolFromSmiles(
"[Na]Oc1c([12C@H](F)Cl)c(O[2H])c(C(=O)O)cc1CC=CO")
nmol = rdMolStandardize.SuperParent(mol, skipStandardize=True)
self.assertEqual(Chem.MolToSmiles(nmol),
"O=CCCc1cc(C(=O)[O-])c(O)c(C(F)Cl)c1O.[Na+]")
def test20NoneHandling(self):
with self.assertRaises(ValueError):
rdMolStandardize.ChargeParent(None)
with self.assertRaises(ValueError):
rdMolStandardize.Cleanup(None)
with self.assertRaises(ValueError):
rdMolStandardize.FragmentParent(None)
with self.assertRaises(ValueError):
rdMolStandardize.Normalize(None)
with self.assertRaises(ValueError):
rdMolStandardize.Reionize(None)
def fix_mol(
mol: Chem.rdchem.Mol,
n_iter: int = 1,
remove_singleton: bool = False,
largest_only: bool = False,
inplace: bool = False,
) -> Optional[Chem.rdchem.Mol]:
"""Fix error in molecule using a greedy approach.
Args:
mol: input molecule to fix
n_iter: Number of valence fix iteration to apply
remove_singleton: Whether `adjust_singleton` should be applied
largest_only: Whether only the largest fragment should be kept
inplace: Whether to return a copy of the mol or perform in place operation
Returns:
Fixed molecule.
"""
if not inplace:
mol = copy.copy(mol)
m = sanitize_mol(mol) or mol # fail back to mol when the fixer fail
if m is not None:
m = remove_dummies(m)
for _ in range(n_iter):
m = fix_valence(m)
if remove_singleton:
m = adjust_singleton(m)
if largest_only:
# m = max(Chem.rdmolops.GetMolFrags(m, asMols=True, sanitizeFrags=False), key=lambda m: m.GetNumAtoms())
m = rdMolStandardize.FragmentParent(m, skipStandardize=True)
return m
def __init__(self, radius, fpSize, IC50function, molFile):
self.fpgen = rdFingerprintGenerator.GetMorganGenerator(
radius=radius, fpSize=fpSize)
self.getIC50 = IC50function
self.molFile = molFile
# Open SMILES file and convert each sequence to rdkit molecule
with open(self.molFile) as f:
raw_text = f.read()
raw_data = raw_text.split("\n")
mol_list = [Chem.MolFromSmiles(x) for x in raw_data[:1000]]
self.ms = [rdMolStandardize.FragmentParent(x) for x in mol_list]
# Get a count of the BRICS bonds within the molecules
cntr = Counter()
for m in self.ms:
bbnds = BRICS.FindBRICSBonds(m)
for aids, lbls in bbnds:
cntr[lbls] += 1
freqs = sorted([(y, x) for x, y in cntr.items()], reverse=True)
# Keep the top 10 bonds
self.bondsToKeep = [y for x, y in freqs]
def test3FragmentParent(self):
mol = Chem.MolFromSmiles("[Na]OC(=O)c1ccccc1")
nmol = rdMolStandardize.FragmentParent(mol)
self.assertEqual(Chem.MolToSmiles(nmol), "O=C([O-])c1ccccc1")