def uncharge_smiles(smiles):
"""Utility function that returns the uncharged SMILES for a given SMILES string."""
mol = Chem.MolFromSmiles(smiles)
u = Uncharger()
mol = u.uncharge(mol)
if mol:
return Chem.MolToSmiles(mol, isomericSmiles=True)
def normalize(smiles):
#print(smiles)
# Generate Mol
mol = Chem.MolFromSmiles(smiles)
# Uncharge
uncharger = Uncharger()
mol = uncharger.uncharge(mol)
# LargestFragmentChooser
flagmentChooser = LargestFragmentChooser()
mol = flagmentChooser(mol)
# Sanitaize
Chem.SanitizeMol(mol)
# Normalize
normalizer = Normalizer()
mol = normalizer.normalize(mol)
tautomerCanonicalizer = TautomerCanonicalizer()
mol = tautomerCanonicalizer.canonicalize(mol)
return Chem.MolToSmiles(mol)
def normalize(smiles):
#print(smiles)
# Generate Mol
mol1 = Chem.MolFromSmiles(smiles)
# Uncharge
uncharger = Uncharger()
mol2 = uncharger.uncharge(mol1)
# LargestFragmentChooser
flagmentChooser = LargestFragmentChooser()
try:
mol3 = flagmentChooser(mol2)
except:
try:
mol3 = flagmentChooser(mol1)
except:
mol3 = mol1
# Sanitaize
Chem.SanitizeMol(mol3)
# Normalize
normalizer = Normalizer()
mol4 = normalizer.normalize(mol3)
#tautomerCanonicalizer = TautomerCanonicalizer()
#mol = tautomerCanonicalizer.canonicalize(mol)
return Chem.MolToSmiles(mol4)
def FullStandardization(smi):
try:
mol = Chem.MolFromSmiles(smi)
if mol == None:
# If rdkit could not parse the smiles, returns Error 1
return "Error 1"
else:
STD = Standardizer()
LFC = LargestFragmentChooser()
UC = Uncharger()
RI = Reionizer()
TC = TautomerCanonicalizer()
mol = STD(mol)
mol = LFC(mol)
allowed_elements = {
"H", "B", "C", "N", "O", "F", "Si", "P", "S", "Cl", "Se", "Br",
"I"
}
actual_elements = set(
[atom.GetSymbol() for atom in mol.GetAtoms()])
if len(actual_elements - allowed_elements) == 0:
mol = UC(mol)
mol = RI(mol)
RemoveStereochemistry(mol)
mol = TC(mol)
return Chem.MolToSmiles(mol)
else:
# If molecule contains other than the allowed elements, returns "Error 2"
return "Error 2"
except:
return "Check manually"
def normalize(smiles):
from copy import deepcopy
#print(smiles)
# Generate Mol
mol = Chem.MolFromSmiles(smiles)
# Uncharge
uncharger = Uncharger()
try:
mol2 = uncharger.uncharge(mol)
except:
mol2 = mol
mol2 = mol
# LargestFragmentChooser
flagmentChooser = LargestFragmentChooser()
try:
mol3 = flagmentChooser(mol2)
except:
mol3 = mol2
# Sanitaize
mol3_tmp = deepcopy(mol3)
try:
ret = Chem.SanitizeMol(mol3, catchErrors=False)
except:
mol3 = mol3_tmp
# Normalize
normalizer = Normalizer()
try:
mol4 = normalizer.normalize(mol3)
except:
mol4 = mol3
#print(mol4)
tautomerCanonicalizer = TautomerCanonicalizer()
mol4 = tautomerCanonicalizer.canonicalize(mol4)
new_smiles = Chem.MolToSmiles(mol4)
#print(new_smiles)
return new_smiles
class Neutralize(CurationStep):
""" Class to neutralize compounds """
def __init__(self, **kwargs):
self.neutralizer = Uncharger(**kwargs)
def filterFunction(self, cmp):
return self.neutralizer.uncharge(cmp)
def runStep(self, df, cmp_index):
df.iloc[:, cmp_index] = [self.filterFunction(mol) for mol in df[cmp_index]]
return df
def getNeutralMolecule(mol):
uncharger = Uncharger()
return uncharger.uncharge(mol)
def __init__(self, **kwargs):
self.neutralizer = Uncharger(**kwargs)