def preprocess_smi(smi):
# Filter 1- Convert to Canonical Smiles
try:
mol = Chem.MolFromSmiles(smi)
can_smi = Chem.MolToSmiles(mol, True)
except:
return None
# Filter 2- Remove salt
remover = SaltRemover()
mol = Chem.MolFromSmiles(can_smi)
res, deleted = remover.StripMolWithDeleted(mol, dontRemoveEverything=True)
removed_salt_smi = Chem.MolToSmiles(res)
# Filter 3- Remove Charge
uncharger = rdMolStandardize.Uncharger()
m = Chem.MolFromSmiles(removed_salt_smi)
p = uncharger.uncharge(m)
uncharged_smi = Chem.MolToSmiles(p)
# Filter 4 - Standardize the tautomer
clean_smi = MolStandardize.canonicalize_tautomer_smiles(uncharged_smi)
return clean_smi
def test_withDontRemoveEverything(self):
testFile = os.sep.join(
[os.path.dirname(os.path.abspath(__file__)), 'test_data', 'witch-salts.sdf'])
remover = SaltRemover(defnFilename=testFile, defnFormat=InputFormat.MOL)
m = Chem.MolFromSmiles('Cc1ccccc1')
mol, deleted = remover.StripMolWithDeleted(m, dontRemoveEverything=True)
# List should be empty
self.assertFalse(deleted)
self.assertEqual(m, mol)
def test_withSdfFile(self):
testFile = os.sep.join(
[os.path.dirname(os.path.abspath(__file__)), 'test_data', 'witch-salts.sdf'])
remover = SaltRemover(defnFilename=testFile, defnFormat=InputFormat.MOL)
self.assertEqual(len(remover.salts), 240)
m = Chem.MolFromSmiles("Cc1onc(-c2ccccc2)c1C([O-])=NC1C(=O)N2C1SC(C)(C)C2C(=O)O.O.[Na+]")
tuple = remover.StripMolWithDeleted(m)
self.assertEqual(Chem.MolToSmiles(tuple.mol), 'Cc1onc(-c2ccccc2)c1C([O-])=NC1C(=O)N2C1SC(C)(C)C2C(=O)O.O')
self.assertEqual(len(tuple.deleted), 1)
self.assertEqual(Chem.MolToSmiles(tuple.deleted[0]), '[Na+]')
def check_salt(self, molecule: str, subType: str) -> str:
"""
Checks if the molecule is salt.
:param molecule:
:return salt:
"""
remover = SaltRemover()
salt = None
res, deleted = remover.StripMolWithDeleted(self.smiles_mol)
if len(deleted) >= 1:
salt = '_'.join([subType, 'salt'])
return salt
def test_SmilesVsSmarts(self):
# SMARTS
remover = SaltRemover(defnData="[Cl,Br]")
mol = Chem.MolFromSmiles('CN(Br)Cl.Cl')
res = remover.StripMol(mol)
self.assertEqual(res.GetNumAtoms(), 4)
self.assertEqual(Chem.MolToSmiles(res), 'CN(Cl)Br')
mol = Chem.MolFromSmiles('CN(C)C.Cl.Br')
res, deleted = remover.StripMolWithDeleted(mol)
self.assertEqual(Chem.MolToSmiles(res), 'CN(C)C')
# Because we read in SMARTS, we should output as well. Otherwise, we will have
# mismatches
self.assertListEqual([Chem.MolToSmarts(m) for m in deleted], ['[Cl,Br]'])
# SMILES
remover = SaltRemover(defnData="Cl", defnFormat=InputFormat.SMILES)
mol = Chem.MolFromSmiles('CN(Br)Cl.Cl')
res = remover.StripMol(mol)
self.assertEqual(res.GetNumAtoms(), 4)
self.assertEqual(Chem.MolToSmiles(res), 'CN(Cl)Br')
def NeutraliseCharges_RemoveSalt(smiles, reactions=None):
global _reactions
if reactions is None:
if _reactions is None:
_reactions = _InitialiseNeutralisationReactions()
reactions = _reactions
mol = Chem.MolFromSmiles(smiles)
if mol is not None:
remover = SaltRemover()
mol, deleted = remover.StripMolWithDeleted(mol)
replaced = False
for i, (reactant, product) in enumerate(reactions):
while mol.HasSubstructMatch(reactant):
replaced = True
rms = AllChem.ReplaceSubstructs(mol, reactant, product)
mol = rms[0]
if replaced:
return (Chem.MolToSmiles(mol, True), True)
else:
return (smiles, False)
else:
return (None, False)
if __name__ == '__main__':
if len(sys.argv) != 3:
print('Usage: python rdkit_hlogp_batch.py <smiles> <batch_size>')
exit()
BATCH_SIZE = int(sys.argv[2])
hlogp_list = list()
with open(sys.argv[1]) as smiles_file:
file_lines = smiles_file.readlines()
for line in file_lines:
if line.strip():
smiles, cid = str(line).strip().split()[:2]
mol = MolFromSmiles(smiles)
remover = SaltRemover()
res, deleted = remover.StripMolWithDeleted(mol)
if res is not None:
res.SetProp('_Name', cid)
logp = MolLogP(res)
num_heavy_atoms = res.GetNumHeavyAtoms()
if num_heavy_atoms > 99:
num_heavy_atoms = 99
scaled_logp = scale_logp_value(logp)
if logp < 0.0:
sign = 'M'
#remove the minus sign so it's not printed
scaled_logp = scaled_logp * -1
else:
sign = 'P'
key_string = 'H{:02}{}{:03}'.format(num_heavy_atoms, sign, scaled_logp)