def sequence_tunable(
mol,
OP_REMOVE_ISOTOPE=True, OP_NEUTRALISE_CHARGE=True,
OP_REMOVE_STEREO=False, OP_COMMUTE_INCHI=False,
OP_KEEP_BIGGEST=True, OP_ADD_HYDROGEN=True,
OP_KEKULIZE=True, OP_NEUTRALISE_CHARGE_LATE=True
):
"""Tunable sequence of filters for standardization.
Operations will made in the following order:
1 RDKit Cleanup -- always
2 RDKIT SanitizeMol -- always
3 Remove isotope -- optional (default: True)
4 Neutralise charges -- optional (default: True)
5 RDKit SanitizeMol -- if 4 or 5
6 Remove stereo -- optional (default: False)
7 Commute Inchi -- if 6 or optional (default: False)
8 Keep biggest -- optional (default: True)
9 RDKit SanitizeMol -- if any (6, 7, 8)
10 Add hydrogens -- optional (default: True)
11 Kekulize -- optional (default: True)
"""
F = Filters()
# Always perform the basics..
Cleanup(mol)
SanitizeMol(mol, sanitizeOps=SanitizeFlags.SANITIZE_ALL, catchErrors=False)
AssignStereochemistry(mol, cleanIt=True, force=True, flagPossibleStereoCenters=True) # Fix bug TD201904.01
#
if OP_REMOVE_ISOTOPE:
mol = F.remove_isotope(mol)
if OP_NEUTRALISE_CHARGE:
mol = F.neutralise_charge(mol)
if any([OP_REMOVE_ISOTOPE, OP_REMOVE_ISOTOPE]):
SanitizeMol(mol, sanitizeOps=SanitizeFlags.SANITIZE_ALL, catchErrors=False)
#
if OP_REMOVE_STEREO:
mol = F.remove_stereo(mol)
OP_COMMUTE_INCHI = True
if OP_COMMUTE_INCHI:
mol = F.commute_inchi(mol)
if OP_KEEP_BIGGEST:
mol = F.keep_biggest(mol)
if any([OP_REMOVE_STEREO, OP_COMMUTE_INCHI, OP_KEEP_BIGGEST]):
SanitizeMol(mol, sanitizeOps=SanitizeFlags.SANITIZE_ALL, catchErrors=False)
#
if OP_NEUTRALISE_CHARGE_LATE:
mol = F.neutralise_charge(mol)
SanitizeMol(mol, sanitizeOps=SanitizeFlags.SANITIZE_ALL, catchErrors=False)
#
if OP_ADD_HYDROGEN:
mol = F.add_hydrogen(mol, addCoords=True)
if OP_KEKULIZE:
mol = F.kekulize(mol)
#
return mol
def test_remove_stereo():
mol = Filters.remove_stereo(MolFromSmiles('C[C@@H](C(=O)[O-])O'))
assert MolToSmiles(mol) == 'CC(O)C(=O)[O-]'
mol = Filters.remove_stereo(
MolFromInchi(
'InChI=1S/C20H13N3O3/c24-10-5-6-15-12(7-10)14(9-21-15)17-8-13(19(25)23-17)18-11-3-1-2-4-16(11)22-20(18)26/h1-9,21,24H,(H,22,26)(H,23,25)/b18-13+'
))
assert MolToSmiles(
mol) == 'OC1=NC(c2c[nH]c3ccc(O)cc23)=CC1=C1C(O)=Nc2ccccc21'
mol = Filters.commute_inchi(mol) # Expected to change tautomerism
assert MolToSmiles(
mol) == 'O=C1NC(C2=CNC3=C2C=C(O)C=C3)=CC1=C1C(=O)NC2=CC=CC=C21'
def test_commute_inchi():
inchi = 'InChI=1S/C3H6O3/c1-2(4)3(5)6/h2,4H,1H3,(H,5,6)/p-1'
mol = Filters.commute_inchi(MolFromInchi(inchi))
assert MolToInchi(mol) == inchi