def test9Validate(self):
vm = rdMolStandardize.RDKitValidation()
mol = Chem.MolFromSmiles("CO(C)C", sanitize=False)
msg = vm.validate(mol)
self.assertEqual(len(msg), 1)
self.assertEqual
("""INFO: [ValenceValidation] Explicit valence for atom # 1 O, 3, is greater than permitted""",
msg[0])
vm2 = rdMolStandardize.MolVSValidation(
[rdMolStandardize.FragmentValidation()])
# with no argument it also works
# vm2 = rdMolStandardize.MolVSValidation()
mol2 = Chem.MolFromSmiles(
"COc1cccc(C=N[N-]C(N)=O)c1[O-].O.O.O.O=[U+2]=O")
msg2 = vm2.validate(mol2)
self.assertEqual(len(msg2), 1)
self.assertEqual
("""INFO: [FragmentValidation] water/hydroxide is present""", msg2[0])
vm3 = rdMolStandardize.MolVSValidation()
mol3 = Chem.MolFromSmiles("C1COCCO1.O=C(NO)NO")
msg3 = vm3.validate(mol3)
self.assertEqual(len(msg3), 2)
self.assertEqual
("""INFO: [FragmentValidation] 1,2-dimethoxyethane is present""",
msg3[0])
self.assertEqual
("""INFO: [FragmentValidation] 1,4-dioxane is present""", msg3[1])
atomic_no = [6, 7, 8]
allowed_atoms = [Atom(i) for i in atomic_no]
vm4 = rdMolStandardize.AllowedAtomsValidation(allowed_atoms)
mol4 = Chem.MolFromSmiles("CC(=O)CF")
msg4 = vm4.validate(mol4)
self.assertEqual(len(msg4), 1)
self.assertEqual
("""INFO: [AllowedAtomsValidation] Atom F is not in allowedAtoms list""",
msg4[0])
atomic_no = [9, 17, 35]
disallowed_atoms = [Atom(i) for i in atomic_no]
vm5 = rdMolStandardize.DisallowedAtomsValidation(disallowed_atoms)
mol5 = Chem.MolFromSmiles("CC(=O)CF")
msg5 = vm4.validate(mol5)
self.assertEqual(len(msg5), 1)
self.assertEqual
("""INFO: [DisallowedAtomsValidation] Atom F is in disallowedAtoms list""",
msg5[0])
msg6 = rdMolStandardize.ValidateSmiles("ClCCCl.c1ccccc1O")
self.assertEqual(len(msg6), 1)
self.assertEqual
("""INFO: [FragmentValidation] 1,2-dichloroethane is present""",
msg6[0])
def check_mol_rdkit(self, clean=False):
"""
Checks validity of rdmol molecule against internal rules
Valence electrons
Bond order
Charge
Fragments
Args:
self: aemol object
rdmol: rdkit molecule object
Returns:
if clean = True: returns cleaned molecule
else: returns null
"""
if self.rdmol == None:
self.to_rdkit()
rdkit_vm = mol_std.RDKitValidation()
molvs_vm = mol_std.MolVSValidation()
rdkit_vm.validate(self.rdmol)
molvs_vm.validate(self.rdmol)
if clean:
lfc = mol_stf.LargestFragmentChooser()
idx = self.rdmol.GetProp('_Name')
self.rdmol = lfc.choose(rself.rdmol)
mol_std.Cleanup(self.rdmol)
self.rdmol.SetProp('_Name', idx)
def validate_isotopes(mol):
"""Logs if molecule contains isotopes.
Parameters
----------
mol: rdkit.Chem.Mol
A molecule.
Returns
-------
message: str
"""
validation = [rdMolStandardize.IsotopeValidation()]
message = rdMolStandardize.MolVSValidation(validation).validate(mol)
return message or None
def validate_neutrality(mol):
"""Logs if not an overall neutral system.
Parameters
----------
mol: rdkit.Chem.Mol
A molecule.
Returns
-------
message: str
"""
validation = [rdMolStandardize.NeutralValidation()]
message = rdMolStandardize.MolVSValidation(validation).validate(mol)
return message or None
def validate_fragment(mol):
"""Logs if certain fragments are present.
Parameters
----------
mol: rdkit.Chem.Mol
A molecule.
Returns
-------
message: str
"""
validation = [rdMolStandardize.FragmentValidation()]
message = rdMolStandardize.MolVSValidation(validation).validate(mol)
return message or None
def validate_if_no_atom(mol):
"""Logs an error if the molecule has zero atoms.
If the molecule has no atoms, no subsequent validations will run.
Parameters
----------
mol: rdkit.Chem.Mol
A molecule.
Returns
-------
message: str
"""
validation = [rdMolStandardize.NoAtomValidation()]
message = rdMolStandardize.MolVSValidation(validation).validate(mol)
return message or None
def validate_default(mol):
"""Performs the default validation which occurs in MolVS.
Parameters
----------
mol: rdkit.Chem.Mol
A molecule.
Returns
-------
message: str
Notes
-----
Default is to do all following validations:
validate_if_no_atom, validate_fragment, validate_neutrality,
validate_isotopes
"""
message = rdMolStandardize.MolVSValidation().validate(mol)
return message or None