def copy_mol_props(source: Chem.rdchem.Mol, destination: Chem.rdchem.Mol):
"""Copy properties from one source molecule to another destination
molecule.
Args:
source: a molecule to copy from.
destination: a molecule to copy to.
"""
props = source.GetPropsAsDict()
dm.set_mol_props(destination, props)
def test_sdf_props_and_conformer_preserved(tmp_path):
sdf_path = tmp_path / "test.sdf"
# Generate an SDF file
props = dict(test_int=588, test_str="hello")
smiles = "CC1(C2C(C3C(C(=O)C(=C(C3(C(=O)C2=C(C4=C1C=CC=C4O)O)O)O)C(=O)N)N(C)C)O)O"
mol = dm.to_mol(smiles)
mol = dm.set_mol_props(mol, props)
mol = dm.conformers.generate(mol, n_confs=1)
pos = mol.GetConformer().GetPositions()
dm.to_sdf(mol, sdf_path)
# Read sdf file
mols = dm.read_sdf(sdf_path)
mol = mols[0]
# Check properties
assert mol.GetPropsAsDict() == props
# Check conformer
conf = mol.GetConformer()
assert mol.GetNumConformers() == 1
assert conf.Is3D()
np.testing.assert_almost_equal(conf.GetPositions(), pos, decimal=4)
def test_copy_mol_props():
source = dm.to_mol("CCC")
destination = dm.to_mol("CC")
props = {}
props["bool"] = True
props["number"] = 55
props["float"] = 5.555
props["string"] = "hello"
props["something_else"] = type(int)
dm.set_mol_props(source, props)
dm.copy_mol_props(source, destination)
assert destination.GetPropsAsDict() == source.GetPropsAsDict()
def test_set_mol_props():
mol = dm.to_mol("CCC")
props = {}
props["number"] = 55
props["float"] = 5.555
props["string"] = "hello"
props["something_else"] = type(int)
dm.set_mol_props(mol, props)
mol_props = mol.GetPropsAsDict()
assert mol_props["number"] == props["number"]
assert mol_props["float"] == props["float"]
assert mol_props["string"] == props["string"]
assert mol_props["something_else"] == str(props["something_else"])
def _row_to_mol(row):
props = row.to_dict()
if mol_column is not None:
mol = props[mol_column]
else:
if conserve_smiles:
smiles = props[smiles_column]
else:
# If a SMILES column is used to create the molecule then it is removed from the
# properties.
smiles = props.pop(smiles_column)
mol = dm.to_mol(smiles)
if mol is None:
return None
dm.set_mol_props(mol, props)
return mol
def test_sanitize_mol_keep_props_and_conformers():
# Generate a mol with props and a conformer
props = dict(test_int=588, test_str="hello")
smiles = "CCC[N+](=O)[O-]"
mol = dm.to_mol(smiles)
mol = dm.set_mol_props(mol, props)
mol = dm.conformers.generate(mol, n_confs=1)
pos = mol.GetConformer().GetPositions()
# Sanitize
sane_mol = dm.sanitize_mol(mol)
# Check properties
assert sane_mol.GetPropsAsDict() == props
# Check conformer
conf = sane_mol.GetConformer()
assert sane_mol.GetNumConformers() == 1
assert conf.Is3D()
np.testing.assert_almost_equal(conf.GetPositions(), pos, decimal=4)
def sanitize_mol(
mol: Chem.rdchem.Mol,
charge_neutral: bool = False,
sanifix: bool = True,
verbose: bool = True,
add_hs: bool = False,
) -> Optional[Chem.rdchem.Mol]:
"""An augmented version of RDKit `sanitize=True`. It uses a
mol-SMILES-mol conversion to catch potential aromaticity errors
and try to fix aromatic nitrogen (using the popular sanifix4 script).
Optionally, it can neutralize the charge of the molecule.
Note #1: Only the first conformer (if present) will be preserved and
a warning will be displayed if more than one conformer is detected.
Note #2: The molecule's properties will be preserved but the atom's
properties will be lost.
Args:
mol: a molecule.
charge_neutral: whether charge neutralization should be applied.
sanifix: whether to run the sanifix from James Davidson
(sanifix4.py) that try to adjust aromatic nitrogens.
verbose: Whether displaying a warning about multiple conformers.
add_hs: Add hydrogens to the returned molecule. Useful when the input
molecule already contains hydrogens.
Returns:
mol: a molecule.
"""
if mol is None:
return mol
# Extract properties.
original_mol = copy_mol(mol)
properties = original_mol.GetPropsAsDict()
if charge_neutral:
mol = to_neutral(mol)
if sanifix:
mol = _sanifix4.sanifix(mol)
if mol is not None:
# Detect multiple conformers
if verbose and mol.GetNumConformers() > 1:
logger.warning(
f"The molecule contains multiple conformers. Only the first one will be preserved."
)
# Try catch to avoid occasional aromaticity errors
try:
# `cxsmiles` is used here to preserve the first conformer.
mol = to_mol(dm.to_smiles(mol, cxsmiles=True), sanitize=True, add_hs=add_hs) # type: ignore
except Exception:
mol = None
if mol is not None:
# Insert back properties.
mol = dm.set_mol_props(mol, properties)
return mol
