def fix_valence_charge(mol: Chem.rdchem.Mol, inplace: bool = False) -> Optional[Chem.rdchem.Mol]:
"""Fix valence issues that are due to incorrect charges.
Args:
mol: Input molecule with incorrect valence for some atoms
inplace: Whether to modify in place or make a copy.
Returns:
Fixed molecule via charge correction or original molecule if failed.
"""
vm = rdMolStandardize.RDKitValidation()
# Don't fix something that is not broken
if len(vm.validate(mol)) > 0:
if not inplace:
mol = copy.copy(mol)
mol.UpdatePropertyCache(False)
for a in mol.GetAtoms():
n_electron = (
a.GetImplicitValence()
+ a.GetExplicitValence()
- dm.PERIODIC_TABLE.GetDefaultValence(a.GetSymbol())
)
a.SetFormalCharge(n_electron)
return mol
def featurization(r_mol: Chem.rdchem.Mol,
p_mol: Chem.rdchem.Mol,
):
"""
Generates features of the reactant and product for one reaction as input for the network.
Args:
r_mol: RDKit molecule object for the reactant.
p_mol: RDKit molecule object for the product.
Returns:
data: Torch Geometric Data object, storing the atom and bond features
"""
# compute properties with rdkit (only works if dataset is clean)
r_mol.UpdatePropertyCache()
p_mol.UpdatePropertyCache()
# fake the number of "atoms" if we are collapsing substructures
n_atoms = r_mol.GetNumAtoms()
# topological and 3d distance matrices
tD_r = Chem.GetDistanceMatrix(r_mol)
tD_p = Chem.GetDistanceMatrix(p_mol)
D_r = Chem.Get3DDistanceMatrix(r_mol)
D_p = Chem.Get3DDistanceMatrix(p_mol)
f_atoms = list() # atom (node) features
edge_index = list() # list of tuples indicating presence of bonds
f_bonds = list() # bond (edge) features
for a1 in range(n_atoms):
# Node features
f_atoms.append(atom_features(r_mol.GetAtomWithIdx(a1)))
# Edge features
for a2 in range(a1 + 1, n_atoms):
# fully connected graph
edge_index.extend([(a1, a2), (a2, a1)])
# for now, naively include both reac and prod
b1_feats = [D_r[a1][a2], D_p[a1][a2]]
b2_feats = [D_r[a2][a1], D_p[a2][a1]]
# r_bond = r_mol.GetBondBetweenAtoms(a1, a2)
# b1_feats.extend(bond_features(r_bond))
# b2_feats.extend(bond_features(r_bond))
#
# p_bond = p_mol.GetBondBetweenAtoms(a1, a2)
# b1_feats.extend(bond_features(p_bond))
# b2_feats.extend(bond_features(p_bond))
f_bonds.append(b1_feats)
f_bonds.append(b2_feats)
data = tg.data.Data()
data.x = torch.tensor(f_atoms, dtype=torch.float)
data.edge_index = torch.tensor(edge_index, dtype=torch.long).t().contiguous()
data.edge_attr = torch.tensor(f_bonds, dtype=torch.float)
return data
