def extract_shingles(self, individual):
qry_shingles = set()
radius_constr = self.radius + 1
# Reloading molecule to make it aromatic
mol = MolFromSmiles(individual.to_aromatic_smiles())
for atm_idx in range(individual.mol_graph.GetNumAtoms()):
for N in range(1, radius_constr):
bonds = AllChem.FindAtomEnvironmentOfRadiusN(mol, N, atm_idx)
if not bonds:
break
# the reportedly faster method
atoms = set()
for bond_id in bonds:
bond = mol.GetBondWithIdx(bond_id)
atoms.add(bond.GetBeginAtomIdx())
atoms.add(bond.GetEndAtomIdx())
if self.rooted:
new_shingle = Chem.rdmolfiles.MolFragmentToSmiles(
mol, list(atoms), bonds, 0, 0, False, False, atm_idx,
True, False, False)
else:
new_shingle = Chem.rdmolfiles.MolFragmentToSmiles(
mol, list(atoms), bonds, 0, 0, False, False, -1, True,
False, False)
qry_shingles.add(new_shingle)
return qry_shingles
def extract_shingles(smiles, level, as_list=False):
"""
Extracting up to the given level from the given smiles
see https://jcheminf.biomedcentral.com/articles/10.1186/s13321-018-0321-8
"""
if as_list:
qry_shingles = list()
else:
qry_shingles = set()
radius_constr = level + 1
# Reloading molecule to make it aromatic
mol = MolFromSmiles(smiles)
for atm_idx in range(mol.GetNumAtoms()):
for N in range(1, radius_constr):
bonds = AllChem.FindAtomEnvironmentOfRadiusN(mol, N, atm_idx)
if not bonds:
break
# the reportedly faster method
atoms = set()
for bond_id in bonds:
bond = mol.GetBondWithIdx(bond_id)
atoms.add(bond.GetBeginAtomIdx())
atoms.add(bond.GetEndAtomIdx())
# Computed rooted shingle
new_shingle = Chem.rdmolfiles.MolFragmentToSmiles(
mol, list(atoms), bonds, 0, 0, False, False, atm_idx, True,
False, False)
if as_list:
qry_shingles.append(new_shingle)
else:
qry_shingles.add(new_shingle)
return qry_shingles