def get_max_n_atoms(smi_file):
""" Determines the maximum number of atoms per molecule in an input SMILES file.
Args:
smi_file (str) : Full path/filename to SMILES file.
"""
molecules = load_molecules(path=smi_file)
max_n_atoms = 0
for mol in molecules:
n_atoms = mol.GetNumAtoms()
if n_atoms > max_n_atoms:
max_n_atoms = n_atoms
return max_n_atoms
def get_formal_charges(smi_file):
""" Determines the formal charges present in an input SMILES file.
Args:
smi_file (str) : Full path/filename to SMILES file.
"""
molecules = load_molecules(path=smi_file)
# create a list of all the formal charges
formal_charges = list()
for mol in molecules:
for atom in mol.GetAtoms():
formal_charges.append(atom.GetFormalCharge())
# remove duplicate formal charges then sort
set_of_formal_charges = set(formal_charges)
formal_charges_sorted = list(set_of_formal_charges)
formal_charges_sorted.sort()
return formal_charges_sorted
def get_atom_types(smi_file):
""" Determines the atom types present in an input SMILES file.
Args:
smi_file (str) : Full path/filename to SMILES file.
"""
molecules = load_molecules(path=smi_file)
# create a list of all the atom types
atom_types = list()
for mol in molecules:
for atom in mol.GetAtoms():
atom_types.append(atom.GetAtomicNum())
# remove duplicate atom types then sort by atomic number
set_of_atom_types = set(atom_types)
atom_types_sorted = list(set_of_atom_types)
atom_types_sorted.sort()
# return the symbols, for convenience
return [rdkit.Chem.Atom(atom).GetSymbol() for atom in atom_types_sorted]