def test_parse_molecular_formula():
formula = 'C6H9NOF2Cl2Br'
parsed = parse_molecular_formula(formula)
expected = [('C', 6), ('H', 9), ('N', 1), ('O', 1), ('F', 2), ('Cl', 2),
('Br', 1)]
assert parsed == expected
def __init__(self, molecular_formula: str) -> None:
"""
Args:
molecular_formula: target molecular formula
"""
super().__init__()
element_occurrences = parse_molecular_formula(molecular_formula)
total_number_atoms = sum(element_tuple[1] for element_tuple in element_occurrences)
# scoring functions for each element
self.functions = [RdkitScoringFunction(descriptor=AtomCounter(element),
score_modifier=GaussianModifier(mu=n_atoms, sigma=1.0))
for element, n_atoms in element_occurrences]
# scoring functions for the total number of atoms
self.functions.append(RdkitScoringFunction(descriptor=num_atoms,
score_modifier=GaussianModifier(mu=total_number_atoms, sigma=2.0)))
def determine_scoring_functions(
molecular_formula: str) -> List[RdkitScoringFunction]:
element_occurrences = parse_molecular_formula(molecular_formula)
total_number_atoms = sum(element_tuple[1]
for element_tuple in element_occurrences)
# scoring functions for each element
functions = [
RdkitScoringFunction(descriptor=AtomCounter(element),
score_modifier=GaussianModifier(mu=n_atoms,
sigma=1.0))
for element, n_atoms in element_occurrences
]
# scoring functions for the total number of atoms
functions.append(
RdkitScoringFunction(descriptor=num_atoms,
score_modifier=GaussianModifier(
mu=total_number_atoms, sigma=2.0)))
return functions