def test_porphyrin(self, use_ILP: bool = True) -> None:
with open('pdbs/tetraphenylporphyrin.pdb') as fh:
input_molecule = molecule_from_pdb_str(
fh.read(),
name='porphyrin',
)
input_molecule.remove_all_hydrogens(mark_all_uncapped=True)
input_molecule.write_graph(
'input',
output_size=(1200, 1200),
graph_kwargs={'include_atom_index': False},
)
tautomers = input_molecule.get_all_tautomers(
net_charge=0,
total_number_hydrogens=30,
enforce_octet_rule=True,
allow_radicals=False,
)
assert len(tautomers) == 21, len(tautomers)
for (n, molecule) in enumerate(tautomers, start=1):
molecule.name = input_molecule.name
molecule.write_graph(
'_tautomer_{0}'.format(n),
output_size=(1200, 1200),
graph_kwargs={'include_atom_index': False},
)
def test_violuric_acid(self, use_ILP: bool = True) -> None:
with open('pdbs/violuric_acid.pdb') as fh:
input_molecule = molecule_from_pdb_str(
fh.read(),
name='violuric_acid',
)
input_molecule.remove_all_hydrogens(mark_all_uncapped=True)
input_molecule.write_graph(
'input',
output_size=(1200, 1200),
graph_kwargs={'include_atom_index': False},
)
tautomers = input_molecule.get_all_tautomers(
#net_charge=0,
total_number_hydrogens=3,
enforce_octet_rule=True,
allow_radicals=False,
)
for (n, molecule) in enumerate(tautomers, start=1):
molecule.name = input_molecule.name
molecule.write_graph(
'_tautomer_{0}'.format(n),
output_size=(1200, 1200),
graph_kwargs={
'include_atom_index': False,
'vertex_color_scheme': 'elements',
'vertex_label_template': ''
},
)
assert len(tautomers) == 15, len(tautomers)
def test_ammonium(self):
with open('pdbs/ammonium.pdb') as fh:
input_molecule = molecule_from_pdb_str(
fh.read(),
name='ammonium',
)
input_molecule.remove_all_hydrogens(mark_all_uncapped=True)
input_molecule.write_graph(
'input',
output_size=(600, 600),
graph_kwargs={'include_atom_index': False},
)
tautomers = input_molecule.get_all_tautomers(
net_charge=1,
total_number_hydrogens=4,
enforce_octet_rule=True,
allow_radicals=False,
)
assert len(tautomers) == 1, len(tautomers)
for (n, molecule) in enumerate(tautomers, start=1):
molecule.name = input_molecule.name
molecule.write_graph(
'_tautomer_{0}'.format(n),
output_size=(600, 600),
graph_kwargs={'include_atom_index': True},
)
def test_ammonium_fail(self):
with open('pdbs/ammonium.pdb') as fh:
input_molecule = molecule_from_pdb_str(
fh.read(),
name='ammonium',
)
input_molecule.remove_all_hydrogens(mark_all_uncapped=True)
input_molecule.write_graph(
'input',
output_size=(600, 600),
graph_kwargs={'include_atom_index': False},
)
with self.assertRaises(Exception):
tautomers = input_molecule.get_all_tautomers(
net_charge=1,
total_number_hydrogens=4,
maximum_number_hydrogens_per_atom=2,
enforce_octet_rule=True,
allow_radicals=False,
)
with self.assertRaises(Exception):
tautomers = input_molecule.get_all_tautomers(
net_charge=0,
total_number_hydrogens=4,
maximum_number_hydrogens_per_atom=3,
enforce_octet_rule=True,
allow_radicals=False,
)
def test_benzene_fail(self):
with open('pdbs/benzene.pdb') as fh:
input_molecule = molecule_from_pdb_str(
fh.read(),
name='benzene_fail',
)
input_molecule.remove_all_hydrogens(mark_all_uncapped=True)
input_molecule.write_graph(
'input',
output_size=(600, 600),
graph_kwargs={'include_atom_index': True},
)
tautomers = input_molecule.get_all_tautomers(
net_charge=0,
total_number_hydrogens=6,
enforce_octet_rule=True,
allow_radicals=False,
disallow_triple_bond_in_small_rings=False,
disallow_allenes_in_small_rings=False,
disallow_allenes_completely=False,
lock_phenyl_rings=False,
)
assert len(tautomers) == 5, len(tautomers)
for (n, molecule) in enumerate(tautomers, start=1):
molecule.name = input_molecule.name
molecule.write_graph(
'_tautomer_{0}'.format(n),
output_size=(600, 600),
graph_kwargs={'include_atom_index': False},
)
def test_methylimidazole(self, use_ILP: bool = True) -> None:
with open('pdbs/methylimidazole.pdb') as fh:
input_molecule = molecule_from_pdb_str(
fh.read(),
name='methylimidazole',
)
input_molecule.remove_all_hydrogens(mark_all_uncapped=True)
input_molecule.write_graph(
'input',
output_size=(600, 600),
graph_kwargs={'include_atom_index': False},
)
tautomers = input_molecule.get_all_tautomers(
net_charge=0,
total_number_hydrogens=6,
enforce_octet_rule=True,
allow_radicals=False,
)
for (n, molecule) in enumerate(tautomers, start=1):
molecule.name = input_molecule.name
molecule.write_graph(
'_tautomer_{0}'.format(n),
output_size=(600, 600),
graph_kwargs={'include_atom_index': False},
)
def test_carbon_dioxide(self) -> None:
with open('pdbs/carbon_dioxide.pdb') as fh:
input_molecule = molecule_from_pdb_str(
fh.read(),
name='carbon_dioxide',
)
input_molecule.assign_bond_orders_and_charges_with_ILP(
enforce_octet_rule=True, )
input_molecule.write_graph(
'',
output_size=(400, 400),
graph_kwargs={'include_atom_index': True},
)
def test_skeletal_rearrangement(self):
with open('pdbs/warfarin.pdb') as fh:
input_molecule = molecule_from_pdb_str(
fh.read(),
name='warfarin_extended',
)
input_molecule.remove_all_hydrogens(mark_all_uncapped=True)
input_molecule.write_graph(
'input',
output_size=(1200, 1200),
graph_kwargs={'include_atom_index': False},
)
with self.assertRaises(TypeError):
tautomers = input_molecule.get_all_tautomers(
net_charge=0,
total_number_hydrogens=16,
enforce_octet_rule=True,
allow_radicals=False,
skeletal_rearrangements=[(1, 2, 3)],
)
tautomers = input_molecule.get_all_tautomers(
net_charge=0,
total_number_hydrogens=16,
enforce_octet_rule=True,
allow_radicals=False,
skeletal_rearrangements=[
(2, 10), (2, 8)
], # Bonds ('C13', 'O1') and ('C13', 'O3')
)
assert len(tautomers) == 53, len(tautomers)
for (n, molecule) in enumerate(tautomers, start=1):
molecule.name = input_molecule.name
molecule.write_graph(
'_tautomer_{0}'.format(n),
output_size=(1200, 1200),
graph_kwargs={
'include_atom_index': False,
'vertex_color_scheme': 'elements',
'vertex_label_template': ''
},
)
def test_example_porphyrin(self, use_ILP: bool = True) -> None:
with open('pdbs/tetraphenylporphyrin.pdb') as fh:
uncapped_molecule = molecule_from_pdb_str(
fh.read(),
name='porphyrin',
)
_, _, pos = uncapped_molecule.write_graph(
'input',
output_size=(1200, 1200),
graph_kwargs={'include_atom_index': False},
)
capped_molecule = getattr(uncapped_molecule,
CAPPING_FUNCTION_NAME)(debug=None)
capped_molecule.write_graph(
'output',
output_size=(1200, 1200),
graph_kwargs={'include_atom_index': False},
pos=None,
)
def test_radicals(self):
with open('pdbs/nitric_oxide.pdb') as fh:
input_molecule = molecule_from_pdb_str(
fh.read(),
name='nitric_oxide',
)
input_molecule.remove_all_hydrogens(mark_all_uncapped=True)
input_molecule.write_graph(
'input',
output_size=(600, 600),
graph_kwargs={'include_atom_index': False},
)
with self.assertRaises(Exception):
tautomers = input_molecule.get_all_tautomers(
net_charge=0,
total_number_hydrogens=0,
enforce_octet_rule=True,
allow_radicals=False,
)
tautomers = input_molecule.get_all_tautomers(
net_charge=0,
total_number_hydrogens=0,
enforce_octet_rule=False,
allow_radicals=True,
)
assert len(tautomers) == 1, len(tautomers)
for (n, molecule) in enumerate(tautomers, start=1):
molecule.name = input_molecule.name
molecule.write_graph(
'_tautomer_{0}'.format(n),
output_size=(600, 600),
graph_kwargs={'include_atom_index': True},
)
tautomer = tautomers[0]
assert list(tautomer.bond_orders.items()) == [2]
def test_guanidinium(self) -> None:
with open('pdbs/guanidinium.pdb') as fh:
input_molecule = molecule_from_pdb_str(
fh.read(),
name='guanidinium_fail',
)
input_molecule.assign_bond_orders_and_charges_with_ILP(
enforce_octet_rule=True,
debug=stderr,
)
input_molecule.write_graph(
'',
output_size=(400, 400),
graph_kwargs={
'include_atom_index': False,
'vertex_color_scheme': 'elements',
'vertex_label_template': '{charge_str}',
},
)
def test_capping_peptide(
peptide_pdb_filepath: str,
peptide_net_charge: int,
peptide_number_hydrogens: Optional[int] = None) -> None:
peptide_name, _ = basename(peptide_pdb_filepath).split('.')
with open(peptide_pdb_filepath) as fh:
input_molecule = molecule_from_pdb_str(
fh.read(),
name=peptide_name,
net_charge=peptide_net_charge,
)
molecule_copy = deepcopy(input_molecule)
molecule_copy.assign_bond_orders_and_charges_with_ILP()
old_formula, old_charge = molecule_copy.formula(
charge=True), molecule_copy.netcharge()
molecule_copy.write_graph('input',
graph_kwargs={
'include_atom_index': False,
'vertex_color_scheme': 'elements',
'vertex_label_template': '{charge_str}',
})
input_molecule.remove_atoms_with_predicate(
lambda atom: atom.element == 'H',
reset_valences=False,
renumber_atoms=False,
)
kept_atom_ids = [atom.index for atom in input_molecule.atoms.values()]
def enforce_valence_aromatic_rings() -> None:
molecule_copy.assign_aromatic_bonds()
aromatic_atom_ids = {
atom_id
for atom_id in reduce(
lambda acc, e: acc | set(e),
molecule_copy.aromatic_rings,
set(),
)
}
input_molecule.atoms = {
atom_id: atom if (not atom.capped and atom_id in aromatic_atom_ids)
else atom._replace(valence=None)
for (atom_id, atom) in input_molecule.atoms.items()
}
enforce_valence_aromatic_rings()
now = datetime.now()
new_molecule = input_molecule.get_best_capped_molecule_with_ILP(
enforce_octet_rule=True,
net_charge=old_charge,
number_hydrogens=peptide_number_hydrogens,
)
print((datetime.now() - now).total_seconds())
new_formula = new_molecule.formula(charge=True)
print(
new_molecule.write_graph(
'capped',
graph_kwargs={
'include_atom_index': False,
'vertex_color_scheme': 'elements',
'vertex_label_template': '{charge_str}',
},
))
with open(peptide_pdb_filepath.replace('.pdb', '_capped.pdb'), 'wt') as fh:
fh.write(new_molecule.dummy_pdb())
print(compare_capped_molecules(molecule_copy, new_molecule, kept_atom_ids))
assert old_formula == new_formula, (old_formula, new_formula,
compare_capped_molecules(
molecule_copy, new_molecule,
kept_atom_ids))
CONECT 5 4
CONECT 6 4
CONECT 7 4
END''',
}
OPTIONS = {
'warfarin': {
'total_number_hydrogens': 16,
'net_charge': 0
},
}
if __name__ == '__main__':
for (molecule_name, pdb_str) in PDBS.items():
molecule = molecule_from_pdb_str(pdb_str, name=molecule_name)
if molecule.name in {'warfarin'}:
print(
molecule.get_all_tautomers(
**OPTIONS[molecule_name] if molecule_name in
OPTIONS else {}))
else:
print(
molecule.assign_bond_orders_and_charges_with_ILP(
enforce_octet_rule=True))
print(
molecule.write_graph(molecule_name,
output_size=(int(2100 / 1.5),
int(2970 / 1.5))))
if molecule_name == 'warfarin':
print(molecule)
