def test_max_reduction(smiles):
"""
starting from a single atom with no layers,
you should get [*:1] in a minimum of 7 steps
"""
mol = mol_toolkit.Mol.from_smiles(smiles)
cluster_lists = [('1', [[(0, )]])]
# create reducer
red = SMIRKSifier([mol], cluster_lists, max_layers=0)
smirks_list = red.reduce(10)
final_smirks = smirks_list[0][1]
assert final_smirks == '[*:1]'
def test_more_complex_reducer():
"""
Check that all SMIRKSifier class functions at least work
"""
smiles = ['CC', 'C=C', 'C#C']
mols = [mol_toolkit.Mol.from_smiles(s) for s in smiles]
c1 = [[(0, 1)]] * len(smiles)
c2 = [[(0, 2)]] * len(smiles)
cluster_lists = [('1', c1), ('2', c2)]
# create reducer
red = SMIRKSifier(mols, cluster_lists, verbose=False)
# make sure printing runs:
print_smirks(red.current_smirks)
# run for a long time (assumed to hit all possible methods)
smirks_list = red.reduce(2000)
def test_complex_clusters(mol_file, frag):
# load molecules and set aromaticity
mols_list = mols_from_mol2(mol_file)
for m in mols_list:
m.set_aromaticity_mdl()
# load smirks list
smirks_list = parse_smarts_file("%s_smirks.smarts" % frag)
# type molecules with these smirks
clusters = create_tuples_for_clusters(smirks_list, mols_list)
# smirksify these clusters
create_frag = SMIRKSifier(mols_list, clusters, verbose=False, max_layers=2)
# try reducing these SMIRKS
create_frag.reduce(10)
def test_layer_choice(layers):
mol1 = mol_toolkit.Mol.from_smiles('CCC')
mol2 = mol_toolkit.Mol.from_smiles('CCCC')
# cluster 1 has bond 0-1 in mol1
# cluster 2 has bond 0-1 and 2-3 in mol2
# this should always need 1 layer to work
clusters = [('1', [[(0, 1)], []]), ('2', [[], [(0, 1), (2, 3)]])]
red = SMIRKSifier([mol1, mol2], clusters, max_layers=layers)
assert red.layers == 1
def test_failed_layers():
mol1 = mol_toolkit.Mol.from_smiles('CCC')
mol2 = mol_toolkit.Mol.from_smiles('CCCC')
# cluster 1 has bond 0-1 in mol1
# cluster 2 has bond 0-1 and 2-3 in mol2
# the only way to distinguish these is
# with more than 1 layer so max_layers = 0 will fail
clusters = [('1', [[(0, 1)], []]), ('2', [[], [(0, 1), (3, 2)]])]
with pytest.raises(ClusteringError):
red = SMIRKSifier([mol1, mol2], clusters, max_layers=0)
print(red.current_smirks)
print_smirks(red.current_smirks)
from chemper.mol_toolkits.mol_toolkit import Mol
from chemper.smirksify import SMIRKSifier, print_smirks
# make molecules from smiles
mols = [Mol.from_smiles('CCO'), Mol.from_smiles('CC=C')]
# make clusters for each of the 6 bond types:
# carbon-carbon single bond 1 ethanol, 1 propene
cc_single = ('cc_single', [[(0, 1)], [(0, 1)]])
# carbon-carbon double bond 0 ethanol, 1 propene
cc_double = ('cc_double', [[], [(1, 2)]])
# carbon-oxygen bond 1 ethanol, 0 propene
co = ('co', [[(1, 2)], []])
# hydrogen-tetrahedral carbon 5 ethanol, 3 propene
hc_tet = ('hc_tet', [[(0, 3), (0, 4), (0, 5), (1, 6), (1, 7)],
[(0, 3), (0, 4), (0, 5)]])
# hydrogen-planar carbon bond 0 ethanol, 3 propene
hc_plan = ('hc_plan', [[], [(1, 6), (2, 7), (2, 8)]])
# hydrogen-oxygen bond 1 ethanol, 0 propene
ho = ('ho', [[(2, 8)], []])
# initiate SMIRKSifier with default max_layers = 5 and verbose = True
fier = SMIRKSifier(mols, [cc_single, cc_double, co, hc_tet, hc_plan, ho])
# print initial SMIRKS
print_smirks(fier.current_smirks)
# Reduce SMIRKS with default 1000 iterations
fier.reduce()
# print final SMIRKS
print_smirks(fier.current_smirks)