def setUp(self):
"""
Set up tests.
"""
self.reader = serial.MolReader()
# generate molecules
smiles = [
'CC(=O)OC1=CC=CC=C1C(=O)O', 'CC(C)CC1=CC=C(C=C1)C(C)C(=O)O',
'CC1=CC=C(C=C1)C2=CC(=NN2C3=CC=C(C=C3)S(=O)(=O)N)C(F)(F)F'
]
names = ['aspirin', 'ibuprofen', 'celecoxib']
self.mols = []
for s, n in zip(smiles, names):
mol = Chem.MolFromSmiles(s)
mol.SetProp('_Name', n)
AllChem.Compute2DCoords(mol)
self.mols.append(mol)
# write molecules to file
self.temp_dir = tempfile.mkdtemp()
writer = serial.MolWriter()
_, self.filename = tempfile.mkstemp(dir=self.temp_dir,
suffix='.sdf.gz')
with writer.open(self.filename) as w:
w.write(self.mols)
self.sharder = DatasetSharder(filename=self.filename,
write_shards=False)
self.reader = serial.MolReader()
def test_chiral_scaffolds(self):
"""
Test chiral scaffold generation.
"""
# romosetron
mol = Chem.MolFromSmiles(
'CN1C=C(C2=CC=CC=C21)C(=O)[C@@H]3CCC4=C(C3)NC=N4')
mol.SetProp('_Name', 'romosetron')
AllChem.Compute2DCoords(mol)
self.mols[1] = mol
self.names[1] = 'romosetron'
self.smiles[1] = Chem.MolToSmiles(mol, isomericSmiles=True)
# write mols
_, self.input_filename = tempfile.mkstemp(suffix='.sdf',
dir=self.temp_dir)
writer = serial.MolWriter()
writer.open(self.input_filename)
writer.write(self.mols)
writer.close()
# run script w/o chiral scaffolds
data = self.check_output(['--scaffolds', 'circular'], (2, 2048))
achiral_scaffold = data['scaffolds'][1]
# run script w/ chiral scaffolds
data = self.check_output(
['--scaffolds', '--chiral-scaffolds', 'circular'], (2, 2048))
chiral_scaffold = data['scaffolds'][1]
assert achiral_scaffold != chiral_scaffold
def test_assign_stereo_from_3d(self):
"""
Test --stereo-from-3d.
"""
# generate conformers for ibuprofen
engine = conformers.ConformerGenerator()
mol = engine.generate_conformers(self.mols[1])
assert mol.GetNumConformers() > 0
self.mols[1] = mol
# rewrite input file
_, self.input_filename = tempfile.mkstemp(dir=self.temp_dir,
suffix='.sdf')
with serial.MolWriter().open(self.input_filename) as writer:
writer.write(self.mols)
# check for absence of chirality using default arguments
database = self.check_output(
['-i', self.input_filename, '-o', self.output_filename])
chiral = False
for smiles in database:
if '@' in smiles:
chiral = True
assert not chiral
# check for presence of chiraliy using --stereo-from-3d
database = self.check_output([
'-i', self.input_filename, '-o', self.output_filename,
'--stereo-from-3d'
])
chiral = False
for smiles in database:
if '@' in smiles:
chiral = True
assert chiral
def setUp(self):
"""
Set up for tests. Writes molecules and targets to files.
"""
self.temp_dir = tempfile.mkdtemp()
smiles = [
'CC(=O)OC1=CC=CC=C1C(=O)O', 'C[C@@H](C1=CC=C(C=C1)CC(C)C)C(=O)O'
]
self.names = ['aspirin', 'ibuprofen']
engine = conformers.ConformerGenerator(max_conformers=1)
self.mols = []
self.smiles = [] # use RDKit-generated SMILES
for i in xrange(len(smiles)):
mol = Chem.MolFromSmiles(smiles[i])
mol.SetProp('_Name', self.names[i])
self.mols.append(engine.generate_conformers(mol))
self.smiles.append(
Chem.MolToSmiles(mol, isomericSmiles=True, canonical=True))
# write mols
_, self.input_filename = tempfile.mkstemp(suffix='.sdf',
dir=self.temp_dir)
writer = serial.MolWriter()
writer.open(self.input_filename)
writer.write(self.mols)
writer.close()
# write targets
self.targets = [0, 1]
_, self.targets_filename = tempfile.mkstemp(suffix='.pkl',
dir=self.temp_dir)
write_pickle(self.targets, self.targets_filename)
def setUp(self):
"""
Add writer to inherited setup.
"""
super(TestMolWriter, self).setUp()
self.writer = serial.MolWriter()
self.aspirin_sdf = Chem.MolToMolBlock(self.aspirin)
self.aspirin_smiles = Chem.MolToSmiles(self.aspirin) + '\taspirin'
def test_stereo_sdf(self):
"""
Test stereochemistry preservation when writing to SDF.
"""
_, filename = tempfile.mkstemp(suffix='.sdf', dir=self.temp_dir)
writer = serial.MolWriter(stereo=True)
writer.open(filename)
writer.write([self.levalbuterol])
writer.close()
self.reader.open(filename)
mols = self.reader.get_mols()
assert mols.next().ToBinary() == self.levalbuterol.ToBinary()
def test_read_multiple_pickles(self):
"""
Test reading a file containing multiple pickles. This can occur if
MolWriter.write is called multiple times.
"""
_, filename = tempfile.mkstemp(suffix='.pkl', dir=self.temp_dir)
with serial.MolWriter().open(filename) as writer:
writer.write([self.aspirin])
writer.write([self.levalbuterol])
with self.reader.open(filename) as reader:
mols = list(reader)
assert len(mols) == 2
assert mols[0].ToBinary() == self.aspirin.ToBinary()
assert mols[1].ToBinary() == self.levalbuterol.ToBinary()
def test_stereo_smi(self):
"""
Test stereochemistry preservation when writing to SMILES.
"""
# FIXME avoid this and use self.levalbuterol.RemoveAllConformers()
ref_mol = Chem.MolFromSmiles(
Chem.MolToSmiles(self.levalbuterol, isomericSmiles=True))
_, filename = tempfile.mkstemp(suffix='.smi', dir=self.temp_dir)
writer = serial.MolWriter(stereo=True)
writer.open(filename)
writer.write([self.levalbuterol])
writer.close()
self.reader.open(filename)
mols = self.reader.get_mols()
assert mols.next().ToBinary() == ref_mol.ToBinary()
def test_stereo_to_3d(self):
"""
Test main with --stereo-to-3d.
"""
# generate conformers for ibuprofen
engine = conformers.ConformerGenerator()
self.mols[1] = engine.generate_conformers(self.mols[1])
assert self.mols[1].GetNumConformers() > 0
# rewrite actives file with 3D coordinates
_, self.active_filename = tempfile.mkstemp(dir=self.temp_dir,
suffix='.sdf')
with serial.MolWriter().open(self.active_filename) as writer:
for mol, y in zip(self.mols, self.y):
if y:
writer.write([self.mols[1]])
# check for absence of chirality using default arguments
smiles, targets = self.check_output([
'-a', self.active_filename, '-d', self.decoy_filename, '-o',
self.output_filename
])
chiral = False
for this_smiles in smiles:
if '@' in this_smiles:
chiral = True
assert not chiral
# update reference SMILES
self.engine = SmilesGenerator(assign_stereo_from_3d=True)
self.smiles[1] = self.engine.get_smiles(self.mols[1])
# check for presence of chiraliy using --stereo-from-3d
smiles, targets = self.check_output([
'-a', self.active_filename, '-d', self.decoy_filename, '-o',
self.output_filename, '--stereo-from-3d'
])
chiral = False
for this_smiles in smiles:
if '@' in this_smiles:
chiral = True
assert chiral
def test_collate_mols2(self):
"""
Test collate_mols where targets are pruned.
"""
# write targets
targets = {'names': ['aspirin', 'ibuprofen'], 'y': [0, 1]}
write_pickle(targets, self.targets_filename)
# write mols
writer = serial.MolWriter()
writer.open(self.input_filename)
writer.write([self.mols[0]])
writer.close()
# run script
self.check_output(['circular'], (1, 2048),
targets=[0],
names=['aspirin'],
smiles=[self.smiles[0]])
def test_no_stereo_smiles(self):
"""
Test stereochemistry removal when writing to SMILES.
"""
_, filename = tempfile.mkstemp(suffix='.smi', dir=self.temp_dir)
writer = serial.MolWriter(stereo=False)
writer.open(filename)
writer.write([self.levalbuterol])
writer.close()
self.reader.open(filename)
mols = self.reader.get_mols()
mol = mols.next()
# make sure the written molecule differs from the reference
assert mol.ToBinary() != self.levalbuterol.ToBinary()
# check again after removing stereochemistry
AllChem.RemoveStereochemistry(self.levalbuterol)
# FIXME get ToBinary test to work
# assert mol.ToBinary() == self.levalbuterol.ToBinary()
assert Chem.MolToSmiles(mol, isomericSmiles=True) == Chem.MolToSmiles(
self.levalbuterol, isomericSmiles=True)
def setUp(self):
"""
Set up tests.
"""
self.temp_dir = tempfile.mkdtemp()
self.mols = []
aspirin = Chem.MolFromSmiles('CC(=O)OC1=CC=CC=C1C(=O)O')
aspirin.SetProp('_Name', 'aspirin1')
aspirin.SetProp('NR-Aromatase', '0')
aspirin.SetProp('SR-ATAD5', '1')
aspirin.SetProp('NR-ER', '0')
aspirin.SetProp('SR-p53', '0')
aspirin.SetProp('NR-AhR', '1')
aspirin.SetProp('SR-ARE', '1')
aspirin.SetProp('Irrelevant', 'blah')
self.mols.append(aspirin)
ibuprofen = Chem.MolFromSmiles('CC(C)CC1=CC=C(C=C1)C(C)C(=O)O')
ibuprofen.SetProp('_Name', 'ibuprofen')
ibuprofen.SetProp('SR-ATAD5', '1')
ibuprofen.SetProp('NR-ER', '1')
ibuprofen.SetProp('SR-p53', '1')
ibuprofen.SetProp('NR-AhR', '1')
ibuprofen.SetProp('SR-ARE', '0')
ibuprofen.SetProp('Irrelevant', 'blah2')
self.mols.append(ibuprofen)
aspirin2 = Chem.MolFromSmiles('CC(=O)OC1=CC=CC=C1C(=O)O')
aspirin2.SetProp('_Name', 'aspirin2')
aspirin2.SetProp('SR-ATAD5', '0')
aspirin2.SetProp('NR-ER', '0')
aspirin2.SetProp('SR-p53', '0')
aspirin2.SetProp('NR-AhR', '1')
aspirin2.SetProp('SR-ARE', '1')
aspirin2.SetProp('Irrelevant', 'blah3')
self.mols.append(aspirin2)
aspirin3 = Chem.MolFromSmiles('CC(=O)OC1=CC=CC=C1C(=O)O')
aspirin3.SetProp('_Name', 'aspirin3')
aspirin3.SetProp('SR-ATAD5', '1')
aspirin3.SetProp('NR-ER', '0')
aspirin3.SetProp('SR-p53', '0')
aspirin3.SetProp('NR-AhR', '1')
aspirin3.SetProp('SR-ARE', '1')
aspirin3.SetProp('Irrelevant', 'blah4')
self.mols.append(aspirin3)
aspirin4 = Chem.MolFromSmiles('CC(=O)OC1=CC=CC=C1C(=O)O')
aspirin4.SetProp('_Name', 'aspirin4')
aspirin4.SetProp('SR-ATAD5', '0')
aspirin4.SetProp('NR-ER', '0')
aspirin4.SetProp('SR-p53', '1')
aspirin4.SetProp('NR-AhR', '0')
aspirin4.SetProp('SR-ARE', '1')
aspirin4.SetProp('Irrelevant', 'blah5')
self.mols.append(aspirin4)
self.smiles = [
Chem.MolToSmiles(mol, isomericSmiles=True) for mol in self.mols
]
# write input file
_, self.filename = tempfile.mkstemp(dir=self.temp_dir, suffix='.sdf')
with serial.MolWriter().open(self.filename) as writer:
writer.write(self.mols)
# set up parser
self.engine = Tox21Parser(self.filename)