def check_database(self, mols=None, filename=None):
"""
Check database contents.
Parameters
----------
mols : list, optional
Molecules that should be in the database. Defaults to self.mols.
filename : str, optional
Existing database filename.
"""
if mols is None:
mols = self.mols
if filename is not None:
database = MoleculeDatabase()
database.load(filename)
else:
database = self.database
# check for appropriate length
assert len(database) == len(mols)
# check that SMILES are what we expect
for mol in mols:
assert database.engine.get_smiles(mol) in database
def check_database(self, mols=None, filename=None):
"""
Check database contents.
Parameters
----------
mols : list, optional
Molecules that should be in the database. Defaults to self.mols.
filename : str, optional
Existing database filename.
"""
if mols is None:
mols = self.mols
if filename is not None:
database = MoleculeDatabase()
database.load(filename)
else:
database = self.database
# check for appropriate length
assert len(database) == len(mols)
# check that SMILES are what we expect
for mol in mols:
assert database.engine.get_smiles(mol) in database
def test_update(self):
"""
Test updating an existing database.
"""
_, database_filename = tempfile.mkstemp(dir=self.temp_dir)
database = MoleculeDatabase()
database.add_mol(self.mols[0])
database.save(database_filename)
self.check_output(["-i", self.input_filename, "-o", self.output_filename, "-d", database_filename])
def check_output(self, input_args):
"""
Run main and examine the resulting database.
Parameters
----------
args : list
Command-line arguments.
"""
args = parse_args(input_args)
main(args.input, args.output, args.database, args.stereo_from_3d)
database = MoleculeDatabase()
database.load(args.output)
assert len(database) == len(self.mols)
return database
def check_output(self, input_args):
"""
Run main and examine the resulting database.
Parameters
----------
args : list
Command-line arguments.
"""
args = parse_args(input_args)
main(args.input, args.output, args.database, args.stereo_from_3d)
database = MoleculeDatabase()
database.load(args.output)
assert len(database) == len(self.mols)
return database
def get_smiles(filename, assign_stereo_from_3d=False):
"""
Get SMILES for molecules.
Parameters
----------
filename : str
Input molecule filename.
assign_stereo_from_3d : bool, optional (default False)
Assign stereochemistry from 3D coordinates.
"""
database = MoleculeDatabase(assign_stereo_from_3d=assign_stereo_from_3d)
with serial.MolReader().open(filename) as reader:
for mol in reader:
database.add_mol(mol)
return list(database.smiles)
def get_smiles(filename, assign_stereo_from_3d=False):
"""
Get SMILES for molecules.
Parameters
----------
filename : str
Input molecule filename.
assign_stereo_from_3d : bool, optional (default False)
Assign stereochemistry from 3D coordinates.
"""
database = MoleculeDatabase(assign_stereo_from_3d=assign_stereo_from_3d)
with serial.MolReader().open(filename) as reader:
for mol in reader:
database.add_mol(mol)
return list(database.smiles)
def setUp(self):
"""
Set up tests.
"""
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.cids = [2244, 3672, 2662]
self.mols = []
for s, n in zip(smiles, names):
mol = Chem.MolFromSmiles(s)
mol.SetProp('_Name', n)
self.mols.append(mol)
self.temp_dir = tempfile.mkdtemp()
self.database = MoleculeDatabase()
def test_update(self):
"""
Test updating an existing database.
"""
_, database_filename = tempfile.mkstemp(dir=self.temp_dir)
database = MoleculeDatabase()
database.add_mol(self.mols[0])
database.save(database_filename)
self.check_output([
'-i', self.input_filename, '-o', self.output_filename, '-d',
database_filename
])
def setUp(self):
"""
Set up tests.
"""
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.cids = [2244, 3672, 2662]
self.mols = []
for s, n in zip(smiles, names):
mol = Chem.MolFromSmiles(s)
mol.SetProp("_Name", n)
self.mols.append(mol)
self.temp_dir = tempfile.mkdtemp()
self.database = MoleculeDatabase()
def main(input_filenames,
output_filename,
database_filename=None,
assign_stereo_from_3d=False):
"""
Update or create a molecule database.
Parameters
----------
input_filenames : list
Input molecule filename(s).
output_filename : str
Output filename.
database_filename : str, optional
Existing database to update.
assign_stereo_from_3d : bool, optional (default False)
Whether to assign stereochemistry from 3D coordinates.
"""
database = MoleculeDatabase(assign_stereo_from_3d=assign_stereo_from_3d)
if database_filename is not None:
database.load(database_filename)
initial_size = len(database)
for filename in input_filenames:
print filename
with serial.MolReader().open(filename) as reader:
for mol in reader:
try:
database.add_mol(mol)
except ValueError:
if mol.HasProp('_Name'):
print 'Skipping {}'.format(mol.GetProp('_Name'))
else:
print 'Skipping {}'.format(
Chem.MolToSmiles(mol, isomericSmiles=True))
final_size = len(database)
print '{} molecules added to the database'.format(final_size -
initial_size)
database.save(output_filename)
def main(input_filenames, output_filename, database_filename=None,
assign_stereo_from_3d=False):
"""
Update or create a molecule database.
Parameters
----------
input_filenames : list
Input molecule filename(s).
output_filename : str
Output filename.
database_filename : str, optional
Existing database to update.
assign_stereo_from_3d : bool, optional (default False)
Whether to assign stereochemistry from 3D coordinates.
"""
database = MoleculeDatabase(assign_stereo_from_3d=assign_stereo_from_3d)
if database_filename is not None:
database.load(database_filename)
initial_size = len(database)
for filename in input_filenames:
print filename
with serial.MolReader().open(filename) as reader:
for mol in reader:
try:
database.add_mol(mol)
except ValueError:
if mol.HasProp('_Name'):
print 'Skipping {}'.format(mol.GetProp('_Name'))
else:
print 'Skipping {}'.format(
Chem.MolToSmiles(mol, isomericSmiles=True))
final_size = len(database)
print '{} molecules added to the database'.format(
final_size - initial_size)
database.save(output_filename)
class TestMoleculeDatabase(unittest.TestCase):
"""
Tests for MoleculeDatabase.
"""
def setUp(self):
"""
Set up tests.
"""
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.cids = [2244, 3672, 2662]
self.mols = []
for s, n in zip(smiles, names):
mol = Chem.MolFromSmiles(s)
mol.SetProp("_Name", n)
self.mols.append(mol)
self.temp_dir = tempfile.mkdtemp()
self.database = MoleculeDatabase()
def tearDown(self):
"""
Clean up tests.
"""
shutil.rmtree(self.temp_dir)
def check_database(self, mols=None, filename=None):
"""
Check database contents.
Parameters
----------
mols : list, optional
Molecules that should be in the database. Defaults to self.mols.
filename : str, optional
Existing database filename.
"""
if mols is None:
mols = self.mols
if filename is not None:
database = MoleculeDatabase()
database.load(filename)
else:
database = self.database
# check for appropriate length
assert len(database) == len(mols)
# check that SMILES are what we expect
for mol in mols:
assert database.engine.get_smiles(mol) in database
def test_load(self):
"""
Test MoleculeDatabase.load.
"""
_, filename = tempfile.mkstemp(dir=self.temp_dir)
with open(filename, "wb") as f:
f.write("{}\n".format(self.database.engine.get_smiles(self.mols[0])))
self.check_database([self.mols[0]], filename)
def test_load_gz(self):
"""
Test MoleculeDatabase.load with gzipped input.
"""
_, filename = tempfile.mkstemp(dir=self.temp_dir, suffix=".gz")
with gzip.open(filename, "wb") as f:
f.write("{}\n".format(self.database.engine.get_smiles(self.mols[0])))
self.check_database([self.mols[0]], filename)
def test_load_bogus(self):
"""
Test failure on loading a bogus dataset.
"""
_, filename = tempfile.mkstemp(dir=self.temp_dir)
with open(filename, "wb") as f:
f.write("bogus\n")
try:
self.database.load(filename)
raise AssertionError
except ValueError:
pass
def test_save(self):
"""
Test MoleculeDatabase.save.
"""
_, filename = tempfile.mkstemp(dir=self.temp_dir)
for mol in self.mols:
self.database.add_mol(mol)
self.database.save(filename)
self.check_database(filename=filename)
with open(filename) as f:
assert len(f.readlines()) == len(self.mols)
def test_save_gz(self):
"""
Test MoleculeDatabase.save with gzipped output.
"""
_, filename = tempfile.mkstemp(dir=self.temp_dir, suffix=".gz")
for mol in self.mols:
self.database.add_mol(mol)
self.database.save(filename)
self.check_database(filename=filename)
with gzip.open(filename) as f:
assert len(f.readlines()) == len(self.mols)
def test_add_mol(self):
"""
Test MoleculeDatabase.add_mol.
"""
for mol in self.mols:
self.database.add_mol(mol)
self.check_database()
def test_add_mol_duplicate(self):
"""
Test MoleculeDatabase.add_mol with a duplicate molecule.
"""
for mol in self.mols: # add once
self.database.add_mol(mol)
for mol in self.mols: # add twice
self.database.add_mol(mol)
self.check_database()
class TestMoleculeDatabase(unittest.TestCase):
"""
Tests for MoleculeDatabase.
"""
def setUp(self):
"""
Set up tests.
"""
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.cids = [2244, 3672, 2662]
self.mols = []
for s, n in zip(smiles, names):
mol = Chem.MolFromSmiles(s)
mol.SetProp('_Name', n)
self.mols.append(mol)
self.temp_dir = tempfile.mkdtemp()
self.database = MoleculeDatabase()
def tearDown(self):
"""
Clean up tests.
"""
shutil.rmtree(self.temp_dir)
def check_database(self, mols=None, filename=None):
"""
Check database contents.
Parameters
----------
mols : list, optional
Molecules that should be in the database. Defaults to self.mols.
filename : str, optional
Existing database filename.
"""
if mols is None:
mols = self.mols
if filename is not None:
database = MoleculeDatabase()
database.load(filename)
else:
database = self.database
# check for appropriate length
assert len(database) == len(mols)
# check that SMILES are what we expect
for mol in mols:
assert database.engine.get_smiles(mol) in database
def test_load(self):
"""
Test MoleculeDatabase.load.
"""
_, filename = tempfile.mkstemp(dir=self.temp_dir)
with open(filename, 'wb') as f:
f.write('{}\n'.format(self.database.engine.get_smiles(
self.mols[0])))
self.check_database([self.mols[0]], filename)
def test_load_gz(self):
"""
Test MoleculeDatabase.load with gzipped input.
"""
_, filename = tempfile.mkstemp(dir=self.temp_dir, suffix='.gz')
with gzip.open(filename, 'wb') as f:
f.write('{}\n'.format(self.database.engine.get_smiles(
self.mols[0])))
self.check_database([self.mols[0]], filename)
def test_load_bogus(self):
"""
Test failure on loading a bogus dataset.
"""
_, filename = tempfile.mkstemp(dir=self.temp_dir)
with open(filename, 'wb') as f:
f.write('bogus\n')
try:
self.database.load(filename)
raise AssertionError
except ValueError:
pass
def test_save(self):
"""
Test MoleculeDatabase.save.
"""
_, filename = tempfile.mkstemp(dir=self.temp_dir)
for mol in self.mols:
self.database.add_mol(mol)
self.database.save(filename)
self.check_database(filename=filename)
with open(filename) as f:
assert len(f.readlines()) == len(self.mols)
def test_save_gz(self):
"""
Test MoleculeDatabase.save with gzipped output.
"""
_, filename = tempfile.mkstemp(dir=self.temp_dir, suffix='.gz')
for mol in self.mols:
self.database.add_mol(mol)
self.database.save(filename)
self.check_database(filename=filename)
with gzip.open(filename) as f:
assert len(f.readlines()) == len(self.mols)
def test_add_mol(self):
"""
Test MoleculeDatabase.add_mol.
"""
for mol in self.mols:
self.database.add_mol(mol)
self.check_database()
def test_add_mol_duplicate(self):
"""
Test MoleculeDatabase.add_mol with a duplicate molecule.
"""
for mol in self.mols: # add once
self.database.add_mol(mol)
for mol in self.mols: # add twice
self.database.add_mol(mol)
self.check_database()