def setUp(self):
"""
Set up tests.
"""
self.temp_dir = tempfile.mkdtemp()
self.map = {
'CID645443':
'Cc1ccc(-n2c3c(cc(C(=O)Nc4cccc(C)n4)c2=O)C(=O)CCC3)cc1',
'CID2997889': 'CC(C)(C)C(=O)Nc1ccc(-c2cn3ccsc3n2)cc1',
'CID2244': 'CC(=O)Oc1ccccc1C(=O)O',
'CID2662': 'Cc1ccc(-c2cc(C(F)(F)F)nn2-c2ccc(S(N)(=O)=O)cc2)cc1',
'CID3672': 'CC(C)Cc1ccc(C(C)C(=O)O)cc1'
}
_, self.map_filename = tempfile.mkstemp(dir=self.temp_dir,
suffix='.pkl')
write_pickle(self.map, self.map_filename)
# use a subset of AID588342
# note that CID 654924 is duplicated
this_dir = os.path.split(os.path.realpath(__file__))[0]
self.data_filename = os.path.join(this_dir, 'data/test_pcba_data.csv')
# set up parser
# settings match PcbaParser defaults
self.engine = AssayDataParser(self.data_filename,
self.map_filename,
delimiter=',',
primary_key='PUBCHEM_CID',
activity_key='PUBCHEM_ACTIVITY_OUTCOME',
activity_value='Active',
id_prefix='CID')
def setUp(self):
"""
Set up tests.
"""
self.temp_dir = tempfile.mkdtemp()
self.map = {
"CID645443": "Cc1ccc(-n2c3c(cc(C(=O)Nc4cccc(C)n4)c2=O)C(=O)CCC3)cc1",
"CID2997889": "CC(C)(C)C(=O)Nc1ccc(-c2cn3ccsc3n2)cc1",
"CID2244": "CC(=O)Oc1ccccc1C(=O)O",
"CID2662": "Cc1ccc(-c2cc(C(F)(F)F)nn2-c2ccc(S(N)(=O)=O)cc2)cc1",
"CID3672": "CC(C)Cc1ccc(C(C)C(=O)O)cc1",
}
_, self.map_filename = tempfile.mkstemp(dir=self.temp_dir, suffix=".pkl")
write_pickle(self.map, self.map_filename)
# use a subset of AID588342
# note that CID 654924 is duplicated
this_dir = os.path.split(os.path.realpath(__file__))[0]
self.data_filename = os.path.join(this_dir, "data/test_pcba_data.csv")
# set up parser
# settings match PcbaParser defaults
self.engine = AssayDataParser(
self.data_filename,
self.map_filename,
delimiter=",",
primary_key="PUBCHEM_CID",
activity_key="PUBCHEM_ACTIVITY_OUTCOME",
activity_value="Active",
id_prefix="CID",
)
class TestAssayDataParser(unittest.TestCase):
"""
Tests for AssayDataParser.
"""
def setUp(self):
"""
Set up tests.
"""
self.temp_dir = tempfile.mkdtemp()
self.map = {
'CID645443':
'Cc1ccc(-n2c3c(cc(C(=O)Nc4cccc(C)n4)c2=O)C(=O)CCC3)cc1',
'CID2997889': 'CC(C)(C)C(=O)Nc1ccc(-c2cn3ccsc3n2)cc1',
'CID2244': 'CC(=O)Oc1ccccc1C(=O)O',
'CID2662': 'Cc1ccc(-c2cc(C(F)(F)F)nn2-c2ccc(S(N)(=O)=O)cc2)cc1',
'CID3672': 'CC(C)Cc1ccc(C(C)C(=O)O)cc1'
}
_, self.map_filename = tempfile.mkstemp(dir=self.temp_dir,
suffix='.pkl')
write_pickle(self.map, self.map_filename)
# use a subset of AID588342
# note that CID 654924 is duplicated
this_dir = os.path.split(os.path.realpath(__file__))[0]
self.data_filename = os.path.join(this_dir, 'data/test_pcba_data.csv')
# set up parser
# settings match PcbaParser defaults
self.engine = AssayDataParser(self.data_filename,
self.map_filename,
delimiter=',',
primary_key='PUBCHEM_CID',
activity_key='PUBCHEM_ACTIVITY_OUTCOME',
activity_value='Active',
id_prefix='CID')
def tearDown(self):
"""
Clean up tests.
"""
shutil.rmtree(self.temp_dir)
def test_read_data(self):
"""
Test AssayDataParser.read_data.
"""
data = self.engine.read_data()
assert data.shape[0] == 4 # CID 654924 is duplicated
assert np.array_equal(data.PUBCHEM_CID,
[645443, 645449, 654924, 2997889])
def test_map_ids_to_smiles(self):
"""
Test AssayDataParser.map_ids_to_smiles.
"""
data = self.engine.read_data()
id_map = read_pickle(self.map_filename)
smiles, indices = self.engine.map_ids_to_smiles(
data.PUBCHEM_CID, id_map)
assert len(smiles) == len(indices) == 2
assert smiles[0] == self.map['CID645443']
assert smiles[1] == self.map['CID2997889']
assert np.array_equal(indices, [0, 3])
class TestAssayDataParser(unittest.TestCase):
"""
Tests for AssayDataParser.
"""
def setUp(self):
"""
Set up tests.
"""
self.temp_dir = tempfile.mkdtemp()
self.map = {
"CID645443": "Cc1ccc(-n2c3c(cc(C(=O)Nc4cccc(C)n4)c2=O)C(=O)CCC3)cc1",
"CID2997889": "CC(C)(C)C(=O)Nc1ccc(-c2cn3ccsc3n2)cc1",
"CID2244": "CC(=O)Oc1ccccc1C(=O)O",
"CID2662": "Cc1ccc(-c2cc(C(F)(F)F)nn2-c2ccc(S(N)(=O)=O)cc2)cc1",
"CID3672": "CC(C)Cc1ccc(C(C)C(=O)O)cc1",
}
_, self.map_filename = tempfile.mkstemp(dir=self.temp_dir, suffix=".pkl")
write_pickle(self.map, self.map_filename)
# use a subset of AID588342
# note that CID 654924 is duplicated
this_dir = os.path.split(os.path.realpath(__file__))[0]
self.data_filename = os.path.join(this_dir, "data/test_pcba_data.csv")
# set up parser
# settings match PcbaParser defaults
self.engine = AssayDataParser(
self.data_filename,
self.map_filename,
delimiter=",",
primary_key="PUBCHEM_CID",
activity_key="PUBCHEM_ACTIVITY_OUTCOME",
activity_value="Active",
id_prefix="CID",
)
def tearDown(self):
"""
Clean up tests.
"""
shutil.rmtree(self.temp_dir)
def test_read_data(self):
"""
Test AssayDataParser.read_data.
"""
data = self.engine.read_data()
assert data.shape[0] == 4 # CID 654924 is duplicated
assert np.array_equal(data.PUBCHEM_CID, [645443, 645449, 654924, 2997889])
def test_map_ids_to_smiles(self):
"""
Test AssayDataParser.map_ids_to_smiles.
"""
data = self.engine.read_data()
id_map = read_pickle(self.map_filename)
smiles, indices = self.engine.map_ids_to_smiles(data.PUBCHEM_CID, id_map)
assert len(smiles) == len(indices) == 2
assert smiles[0] == self.map["CID645443"]
assert smiles[1] == self.map["CID2997889"]
assert np.array_equal(indices, [0, 3])
