def setUp(self):
enum = ScoringFunctionComponentNameEnum()
predictive_property = create_predictive_property_component_regression()
activity = create_activity_component_regression()
qed_score = ComponentParameters(component_type=enum.QED_SCORE,
name="qed_score_name",
weight=1.,
smiles=[],
model_path="",
specific_parameters={})
custom_alerts = ComponentParameters(component_type=enum.CUSTOM_ALERTS,
name="custom_alerts_name",
weight=1.,
smiles=["CCCOOO"],
model_path="",
specific_parameters={})
matching_substructure = ComponentParameters(
component_type=enum.MATCHING_SUBSTRUCTURE,
name="matching_substructure_name",
weight=1.,
smiles=["*CCC"],
model_path="",
specific_parameters={})
self.sf_instance = CustomSum(parameters=[
activity, qed_score, custom_alerts, matching_substructure,
predictive_property
])
class Test_custom_sum(unittest.TestCase):
def setUp(self):
enum = ScoringFunctionComponentNameEnum()
predictive_property = create_predictive_property_component_regression()
activity = create_activity_component_regression()
qed_score = ComponentParameters(component_type=enum.QED_SCORE,
name="qed_score_name",
weight=1.,
smiles=[],
model_path="",
specific_parameters={})
custom_alerts = ComponentParameters(component_type=enum.CUSTOM_ALERTS,
name="custom_alerts_name",
weight=1.,
smiles=["CCCOOO"],
model_path="",
specific_parameters={})
matching_substructure = ComponentParameters(component_type=enum.MATCHING_SUBSTRUCTURE,
name="matching_substructure_name",
weight=1.,
smiles=["*CCC"],
model_path="",
specific_parameters={})
self.sf_instance = CustomSum(
parameters=[activity, qed_score, custom_alerts, matching_substructure, predictive_property])
def test_special_selectivity_multiplicative_no_sigm_trans_1(self):
score = self.sf_instance.get_final_score(smiles=["O=S(=O)(c3ccc(n1nc(cc1c2ccc(cc2)C)C(F)(F)F)cc3)N"])
self.assertAlmostEqual(score.total_score[0], 0.3631, 3)
def test_special_selectivity_multiplicative_no_sigm_trans_3(self):
score = self.sf_instance.get_final_score(smiles=["CCCOOOCCCOOO"])
self.assertEqual(score.total_score, 0)
def setUpClass(self):
sf_enum = ScoringFunctionComponentNameEnum()
csp_enum = ComponentSpecificParametersEnum()
ts_parameters = ComponentParameters(
component_type=sf_enum.NUM_HBD_LIPINSKI,
name="NumHBD_Lipinski",
weight=1.,
smiles=[],
model_path="",
specific_parameters={csp_enum.TRANSFORMATION: False})
self.sf_state = CustomSum(parameters=[ts_parameters])
def setUpClass(self):
sf_enum = ScoringFunctionComponentNameEnum()
csp_enum = ComponentSpecificParametersEnum()
ts_parameters = ComponentParameters(
component_type=sf_enum.NUM_ROTATABLE_BONDS,
name="NumRotatableBonds",
weight=1.,
smiles=[],
model_path="",
specific_parameters={csp_enum.TRANSFORMATION: False})
self.sf_state = CustomSum(parameters=[ts_parameters])
def setUpClass(self):
sf_enum = ScoringFunctionComponentNameEnum()
csp_enum = ComponentSpecificParametersEnum()
ts_parameters = ComponentParameters(
component_type=sf_enum.MOLECULAR_WEIGHT,
name="MW",
weight=1.,
smiles=[],
model_path="",
specific_parameters={csp_enum.TRANSFORMATION: False})
self.sf_state = CustomSum(parameters=[ts_parameters])
def setUpClass(self):
sf_enum = ScoringFunctionComponentNameEnum()
utils_general.set_default_device_cuda()
self.log_path = MAIN_TEST_PATH
if not os.path.isdir(self.log_path):
os.makedirs(self.log_path)
smiles = np.array(['CCC', 'CCCC', 'CCCCCC'])
score = [0, 0.5, 1.]
prior_likelihood = ts.tensor([0, 10, 100])
prior = Model.load_from_file(RANDOM_PRIOR_PATH)
config = InceptionConfiguration(smiles=smiles,
memory_size=4,
sample_size=4)
scoring = ComponentParameters(
component_type=sf_enum.JACCARD_DISTANCE,
name="jaccard_distance",
weight=1.,
smiles=[
"CONN", "O=S(=O)(c3ccc(n1nc(cc1c2ccc(cc2)C)C(F)(F)F)cc3)N"
],
model_path="",
specific_parameters={})
scoringfunction = CustomSum(parameters=[scoring])
self.inception_model = Inception(configuration=config,
scoring_function=scoringfunction,
prior=prior)
self.inception_model.add(smiles, score, prior_likelihood)
class Test_tpsa_score_with_double_sigmoid(unittest.TestCase):
@classmethod
def setUpClass(self):
sf_enum = ScoringFunctionComponentNameEnum()
csp_enum = ComponentSpecificParametersEnum()
tt_enum = TransformationTypeEnum()
specific_parameters = {
csp_enum.TRANSFORMATION: True,
csp_enum.LOW: 2,
csp_enum.HIGH: 5,
csp_enum.TRANSFORMATION_TYPE: tt_enum.STEP
}
ts_parameters = ComponentParameters(
component_type=sf_enum.NUM_ROTATABLE_BONDS,
name="NumRotatableBonds",
weight=1.,
smiles=[],
model_path="",
specific_parameters=specific_parameters)
self.sf_state = CustomSum(parameters=[ts_parameters])
def test_num_rot_1(self):
smiles = [
"OC(=O)P(=O)(O)O", "C12C3C4C1C5C2C3C45", '[NH4+].[Cl-]',
'n1cccc2ccccc12',
'O=S(=O)(c3ccc(n1nc(cc1c2ccc(cc2)C)C(F)(F)F)cc3)N'
]
values = np.array([0., 0., 0., 0., 1.])
score = self.sf_state.get_final_score(smiles=smiles)
npt.assert_array_equal(score.total_score, values)
class Test_tpsa_score_with_double_sigmoid(unittest.TestCase):
@classmethod
def setUpClass(self):
sf_enum = ScoringFunctionComponentNameEnum()
csp_enum = ComponentSpecificParametersEnum()
tt_enum = TransformationTypeEnum()
specific_parameters = {
csp_enum.TRANSFORMATION: True,
csp_enum.LOW: 0,
csp_enum.HIGH: 1,
csp_enum.TRANSFORMATION_TYPE: tt_enum.STEP
}
ts_parameters = ComponentParameters(
component_type=sf_enum.NUM_HBD_LIPINSKI,
name="NumHBD_Lipinski",
weight=1.,
smiles=[],
model_path="",
specific_parameters=specific_parameters)
self.sf_state = CustomSum(parameters=[ts_parameters])
def test_hbd_1(self):
smiles = ["C(=O)N", 'O=S(=O)(c3ccc(n1nc(cc1c2ccc(cc2)C)C(F)(F)F)cc3)N']
values = np.array([1.0, 1.0])
score = self.sf_state.get_final_score(smiles=smiles)
npt.assert_array_equal(score.total_score, values)
class Test_num_rings_score_no_transformation(unittest.TestCase):
@classmethod
def setUpClass(self):
sf_enum = ScoringFunctionComponentNameEnum()
csp_enum = ComponentSpecificParametersEnum()
ts_parameters = ComponentParameters(component_type=sf_enum.NUM_RINGS,
name="Number of Rings",
weight=1.,
smiles=[],
model_path="",
specific_parameters={
csp_enum.TRANSFORMATION: False
})
self.sf_state = CustomSum(parameters=[ts_parameters])
def test_num_rings_1(self):
smiles = [
"C1=CC2=C(C=C1)C1=CC=CC=C21",
"C12C3C4C1C5C2C3C45",
'[NH4+].[Cl-]',
'n1cccc2ccccc12',
'O=S(=O)(c3ccc(n1nc(cc1c2ccc(cc2)C)C(F)(F)F)cc3)N'
]
values = np.array([3., 6., 0., 2., 3.])
score = self.sf_state.get_final_score(smiles=smiles)
npt.assert_array_almost_equal(score.total_score, values, 2)
class Test_slogp_score_with_double_sigmoid(unittest.TestCase):
@classmethod
def setUpClass(self):
sf_enum = ScoringFunctionComponentNameEnum()
csp_enum = ComponentSpecificParametersEnum()
tt_enum = TransformationTypeEnum()
specific_parameters = {
csp_enum.TRANSFORMATION: True,
csp_enum.LOW: 1,
csp_enum.HIGH: 3,
csp_enum.COEF_DIV: 3,
csp_enum.COEF_SI: 10,
csp_enum.COEF_SE: 10,
csp_enum.TRANSFORMATION_TYPE: tt_enum.DOUBLE_SIGMOID
}
ts_parameters = ComponentParameters(
component_type=sf_enum.SLOGP,
name="SlogP",
weight=1.,
smiles=[],
model_path="",
specific_parameters=specific_parameters)
self.sf_state = CustomSum(parameters=[ts_parameters])
def test_slogp_1(self):
smiles = [
"OC(=O)P(=O)(O)O", "Cc1ccccc1N1C(=O)c2cc(S(N)(=O)=O)c(Cl)cc2NC1C",
"N12CC3C(=NC4C(C=3)=CC=CC=4)C1=CC1=C(COC(=O)C1(O)CC)C2=O",
"N12CC3C(=NC4C(C=3C(=O)O)=CC3=C(OCCO3)C=4)C1=CC1=C(COC(=O)C1(O)CC)C2=O",
"FC1C=CC(CC(=NS(=O)(=O)C2C=CC(C)=CC=2)N2CCN(CC3C4C(=CC=CC=4)N=C4C=3CN3C4=CC4=C(COC(=O)C4(O)CC)C3=O)CC2)=CC=1"
]
values = np.array([0.0, 0.9, 1.0, 1.0, 0.0])
score = self.sf_state.get_final_score(smiles=smiles)
npt.assert_array_almost_equal(score.total_score, values, 2)
class Test_tpsa_score_with_double_sigmoid(unittest.TestCase):
@classmethod
def setUpClass(self):
sf_enum = ScoringFunctionComponentNameEnum()
csp_enum = ComponentSpecificParametersEnum()
tt_enum = TransformationTypeEnum()
specific_parameters = {
csp_enum.TRANSFORMATION: True,
csp_enum.LOW: 0,
csp_enum.HIGH: 135,
csp_enum.COEF_DIV: 100,
csp_enum.COEF_SI: 200,
csp_enum.COEF_SE: 200,
csp_enum.TRANSFORMATION_TYPE: tt_enum.DOUBLE_SIGMOID
}
ts_parameters = ComponentParameters(
component_type=sf_enum.TPSA,
name="TPSA",
weight=1.,
smiles=[],
model_path="",
specific_parameters=specific_parameters)
self.sf_state = CustomSum(parameters=[ts_parameters])
def test_tpsa_1(self):
smiles = [
"OC(=O)P(=O)(O)O", "C12C3C4C1C5C2C3C45", '[NH4+].[Cl-]',
'n1cccc2ccccc12',
'O=S(=O)(c3ccc(n1nc(cc1c2ccc(cc2)C)C(F)(F)F)cc3)N'
]
values = np.array([1., 0.5, 1., 1., 1.])
score = self.sf_state.get_final_score(smiles=smiles)
npt.assert_array_almost_equal(score.total_score, values, 2)
def setUpClass(self):
sf_enum = ScoringFunctionComponentNameEnum()
csp_enum = ComponentSpecificParametersEnum()
tt_enum = TransformationTypeEnum()
specific_parameters = {
csp_enum.TRANSFORMATION: True,
csp_enum.LOW: 2,
csp_enum.HIGH: 5,
csp_enum.TRANSFORMATION_TYPE: tt_enum.STEP
}
ts_parameters = ComponentParameters(
component_type=sf_enum.NUM_ROTATABLE_BONDS,
name="NumRotatableBonds",
weight=1.,
smiles=[],
model_path="",
specific_parameters=specific_parameters)
self.sf_state = CustomSum(parameters=[ts_parameters])
def setUpClass(self):
sf_enum = ScoringFunctionComponentNameEnum()
csp_enum = ComponentSpecificParametersEnum()
tt_enum = TransformationTypeEnum()
specific_parameters = {
csp_enum.TRANSFORMATION: True,
csp_enum.LOW: 0,
csp_enum.HIGH: 1,
csp_enum.TRANSFORMATION_TYPE: tt_enum.STEP
}
ts_parameters = ComponentParameters(
component_type=sf_enum.NUM_HBD_LIPINSKI,
name="NumHBD_Lipinski",
weight=1.,
smiles=[],
model_path="",
specific_parameters=specific_parameters)
self.sf_state = CustomSum(parameters=[ts_parameters])
def setUpClass(self):
sf_enum = ScoringFunctionComponentNameEnum()
csp_enum = ComponentSpecificParametersEnum()
tt_enum = TransformationTypeEnum()
specific_parameters = {
csp_enum.TRANSFORMATION: True,
csp_enum.LOW: 0,
csp_enum.HIGH: 135,
csp_enum.COEF_DIV: 100,
csp_enum.COEF_SI: 200,
csp_enum.COEF_SE: 200,
csp_enum.TRANSFORMATION_TYPE: tt_enum.DOUBLE_SIGMOID
}
ts_parameters = ComponentParameters(
component_type=sf_enum.TPSA,
name="TPSA",
weight=1.,
smiles=[],
model_path="",
specific_parameters=specific_parameters)
self.sf_state = CustomSum(parameters=[ts_parameters])
def test_eval_add_2(self):
sf_enum = ScoringFunctionComponentNameEnum()
smiles = np.array(['CCC', 'CCCC', 'O=S(=O)(c3ccc(n1nc(cc1c2ccc(cc2)C)C(F)(F)F)cc3)N'])
scoring = ComponentParameters(component_type=sf_enum.TANIMOTO_SIMILARITY,
name="tanimoto_similarity",
weight=1.,
smiles=["CCC", "CC"],
model_path="",
specific_parameters={})
scoringfunction = CustomSum(parameters=[scoring])
prior = Model.load_from_file(RANDOM_PRIOR_PATH)
self.inception_model.evaluate_and_add(smiles, scoringfunction, prior)
self.assertEqual(len(self.inception_model.memory), 4)
nt.assert_almost_equal(np.array(self.inception_model.memory['score'].values),
np.array([0.96, 0.9412, 0.9286, 0.0345]), 4)
class Test_hbd_score_no_transformation(unittest.TestCase):
@classmethod
def setUpClass(self):
sf_enum = ScoringFunctionComponentNameEnum()
csp_enum = ComponentSpecificParametersEnum()
ts_parameters = ComponentParameters(
component_type=sf_enum.NUM_HBD_LIPINSKI,
name="NumHBD_Lipinski",
weight=1.,
smiles=[],
model_path="",
specific_parameters={csp_enum.TRANSFORMATION: False})
self.sf_state = CustomSum(parameters=[ts_parameters])
def test_hbd_1(self):
smiles = ["C(=O)N", 'O=S(=O)(c3ccc(n1nc(cc1c2ccc(cc2)C)C(F)(F)F)cc3)N']
values = np.array([1., 1.])
score = self.sf_state.get_final_score(smiles=smiles)
npt.assert_array_equal(score.total_score, values)
def test_empty_eval_add_1(self):
sf_enum = ScoringFunctionComponentNameEnum()
smiles = np.array(['CCC', 'CCCC', 'CC', 'COO'])
scoring = ComponentParameters(
component_type=sf_enum.TANIMOTO_SIMILARITY,
name="tanimoto_similarity",
weight=1.,
smiles=["CCC", "CC"],
model_path="",
specific_parameters={})
scoringfunction = CustomSum(parameters=[scoring])
prior = Model.load_from_file(RANDOM_PRIOR_PATH)
self.inception_model.evaluate_and_add(smiles, scoringfunction, prior)
self.assertEqual(len(self.inception_model.memory), 4)
nt.assert_almost_equal(
np.array(self.inception_model.memory['score'].values),
np.array([1, 1, 0.6667, 0.1250]), 4)
self.assertEqual(
len(np.array(self.inception_model.memory['likelihood'].values)), 4)
class Test_mw_score_no_transformation(unittest.TestCase):
@classmethod
def setUpClass(self):
sf_enum = ScoringFunctionComponentNameEnum()
csp_enum = ComponentSpecificParametersEnum()
ts_parameters = ComponentParameters(
component_type=sf_enum.MOLECULAR_WEIGHT,
name="MW",
weight=1.,
smiles=[],
model_path="",
specific_parameters={csp_enum.TRANSFORMATION: False})
self.sf_state = CustomSum(parameters=[ts_parameters])
def test_mw_1(self):
smiles = [
"[NH4+].[Cl-]", 'n1cccc2ccccc12',
'O=S(=O)(c3ccc(n1nc(cc1c2ccc(cc2)C)C(F)(F)F)cc3)N'
]
values = np.array([53.49, 129.16, 381.38])
score = self.sf_state.get_final_score(smiles=smiles)
npt.assert_array_almost_equal(score.total_score, values, 2)
class Test_tpsa_score_no_transformation(unittest.TestCase):
@classmethod
def setUpClass(self):
sf_enum = ScoringFunctionComponentNameEnum()
csp_enum = ComponentSpecificParametersEnum()
ts_parameters = ComponentParameters(
component_type=sf_enum.TPSA,
name="TPSA",
weight=1.,
smiles=[],
model_path="",
specific_parameters={csp_enum.TRANSFORMATION: False})
self.sf_state = CustomSum(parameters=[ts_parameters])
def test_tpsa_1(self):
smiles = [
"OC(=O)P(=O)(O)O", "C12C3C4C1C5C2C3C45", '[NH4+].[Cl-]',
'n1cccc2ccccc12',
'O=S(=O)(c3ccc(n1nc(cc1c2ccc(cc2)C)C(F)(F)F)cc3)N'
]
values = np.array([94.83, 0., 36.5, 12.89, 77.98])
score = self.sf_state.get_final_score(smiles=smiles)
npt.assert_array_almost_equal(score.total_score, values, 2)
class Test_slogp_score_no_transformation(unittest.TestCase):
@classmethod
def setUpClass(self):
sf_enum = ScoringFunctionComponentNameEnum()
csp_enum = ComponentSpecificParametersEnum()
ts_parameters = ComponentParameters(
component_type=sf_enum.SLOGP,
name="SlogP",
weight=1.,
smiles=[],
model_path="",
specific_parameters={csp_enum.TRANSFORMATION: False})
self.sf_state = CustomSum(parameters=[ts_parameters])
def test_slogp_1(self):
smiles = [
"OC(=O)P(=O)(O)O", "Cc1ccccc1N1C(=O)c2cc(S(N)(=O)=O)c(Cl)cc2NC1C",
"N12CC3C(=NC4C(C=3)=CC=CC=4)C1=CC1=C(COC(=O)C1(O)CC)C2=O",
"N12CC3C(=NC4C(C=3C(=O)O)=CC3=C(OCCO3)C=4)C1=CC1=C(COC(=O)C1(O)CC)C2=O",
"FC1C=CC(CC(=NS(=O)(=O)C2C=CC(C)=CC=2)N2CCN(CC3C4C(=CC=CC=4)N=C4C=3CN3C4=CC4=C(COC(=O)C4(O)CC)C3=O)CC2)=CC=1"
]
values = np.array([-0.1579, 2.71412, 2.0796, 1.549, 4.67482])
score = self.sf_state.get_final_score(smiles=smiles)
npt.assert_array_almost_equal(score.total_score, values, 2)
