def __init__(self, parameters: List[ComponentParameters], parallel=False):
self.component_enum = ScoringFunctionComponentNameEnum()
self.component_specific_parameters = ComponentSpecificParametersEnum()
factory = ScoreComponentFactory(parameters)
self.scoring_components = factory.create_score_components()
if parallel:
self.get_final_score = self._parallel_final_score
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 setUp(self):
self.scaffold_enum = ScaffoldFilterEnum()
self.sf_enum = ScoringFunctionComponentNameEnum()
self.workfolders = [MAIN_TEST_PATH]
# create a scaffold filter and fill it with a few entries
smiles = [
"O=S(=O)(c3ccc(n1nc(cc1c2ccc(cc2)C)C(F)(F)F)cc3)N", "CCC", "CCCCC",
"CC"
]
scores = np.array([1.0, 0.5, 0.4, 0.3])
valid_idx = [0, 1, 2, 3]
component_parameters = ComponentParameters(
component_type=self.sf_enum.TANIMOTO_SIMILARITY,
name="tanimoto_similarity",
weight=1.,
smiles=smiles,
model_path="",
specific_parameters={})
component_score_summary = ComponentSummary(scores,
component_parameters)
final_summary = FinalSummary(scores, smiles, valid_idx,
[component_score_summary],
[component_score_summary])
sf_parameters = ScaffoldParameters(name=self.scaffold_enum.NO_FILTER,
minscore=0.5,
minsimilarity=0.4,
nbmax=1)
scaffold_filter_factory = ScaffoldFilterFactory()
self.scaffold_filter = scaffold_filter_factory.load_scaffold_filter(
sf_parameters)
self.scaffold_filter.score(final_summary)
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)
def __init__(self, configuration: GeneralConfigurationEnvelope):
super().__init__(configuration)
self._rows = 2
self._columns = 5
self._sample_size = self._rows * self._columns
self._sf_component_enum = ScoringFunctionComponentNameEnum()
self._is_dev = ull._is_development_environment()
def create_custom_alerts_configuration():
custom_alerts_list = [
'[*;r7]',
'[*;r8]',
'[*;r9]',
'[*;r10]',
'[*;r11]',
'[*;r12]',
'[*;r13]',
'[*;r14]',
'[*;r15]',
'[*;r16]',
'[*;r17]',
'[#8][#8]',
'[#6;+]',
'[#16][#16]',
'[#7;!n][S;!$(S(=O)=O)]',
'[#7;!n][#7;!n]',
'C#C',
'C(=[O,S])[O,S]',
'[#7;!n][C;!$(C(=[O,N])[N,O])][#16;!s]',
'[#7;!n][C;!$(C(=[O,N])[N,O])][#7;!n]',
'[#7;!n][C;!$(C(=[O,N])[N,O])][#8;!o]',
'[#8;!o][C;!$(C(=[O,N])[N,O])][#16;!s]',
'[#8;!o][C;!$(C(=[O,N])[N,O])][#8;!o]',
'[#16;!s][C;!$(C(=[O,N])[N,O])][#16;!s]']
sf_enum = ScoringFunctionComponentNameEnum()
parameters = ComponentParameters(component_type=sf_enum.CUSTOM_ALERTS,
name="custom_alerts",
weight=1.,
smiles=custom_alerts_list,
model_path="",
specific_parameters={})
return parameters
def setUpClass(cls):
enum = ScoringFunctionComponentNameEnum()
parameters = ComponentParameters(component_type=enum.TANIMOTO_SIMILARITY,
name="tanimoto_similarity",
weight=1.,
smiles=["CCC", "O=S(=O)(c3ccc(n1nc(cc1c2ccc(cc2)C)C(F)(F)F)cc3)N"],
model_path="",
specific_parameters={})
cls.component = TanimotoSimilarity(parameters)
def setUpClass(self):
csp_enum = ComponentSpecificParametersEnum()
transf_type = TransformationTypeEnum()
sf_enum = ScoringFunctionComponentNameEnum()
activity = create_activity_component_regression()
activity.specific_parameters[
csp_enum.TRANSFORMATION_TYPE] = transf_type.DOUBLE_SIGMOID
activity.specific_parameters[csp_enum.COEF_DIV] = 100.
activity.specific_parameters[csp_enum.COEF_SI] = 150.
activity.specific_parameters[csp_enum.COEF_SE] = 150.
off_activity = create_offtarget_activity_component_regression()
delta_params = {
"high": 3.0,
"k": 0.25,
"low": 0.0,
"transformation": True,
"transformation_type": "sigmoid"
}
selectivity = ComponentParameters(
component_type=sf_enum.SELECTIVITY,
name="desirability",
weight=1.,
smiles=[],
model_path="",
specific_parameters={
"activity_model_path": activity.model_path,
"offtarget_model_path": off_activity.model_path,
"activity_specific_parameters":
activity.specific_parameters.copy(),
"offtarget_specific_parameters":
off_activity.specific_parameters,
"delta_transformation_parameters": delta_params
})
qed_score = ComponentParameters(component_type=sf_enum.QED_SCORE,
name="qed_score",
weight=1.,
smiles=[],
model_path="",
specific_parameters={})
matching_substructure = ComponentParameters(
component_type=sf_enum.MATCHING_SUBSTRUCTURE,
name="matching_substructure",
weight=1.,
smiles=["[*]n1cccc1CC"],
model_path="",
specific_parameters={})
custom_alerts = create_custom_alerts_configuration()
self.sf_state = CustomProduct(parameters=[
activity, selectivity, qed_score, matching_substructure,
custom_alerts
])
def setUpClass(self):
utils_general.set_default_device_cuda()
lm_enum = LoggingModeEnum()
run_mode_enum = RunningModeEnum()
sf_enum = ScoringFunctionNameEnum()
sf_component_enum = ScoringFunctionComponentNameEnum()
filter_enum = ScaffoldFilterEnum()
self.workfolder = MAIN_TEST_PATH
smiles = ["CCC", "c1ccccc1CCC"]
ts_parameters = vars(
ComponentParameters(
name="tanimoto similarity",
weight=1,
smiles=smiles,
model_path="",
specific_parameters={},
component_type=sf_component_enum.TANIMOTO_SIMILARITY))
sf_parameters = ScoringFuncionParameters(name=sf_enum.CUSTOM_SUM,
parameters=[ts_parameters])
scoring_function = ScoringFunctionFactory(sf_parameters)
logging = ReinforcementLoggerConfiguration(
sender="1",
recipient=lm_enum.LOCAL,
logging_path=f"{self.workfolder}/log",
resultdir=self.workfolder,
logging_frequency=0,
job_name="unit_test_job")
rl_config = ReinforcementLearningConfiguration(prior=RANDOM_PRIOR_PATH,
agent=RANDOM_PRIOR_PATH,
n_steps=3)
scaffold_parameters = ScaffoldParameters(
filter_enum.IDENTICAL_MURCKO_SCAFFOLD, 0.05, 25, 0.4)
scaffold_filter = self._setup_scaffold_filter(scaffold_parameters)
inception_config = InceptionConfiguration(smiles, 100, 10)
inception = Inception(inception_config, scoring_function,
Model.load_from_file(rl_config.prior))
parameters = ReinforcementLearningComponents(
scoring_function=vars(scoring_function),
diversity_filter=vars(scaffold_filter),
reinforcement_learning=vars(rl_config),
inception=vars(inception_config))
configuration = GeneralConfigurationEnvelope(
parameters=vars(parameters),
logging=vars(logging),
run_type=run_mode_enum.REINFORCEMENT_LEARNING,
version="2.0")
self.runner = ReinforcementRunner(configuration,
config=rl_config,
scaffold_filter=scaffold_filter,
scoring_function=scoring_function,
inception=inception)
def setUpClass(cls):
sf_enum = ScoringFunctionComponentNameEnum()
cls.matching_pattern = "XXXX"
cls.parameters = ComponentParameters(
component_type=sf_enum.MATCHING_SUBSTRUCTURE,
name="matching_substructure",
weight=1.,
smiles=[cls.matching_pattern],
model_path="",
specific_parameters={})
def setUpClass(cls):
sf_enum = ScoringFunctionComponentNameEnum()
parameters = ComponentParameters(
component_type=sf_enum.MATCHING_SUBSTRUCTURE,
name="matching_substructure",
weight=1.,
smiles=["c1ccccc1"],
model_path="",
specific_parameters={})
cls.component = MatchingSubstructure(parameters)
def create_predictive_property_component_classification():
sf_enum = ScoringFunctionComponentNameEnum()
specific_parameters = _specific_parameters_classifiaction_predictive_model()
parameters = ComponentParameters(component_type=sf_enum.PREDICTIVE_PROPERTY,
name="predictive_property_classification",
weight=1.,
smiles=[],
model_path=ACTIVITY_CLASSIFICATION,
specific_parameters=specific_parameters)
return parameters
def create_activity_component_regression():
sf_enum = ScoringFunctionComponentNameEnum()
specific_parameters = _specific_parameters_regression_predictive_model()
parameters = ComponentParameters(component_type=sf_enum.PREDICTIVE_PROPERTY,
name="activity",
weight=1.,
smiles=[],
model_path=ACTIVITY_REGRESSION,
specific_parameters=specific_parameters)
return 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()
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(cls):
sf_enum = ScoringFunctionComponentNameEnum()
parameters = ComponentParameters(component_type=sf_enum.QED_SCORE,
name="qed_score",
weight=1.,
smiles=[],
model_path="",
specific_parameters={})
cls.component = QedScore(parameters)
cls.smile = "C1CCCCCCCCC1"
cls.mol = Chem.MolFromSmiles(cls.smile)
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()
predictive_property = create_predictive_property_component_regression()
activity = create_activity_component_regression()
qed_score = ComponentParameters(component_type=sf_enum.QED_SCORE,
name="qed_score_name",
weight=1.,
smiles=[],
model_path="",
specific_parameters={})
self.sf_state = CustomProduct(parameters=[activity, qed_score, predictive_property])
def setUpClass(cls):
sf_enum = ScoringFunctionComponentNameEnum()
parameters = ComponentParameters(
component_type=sf_enum.JACCARD_DISTANCE,
name="jaccard_distance",
weight=1.,
smiles=[
"O=S(=O)(c3ccc(n1nc(cc1c2ccc(cc2)C)C(F)(F)F)cc3)N", "CCCCC"
],
model_path="",
specific_parameters={})
cls.component = JaccardDistance(parameters)
def __init__(self, configuration: GeneralConfigurationEnvelope):
super().__init__(configuration)
self._summary_writer = SummaryWriter(
log_dir=self._log_config.logging_path)
self._summary_writer.add_text(
'Legends',
'The values under each compound are read as: [Agent; Prior; Target; Score]'
)
# _rows and _columns define the shape of the output grid of molecule images in tensorboard.
self._rows = 4
self._columns = 4
self._sample_size = self._rows * self._columns
self._sf_component_enum = ScoringFunctionComponentNameEnum()
self._console_message_formatter = ConsoleMessage()
def create_offtarget_activity_component_regression():
csp_enum = ComponentSpecificParametersEnum()
sf_enum = ScoringFunctionComponentNameEnum()
specific_parameters = _specific_parameters_regression_predictive_model()
specific_parameters[csp_enum.HIGH] = 3
specific_parameters[csp_enum.LOW] = 0
specific_parameters[csp_enum.TRANSFORMATION] = False
parameters = ComponentParameters(component_type=sf_enum.PREDICTIVE_PROPERTY,
name="offtarget_activity",
weight=1.,
smiles=[],
model_path=OFFTARGET_ACTIVITY_REGRESSION,
specific_parameters=specific_parameters)
return parameters
def create_offtarget_activity_component_classification():
csp_enum = ComponentSpecificParametersEnum()
sf_enum = ScoringFunctionComponentNameEnum()
specific_parameters = _specific_parameters_classifiaction_predictive_model()
specific_parameters[csp_enum.HIGH] = 3
specific_parameters[csp_enum.LOW] = 0
specific_parameters[csp_enum.TRANSFORMATION] = False
parameters = ComponentParameters(component_type=sf_enum.PREDICTIVE_PROPERTY,
name="predictive_property_classification",
weight=1.,
smiles=[],
model_path=ACTIVITY_CLASSIFICATION,
specific_parameters=specific_parameters)
return 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)
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 setUp(self):
self.rm_enums = RunningModeEnum()
self.cs_enum = ComponentSpecificParametersEnum()
self.tf_enum = TransformationTypeEnum()
self.sfc_enum = ScoringFunctionComponentNameEnum()
self.lm_enum = LoggingModeEnum()
self.parameters = create_activity_component_regression()
log_conf = BaseLoggerConfiguration(
sender="http://10.59.162.10:8081",
recipient=self.lm_enum.LOCAL,
logging_path=f"{MAIN_TEST_PATH}/log",
job_name="model_validation_test",
job_id="1")
self.configuration_envelope = GeneralConfigurationEnvelope(
parameters=vars(self.parameters),
logging=vars(log_conf),
run_type=self.rm_enums.VALIDATION,
version="2.0")
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 _default_scoring_component_registry(self) -> dict:
enum = ScoringFunctionComponentNameEnum()
component_map = {
enum.MATCHING_SUBSTRUCTURE: MatchingSubstructure,
enum.PREDICTIVE_PROPERTY: PredictivePropertyComponent,
enum.TANIMOTO_SIMILARITY: TanimotoSimilarity,
enum.JACCARD_DISTANCE: JaccardDistance,
enum.CUSTOM_ALERTS: CustomAlerts,
enum.QED_SCORE: QedScore,
enum.MOLECULAR_WEIGHT: MolWeight,
enum.TPSA: PSA,
enum.NUM_ROTATABLE_BONDS: RotatableBonds,
enum.NUM_HBD_LIPINSKI: HBD_Lipinski,
enum.NUM_RINGS: NumRings,
enum.SELECTIVITY: SelectivityComponent,
enum.SA_SCORE: SASComponent
}
return component_map
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)
def setUpClass(cls):
csp_enum = ComponentSpecificParametersEnum()
transf_type = TransformationTypeEnum()
enum = ScoringFunctionComponentNameEnum()
delta_params = {
"high": 3.0,
"k": 0.25,
"low": 0.0,
"transformation": True,
"transformation_type": "sigmoid"
}
activity = create_activity_component_classification()
activity.specific_parameters[
csp_enum.TRANSFORMATION_TYPE] = transf_type.DOUBLE_SIGMOID
activity.specific_parameters[csp_enum.COEF_DIV] = 100.
activity.specific_parameters[csp_enum.COEF_SI] = 150.
activity.specific_parameters[csp_enum.COEF_SE] = 150.
off_activity = create_offtarget_activity_component_classification()
selectivity = ComponentParameters(
component_type=enum.SELECTIVITY,
name="desirability",
weight=1.,
smiles=[],
model_path="",
specific_parameters={
"activity_model_path":
activity.model_path,
"offtarget_model_path":
off_activity.model_path,
"activity_specific_parameters":
activity.specific_parameters.copy(),
"offtarget_specific_parameters":
off_activity.specific_parameters.copy(),
"delta_transformation_parameters":
delta_params
})
cls.component = SelectivityComponent(parameters=selectivity)
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])
