Ctrl+K

poli.core.chemistry.tdc_black_box.TDCBlackBox

poli.core.chemistry.tdc_black_box.TDCBlackBox#

class poli.core.chemistry.tdc_black_box.TDCBlackBox(oracle_name: str, string_representation: Literal['SMILES', 'SELFIES'] = 'SMILES', force_isolation: bool = False, batch_size: Optional[int] = None, parallelize: bool = False, num_workers: Optional[int] = None, evaluation_budget: int = inf, **kwargs_for_oracle)#

An abstract black box for the TDC (Therapeutics Data Commons) problems [1].

Parameters

  • oracle_name (str) – The name of the oracle to be used.

  • string_representation (Literal["SMILES", "SELFIES"], optional) – A string (either “SMILES” or “SELFIES”) specifying which molecule representation you plan to use.

  • batch_size (int, optional) – The batch size for simultaneous execution, by default None.

  • parallelize (bool, optional) – Flag indicating whether to parallelize execution, by default False.

  • num_workers (int, optional) – The number of workers for parallel execution, by default None.

  • evaluation_budget (int, optional) – The maximum number of function evaluations. Default is infinity.

  • force_isolation (bool, optional) – Whether to force the isolation of the black box. Default is False.

  • **kwargs_for_oracle (dict) – Other keyword arguments to be passed to the oracle.

oracle_name#

The name of the oracle.

Type

str

__init__(self, oracle_name, string_representation="SMILES", force_isolation=False, batch_size=None, parallelize=False, num_workers=None, evaluation_budget=float("inf"), \*\*kwargs_for_oracle

Initializes a new instance of the abstract TDC class.

References

[1] Artificial intelligence foundation for therapeutic science.

Huang, K., Fu, T., Gao, W. et al. Nat Chem Biol 18, 1033-1036 (2022). https://doi.org/10.1038/s41589-022-01131-2

__init__(oracle_name: str, string_representation: Literal['SMILES', 'SELFIES'] = 'SMILES', force_isolation: bool = False, batch_size: Optional[int] = None, parallelize: bool = False, num_workers: Optional[int] = None, evaluation_budget: int = inf, **kwargs_for_oracle)#

Initialize the AbstractBlackBox object.

Parameters

  • batch_size (int, optional) – The batch size for parallel execution, by default None.

  • parallelize (bool, optional) – Flag indicating whether to parallelize the execution, by default False.

  • num_workers (int, optional) – The number of workers for parallel execution, by default we use half the available CPUs.

  • evaluation_budget (int, optional) – The maximum number of evaluations allowed for the black box function, by default float(“inf”).

Methods

__init__(oracle_name[, ...])

Initialize the AbstractBlackBox object.

reset_evaluation_budget()

Resets the evaluation budget by setting the number of evaluations made to 0.

set_observer(observer)

Set the observer object for recording observations during evaluation.

terminate()

Terminate the black box optimization problem.