Reactivity

class mlipaudit.benchmarks.reactivity.reactivity.ReactivityBenchmark(force_field: ForceField | Calculator, data_input_dir: str | PathLike = './data', run_mode: RunMode | Literal['dev', 'fast', 'standard'] = RunMode.STANDARD)

Benchmark for transition state energies.

name

The unique benchmark name that should be used to run the benchmark from the CLI and that will determine the output folder name for the result file. The name is reactivity.

Type:

str

category

A string that describes the category of the benchmark, used for example, in the UI app for grouping. Default, if not overridden, is “General”. This benchmark’s category is “Small Molecules”.

Type:

str

result_class

A reference to the type of BenchmarkResult that will determine the return type of self.analyze(). The result class is ReactivityResult.

Type:

type[mlipaudit.benchmark.BenchmarkResult] | None

model_output_class

A reference to the ReactivityModelOutput class.

Type:

type[mlipaudit.benchmark.ModelOutput] | None

required_elements

The set of atomic element types that are present in the benchmark’s input files.

Type:

set[str] | None

skip_if_elements_missing

Whether the benchmark should be skipped entirely if there are some atomic element types that the model cannot handle. If False, the benchmark must have its own custom logic to handle missing atomic element types. For this benchmark, the attribute is set to True.

Type:

bool

__init__(force_field: ForceField | Calculator, data_input_dir: str | PathLike = './data', run_mode: RunMode | Literal['dev', 'fast', 'standard'] = RunMode.STANDARD) → None

Initializes the benchmark.

Parameters:

• force_field – The force field model to be benchmarked.

• data_input_dir – The local input data directory. Defaults to “./data”. If the subdirectory “{data_input_dir}/{benchmark_name}” exists, the benchmark expects the relevant data to be in there, otherwise it will download it from HuggingFace.

• run_mode – Whether to run the standard benchmark length, a faster version, or a very fast development version. Subclasses should ensure that when RunMode.DEV, their benchmark runs in a much shorter timeframe, by running on a reduced number of test cases, for instance. Implementing RunMode.FAST being different from RunMode.STANDARD is optional and only recommended for very long-running benchmarks. This argument can also be passed as a string “dev”, “fast”, or “standard”.

Raises:

• ChemicalElementsMissingError – If initialization is attempted with a force field that cannot perform inference on the required elements.

• ValueError – If force field type is not compatible.

run_model() → None

Run energy predictions.

analyze() → ReactivityResult

Analysis.

Returns:

A ReactivityResult object with the benchmark results.

Raises:

RuntimeError – If called before run_model().

class mlipaudit.benchmarks.reactivity.reactivity.ReactivityResult(*, failed: bool = False, score: Annotated[float | None, Ge(ge=0), Le(le=1)] = None, reaction_results: dict[str, ReactionResult] = {}, mae_activation_energy: Annotated[float, Ge(ge=0)] | None = None, rmse_activation_energy: Annotated[float, Ge(ge=0)] | None = None, mae_enthalpy_of_reaction: Annotated[float, Ge(ge=0)] | None = None, rmse_enthalpy_of_reaction: Annotated[float, Ge(ge=0)] | None = None, failed_reactions: list[str] = [])

Result object for the reactivity benchmark.

reaction_results

A dictionary of reaction results where the keys are the reaction identifiers.

Type:

dict[str, mlipaudit.benchmarks.reactivity.reactivity.ReactionResult]

mae_activation_energy

The MAE of the activation energies.

Type:

float | None

rmse_activation_energy

The RMSE of the activation energies.

Type:

float | None

mae_enthalpy_of_reaction

The MAE of the enthalpies of reactions.

Type:

float | None

rmse_enthalpy_of_reaction

The RMSE of the enthalpies of reactions.

Type:

float | None

failed_reactions

A list of reaction ids for which inference failed.

Type:

list[str]

failed

Whether all the simulations or inferences failed and no analysis could be performed. Defaults to False.

Type:

bool

score

the final score for the benchmark between 0 and 1.

Type:

float | None

class mlipaudit.benchmarks.reactivity.reactivity.ReactivityModelOutput(*, reaction_ids: list[str], energy_predictions: list[ReactionModelOutput], failed_reactions: list[str] = [])

Stores the model outputs for the reactivity benchmark, consisting of the energy predictions for each reaction.

reaction_ids

A list of reaction identifiers for the successful reactions.

Type:

list[str]

energy_predictions

A corresponding list of energy predictions for each successful reaction.

Type:

list[mlipaudit.benchmarks.reactivity.reactivity.ReactionModelOutput]

failed_reactions

A list of reaction ids for which inference failed.

Type:

list[str]