torchcell.datasets.scerevisiae.sgd.GeneEssentialitySgdDataset

class GeneEssentialitySgdDataset(root: str = 'data/torchcell/gene_essentiality_sgd', io_workers: int = 0, transform: Callable[[...], Any] | None = None, pre_transform: Callable[[...], Any] | None = None, **kwargs: Any)

Bases: ExperimentDataset

Gene essentiality experiments built from SGD inviable null phenotypes.

organism: ClassVar[Organism] = 'scerevisiae'

each loader declares its own, the build’s organism switch reads it off the class (dataset_organism), and a loader that forgot it is refused by name instead of inheriting an organism it may not have.

Type:

The host organism every record describes. Annotated here WITHOUT a value

property experiment_class: type[GeneEssentialityExperiment]

Return the experiment model class for this dataset.

property reference_class: type[GeneEssentialityExperimentReference]

Return the experiment reference model class for this dataset.

property raw_file_names: list[str]

the source is the pinned dump under $DATA_ROOT.

Type:

No files in raw/

download() → None

Do nothing; the pinned dump is verified in process(), never fetched.

preprocess_raw(df: DataFrame, preprocess: dict[str, Any] | None = None) → DataFrame

Return the DataFrame unchanged (no raw preprocessing needed).

process() → None

Verify the SGD dump, apply the allele rule, and write the LMDB and ledger.

static create_experiment(dataset_name: str, annotation: SgdAnnotation, environment: Environment) → tuple[GeneEssentialityExperiment, GeneEssentialityExperimentReference, Publication]

Build the experiment, reference, and publication for one annotation.