torchcell.datasets.scerevisiae.vanacloig2022.EnvChemgenVanacloig2022Dataset

class EnvChemgenVanacloig2022Dataset(root: str = 'data/torchcell/env_chemgen_vanacloig2022', io_workers: int = 0, transform: Callable[[...], Any] | None = None, pre_transform: Callable[[...], Any] | None = None, **kwargs: Any)

Bases: ExperimentDataset

Anaerobic chemical-genomic env x geno -> log2(inhibitor/control) response screen.

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[Experiment]

Experiment schema class produced by this dataset.

property reference_class: type[ExperimentReference]

Experiment-reference schema class produced by this dataset.

property raw_file_names: list[str]

The GEO raw barcode-count matrix required before processing.

download() → None

Link the mirror file into raw/ after verifying it against DATA_SHA256.

The mirror + the DATA_SHA256 pin is canonical; the GEO URL is retrieval metadata that deposit_raw_mirror re-runs, never a live build dependency. The manifest is the retrieval record and must carry the pin, else ManifestPinMismatchError names both digests.

process() → None

Recompute per-(gene, condition) log2 responses from raw counts; write LMDB.

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

Preprocessing is handled inside process() for this dataset.

create_experiment() → None

Experiment construction is handled inline in process() for this dataset.