torchcell.datasets.scerevisiae.cooper2010.AminoAcidCooper2010Dataset

class AminoAcidCooper2010Dataset(root: str = 'data/torchcell/amino_acid_cooper2010', io_workers: int = 0, transform: Callable[[...], Any] | None = None, pre_transform: Callable[[...], Any] | None = None, genome: Any | None = None, **kwargs: Any)

Bases: ExperimentDataset

Cooper 2010 CE-LIF amino-acid pools of the deletion collection (ratio to plate).

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 deposited Supplemental Table 4 required before processing.

download() → None

Link Table 4 from the sha256-verified raw mirror. There is no network path.

The supplement is behind a login wall, so the mirror (the stored artifact plus its sha256) is the only source; an absent mirror raises with the manual recipe.

create_experiment(row: KeptRow) → tuple[MetaboliteExperiment, MetaboliteExperimentReference, Publication]

Build the Metabolite experiment/reference/publication for one kept row.

process() → None

Parse Table 4, apply the retention rules, write the LMDB and the ledgers.

Table 4 in raw/ is verified against its sha256 pin before any row is read; a mismatch raises RawSha256MismatchError and no store is written.

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

Preprocessing is handled inside process() for this dataset.