torchcell.datasets.scerevisiae.costanzo2016.SmfCostanzo2016Dataset

class SmfCostanzo2016Dataset(root: str = 'data/torchcell/smf_costanzo2016', io_workers: int = 0, transform: Callable[[...], Any] | None = None, pre_transform: Callable[[...], Any] | None = None, **kwargs: Any)

Bases: ExperimentDataset

Single-mutant fitness dataset from Costanzo et al. 2016.

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[FitnessExperiment]

Return the FitnessExperiment type for SMF data.

property reference_class: type[FitnessExperimentReference]

Return the FitnessExperimentReference type for SMF data.

property raw_file_names: str

Return the single-mutant fitness raw spreadsheet name.

download() → None

Download and unpack the Costanzo archive, keeping the SMF spreadsheet.

process() → None

Read the SMF spreadsheet and write experiment records into LMDB.

preprocess_raw(df: DataFrame) → DataFrame

Derive perturbation type from strain IDs and clean the SMF table.

static compute_phenotype_reference_std(df: DataFrame) → tuple[Any, Any]

Return mean SMF stddev at 26C and 30C used as reference noise.

static create_experiment(dataset_name: str, row: Series, phenotype_reference_std_26: Any, phenotype_reference_std_30: Any) → tuple[FitnessExperiment, FitnessExperimentReference, Publication]

Build SMF experiment, reference, and publication objects for a row.