torchcell.datasets.NucleotideTransformerDataset

class NucleotideTransformerDataset(root: str, genome: SCerevisiaeGenome, model_name: str | None = None, transform: Callable[[...], Any] | None = None, pre_transform: Callable[[...], Any] | None = None)[source]

Bases: BaseEmbeddingDataset

Per-gene Nucleotide Transformer sequence embeddings keyed by window model.

static parse_genome(genome: SCerevisiaeGenome | None) → ParsedGenome | None[source]

Build a ParsedGenome holding the gene set, or None if genome is None.

initialize_model() → NucleotideTransformer | None[source]

Instantiate the NucleotideTransformer model, or None if no model name.

process() → None[source]

Embed each gene’s windowed sequence and save the collated dataset.