torchcell.models.dcell.DCell

class DCell(hetero_data: HeteroData, min_subsystem_size: int = 20, subsystem_ratio: float = 0.3, output_size: int = 1)

Bases: Module

DCell network mirroring the GO ontology as a hierarchy of subsystems.

property num_parameters: dict[str, int]

Count parameters in different parts of the model.

forward(cell_graph: HeteroData, batch: HeteroData) → tuple[Tensor, dict[str, Any]]

Forward pass through DCell hierarchy.

Parameters:

• cell_graph – Cell graph (not used by DCell, included for compatibility with trainer)

• batch – The batch data containing gene states and GO information