Garfield.data.GraphAnnTorchDataset

class Garfield.data.GraphAnnTorchDataset(adata, label_name: str | None = None, adj_key: Literal['spatial_connectivities', 'connectivities'] = 'spatial_connectivities', edge_label_adj_key: str = 'edge_label_spatial_connectivities', used_feat: bool = False, self_loops: bool = True)

Spatially annotated torch dataset class to extract node features, node labels, adjacency matrix and edge indices in a standardized format from an AnnData object.

Parameters:

• adata – AnnData object with counts stored in ´adata.layers[counts_key]´ or ´adata.X´ depending on ´counts_key´, and sparse adjacency matrix stored in ´adata.obsp[adj_key]´.

• adj_key – Key under which the sparse adjacency matrix is stored in ´adata.obsp´.

• self_loops – If ´True´, add self loops to the adjacency matrix to model autocrine communication.

__init__(adata, label_name: str | None = None, adj_key: Literal['spatial_connectivities', 'connectivities'] = 'spatial_connectivities', edge_label_adj_key: str = 'edge_label_spatial_connectivities', used_feat: bool = False, self_loops: bool = True)

Methods

__init__(adata[, label_name, adj_key, ...])