nichecompass.data.SpatialAnnTorchDataset

class nichecompass.data.SpatialAnnTorchDataset(adata, cat_covariates_label_encoders, adata_atac=None, counts_key='counts', adj_key='spatial_connectivities', edge_label_adj_key='edge_label_spatial_connectivities', self_loops=True, cat_covariates_keys=None)

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) – 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]´.

  • adata_atac (Optional[AnnData] (default: None)) – Additional optional AnnData object with paired spatial ATAC data.

  • cat_covariates_label_encoders (List[dict]) – List of categorical covariates label encoders from the model (label encoding indeces need to be aligned with the ones from the model to get the correct categorical covariates embeddings).

  • counts_key (Optional[str] (default: 'counts')) – Key under which the counts are stored in ´adata.layer´. If ´None´, uses ´adata.X´ as counts.

  • adj_key (str (default: 'spatial_connectivities')) – Key under which the sparse adjacency matrix is stored in ´adata.obsp´.

  • self_loops (bool (default: True)) – If ´True´, add self loops to the adjacency matrix to model autocrine communication.

  • cat_covariates_keys (Optional[str] (default: None)) – Keys under which the categorical covariates are stored in ´adata.obs´.

Methods table

Methods