scSLAT.model.loaddata.load_anndatas
- scSLAT.model.loaddata.load_anndatas(adatas, feature='DPCA', dim=50, self_loop=False, join='inner', backend='sklearn', singular=True, check_order=True, n_top_genes=2500)[source]
Transfer adatas with spatial info into PyG datasets
- Return type:
Parameters:
- adatas
List of Anndata objects
- feature
use which data to build graph - PCA (default) - DPCA (For batch effect correction) - Harmony (For batch effect correction) - GLUE (NOTE: only suitable for multi-omics integration)
- dim
dimension of embedding, works for [‘PCA’, ‘DPCA’, ‘Harmony’, ‘GLUE’]
- self_loop
whether to add self loop on graph
- join
how to concatenate two adata
- backend
backend to calculate DPCA
- singular
whether to multiple singular value in DPCA
- check_order
whether to check the order of adata1 and adata2
- n_top_genes
number of highly variable genes
Note:
Only support ‘Spatial_Net’ which store in adata.uns yet