rapids_singlecell.tl.diffmap

rapids_singlecell.tl.diffmap(adata, n_comps=15, *, neighbors_key=None, sort='decrease', density_normalize=True)

Diffusion maps has been proposed for visualizing single-cell data.

This is a reimplementation of scanpys function.

The width (“sigma”) of the connectivity kernel is implicitly determined by the number of neighbors used to compute the single-cell graph in scanpy.pp.neighbors() or neighbors().

Parameters:

adata AnnData

Annotated data matrix.

n_comps int (default: 15)

The number of dimensions of the representation.

neighbors_key str (default: None)

If not specified, diffmap looks at .obsp['connectivities'] for neighbors connectivities If specified, diffmap looks at .obsp['neighbors_key_ connectivities'] for neighbors connectivities

sort str (default: 'decrease')

Leave as is for the same behavior as sc.tl.diffmap

density_normalize bool (default: True)

Leave as is for the same behavior as sc.tl.diffmap

Return type:

None

Returns:

updates adata with the following fields.

X_diffmapnumpy.ndarray (adata.obsm)

Diffusion map representation of data, which is the right eigen basis of the transition matrix with eigenvectors as columns.

diffmap_evalsnumpy.ndarray (adata.uns)

Array of size (number of eigen vectors). Eigenvalues of transition matrix.