rapids_singlecell.tl.embedding_density

rapids_singlecell.tl.embedding_density(adata, basis='umap', *, groupby=None, key_added=None, batchsize=10000, components=None)

Calculate the density of cells in an embedding (per condition). Gaussian kernel density estimation is used to calculate the density of cells in an embedded space. This can be performed per category over a categorical cell annotation. The cell density can be plotted using the pl.embedding_density function. Note that density values are scaled to be between 0 and 1. Thus, the density value at each cell is only comparable to densities in the same category. This function was written by Sophie Tritschler and implemented into Scanpy by Malte Luecken. This function uses cuML’s KernelDensity. It returns log Likelihood as does sklearn’s implementation. scipy.stats implementation, used in scanpy, returns PDF.

Parameters:

adata AnnData

The annotated data matrix.

basis str (default: 'umap')

The embedding over which the density will be calculated. This embedded representation should be found in adata.obsm['X_[basis]']`.

groupby str | None (default: None)

Key for categorical observation/cell annotation for which densities are calculated per category.

key_added str | None (default: None)

Name of the .obs covariate that will be added with the density estimates.

batchsize int (default: 10000)

Number of cells that should be processed together.

components Union[str, Sequence[str]] (default: None)

The embedding dimensions over which the density should be calculated. This is limited to two components.

Return type:

None

Returns:

Updates adata.obs with an additional field specified by the key_added parameter. This parameter defaults to [basis]_density_[groupby], where [basis] is one of umap, diffmap, pca, tsne, or draw_graph_fa and [groupby] denotes the parameter input.

Updates adata.uns with an additional field [key_added]_params.