FACSPy.tl._compute_diffmap

FACSPy.tl._compute_diffmap#

FACSPy.tl._compute_diffmap(adata, n_comps=15, neighbors_key=None, random_state=187)#

Internal function to compute the Diffmap embedding. The core of the function is implemented from scanpy with the important difference that the diffmap coordinates are returned and not written to the adata object.

Parameters:

  • adata (AnnData) – The anndata object of shape n_obs x n_vars where rows correspond to cells and columns to the channels

  • n_comps (int) – The number of dimensions of the representation.

  • neighbors_key (Optional[str]) – If specified, umap looks .uns[neighbors_key] for neighbors settings and .obsp[f’{neighbors_key}’][‘connectivities_key’] for connectivities.

Return type:

tuple[ndarray, ndarray]

Returns:

  • dpt.eigen_basis – The diffusion map coordinates

  • dpt.eigen_values – The diffusion map eigen values

Contents