snapatac2.tl.laplacian#

snapatac2.tl.laplacian(data, n_comps=None, features='selected', random_state=0, inplace=True)[source]#

Convert chromatin accessibility profiles of cells into lower dimensional representations.

Convert chromatin accessibility profiles of cells into lower dimensional representations using the spectrum of the normalized graph Laplacian defined by pairwise similarity between cells.

Parameters

  • data (AnnData) – AnnData object

  • n_comps (Optional[int]) – Number of dimensions to keep

  • features (Union[str, ndarray, None]) – Boolean index mask. True means that the feature is kept. False means the feature is removed.

  • random_state (int) – Seed of the random state generator

Return type

Optional[ndarray]

Returns

  • if inplace=True it stores Spectral embedding of data in the field

  • adata.obsm["X_spectral"], otherwise it returns the result as a numpy array.