cellrank.external.kernels.StationaryOTKernel

class cellrank.external.kernels.StationaryOTKernel(adata, g, terminal_states=None, **kwargs)[source]

Stationary optimal transport kernel from [Zhang et al., 2021].

This class requires the statOT package, which can be installed as pip install statot POT.

Parameters

adata (anndata.AnnData) – Annotated data object.
terminal_states (Union[str, Series, None]) – Key in anndata.AnnData.obs or a categorical pandas.Series where non-NaN values mark the terminal states. If None, terminal states are assumed to be present in anndata.AnnData.obs ['terminal_states'].
g (Union[str, ndarray]) – Key in anndata.AnnData.obs containing relative growth rates for cells or the array itself.
kwargs (Any) – Keyword arguments for the parent class.

Attributes

`adata`	Annotated data object.
`backward`	None.
`kernels`	Underlying base kernels.
`params`	Parameters which are used to compute the transition matrix.
`shape`	`(n_cells, n_cells)`.
`transition_matrix`	Row-normalized transition matrix.

Methods

`compute_transition_matrix`(eps, dt[, basis, ...])	Compute transition matrix using stationary OT [Zhang et al., 2021].
`copy`([deep])	Not implemented.
`plot_projection`([basis, key_added, ...])	Plot `transition_matrix` as a stream or a grid plot.
`plot_random_walks`([n_sims, max_iter, seed, ...])	Plot random walks in an embedding.
`plot_single_flow`(cluster, cluster_key, time_key)	Visualize outgoing flow from a cluster of cells [Mittnenzweig et al., 2021].
`read`(fname[, adata, copy])	Deserialize self from a file.
`write`(fname[, write_adata, ext])	Serialize self to a file.
`write_to_adata`([key, copy])	Write the transition matrix and parameters used for computation to the underlying `adata` object.