class cellrank.tl.kernels.PrecomputedKernel(object, adata=None, obsp_key=None, **kwargs)[source]

Kernel which contains a precomputed transition matrix.

  • object (Union[str, bool, ndarray, spmatrix, AnnData, KernelExpression]) –

    Can be one of the following types:

    • anndata.AnnData - annotated data object.

    • scipy.sparse.spmatrix, numpy.ndarray - row-normalized transition matrix.

    • cellrank.tl.kernels.KernelExpression - kernel expression.

    • str - key in anndata.AnnData.obsp where the transition matrix is stored. adata must be provided in this case.

    • bool - directionality of the transition matrix that will be used to infer its storage location. If None, the directionality will be determined automatically. adata must be provided in this case.

  • adata (anndata.AnnData) – Annotated data object. Must be provided when object is str or bool.

  • obsp_key (Optional[str]) – Key in anndata.AnnData.obsp where the transition matrix is stored. If None, it will be determined automatically. Only used when object is anndata.AnnData.

  • copy – Whether or not to copy the stored transition matrix.

  • backward – Hint whether this is a forward, backward or a unidirectional kernel. Only used when object is anndata.AnnData.



Annotated data object.


Direction of the process.


Underlying base kernels.


Parameters which are used to compute the transition matrix.


(n_cells, n_cells).


Row-normalized transition matrix.


compute_transition_matrix(*_, **__)

Do nothing and return self.

copy(*[, deep])

Return a copy of itself.

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.