# cellrank.tl.kernels.VelocityKernel

class cellrank.tl.kernels.VelocityKernel(adata, backward=False, xkey='Ms', vkey='velocity', **kwargs)[source]

Kernel which computes a transition matrix based on RNA velocity.

This borrows ideas from both and . In short, for each cell i, we compute transition probabilities $$p_{i, j}$$ to each cell j in the neighborhood of i. The transition probabilities are computed as a multinomial logistic regression where the weights $$w_j$$ (for all j) are given by the vector that connects cell i with cell j in gene expression space, and the features $$x_i$$ are given by the velocity vector $$v_i$$ of cell i.

Parameters

Attributes

 adata Annotated data object. backward Direction of the process. kernels Underlying base kernels. logits Array of shape (n_cells, n_cells) containing unnormalized transition matrix. 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([model, ...]) Compute transition matrix based on velocity directions on the local manifold. 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 . 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.