cellrank.external.kernels.WOTKernel

class cellrank.external.kernels.WOTKernel(adata, backward=False, time_key='exp_time', **kwargs)[source]

Waddington optimal transport kernel from [Schiebinger et al., 2019].

This class requires the wot package, which can be installed as pip install git+https://github.com/broadinstitute/wot.

Parameters

adata (anndata.AnnData) – Annotated data object.
backward (bool) – Direction of the process.
time_key (str) – Key in anndata.AnnData.obs where experimental time is stored. The experimental time can be of either of a numeric or an ordered categorical type.
kwargs (Any) – Keyword arguments for the parent class.

Examples

Workflow:

# import packages, load data
import scanpy as sc
import cellrank as cr
adata = cr.datasets.lung()

# filter, normalize and annotate highly variable genes
sc.pp.filter_genes(adata, min_cells=10)
sc.pp.normalize_total(adata)
sc.pp.log1p(adata)
sc.pp.highly_variable_genes(adata)

# estimate proliferation and apoptosis from gene sets (see. e.g. WOT tutorial for example lists)
proliferation_genes = ...
apoptosis_genes = ...
sc.tl.score_genes(adata, gene_list=proliferation_genes, score_name='proliferation')
sc.tl.score_genes(adata, gene_list=apoptosis_genes, score_name='apoptosis')

# initialize kernel, estimate initial growth rate based on scores from above
from cellrank.external.kernels import WOTKernel
ot = WOTKernel(adata, time_key='day')
ot.compute_initial_growth_rates(proliferation_key='proliferation',
                                apoptosis_key='apoptosis',
                                key_added='initial_growth_rates')

# compute transport maps, aggregate into one single transition matrix
ot.compute_transition_matrix(growth_rate_key='initial_growth_rates', growth_iters=3)

Attributes

`adata`	Annotated data object.
`backward`	None.
`growth_rates`	Estimated cell growth rates for each growth rate iteration.
`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_initial_growth_rates`([...])	Estimate initial growth rates using a birth-death process as described in [Schiebinger et al., 2019].
`compute_transition_matrix`([cost_matrices, ...])	Compute transition matrix using Waddington OT [Schiebinger et al., 2019].
`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.