Plot initial states

This example shows how to compute and plot the initial states of the cell-state transition.

CellRank can be applied to any cell-state transition, be it differentiation, regeneration, reprogramming or other.

import cellrank as cr

adata = cr.datasets.pancreas_preprocessed("../example.h5ad")
adata

Out:

AnnData object with n_obs × n_vars = 2531 × 2000
    obs: 'day', 'proliferation', 'G2M_score', 'S_score', 'phase', 'clusters_coarse', 'clusters', 'clusters_fine', 'louvain_Alpha', 'louvain_Beta', 'initial_size_unspliced', 'initial_size_spliced', 'initial_size', 'n_counts', 'velocity_self_transition', 'dpt_pseudotime'
    var: 'highly_variable_genes', 'gene_count_corr', 'means', 'dispersions', 'dispersions_norm', 'fit_r2', 'fit_alpha', 'fit_beta', 'fit_gamma', 'fit_t_', 'fit_scaling', 'fit_std_u', 'fit_std_s', 'fit_likelihood', 'fit_u0', 'fit_s0', 'fit_pval_steady', 'fit_steady_u', 'fit_steady_s', 'fit_variance', 'fit_alignment_scaling', 'velocity_genes'
    uns: 'clusters_colors', 'clusters_fine_colors', 'diffmap_evals', 'iroot', 'louvain_Alpha_colors', 'louvain_Beta_colors', 'neighbors', 'pca', 'recover_dynamics', 'velocity_graph', 'velocity_graph_neg', 'velocity_params'
    obsm: 'X_diffmap', 'X_pca', 'X_umap', 'velocity_umap'
    varm: 'PCs', 'loss'
    layers: 'Ms', 'Mu', 'fit_t', 'fit_tau', 'fit_tau_', 'spliced', 'unspliced', 'velocity', 'velocity_u'
    obsp: 'connectivities', 'distances'

First, we compute the initial states. By default, we’re using the cellrank.tl.estimators.GPCCA estimator. The parameter cluster_key tries to associate the names of the initial states with cluster labels, whereas n_cells controls how many cells we take from each initial state as categorical observation - this is only available to the above mentioned estimator. We can show some plots of interest by specifying show_plots=True.

cr.tl.initial_states(
    adata,
    cluster_key="clusters",
    n_cells=30,
    softmax_scale=4,
    n_states=1,
    show_progress_bar=False,
)

Out:

/home/docs/checkouts/readthedocs.org/user_builds/cellrank/checkouts/stable/examples/plotting/plot_initial_states.py:20: DeprecationWarning: `cellrank.tl.initial_states` will be removed in version `2.0`. Please use the `cellrank.kernels` or `cellrank.estimators` interface instead.
  cr.tl.initial_states(
/home/docs/checkouts/readthedocs.org/user_builds/cellrank/checkouts/stable/cellrank/tl/_init_term_states.py:156: DeprecationWarning: `cellrank.tl.transition_matrix` will be removed in version `2.0`. Please use the `cellrank.kernels` or `cellrank.estimators` interface instead.
  kernel = transition_matrix(

We can now plot the initial states. By default, when using cellrank.tl.estimators.GPCCA, we plot continuous membership vectors to visualize individual cells associations with an initial state.

We can also plot membership vectors for different initial states separately if we computed more than one initial state using same_plot=False. As we only have one initial state here, this does not make sense.

cr.pl.initial_states(adata)

Lastly, we can discretize the assignment of cells to initial states by showing the cells most likely to belong to the initial state by specifying the discrete parameter.

cr.pl.initial_states(adata, discrete=True)

To see how to compute and plot the terminal states or the lineages, see Plot terminal states or Plot lineages, respectively.

Estimated memory usage: 320 MB