CellRank 1.2.0 (2021-02-02)


  • Fix a bug when computing the Schur decomposition for reducible Markov chains (Schur vectors appear to not be D-orthogonal). GPCCA requires the leading Schur vectors to be orthogonal w.r.t. a symmetric, positive definite matrix \(D\) PR 453.

  • Fix not falling back to mode='monte_carlo' if no jax is found when using mode='stochastic' in cellrank.tl.kernels.VelocityKernel.compute_transition_matrix() PR 472.

  • Fix pandas v1.0.1 indexing error in cellrank.tl.lineage_drivers() PR 475.

  • Fix not correctly propagating colors during aggregation in cellrank.tl.Lineage PR 482.


  • Completely refactored the underlying code base of GPCCA and set it up as it’s own package called pyGPCCA with documentation and an example. Going forwards, this will ensure that one of the “engines” of CellRank is also easy to maintain to extend. Further, this will make CellRank’s installation more convenient by not needing to vendorize additional dependencies PR 472.

  • Add cellrank.pl.circular_projection() visualizing computed fate probabilities as done in [Velten et al., 2017]. PR 459.

  • Allow legends not to be plotted by passing legend_loc="none", as done in scVelo PR 470.