scVelo – stochastic single cell RNA velocity¶
scVelo is a scalable toolkit for estimating and analyzing stochastic RNA velocities in single cells.
RNA velocity is the time derivative of mRNA abundance obtained by distinguishing unspliced (precursor) from spliced (mature) mRNA, and serves as a predictive indicator for the future state of an individual cell. The main principles of RNA velocity estimation have been presented in velocyto (La Manno et al., 2018) and are based on a deterministic model of transcriptional dynamics. scVelo uses a stochastic formulation and incorporates intrinsic expression variability.
It is compatible with scanpy (Wolf et al., 2018). Making use of sparse implementation, iterative neighbors search and other techniques, it is remarkably efficient in terms of memory and runtime without loss in accuracy (<1GB and <1min for 30,000 cells on a MacBook Pro 2017 with 2.3 GHz i5).
I highly recommend going through some exemplary notebooks.
Report issues and see the code on GitHub.