cellrank 1.0.0rc8

CellRank - Probabilistic Fate Mapping using RNA Velocity

CellRank - Probabilistic Fate Mapping using RNA Velocity

CellRank is a toolkit to uncover cellular dynamics based on scRNA-seq data with RNA velocity annotation, see La Manno et al. (2018) and Bergen et al. (2019). CellRank models cellular dynamics as a Markov chain, where transition probabilities are computed based on RNA velocity and transcriptomic similarity, taking into account uncertainty in the velocities. The Markov chain is coarse grained into a set of metastable states which represent root & final states as well as transient intermediate states. For each cell, we obtain the probability of it belonging to each metastable state, i.e. we compute a fate map on the single cell level. We show an example of such a fate map in the figure above, which has been computed using the data of pancreatic endocrinogenesis.

CellRank scales to large cell numbers, is fully compatible with scanpy and scvelo and is easy to use. For installation instructions, documentation and tutorials, visit cellrank.org.

CellRank’s key applications

• compute root & final as well as intermediate metastable states of your developmental/dynamical process

• infer fate probabilities towards these states for each single cell

• visualise gene expression trends towards/from specific states

• identify potential driver genes for each state

Installation

Install CellRank by running:

conda install -c conda-forge -c bioconda cellrank
# or with extra libraries, useful for large datasets
conda install -c conda-forge -c bioconda cellrank-krylov

or via PyPI:

pip install cellrank
# or with extra libraries, useful for large datasets
pip install 'cellrank[krylov]'

Support

We welcome your feedback! Feel free to open an issue or send us an email if you encounter a bug, need our help or just want to make a comment/suggestion.

CellRank was developed in collaboration between the Theislab and the Peerlab.