cellrank  by scverse

Cellular dynamics framework for multi-view single-cell data

Created 6 years ago
432 stars

Top 68.9% on SourcePulse

GitHubView on GitHub
1 Expert Loves This Project
Project Summary

CellRank provides a unified framework for analyzing cellular dynamics using Markov state modeling on multi-view single-cell data. It empowers researchers and bioinformaticians to infer complex cellular processes like differentiation, fate mapping, and gene expression trends, offering significant benefits in understanding biological systems.

How It Works

CellRank employs Markov state modeling to capture the probabilistic transitions between cellular states derived from multi-view single-cell data. Its core advantage lies in its modularity and compatibility with the scverse ecosystem, allowing integration with various biological priors such as RNA velocity, pseudotime, or experimental time points. This approach, powered by the pyGPCCA backend, enables scalable and robust analysis of cellular dynamics.

Quick Start & Requirements

  • Primary install: pip install cellrank
  • Prerequisites: Fully compatible with the scverse ecosystem. Specific Python versions or hardware requirements are not detailed in the provided text.
  • Documentation: https://cellrank.readthedocs.io/

Highlighted Details

  • Estimates differentiation direction using diverse priors including RNA velocity, pseudotime, and developmental potential.
  • Computes initial, terminal, and intermediate macrostates.
  • Infers fate probabilities and identifies driver genes.
  • Facilitates visualization and clustering of gene expression trends.

Maintenance & Community

CellRank is part of the scverse ecosystem, indicating a collaborative development environment. Users are encouraged to open issues for bugs, suggestions, or support. Specific community channels or contributor details are not provided.

Licensing & Compatibility

The license type is not explicitly stated in the provided README. This absence may pose compatibility concerns for commercial use or integration into closed-source projects.

Limitations & Caveats

The provided README does not detail specific limitations, unsupported platforms, or known bugs. The lack of an explicit license is a notable omission requiring further investigation for adoption.

Health Check
Last Commit

4 days ago

Responsiveness

Inactive

Pull Requests (30d)
30
Issues (30d)
5
Star History
9 stars in the last 30 days

Explore Similar Projects

Starred by Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), Vincent Weisser Vincent Weisser(Cofounder of Prime Intellect), and
2 more.

evo by evo-design

0.3%
1k
DNA foundation model for long-context biological sequence modeling and design
Created 2 years ago
Updated 3 weeks ago
Feedback? Help us improve.