VeloCycle is a Bayesian model of RNA velocity that couples velocity field and manifold estimation in a unified framework, enabling formal statistical testing of gene expression dynamics. It fits an inferentially coherent model directly on raw data, eliminating heuristics that dominate current scRNA analyses.
Key features: - Formal statistical testing of dynamics - End-to-end Bayesian inference - Cell cycle speed quantification - Manifold-constrained velocity estimation
Find the GitHub repo here