Comprehensive RNA velocity by modeling the cascade of gene regulation, transcription, and splicing from single-cell RNA sequencing data with TSvelo.

Abstract

RNA velocity approaches fit gene dynamics and infer cell fate by modeling the splicing process using single-cell RNA sequencing (scRNA-seq) data. However, due to the short time scale of splicing, high noise, and large complexity of data, existing RNA velocity methods often fail to precisely capture the complex velocity dynamics for individual genes and single cells, which makes their downstream analysis less reliable and less robust. We propose <b>TSvelo</b>, a comprehensive RNA <b>velo</b>city mathematics framework that can model the cascade of gene regulation, <b>T</b>ranscription and <b>S</b>plicing using highly interpretable neural ordinary differential equations. TSvelo can precisely capture the transcription-unspliced-spliced 3D dynamics of all genes simultaneously, infer unified latent time shared by genes within a single cell, and be applied to multi-lineage datasets. Experiments on six scRNA-seq datasets, including two multi-lineage datasets, demonstrate TSvelo's superiority.