"scVelo" predicts cell development
Mathematical method for the analysis of gene activity
How do cells develop? A research team from the Department of Mathematics at the Technical University of Munich (TUM) and the Institute of Computational Biology (ICB) at Helmholtz Zentrum Munich has developed the open source software "scVelo" (Single-cell Velocity), which calculates the dynamics of gene activity in single cells. This allows biologists to robustly predict the future state of individual cells.
Approximation of the RNA velocity
The recently introduced method "RNA Velocity" enables the computational reconstruction of the developmental course of an individual cell and predicts the future state on a timescale of hours. This is done by determining the RNA velocity - the temporal deviation of the expression state of a single gene. The basis is the ratio of its unspliced (pre-m RNA) to its spliced messenger RNA (mRNA). Splicing is a step in the further processing of the RNA.
However, the method was previously only applicable to steady-state cell populations. With "scVelo", the researchers have now methodically extended the concept of "RNA velocity".
Single-cell Velocity decodes cell developments
"scVelo" uses a likelihood-based dynamical model to estimate RNA velocity. An artificial intelligence (AI) solves the full gene-wise transcriptional dynamics. This allows researchers to generalize the concept of RNA velocity to a wide variety of biological systems including dynamic populations. These cell populations are of crucial importance to understand cell development and disease response.
"We have used scVelo to reveal cell development in the endocrine pancreas, in the hippocampus, and to study dynamic processes in lung regeneration – and this is just the beginning", says Volker Bergen, main creator of scVelo and first author of the corresponding study Generalizing RNA velocity to transient cell states through dynamical modeling in Nature Biotechnology.
With scVelo, researchers can estimate reaction rates of RNA transcription, splicing and degradation without the need of any experimental data. These rates can help to better understand the cell identity and phenotypic heterogeneity. Their introduction of a latent time reconstructs the unknown developmental time to position the cells along the trajectory of the underlying biological process. That is particularly useful to better understand cellular decision-making. Moreover, scVelo reveals regulatory changes and putative driver genes therein.
A boost for personalized and predictive medicine
AI-based tools like scVelo give rise to personalized treatments. Going from static snapshots to full dynamics allows researchers to move from descriptive towards predictive models. In the future, this might help to better understand disease progression such as tumor formation, or to unravel cell signaling in response to cancer treatment.
"scVelo has been downloaded almost 60.000 times since its release last year. It has become a stepping-stone tool towards the kinetic foundation for single-cell transcriptomics", adds Fabian Theis, Professor of Mathematical Modelling of Biological Systems at the TUM and Director at the ICB, who conceived the study.
This article is based on the original ICB press release: AI & Single Cell Genomics: New Software Predicts the Fate of a Cell