RNA velocity is a promising technique for quantifying cellular transitions from single-cell transcriptome experiments and revealing transient cellular dynamics among a heterogeneous cell population. However, the cell transitions estimated from high-dimensional RNA velocity are often unstable or inaccurate, partly due to the high technical noise and less informative projection.
Researchers at the University of Hong Kong have developed Velocity Autoencoder (VeloAE), a tailored representation learning method, to learn a low-dimensional representation of RNA velocity on which cellular transitions can be robustly estimated. On various experimental datasets, they show that VeloAE can both accurately identify stimulation dynamics in time-series designs and effectively capture expected cellular differentiation in different biological systems. VeloAE, therefore, enhances the usefulness of RNA velocity for studying a wide range of biological processes.
Overview of the VeloAE model with exemplified low-dimensional projection effects
Compared to a standard autoencoder, VeloAE has a cohort aggregation module with a GCN in the encoder and an attentive combination module as decoder. Once fitted, velocity can be jointly quantified in the lower-dimensional space of spliced and unspliced expressions. Examples in box: The cell transition probability and its directionality are smoothed and corrected from original space (Left) to a learned low-dimensional space (Right) for one cell to its neighboring cells (Upper Row) or for neighboring cells to a more consistent common differentiation direction (Lower Row).