Deep dynamical models of single-cell multiomic velocities predict loss-of-function and rescue perturbations in B cells

Abstract

We present DynaVelo, a generative neural ordinary differential equation (ODE) model that learns the joint dynamics of gene expression and transcription factor (TF) motif activities in evolving cell systems using single-cell multiome data. DynaVelo leverages partial RNA velocity information together with single-cell TF motif accessibility data to improve the modeling of cell state dynamics and identification of TF drivers. We show that DynaVelo recovers the complex and bifurcating in vivo dynamics of wildtype murine germinal center (GC) B cells and reveals how these cell dynamics change under loss-of-function mutations in epigenetic regulators.

Alireza Karbalayghareh

Senior Research Scientist, AI/ML

My research focuses on developing universal AI models of gene regulation in immune cells, capturing cis-regulation, trans-regulation, and intercellular signaling by using single-cell multiomic observational, spatial, time-resolved, and perturbational data across diverse biological contexts to understand, engineer, and reprogram the immune system to prevent and treat diseases.