LMP Special Seminar: Inferring biophysical models of cell differentiation from single-cell omics data

Single-cell omics methods provide high-throughput, molecular-scale measurements of cellular processes, offering insights into the cell fate decision-making machinery. However, the high dimensionality, stochasticity, and cross-sectional nature of these measurements hinder their integration with biophysical models of gene regulation. Our research aims to bridge this gap by combining generative AI and biophysical models to reverse-engineer cell fate decision-making. I will present probability flow inference (PFI), a method we developed to infer biophysical models of gene regulation from time-resolved single-cell RNA-seq data. I will demonstrate that PFI can naturally account for intrinsic stochasticity and cellular proliferation, outperforming state-of-the-art generative models in identifying gene regulatory networks from Hematopoietic Stem Cell differentiation data.