Learning biophysical models of gene regulation with probability flow matching

2026-04-27

AI Summary

Current methods struggle to infer gene regulatory dynamics from single-cell RNA sequencing data that are both mechanistically interpretable and generalizable across conditions. This work proposes a Probabilistic Flow Matching (PFM) framework that, for the first time, integrates biophysical consistency constraints into stochastic process modeling to directly learn regulatory-mechanism-compliant dynamical systems from time-resolved single-cell data. PFM accurately captures cell fate decisions, lineage transitions, and perturbation responses while jointly inferring proliferation and death dynamics. Experiments on three hematopoietic datasets demonstrate that PFM not only achieves high-precision interpolation but also correctly recapitulates lineage transitions, fate specification, and genetic perturbation effects, significantly outperforming non-mechanistic baseline approaches.

Abstract

Cellular differentiation is governed by gene regulatory networks, the high-dimensional stochastic biochemical systems that determine the transcriptional landscape and mediate cellular responses to signals and perturbations. Although single-cell RNA sequencing provides quantitative snapshots of the transcriptome, current methods for inferring gene-regulatory dynamics often lack mechanistic interpretability and fail to generalize to unseen conditions. Here we introduce Probability Flow Matching (PFM), a scalable framework for learning biophysically consistent stochastic processes directly from time-resolved single-cell measurements. Applying PFM to three hematopoiesis datasets, we show that models with similar interpolation accuracy can encode fundamentally different dynamics, with only biophysically consistent formulations accurately capturing mechanisms of lineage transitions, fate specification, and gene perturbation responses. We further demonstrate that PFM accommodates unbalanced populations, enabling simultaneous inference of cellular proliferation and death dynamics. Together, these results establish PFM as a flexible, scalable framework for integrating mechanistic modeling with single-cell omics.

Problem

• gene regulatory networks
• single-cell RNA sequencing
• mechanistic interpretability
• generalization
• cellular differentiation

Innovation

• Probability Flow Matching
• gene regulatory networks
• single-cell RNA sequencing
• biophysical modeling
• cellular dynamics