A latent space thermodynamic model of cell differentiation

Abstract

Inferring the governing dynamics of differentiation that capture cell state evolution remains a central challenge in single-cell biology. We present Single-Cell Latent Space Dynamics (scLSD), a thermodynamics-inspired framework that models cell differentiation as evolution on a learned Waddington landscape in latent space. scLSD jointly infers a low-dimensional cell state, a differentiable potential function governing developmental flow, and a local entropy term that associates with cellular plasticity. Using a neural ordinary differential equation, scLSD reconstructs continuous differentiation trajectories from time-ordered single-cell data. Across diverse developmental systems, scLSD accurately recovers lineage hierarchies, predicts fate commitment for unseen cell types, and outperforms existing trajectory inference approaches in directional and cell fate prediction accuracy. In silico gene perturbations reveal how individual regulators reshape the landscape, and the proposed entropy measure is informative of plasticity in development and cancer.