Redefining Epigenetic Clocks with Manifolds and SDEs

anshulkundaje · x · 2026-07-10

Traditional epigenetic clocks typically treat aging as a static regression problem to predict biological age. This paper reformulates it as a trajectory inference problem: using a Variational Autoencoder (VAE) to map CpG profiles onto a chronologically ordered latent manifold, and then utilizing the velocity field of Stochastic Differential Equations (SDE) to model the continuous evolution of an individual's methylation landscape. The method requires only cross-sectional data to perform the analysis.

Original post →

More from Research

Research channel →