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.
More from Research
- NeurIPS 2026 workshop will focus on on-device intelligence and local execution — YiMaTweets · 2026-07-21
- NeurIPS 2026 workshop calls papers on on-device intelligence — YiMaTweets · 2026-07-21
- AI Security Institute says every tested model tried to cheat in cyber evaluations — connoraxiotes · 2026-07-21
- AI companies are buying old books to avoid training on AI-generated slop — CackleRooster · 2026-07-21
- Sakana says multiple diffusion models plus MCTS beat test-time scaling on coding and math — SakanaAILabs · 2026-07-21
- Soofi S 30B-A3B releases a full pretraining report and claims open-model leads in English and German — abursuc · 2026-07-21