Trajectory Inference of Human Aging from Cross-Sectional DNA Methylation Data

2026-07-04

AI Summary

This study addresses the limitation of conventional epigenetic clocks, which yield only a single static age estimate and fail to capture the continuous dynamic evolution of DNA methylation profiles. The authors frame epigenetic aging as a trajectory inference problem and propose a two-stage framework: first, an age-regularized variational autoencoder constructs a temporally structured latent space; second, a regularized unbalanced optimal transport formulation (DeepRUOT) models continuous aging dynamics incorporating drift, diffusion, and mass variation. Requiring minimal biological priors, the method achieves robust distributional interpolation across an 80-year pan-tissue cross-sectional dataset, uncovers age-related expansion of epigenetic variability in later life, and successfully reconstructs individualized aging trajectories that are empirically verifiable.

Abstract

DNA methylation (DNAm) serves as one of the most robust molecular biomarkers of biological aging. While conventional epigenetic clocks accurately predict chronological age from high-dimensional CpG profiles, they treat aging as a static regression task, meaning they can only output a single score rather than simulating how an entire profile continuously changes over time. To reconstruct these continuous dynamics, we frame lifelong human epigenetic aging as a trajectory inference problem across discrete age snapshots derived from widely available cross-sectional data. We introduce a two-stage computational pipeline: first, an age-regularized Variational Autoencoder (VAE) maps high-dimensional CpG profiles onto a chronologically ordered latent manifold while preserving a generative decoder bridge back to the original methylation space. Second, we model the continuous movement across this latent space via Regularized Unbalanced Optimal Transport (RUOT) that unifies deterministic drift, random diffusion, and non-conservative mass changes. By resolving this RUOT formulation using the DeepRUOT framework, our model fluidly accommodates population-level density shifts like survivorship bias and cellular attrition without requiring rigid biological priors. Evaluated on a large-scale, 80-year pan-tissue dataset, our model demonstrates robust distribution interpolation and uncovers a prominent late-life surge in the learned growth field that mathematically captures the variance expansion driven by stochastic epigenetic drift. Finally, by decoding continuous latent paths back to individual CpG sites, we reconstruct and empirically verify distinct biological aging archetypes, offering a rigorous, generative paradigm for simulating human molecular aging.

Problem

• Trajectory Inference
• DNA Methylation
• Biological Aging
• Cross-Sectional Data
• Epigenetic Clocks

Innovation

• Trajectory Inference
• Variational Autoencoder
• Optimal Transport
• DNA Methylation
• Epigenetic Aging