PulseAugur
EN
LIVE 09:39:44

New AI Model Infers Human Aging Trajectories from DNA Methylation Data

Researchers have developed a novel computational pipeline to infer human aging trajectories from DNA methylation data. This two-stage approach utilizes a variational autoencoder to map methylation profiles onto a chronological latent space and then employs Regularized Unbalanced Optimal Transport (RUOT) to model continuous changes within this space. The DeepRUOT framework allows the model to accommodate population-level shifts and reconstruct distinct biological aging archetypes, offering a generative method for simulating molecular aging. AI

RANK_REASON The cluster contains a research paper detailing a new computational method for inferring biological aging from molecular data. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New AI Model Infers Human Aging Trajectories from DNA Methylation Data

COVERAGE [1]

  1. arXiv cs.LG TIER_1 English(EN) · Chandan Gupta, Syed Haider, Pietro Li\`o ·

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

    arXiv:2607.06583v1 Announce Type: cross 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 …