June 2nd, 2026
Researchers continue to produce new aging clocks at a fair pace. Any sufficiently complex set of biological data obtained from people of various ages can yield a clock given the use of various forms of machine learning. It is straightforward to make a new clock. Most of these will vanish into obscurity, as they will demonstrate no advantages over existing, more well studied clocks. The need is not for new clocks, but to solve the challenges inherent in the use of any clock, which is to say that it is entirely unclear as to whether a clock provides a reasonable representation of biological aging, and whether it can be trusted as an assessment of any given intervention to slow or reverse aspects of aging. The research community struggles to connect clock parameters to aging in any meaningful way that yields confidence in the ability of a clock to assess novel forms of therapy.
Amino acids are fundamental to human physiology, yet their impact on growth, development, and aging remains elusive. Here, we introduce AmiAge, a biological age predictor constructed using a Random Forest model trained on the concentrations of 18 amino acids across individuals aged 1 to 89 years. Leveraging data from 9 studies encompassing over 11,000 in-house and more than 270,000 publicly available samples with diverse demographic and genetic backgrounds,
