Machine Learning Immune Clock Built on Naive T Cells Tracks Immune Aging With R Near 0.9

A Chinese-born PI presented an ImmuneZoom AI4Science seminar on reshaping the aging immune system through primary lymphoid organs, covering a decade of work on HSC epigenetics, thymic involution-driven T cell aging, and a machine learning immune clock. The naive T cell-based multi-omics clock, N-time, was trained and validated in 4 independent cohorts with R of about 0.9, outperforming total T cell models at about 0.8. In chronic viral infection and autoimmune patients it predicted older immune ages, with accelerators linked to T cell activation, inflammation and cytotoxicity, and decelerators linked to ribosomal translation and TGF-beta signaling.