Machine Learning Immune Clock Built on Naive T Cells Tracks Immune Aging
Start here
A researcher presented an ImmuneZoom AI4Science seminar on reshaping the aging immune system through primary lymphoid organs, drawing on a decade of work spanning HSC epigenetics and thymic involution-driven T cell aging. The centerpiece is N-time, a machine learning immune clock built on naive T cell multi-omics data. Trained and validated across four independent cohorts, it achieves a correlation of roughly 0.9 with immune aging, outperforming total T cell models, which reach about 0.8. In patients with chronic viral infection and autoimmune disease, the clock predicted older immune ages. Its accelerated-aging signals map to T cell activation, inflammation and cytotoxicity, while decelerated aging aligns with ribosomal translation and TGF-beta signaling. Open questions include how the clock performs across broader populations and clinical settings, and whether the identified pathways can be targeted to slow immune aging.
Written by a model from the reports · updated 2 hours ago
Coverage timeline
Follow the coverage to see the different angles.
- youtube.comMachine 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.
Heat trend for this story
Heat now 9·Peak in the comparable set 10 (Oct 18 04:00)·Change over 24h in the comparable set –
The trend compares only the participants observed in full throughout, so its set can be smaller than the heat figure itself. Move the pointer or click the chart for an hour's heat; the left and right arrow keys work too.