Translating cellular aging clocks into disease risk prediction

Cell Rep Med. 2026 Aug 18;7(8):102996. doi: 10.1016/j.xcrm.2026.102996.

ABSTRACT

Ding et al. mapped over 7,000 plasma proteins to more than 40 cell types and developed machine learning aging clocks across 60,000 individuals, demonstrating that cell-type-specific biological aging is heterogeneous, measurable from blood alone, and powerfully predictive of neurodegenerative disease, cancer, and mortality up to 15 years before clinical onset.¹.

PMID:42612620 | DOI:10.1016/j.xcrm.2026.102996