Chronological age prediction from DNA methylation sheds light on human aging, health, and lifespan. Current clocks are mostly based on linear models and rely upon hundreds of sites across the genome. Here, we present GP-age, an epigenetic non-linear cohort-based clock for blood, based upon 11,910 methylomes. Using 30 CpG sites alone, GP-age outperforms state-of-the-art models, with a median accuracy of ∼2 years on held-out blood samples, for both array and sequencing-based data. We show that aging-related changes occur at multiple neighboring CpGs, with implications for using fragment-level analysis of sequencing data in aging research. By training three independent clocks, we show enrichment of donors with consistent deviation between predicted and actual age, suggesting individual rates of biological aging. Overall, we provide a compact yet accurate alternative to array-based clocks for blood, with applications in longitudinal aging research, forensic profiling, and monitoring epigenetic processes in transplantation medicine and cancer.
Bibliographical noteFunding Information:
We wish to thank Nir Friedman, Netanel Loyfer, Alon Appleboim, Josh Moss, Mor Nitzan, Yair Weiss, Roy Friedman, Michael Hassid, and members of the Kaplan and Dor labs for helpful discussions and comments. This work was supported by grants from the Israel Science Foundation ( 1250/18 ), the Center for Interdisciplinary Data Science Research , and the Israeli Center for Forensic DNA , by the Ministry of Innovation, Science and Technology . M.V. is supported by excellence fellowships from KLA and from the School of Computer Science and Engineering.
© 2023 The Author(s)
- CP: Genetics
- CP: Systems biology
- DNA methylation
- computational biology
- machine learning