Genome-wide methylation prediction of biological age using reproducing kernel Hilbert spaces and Bayesian ridge regressions

The use of DNA methylation signatures to predict chronological age and the aging rate is of interest in many fields, including disease prevention and treatment, forensics, and anti-aging medicine. Although a large number of methylation markers have been found to be significantly associated with age, most age-prediction methods use a small number of markers selected based on either previously published studies or datasets containing methylation information. Here, we implemented reproducing kernel Hilbert spaces (RKHS) regression and ridge regression model in a Bayesian framework that utilized phenotypic and methylation profiles simultaneously to predict chronological age. We used over 450,000 CpG sites from the whole blood of a large cohort of 4,409 human individuals with a range of 10-101 years of age. Models were fitted using adjusted and un-adjusted methylation measurements for cell heterogeneity. Non-adjusted methylation scores delivered a significantly higher prediction accuracy than adjusted methylation data, with a correlation between age and predicted age of 0.98 and a root-mean-square error (RMSE) of 3.54 years in non-adjusted data, 0.90 (correlation) and 7.16 (RMSE) years in adjusted data. Reducing the number of predictors through subset selection improved predictive power with a correlation of 0.98 and an RMSE of 2.98 years in the RKHS model. We found distinct global methylation patterns, with significant hypermethylation in CpG islands and hypomethylation in other CpG types including CpG shore, shelf, and open sea (p < 5e-06). Epigenetic drift seemed to be a widespread phenomenon as more than 97% of the age-associated methylation sites had heteroscedasticity. Apparent methylomic aging rate (AMAR) had a sex-specific pattern, with an increase in AMAR in females with age compared to males.