Effect of long-term caloric restriction on DNA methylation measures of biological aging in healthy adults from the CALERIE trial

Abstract

The geroscience hypothesis proposes that therapy to slow or reverse molecular changes that occur with aging can delay or prevent multiple chronic diseases and extend healthy lifespan^1-3. Caloric restriction (CR), defined as lessening caloric intake without depriving essential nutrients⁴, results in changes in molecular processes that have been associated with aging, including DNA methylation (DNAm)^5-7, and is established to increase healthy lifespan in multiple species^8,9. Here we report the results of a post hoc analysis of the influence of CR on DNAm measures of aging in blood samples from the Comprehensive Assessment of Long-term Effects of Reducing Intake of Energy (CALERIE) trial, a randomized controlled trial in which n = 220 adults without obesity were randomized to 25% CR or ad libitum control diet for 2 yr (ref. ¹⁰). We found that CALERIE intervention slowed the pace of aging, as measured by the DunedinPACE DNAm algorithm, but did not lead to significant changes in biological age estimates measured by various DNAm clocks including PhenoAge and GrimAge. Treatment effect sizes were small. Nevertheless, modest slowing of the pace of aging can have profound effects on population health^11-13. The finding that CR modified DunedinPACE in a randomized controlled trial supports the geroscience hypothesis, building on evidence from small and uncontrolled studies^14-16 and contrasting with reports that biological aging may not be modifiable¹⁷. Ultimately, a conclusive test of the geroscience hypothesis will require trials with long-term follow-up to establish effects of intervention on primary healthy-aging endpoints, including incidence of chronic disease and mortality^18-20.

Fig. 1. Consort diagram for the CALERIE Trial.

DNAm was assayed from blood samples collected at baseline, 12 months and 24 months. Of the n = 197 participants for whom DNAm data were available from baseline and at least one follow-up assessment, baseline to 12-month change was measured for n = 125 CR and n = 66 AL participants and baseline to 24-month change was measured for n = 117 CR and n = 68 AL participants.

Fig. 2. Change from baseline to 12- and 24-month follow-up in DNAm measures of aging in the AL and CR groups in the CALERIE Trial.

The figure shows CALERIE Trial treatment effects on three DNAm measures of aging, the PC PhenoAge clock, the PC GrimAge clock and DunedinPACE. Values for the AL control group (n = 69 participants) are graphed in blue. Values for the CR treatment group (n = 128 participants) are graphed in red. For the PhenoAge and GrimAge DNAm clocks, values are denominated in ‘years’ of DNAm age. For the clocks, expected change under the null hypothesis is 1 yr at 12-month follow-up and 2 yr at 24-month follow-up. For the DunedinPACE measure, values are denominated in pace-of-aging units scaled to be interpretable as percentage difference in the rate of aging relative to the reference norm of 1 yr of biological decline per calendar year. For DunedinPACE, expected change under the null hypothesis is zero. The left column of the figure shows box plots of the observed values of the measures at baseline and 12- and 24-month follow-ups. The boxes show the interquartile range; the whiskers show 1.5× the interquartile range; the center line shows the median; individual participant data are plotted as dots and connected with lines. For the PC PhenoAge and PC GrimAge DNAm clocks, the box plots show similar patterns of increase in both AL and CR groups. For DunedinPACE, the box plot shows stability in the AL group and decrease in the CR group. The right column of the figure shows mean values of change from baseline and 95% CIs estimated from mixed models at the 12- and 24-month follow-ups for the AL and CR groups. There is no confidence interval estimated for baseline because change from baseline is exactly zero at this timepoint. For the PC PhenoAge and PC GrimAge DNAm clocks, mean change is similar in the AL and CR groups. For DunedinPACE, mean change is positive in the AL group (although the confidence interval overlaps zero at 24 months) and negative in the CR group. mo, months. Source data