A multi-tissue full lifespan epigenetic clock for mice

Abstract

Human DNA-methylation data have been used to develop highly accurate biomarkers of aging ("epigenetic clocks"). Recent studies demonstrate that similar epigenetic clocks for mice (Mus Musculus) can be slowed by gold standard anti-aging interventions such as calorie restriction and growth hormone receptor knock-outs. Using DNA methylation data from previous publications with data collected in house for a total 1189 samples spanning 193,651 CpG sites, we developed 4 novel epigenetic clocks by choosing different regression models (elastic net- versus ridge regression) and by considering different sets of CpGs (all CpGs vs highly conserved CpGs). We demonstrate that accurate age estimators can be built on the basis of highly conserved CpGs. However, the most accurate clock results from applying elastic net regression to all CpGs. While the anti-aging effect of calorie restriction could be detected with all types of epigenetic clocks, only ridge regression based clocks replicated the finding of slow epigenetic aging effects in dwarf mice. Overall, this study demonstrates that there are trade-offs when it comes to epigenetic clocks in mice. Highly accurate clocks might not be optimal for detecting the beneficial effects of anti-aging interventions.

Keywords: DNA methylation; biological age; epigenetic clock; mouse.

Figure 1

Accuracy of ridge regression epigenetic age predictions. DNA methylation age (y-axis) versus chronological age (x-axis) for all mouse samples. (a) Performance of ridge regression clock based on all 192K CpGs in all training samples. The training set estimates of the accuracy are overly optimistic and should be ignored. (b) Results by tissue type of cross-validated predictions obtained by iteratively withholding one “batch” (tissue x publication). For the batch cross-validation of this clock, the global Pearson correlation between predicted and chronological age was 0.79 (p < 2E-195) with a mae of 3.1 months. All models in these iterative cross-validations had the same size of 193,651 CpGs. (c) Scatter plots by tissue type based on DNAm age estimates made with an iterative leave-one-sample-out cross-validation. The correlation between predicted and chronologic age was 0.85 (p < 6E-258) with a mae of 2.1 months.

Figure 2

Age acceleration due to diet treatments. Results obtained from ridge regression clock. A meta-analysis p-value for the 3 calorie-restriction (CR) experiments is included. (a) Calorie restriction versus standard diet in the C57BL/J strain. (b) Calorie restriction versus standard chow diet in the B6D2F1 strain. (c) Calorie restriction versus standard diet for the HET3 strain. d) Rapamycin enriched diet versus standard diet for the HET3 strain.

Figure 3

Age acceleration and Dwarfism in mice. Results obtained from ridge regression clock. A meta-analysis p-value for the 3 experiments is included. (a) Genetic knockout dwarf mice versus wild type. (b) Snell dwarf mice versus wild type. c) Ames Dwarf mice versus wild type.

Figure 4

Age acceleration and maternal diet. Results obtained from ridge regression clock. (a) Offspring of mothers fed a high fat diet (HFD) who were fed either a high fat or low fat diet (LFD). (b) Offspring of mothers fed a low fat diet who were fed either a high fat or low fat diet.

Figure 5

Genome-wide association results for DNAm Age. (a) Manhattan plot presenting genome-wide association results for DNAm Age. Epigenetic age predictions were calculated using all CpGs clock with ridge regression and leave-one-sample-out estimates. GWAS analysis was based on linear mixed model and a set of 196,148 SNPs (MAF > 0.05) from HMDP mice strains. (b) This SNP as identified using GWAS analysis of epigenetic age predictions. It is located in an LD block on chromosome 6 and contains the genes Npy, Mpp6, Gsdme and Osbp13. A one-sided t-test of DNAm ages between the two allelic groups shown is statistically significant. (c) It is located in an LD block on chromosome 6 and contains the genes Npy, Mpp6, Gsdme and Osbp13. A one-sided t-test of DNAm ages between the two allelic groups shown is statistically significant.