Multi-Omic Associations of Epigenetic Age Acceleration Are Heterogeneously Shaped by Genetic and Environmental Influences

Abstract

Connections between the multi-ome and epigenetic age acceleration (EAA), and especially whether these are influenced by genetic or environmental factors, remain underexplored. We therefore quantified associations between the multi-ome comprising four layers-the proteome, metabolome, external exposome (here, sociodemographic factors), and specific exposome (here, lifestyle)-with six different EAA estimates. Two twin cohorts were used in a discovery-replication scheme, comprising, respectively, young (N = 642; mean age = 22.3) and older (N = 354; mean age = 62.3) twins. Within-pair twin designs were used to assess genetic and environmental effects on associations. We identified 40 multi-omic factors, of which 28 were proteins, associated with EAA in the young twins while adjusting for sex, smoking, and body mass index. Within-pair analyses revealed that genetic confounding influenced these associations heterogeneously, with six multi-omic factors -matrix metalloproteinase 9, complement component C6, histidine, glycoprotein acetyls, lactate, and neighborhood percentage of nonagenarians- remaining significantly associated with EAA, independent of genetic effects. Replication analyses showed that some associations assessed in young twins were consistent in older twins. Our study highlights the differential influence of genetic effects on the associations between the multi-ome and EAA and shows that some, but not all, of the associations persist into adulthood.

Keywords: environment; epigenetic age acceleration; genetics; multi‐omics; twins.

FIGURE 1

Study flow chart. The study was divided into three stages. The first was to quantify the associations between EAA and multi‐omic factors with all twin individuals from the FinnTwin12 cohort, referred to as between‐pair analyses. Next, within‐pair analyses were carried out on all complete same‐sex twin pairs. Finally, replication of the proteins and metabolites identified in FinnTwin12 was performed in the external EH‐Epi sample. EAA: Epigenetic Age Acceleration. MZ pairs: Monozygotic pairs. DZ pairs: Dizygotic pairs.

FIGURE 2

Between‐pair analyses reveal numerous associations between epigenetic age acceleration and multi‐omic factors. Linear mixed‐effect models were used to quantify associations between EAA and multi‐omics factors in between‐pair analyses. Sex, body mass index, and smoking were used as covariates. Correction for multiple testing was based on the number of principal components needed to cover 95% of the initial variance for each omic and is indicated by a solid line. A description of the multi‐omics factors is available in the Supporting Information (Table S2). EAA: Epigenetic age acceleration. p: p value resulting from testing the nullity of the multi‐omic factor coefficient.

FIGURE 3

Common associations between multi‐omic factors and EAA across different EAA estimates, and omic specificities of different EAA estimates. (A) Radar plot showing the number of associations between EAA and proteins, metabolites, and lifestyle or exposome variables for each EAA estimate. Only the GrimAge and GrimAge2 estimates were associated with exposome variables, whereas the DunedinPACE estimate showed a greater number of associations with plasma omics. (B) Upset plot showing the overlap of identified proteins across the 6 EAA estimates. 62% of these proteins were associated with more than one EAA estimate. (C) Circos plots showing the pairwise number of shared associations between EAA estimates. The six circos plots are identical, with connections between an EAA estimate and others colored in red. The thicker the connection between two EAA estimates, the more they share common associations with multi‐omic factors. For example, the DunedinPACE EAA estimate is associated with several multi‐omic factors that are also associated with the GrimAge, GrimAge2, and PhenoAge estimates, but very few with Hannum and Horvath (see circos plot at the bottom right).

FIGURE 4

Comparisons between MZ and DZ pairs in within‐pair analyses provide evidence for genetic confounding in associations. (A) Comparison of estimates in MZ [$\beta$(within MZ pairs)] and DZ [$\beta$(within DZ pairs)] pairs for multi‐omics factors significantly associated with EAA in all pairs [$\beta$(within all pairs)]. Multi‐omics factors located farthest down and to the right are those for which the genetic effects in the association are most intense, as indicated by the arrows on the side of the plot. Conversely, weak genetic effects in associations are indicated by multi‐omics factors with coefficient ratios close to 1. (B) For most multi‐omic factors associated with EAA in all pairs, estimates in DZ twins [$\beta$(within DZ pairs)] are higher than those in MZ twins [$\beta$(within MZ pairs)]. The lower the ratio of MZ to DZ pair coefficients, the more likely the genetic confounding in these associations with EAA. EAA: Epigenetic age acceleration. Variable descriptions are available in the Supporting Information (Table S2).

FIGURE 5

Replication of between‐pair and within‐pair findings from FinnTwin12 young adult twins in the EH‐Epi sample of older adults. (A) Standardized coefficients and their 95% confidence intervals in the EH‐Epi sample next to those found in FinnTwin12. Almost half of the replicated associations had a nominal p value testing the null of the coefficients below 0.05, 9 of which were robust to Bonferroni correction. (B) Comparison of standardized coefficients obtained in within‐pair analyses in the EH‐Epi sample with those found in FinnTwin12 in three configurations: In all pairs, in DZ pairs only, and in MZ pairs only. Associations with nominal p values below 0.05 are labeled and their 95% confidence intervals are shown. The shape of the dots indicates whether the associations were robust to the Bonferroni correction considering all associations tested. Metabolites are annotated with their complete name, with the exception of Glyc. acetyls, being glycoprotein acetyls. Proteins are annotated with their coding genes. C9: Complement component C9. MPO: Myeloperoxidase. MMP9: Matrix metalloproteinase‐9. LRG1: Leucine‐rich alpha‐2‐glycoprotein. CLEC3B: Tetranectin. SERPINA4: Kallistatin. PTPRS: Receptor‐type tyrosine‐protein phosphatase S. SERPINC1: Antithrombin‐III. APOH: Beta‐2‐glycoprotein 1. LAMB1: Laminin subunit beta‐1. CNTN1: Contactin‐1. C5: Complement component C5. TTR: Transthyretin. DPP4: Dipeptidyl peptidase 4. COMP: Cartilage oligomeric matrix protein. CFHR5: Complement factor H‐related protein 5.