Telomere length and metabolic syndrome traits: A Mendelian randomisation study

Abstract

Observational studies have revealed associations between short leucocyte telomere length (LTL), a TL marker in somatic tissues and multiple Metabolic Syndrome (MetS) traits. Animal studies have supported these findings by showing that increased telomere attrition leads to adipose tissue dysfunction and insulin resistance. We investigated the associations between genetically instrumented LTL and MetS traits using Mendelian Randomisation (MR). Fifty-two independent variants identified at FDR<0.05 from a genome-wide association study (GWAS) including 78,592 Europeans and collectively accounting for 2.93% of LTL variance were selected as genetic instruments for LTL. Summary-level data for MetS traits and for the MetS as a binary phenotype were obtained from the largest publicly available GWAS and two-sample MR analyses were used to estimate the associations of LTL with these traits. The combined effect of the genetic instruments was modelled using inverse variance weighted regression and sensitivity analyses with MR-Egger, weighted-median and MR-PRESSO were performed to test for and correct horizonal pleiotropy. Genetically instrumented longer LTL was associated with higher waist-to-hip ratio adjusted for body mass index (β = 0.045 SD, SE = 0.018, p = 0.01), raised systolic (β = 1.529 mmHg, SE = 0.332, p = 4x10^-6 ) and diastolic (β = 0.633 mmHg, SE = 0.222, p = 0.004) blood pressure, and increased MetS risk (OR = 1.133, 95% CI 1.057-1.215). Consistent results were obtained in sensitivity analyses, which provided no evidence of unbalanced horizontal pleiotropy. Telomere shortening might not be a major driver of cellular senescence and dysfunction in human adipose tissue. Future experimental studies should examine the mechanistic bases for the links between longer LTL and increased upper-body fat distribution and raised blood pressure.

Keywords: GWAS; Mendelian randomisation; adipose tissue; ageing; metabolic syndrome; telomeres.

FIGURE 1

Scatter plots showing the relationship of genetically instrumented LTL on the x‐axis, against the following outcomes on the y‐axis: (a) WHRadjBMI (n = 46 SNP instruments), (b) waist circumference adjusted for BMI (n = 30 SNP instruments), (c) systolic blood pressure (n = 45 SNP instruments) and (d) diastolic blood pressure (n = 45 SNP instruments). Data points and error bars are betas ± SEs from the respective GWAS summary statistics