Genetically Higher Level of Mannose Has No Impact on Cardiometabolic Risk Factors: Insight from Mendelian Randomization

Background: There is a handful of controversial data from observational studies on the serum levels of mannose and risks of coronary artery disease (CAD) and other cardiometabolic risk factors. We applied Mendelian Randomization (MR) analysis to obtain estimates of the causal effect of serum mannose on the risk of CAD and on cardiometabolic risk factors. Methods: Two-sample MR was implemented by using summary-level data from the largest genome-wide association studies (GWAS) conducted on serum mannose and CAD and cardiometabolic risk factors. The inverse variance weighted method (IVW) was used to estimate the effects, and a sensitivity analysis including the weighted median (WM)-based method, MR-Egger, MR-Pleiotropy RESidual Sum and Outlier (PRESSO) were applied. Radial MR Methods was applied to remove outliers subject to pleiotropic bias. We further conducted a leave-one-out analysis. Results: Mannose had no significant effect on CAD (IVW: odds ratio: 0.96 (95% Confidence Interval (95%CI): 0.71-1.30)), total cholesterol (TC) (IVW: 95%CI: 0.60-1.08), low density lipoprotein (LDL) (IVW: 95%CI = 0.68-1.15), high density lipoprotein (HDL) (IVW: 95%CI = 0.85-1.20), triglycerides (TG) (IVW: 95%CI = 0.38-1.08), waist circumference (WC) (IVW: 95%CI = 0.94-1.37), body mass index (BMI) (IVW: 95%CI = 0.93-1.29) and fasting blood glucose (FBG) (IVW: 95%CI = 0.92-1.33), with no heterogeneity for CAD, HDL, WC and BMI (all p > 0.092), while a significant heterogeneity was observed for TC (IVW: Q = 44.503), LDL (IVW: Q = 33.450), TG (IVW: Q = 159.645) and FBG (IVW: Q = 0. 32.132). An analysis of MR-PRESSO and radial plots did not highlight any outliers. The results of the leave-one-out method demonstrated that the links were not driven by a single instrument. Conclusions: We did not find any effect of mannose on adiposity, glucose, TC, LDL, TG and CAD.