An Overview of Methods and Exemplars of the Use of Mendelian Randomisation in Nutritional Research

Abstract

Objectives: It is crucial to elucidate the causal relevance of nutritional exposures (such as dietary patterns, food intake, macronutrients intake, circulating micronutrients), or biomarkers in non-communicable diseases (NCDs) in order to find effective strategies for NCD prevention. Classical observational studies have found evidence of associations between nutritional exposures and NCD development, but such studies are prone to confounding and other biases. This has direct relevance for translation research, as using unreliable evidence can lead to the failure of trials of nutritional interventions. Facilitated by the availability of large-scale genetic data, Mendelian randomization studies are increasingly used to ascertain the causal relevance of nutritional exposures and biomarkers for many NCDs. Methods: A narrative overview was conducted in order to demonstrate and describe the utility of Mendelian randomization studies, for individuals with little prior knowledge engaged in nutritional epidemiological research. Results: We provide an overview, rationale and basic description of the methods, as well as strengths and limitations of Mendelian randomization studies. We give selected examples from the contemporary nutritional literature where Mendelian randomization has provided useful evidence on the potential causal relevance of nutritional exposures. Conclusions: The selected exemplars demonstrate the importance of well-conducted Mendelian randomization studies as a robust tool to prioritize nutritional exposures for further investigation.

Keywords: biomarkers; causal; exposures; genetics; mendelian randomisation; non-communicable disease.

Figure 1

Number of published Mendelian Randomization studies related to nutrition in Pubmed from 2010 up to 10 June 2022.

Figure 2

Comparison of a conventional trial with a Mendelian Randomization study. This illustrates the analogy between a conventional randomized controlled trial and a Mendelian randomization study. Δ represents the change.

Figure 3

Illustration of the three key assumptions of Mendelian Randomization studies. This illustrates the relevance, independence and exclusion restriction assumptions of Mendelian Randomization with selenium as the modifiable nutritional exposure. The relevance assumption can be easily tested, and is considered as fulfilled if the SNP-exposure association has an F-statistic > 10. The independence assumption is hard to validate as problems due to pleiotropy and population substructure may occur but associations with known confounders should be null. In general, the exclusion restriction assumption is hard to validate as there may be pleiotropic effects of SNPs or SNPs in linkage disequilibrium correlated with genes that have effects on the outcome independently of the exposure. It is important to perform a variety of sensitivity analyses that make different assumptions about pleiotropy.

Figure 4

Simplified illustration of (a) horizontal and (b) vertical pleiotropy in Mendelian Randomization in nutritional research. This illustrates that (a) horizontal pleiotropy occurs when the SNPs have effects on multiple exposures that are independent of each other; (b) vertical pleiotropy occurs where the effects of one exposure can have a downstream impact on another related exposure. SNP: Single nucleotide polymorphism; SBP: Systolic blood pressure; LDL-C: Low density lipoprotein cholesterol; CAD: Coronary Artery Disease.