Mendelian Randomization and Type 2 Diabetes

Abstract

Type 2 diabetes (T2DM) is a common, complex disease that poses a substantial burden on individual and population health, but we have relatively limited understanding of its underlying pathophysiology. Observational studies have highlighted large numbers of risk factors for T2DM, some of which are modifiable through behavioural or pharmacological intervention. Determining which of these risk factors plays a causal role in the development of T2DM has been a challenge, but Mendelian randomisation (MR) studies are harnessing genetic data in population studies to offer new insights. Using evolving analytical methods, MR studies continue to address questions of causality related to T2DM, including exploring the roles of adiposity, blood lipids and inflammation. The causal roles of a number of important modifiable risk factors have been confirmed by MR studies, while the relevance of others has been called into question. As more MR studies are conducted, methods are developed and refined in order to make the most efficient and reliable use of available genetic and phenotypic data. In this review, the design and findings of some important MR studies related to T2DM are explored and their relevance for translation to clinical practice considered.

Keywords: Causal inference; Mendelian randomisation; Risk factors; Type 2 diabetes.

Fig. 1

Mendelian randomisation studies in type 2 diabetes. MR studies can help to demonstrate the causal relevance of a biomarker or risk factor to risk of developing T2DM. They can also incorporate proteomic, metabolomics, and transcriptomic data, and other bioinformatics resources in order to investigate the biological pathways linking the gene to disease aetiology