MRC Biostatistics Unit, University of Cambridge, Cambridge, UK; Sydney School of Public Health, University of Sydney, Sydney, NSW, Australia.
MRC Biostatistics Unit, University of Cambridge, Cambridge, UK; Cardiovascular Epidemiology Unit, University of Cambridge, Cambridge, UK.
Am J Hum Genet. 2024 Jan 4;111(1):165-180. doi: 10.1016/j.ajhg.2023.12.002.
Mendelian randomization uses genetic variants as instrumental variables to make causal inferences on the effect of an exposure on an outcome. Due to the recent abundance of high-powered genome-wide association studies, many putative causal exposures of interest have large numbers of independent genetic variants with which they associate, each representing a potential instrument for use in a Mendelian randomization analysis. Such polygenic analyses increase the power of the study design to detect causal effects; however, they also increase the potential for bias due to instrument invalidity. Recent attention has been given to dealing with bias caused by correlated pleiotropy, which results from violation of the "instrument strength independent of direct effect" assumption. Although methods have been proposed that can account for this bias, a number of restrictive conditions remain in many commonly used techniques. In this paper, we propose a Bayesian framework for Mendelian randomization that provides valid causal inference under very general settings. We propose the methods MR-Horse and MVMR-Horse, which can be performed without access to individual-level data, using only summary statistics of the type commonly published by genome-wide association studies, and can account for both correlated and uncorrelated pleiotropy. In simulation studies, we show that the approach retains type I error rates below nominal levels even in high-pleiotropy scenarios. We demonstrate the proposed approaches in applied examples in both univariable and multivariable settings, some with very weak instruments.
孟德尔随机化使用遗传变异作为工具变量，对暴露对结局的影响进行因果推断。由于最近高通量全基因组关联研究的大量出现，许多有潜在因果关系的暴露因素都有大量独立的遗传变异与之相关联，每个变异都代表着一种潜在的工具变量，可用于孟德尔随机化分析。这种多基因分析增加了研究设计检测因果效应的能力；然而，它们也增加了由于工具无效而导致偏差的可能性。最近人们开始关注由相关多效性引起的偏差，这是由于违反了“工具强度独立于直接效应”的假设。尽管已经提出了可以解决这种偏差的方法，但在许多常用技术中仍然存在许多限制条件。在本文中，我们提出了一种孟德尔随机化的贝叶斯框架，在非常一般的情况下提供有效的因果推断。我们提出了 MR-Horse 和 MVMR-Horse 方法，这些方法可以在不访问个体水平数据的情况下使用，只使用全基因组关联研究通常公布的汇总统计信息，并且可以同时考虑相关和不相关的多效性。在模拟研究中，我们表明即使在高多效性情况下，该方法也能保持低于名义水平的Ⅰ型错误率。我们在单变量和多变量环境中的应用示例中展示了所提出的方法，其中一些方法的工具变量非常弱。
