Mediation analysis is a powerful tool for studying causal pathways between exposure, mediator, and outcome variables of interest. While classical mediation analysis using observational data often requires strong and sometimes unrealistic assumptions, such as unconfoundedness, Mendelian Randomization (MR) avoids unmeasured confounding bias by employing genetic variants as instrumental variables. We develop a novel MR framework for mediation analysis with genome-wide associate study (GWAS) summary data, and provide solid statistical guarantees. Our framework efficiently integrates information stored in three independent GWAS summary data and mitigates the commonly encountered winner's curse and measurement error bias (a.k.a. instrument selection and weak instrument bias) in MR. As a result, our framework provides valid statistical inference for both direct and mediation effects with enhanced statistical efficiency. As part of this endeavor, we also demonstrate that the concept of winner's curse bias in mediation analysis with MR and summary data is more complex than previously documented in the classical two-sample MR literature, requiring special treatments to address such a bias issue. Through our theoretical investigations, we show that the proposed method delivers consistent and asymptotically normally distributed causal effect estimates. We illustrate the finite-sample performance of our approach through simulation experiments and a case study.

翻译：中介分析是研究暴露变量、中介变量与结局变量之间因果路径的有力工具。传统基于观测数据的中介分析通常需要强假设（如无混杂性），这些假设往往难以满足。而孟德尔随机化（Mendelian Randomization, MR）通过采用遗传变异作为工具变量，可避免未测量的混杂偏倚。我们提出了一种新颖的MR框架，用于基于全基因组关联研究（GWAS）汇总数据的中介分析，并提供了坚实的统计保证。该框架高效整合了来自三项独立GWAS汇总数据的信息，有效减轻了MR中常见的“赢家诅咒”与测量误差偏倚（即工具变量选择偏倚与弱工具变量偏倚）。由此，我们的框架能够为直接效应与中介效应提供有效的统计推断，并显著提升统计效率。此外，我们通过研究表明：在基于MR与汇总数据的中介分析中，“赢家诅咒”偏倚的概念比经典两样本MR文献中记载的更为复杂，需要特殊处理才能解决此类偏倚问题。通过理论推导，我们证明所提出的方法能够提供一致且渐近正态分布的因果效应估计。我们通过模拟实验与案例研究展示了该方法在有限样本下的表现。