Combining the strengths of inverse-variance weighting and Egger regression in Mendelian randomization using a mixture of regressions model

TLDR

Mendelian randomization uses genetic variants as instrumental variables to infer causal relationships, with the inverse‑variance weighted method offering high power when all variants are valid but being biased by horizontal pleiotropy, while Egger regression is robust to pleiotropy but sacrifices power. We propose a two‑component mixture of regressions that combines IVW and Egger regression to achieve greater efficiency and robustness to pleiotropy. The approach employs model averaging and a novel data‑perturbation scheme to account for uncertainties in model and IV selection, providing robust inference in finite samples. Simulations and analyses of 48 risk‑factor–disease and 63 trait pairs demonstrate that the method controls type I error better and achieves higher power than IVW, Egger, and other MR methods, making it a valuable addition to the MR toolbox.

Abstract

With the increasing availability of large-scale GWAS summary data on various traits, Mendelian randomization (MR) has become commonly used to infer causality between a pair of traits, an exposure and an outcome. It depends on using genetic variants, typically SNPs, as instrumental variables (IVs). The inverse-variance weighted (IVW) method (with a fixed-effect meta-analysis model) is most powerful when all IVs are valid; however, when horizontal pleiotropy is present, it may lead to biased inference. On the other hand, Egger regression is one of the most widely used methods robust to (uncorrelated) pleiotropy, but it suffers from loss of power. We propose a two-component mixture of regressions to combine and thus take advantage of both IVW and Egger regression; it is often both more efficient (i.e. higher powered) and more robust to pleiotropy (i.e. controlling type I error) than either IVW or Egger regression alone by accounting for both valid and invalid IVs respectively. We propose a model averaging approach and a novel data perturbation scheme to account for uncertainties in model/IV selection, leading to more robust statistical inference for finite samples. Through extensive simulations and applications to the GWAS summary data of 48 risk factor-disease pairs and 63 genetically uncorrelated trait pairs, we showcase that our proposed methods could often control type I error better while achieving much higher power than IVW and Egger regression (and sometimes than several other new/popular MR methods). We expect that our proposed methods will be a useful addition to the toolbox of Mendelian randomization for causal inference.