Mediation analysis for survival data with high-dimensional mediators

Motivation: Mediation analysis has become a prevalent method to identify causal pathway(s) between an independent variable and a dependent variable through intermediate variable(s). However, little work has been done when the intermediate variables (mediators) are high-dimensional and the outcome is a survival endpoint. In this paper, we introduce a novel method to identify potential mediators in a causal framework of high-dimensional Cox regression. Results: We first reduce the data dimension through a mediation-based sure independence screening method. A de-biased Lasso inference procedure is used for Cox's regression parameters. We adopt a multiple-testing procedure to accurately control the false discovery rate when testing high-dimensional mediation hypotheses. Simulation studies are conducted to demonstrate the performance of our method. We apply this approach to explore the mediation mechanisms of 379330 DNA methylation markers between smoking and overall survival among lung cancer patients in The Cancer Genome Atlas lung cancer cohort. Two methylation sites (cg08108679 and cg26478297) are identified as potential mediating epigenetic markers. Supplementary information: Supplementary data are available at Bioinformatics online.

Automated summary

In this study, a novel method is introduced to identify potential mediators in high-dimensional Cox regression, with successful control of false discovery rate through data dimension reduction and multiple-testing procedure. Application to DNA methylation markers in lung cancer patients reveals two potential mediating epigenetic markers.