High-Dimensional Mediation Analysis for Selecting DNA Methylation Loci Mediating Childhood Trauma and Cortisol Stress Reactivity

Abstract

Childhood trauma tends to influence cortisol stress reactivity through the mediating effects of DNA methylation. Houtepen et al. conducted a study to investigate the role of DNA methylation in cortisol stress reactivity and its relationship with childhood trauma. The study collected a dataset consisting of 385,882 DNA methylation loci, cortisol stress reactivity, one-dimensional score on a childhood trauma questionnaire and several covariates for 85 healthy individuals. Of great scientific interest is to identify the active mediating loci out of the 385,882 ones. Houtepen et al. conducted 385,882 linear mediation analyses, in each of which one locus was considered, and identified three active mediating loci. More recently, van Kesteren and Oberski proposed a coordinate-wise mediation filter (CMF) and applied it to the same dataset. They identified five active mediating loci. Unfortunately, the three loci identified by Houtepen et al. are completely different from the five loci identified by van Kesteren and Oberski, probably because both Houtepen et al. and van Kesteren and Oberski did not consider all loci jointly in their analyses. The high dimensional DNA methylation loci indeed necessitate new techniques for identifying active mediating loci and testing the direct and indirect effects of the early life traumatic stress on later cortisol alteration. Motivated by the contradictory results in the aforementioned two scientific works, we develop a new estimating and testing procedure, and apply it to the same dataset as that analyzed by the two works. We identify three new loci: cg19230917, cg06422529 and cg03199124, and their effect sizes and p-values are 321.196 (p-value = 0.035965), 418.173 (p-value = 0.000234) and 471.865 (p-value = 0.001691), respectively. These three loci possess both reasonably neurobiological interpretations and statistically significant effects via our proposed tests. Based on our new procedure, we further confirm that the childhood trauma does not have significant direct effects on cortisol change—it only indirectly affects cortisol through DNA methylation, and the indirect effect is negative. Supplementary materials for this article are available online.

Keywords:

• Cortisol stress reactivity
• Direct effects
• DNA
• Early life trauma
• High dimensional mediators
• Indirect effects
• Mediation analysis
• Methylation

Supplementary Materials

The supplementary materials consist of detailed explanations of confounders and relationship among the mediators for the empirical analysis in Section 3, and additional numerical comparison with the global test (Djordjilović et al. 2019).

Acknowledgments

The authors are grateful to the editor, the associate editor, and two anonymous referees for the constructive comments and suggestions that led to significant improvement of this work.

Additional information

Funding

Guo’s research was supported by National Natural Science Foundation of China grants (NSFC 12071038) and Beijing Natural Science Foundation (1212004). Liu’s research was supported by grants from National Natural Science Foundation of China grants 11701034, 11771361 and 71988101. Li and Zeng’s research was supported by National Science Foundation, DMS 1820702, 1953196, and 2015539.