Methods for mediation analysis with high-dimensional DNA methylation data: Possible choices and comparisons
Dylan Clark-Boucher,
Xiang Zhou,
Jiacong Du,
Yongmei Liu,
Belinda L Needham,
Jennifer A Smith and
Bhramar Mukherjee
PLOS Genetics, 2023, vol. 19, issue 11, 1-26
Abstract:
Epigenetic researchers often evaluate DNA methylation as a potential mediator of the effect of social/environmental exposures on a health outcome. Modern statistical methods for jointly evaluating many mediators have not been widely adopted. We compare seven methods for high-dimensional mediation analysis with continuous outcomes through both diverse simulations and analysis of DNAm data from a large multi-ethnic cohort in the United States, while providing an R package for their seamless implementation and adoption. Among the considered choices, the best-performing methods for detecting active mediators in simulations are the Bayesian sparse linear mixed model (BSLMM) and high-dimensional mediation analysis (HDMA); while the preferred methods for estimating the global mediation effect are high-dimensional linear mediation analysis (HILMA) and principal component mediation analysis (PCMA). We provide guidelines for epigenetic researchers on choosing the best method in practice and offer suggestions for future methodological development.Author summary: DNA methylation is an epigenetic mechanism that regulates the expression of genes, turning them “on” or “off” to meet the needs of the cell. Changes in methylation activity are associated with both health conditions and socioeconomic factors like education and access to healthcare. Recently, researchers have been interested in whether DNA methylation may act as a link between socioeconomic disadvantage and health. Standard methods to investigate whether DNA methylation is a link, or a mediator, between disadvantage and health do not work well when there are multiple mediators—in this case, DNA methylation sites—under consideration. Our study reviews 12 statistical methods for mediation analysis that can be used to analyze many methylation sites simultaneously. We compare the methods on simulated data and provide guidelines and software for their implementation. We then demonstrate how the methods can be applied to real methylation data by testing whether DNA methylation sites across the genome mediate the effect of lower educational attainment on HbA1c, an important marker of type II diabetes.
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:
Downloads: (external link)
https://journals.plos.org/plosgenetics/article?id=10.1371/journal.pgen.1011022 (text/html)
https://journals.plos.org/plosgenetics/article/fil ... 11022&type=printable (application/pdf)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:plo:pgen00:1011022
DOI: 10.1371/journal.pgen.1011022
Access Statistics for this article
More articles in PLOS Genetics from Public Library of Science
Bibliographic data for series maintained by plosgenetics ().