EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A SuperLearner-based pipeline for the development of DNA methylation-derived predictors of phenotypic traits

Dennis Khodasevich iD, Nina Holland, Lars van der Laan, Andres Cardenas iD

PLOS Computational Biology · 2025

DOI: 10.1371/journal.pcbi.1012768 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2025. Verfasst von Dennis Khodasevich und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Epidemiology and Population Health, Stanford University School of Medicine, Palo Alto, California, United States of America. Hauptthemen laut MEDLINE: DNA Methylation, Epigenomics. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIA NIH HHS, NIEHS NIH HHS, NIMHD NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

DNA methylation (DNAm) provides a window to characterize the impacts of environmental exposures and the biological aging process. Epigenetic clocks are often trained on DNAm using penalized regression of CpG sites, but recent evidence suggests potential benefits of training epigenetic predictors on principal components. Methodology/findings We developed a pipeline to simultaneously train three epigenetic predictors; a traditional CpG Clock, a PCA Clock, and a SuperLearner PCA Clock (SL PCA). We gathered publicly available DNAm datasets to generate i) a novel childhood epigenetic clock, ii) a reconstructed Hannum adult blood clock, and iii) as a proof of concept, a predictor of polybrominated biphenyl exposure using the three developmental methodologies. We used correlation coefficients and median absolute error to assess fit between predicted and observed measures, as well as agreement between duplicates. The SL PCA clocks improved fit with observed phenotypes relative to the PCA clocks or CpG clocks across several datasets. We found evidence for higher agreement between duplicate samples run on alternate DNAm arrays when using SL PCA clocks relative to traditional methods. Analyses examining associations between relevant exposures and epigenetic age acceleration (EAA) produced more precise effect estimates when using predictions derived from SL PCA clocks.

Conclusions

We introduce a novel method for the development of DNAm-based predictors that combines the improved reliability conferred by training on principal components with advanced ensemble-based machine learning. Coupling SuperLearner with PCA in the predictor development process may be especially relevant for studies with longitudinal designs utilizing multiple array types, as well as for the development of predictors of more complex phenotypic traits.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DNA MethylationEpigenomicsHumansEpigenesis, GeneticCpG IslandsPhenotypeComputational BiologyAdultChildMachine LearningPrincipal Component AnalysisAgingMale

Autor:innen und Institutionen

  • Department of Epidemiology and Population Health, Stanford University School of Medicine, Palo Alto, California, United States of America.
  • Center for Environmental Research and Community Health (CERCH), University of California Berkeley School of Public Health, Berkeley, California, United States of America.
  • Department of Statistics, University of Washington, Seattle, Washington, United States of America.

ORCID-Profile: Dennis Khodasevich, Andres Cardenas

Förderung

  • NIA NIH HHS
  • NIEHS NIH HHS
  • NIMHD NIH HHS
  • National Institute of Environmental Health Sciences
  • National Institute on Aging
  • National Institute on Minority Health and Health Disparities
  • U.S. Environmental Protection Agency

Zitieren

APA

Khodasevich, D., Holland, N., van der Laan, L., & Cardenas, A. (2025). A SuperLearner-based pipeline for the development of DNA methylation-derived predictors of phenotypic traits. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1012768

Vancouver

Khodasevich D, Holland N, van der Laan L, Cardenas A. A SuperLearner-based pipeline for the development of DNA methylation-derived predictors of phenotypic traits. PLOS Computational Biology. 2025. doi:10.1371/journal.pcbi.1012768

BibTeX
@article{Khodasevich2025,
  author = {Khodasevich, Dennis and Holland, Nina and van der Laan, Lars and Cardenas, Andres},
  title = {A SuperLearner-based pipeline for the development of DNA methylation-derived predictors of phenotypic traits},
  journal = {PLOS Computational Biology},
  year = {2025},
  doi = {10.1371/journal.pcbi.1012768}
}
Kostenlos starten →