Kristine L Haftorn, Julia Romanowska, Yunsung Lee, Christian M Page, Per M Magnus, Siri E Håberg, Jon Bohlin, Astanand Jugessur, William R P Denault
{"title":"Stability selection enhances feature selection and enables accurate prediction of gestational age using only five DNA methylation sites.","authors":"Kristine L Haftorn, Julia Romanowska, Yunsung Lee, Christian M Page, Per M Magnus, Siri E Håberg, Jon Bohlin, Astanand Jugessur, William R P Denault","doi":"10.1186/s13148-023-01528-3","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>DNA methylation (DNAm) is robustly associated with chronological age in children and adults, and gestational age (GA) in newborns. This property has enabled the development of several epigenetic clocks that can accurately predict chronological age and GA. However, the lack of overlap in predictive CpGs across different epigenetic clocks remains elusive. Our main aim was therefore to identify and characterize CpGs that are stably predictive of GA.</p><p><strong>Results: </strong>We applied a statistical approach called 'stability selection' to DNAm data from 2138 newborns in the Norwegian Mother, Father, and Child Cohort study. Stability selection combines subsampling with variable selection to restrict the number of false discoveries in the set of selected variables. Twenty-four CpGs were identified as being stably predictive of GA. Intriguingly, only up to 10% of the CpGs in previous GA clocks were found to be stably selected. Based on these results, we used generalized additive model regression to develop a new GA clock consisting of only five CpGs, which showed a similar predictive performance as previous GA clocks (R<sup>2</sup> = 0.674, median absolute deviation = 4.4 days). These CpGs were in or near genes and regulatory regions involved in immune responses, metabolism, and developmental processes. Furthermore, accounting for nonlinear associations improved prediction performance in preterm newborns.</p><p><strong>Conclusion: </strong>We present a methodological framework for feature selection that is broadly applicable to any trait that can be predicted from DNAm data. We demonstrate its utility by identifying CpGs that are highly predictive of GA and present a new and highly performant GA clock based on only five CpGs that is more amenable to a clinical setting.</p>","PeriodicalId":48652,"journal":{"name":"Clinical Epigenetics","volume":null,"pages":null},"PeriodicalIF":5.7000,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10339624/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical Epigenetics","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s13148-023-01528-3","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 0
Abstract
Background: DNA methylation (DNAm) is robustly associated with chronological age in children and adults, and gestational age (GA) in newborns. This property has enabled the development of several epigenetic clocks that can accurately predict chronological age and GA. However, the lack of overlap in predictive CpGs across different epigenetic clocks remains elusive. Our main aim was therefore to identify and characterize CpGs that are stably predictive of GA.
Results: We applied a statistical approach called 'stability selection' to DNAm data from 2138 newborns in the Norwegian Mother, Father, and Child Cohort study. Stability selection combines subsampling with variable selection to restrict the number of false discoveries in the set of selected variables. Twenty-four CpGs were identified as being stably predictive of GA. Intriguingly, only up to 10% of the CpGs in previous GA clocks were found to be stably selected. Based on these results, we used generalized additive model regression to develop a new GA clock consisting of only five CpGs, which showed a similar predictive performance as previous GA clocks (R2 = 0.674, median absolute deviation = 4.4 days). These CpGs were in or near genes and regulatory regions involved in immune responses, metabolism, and developmental processes. Furthermore, accounting for nonlinear associations improved prediction performance in preterm newborns.
Conclusion: We present a methodological framework for feature selection that is broadly applicable to any trait that can be predicted from DNAm data. We demonstrate its utility by identifying CpGs that are highly predictive of GA and present a new and highly performant GA clock based on only five CpGs that is more amenable to a clinical setting.
Clinical EpigeneticsBiochemistry, Genetics and Molecular Biology-Developmental Biology
CiteScore
8.90
自引率
5.30%
发文量
150
审稿时长
12 weeks
期刊介绍:
Clinical Epigenetics, the official journal of the Clinical Epigenetics Society, is an open access, peer-reviewed journal that encompasses all aspects of epigenetic principles and mechanisms in relation to human disease, diagnosis and therapy. Clinical trials and research in disease model organisms are particularly welcome.