{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T14:52:05Z","timestamp":1781707925711,"version":"3.54.5"},"reference-count":47,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T00:00:00Z","timestamp":1738800000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000066","name":"National Institute of Environmental Health Sciences","doi-asserted-by":"publisher","award":["R01 ES031259"],"award-info":[{"award-number":["R01 ES031259"]}],"id":[{"id":"10.13039\/100000066","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["R03 AG067064"],"award-info":[{"award-number":["R03 AG067064"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006545","name":"National Institute on Minority Health and Health Disparities","doi-asserted-by":"publisher","award":["R01 MD016595"],"award-info":[{"award-number":["R01 MD016595"]}],"id":[{"id":"10.13039\/100006545","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000066","name":"National Institute of Environmental Health Sciences","doi-asserted-by":"publisher","award":["R01 ES021369"],"award-info":[{"award-number":["R01 ES021369"]}],"id":[{"id":"10.13039\/100000066","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000066","name":"National Institute of Environmental Health Sciences","doi-asserted-by":"publisher","award":["P01 ES009605"],"award-info":[{"award-number":["P01 ES009605"]}],"id":[{"id":"10.13039\/100000066","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000066","name":"National Institute of Environmental Health Sciences","doi-asserted-by":"publisher","award":["R01 ES017054"],"award-info":[{"award-number":["R01 ES017054"]}],"id":[{"id":"10.13039\/100000066","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000066","name":"National Institute of Environmental Health Sciences","doi-asserted-by":"publisher","award":["R01 AG069090"],"award-info":[{"award-number":["R01 AG069090"]}],"id":[{"id":"10.13039\/100000066","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000066","name":"National Institute of Environmental Health Sciences","doi-asserted-by":"publisher","award":["U24 ES028529"],"award-info":[{"award-number":["U24 ES028529"]}],"id":[{"id":"10.13039\/100000066","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000066","name":"National Institute of Environmental Health Sciences","doi-asserted-by":"publisher","award":["P01 ES015572"],"award-info":[{"award-number":["P01 ES015572"]}],"id":[{"id":"10.13039\/100000066","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000139","name":"U.S. Environmental Protection Agency","doi-asserted-by":"publisher","award":["RD 83171001"],"award-info":[{"award-number":["RD 83171001"]}],"id":[{"id":"10.13039\/100000139","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000139","name":"U.S. Environmental Protection Agency","doi-asserted-by":"publisher","award":["RD 82670901"],"award-info":[{"award-number":["RD 82670901"]}],"id":[{"id":"10.13039\/100000139","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000139","name":"U.S. Environmental Protection Agency","doi-asserted-by":"publisher","award":["RD 83451301"],"award-info":[{"award-number":["RD 83451301"]}],"id":[{"id":"10.13039\/100000139","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:sec id=\"sec018\">\n<jats:title>Background<\/jats:title>\n<jats:p>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.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec019\">\n<jats:title>Methodology\/findings<\/jats:title>\n<jats:p>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.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec020\">\n<jats:title>Conclusions<\/jats:title>\n<jats:p>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.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pcbi.1012768","type":"journal-article","created":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T19:03:19Z","timestamp":1738868599000},"page":"e1012768","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":5,"title":["A SuperLearner-based pipeline for the development of DNA methylation-derived predictors of phenotypic traits"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1412-8251","authenticated-orcid":true,"given":"Dennis","family":"Khodasevich","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nina","family":"Holland","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lars","family":"van der Laan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2284-3298","authenticated-orcid":true,"given":"Andres","family":"Cardenas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,2,6]]},"reference":[{"issue":"1","key":"pcbi.1012768.ref001","doi-asserted-by":"crossref","first-page":"osad001","DOI":"10.1093\/exposome\/osad001","article-title":"Epigenetics and the Exposome: DNA methylation as a proxy for health impacts of prenatal environmental exposures","volume":"3","author":"ML Colwell","year":"2023","journal-title":"Exposome"},{"issue":"10","key":"pcbi.1012768.ref002","doi-asserted-by":"crossref","first-page":"3156","DOI":"10.1186\/gb-2013-14-10-r115","article-title":"DNA methylation age of human tissues and cell types","volume":"14","author":"S Horvath","year":"2013","journal-title":"Genome Biol"},{"issue":"2","key":"pcbi.1012768.ref003","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/j.molcel.2012.10.016","article-title":"Genome-wide methylation profiles reveal quantitative views of human aging rates","volume":"49","author":"G Hannum","year":"2013","journal-title":"Mol Cell"},{"issue":"13","key":"pcbi.1012768.ref004","doi-asserted-by":"crossref","first-page":"1469","DOI":"10.2217\/epi-2019-0206","article-title":"EpiSmokEr: a robust classifier to determine smoking status from DNA methylation data","volume":"11","author":"S Bollepalli","year":"2019","journal-title":"Epigenomics"},{"issue":"1","key":"pcbi.1012768.ref005","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41525-022-00320-1","article-title":"Methylation risk scores are associated with a collection of phenotypes within electronic health record systems.","volume":"7","author":"M Thompson","year":"2022","journal-title":"NPJ Genom Med"},{"key":"pcbi.1012768.ref006","doi-asserted-by":"crossref","first-page":"101348","DOI":"10.1016\/j.arr.2021.101348","article-title":"A systematic review of biological, social and environmental factors associated with epigenetic clock acceleration","volume":"69","author":"L Oblak","year":"2021","journal-title":"Ageing Research Reviews"},{"issue":"1","key":"pcbi.1012768.ref007","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1186\/s13059-016-1063-4","article-title":"Prediction of gestational age based on genome-wide differentially methylated regions","volume":"17","author":"J Bohlin","year":"2016","journal-title":"Genome Biol"},{"issue":"4","key":"pcbi.1012768.ref008","doi-asserted-by":"crossref","first-page":"573","DOI":"10.18632\/aging.101414","article-title":"An epigenetic biomarker of aging for lifespan and healthspan","volume":"10","author":"ME Levine","year":"2018","journal-title":"Aging (Albany NY)"},{"issue":"2","key":"pcbi.1012768.ref009","first-page":"303","article-title":"DNA methylation GrimAge strongly predicts lifespan and healthspan","volume":"11","author":"AT Lu","year":"2019","journal-title":"Aging (Albany NY)"},{"key":"pcbi.1012768.ref010","doi-asserted-by":"crossref","unstructured":"Belsky DW, Caspi A, Corcoran DL, Sugden K, Poulton R, Arseneault L, et al. DunedinPACE, a DNA methylation biomarker of the pace of aging. Deelen J, Tyler JK, Suderman M, Deelen J, editors. eLife. 2022 Jan 14;11:e73420.","DOI":"10.7554\/eLife.73420"},{"issue":"1","key":"pcbi.1012768.ref011","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1186\/s13148-019-0730-1","article-title":"Statistical predictions with glmnet","volume":"11","author":"S Engebretsen","year":"2019","journal-title":"Clin Epigenetics"},{"issue":"1","key":"pcbi.1012768.ref012","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1186\/s13148-022-01277-9","article-title":"Batch-effect detection, correction and characterisation in Illumina HumanMethylation450 and MethylationEPIC BeadChip array data","volume":"14","author":"JP Ross","year":"2022","journal-title":"Clin Epigenetics"},{"issue":"11","key":"pcbi.1012768.ref013","doi-asserted-by":"crossref","first-page":"1363","DOI":"10.2217\/epi-2017-0078","article-title":"The correlation of methylation levels measured using Illumina 450K and EPIC BeadChips in blood samples","volume":"9","author":"MW Logue","year":"2017","journal-title":"Epigenomics"},{"issue":"6","key":"pcbi.1012768.ref014","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1080\/15592294.2018.1497386","article-title":"Comparison of DNA methylation measured by Illumina 450K and EPIC BeadChips in blood of newborns and 14-year-old children","volume":"13","author":"O Solomon","year":"2018","journal-title":"Epigenetics"},{"issue":"1","key":"pcbi.1012768.ref015","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1186\/s13148-022-01299-3","article-title":"Low reliability of DNA methylation across Illumina Infinium platforms in cord blood: implications for replication studies and meta-analyses of prenatal exposures","volume":"14","author":"EW Olstad","year":"2022","journal-title":"Clin Epigenetics"},{"issue":"7","key":"pcbi.1012768.ref016","doi-asserted-by":"crossref","first-page":"644","DOI":"10.1038\/s43587-022-00248-2","article-title":"A computational solution for bolstering reliability of epigenetic clocks: implications for clinical trials and longitudinal tracking","volume":"2","author":"AT Higgins-Chen","year":"2022","journal-title":"Nat Aging"},{"issue":"1","key":"pcbi.1012768.ref017","article-title":"Super learner.","volume":"6","author":"MJ Laan van der","year":"2007","journal-title":"Stat Appl Genet Mol Biol [Internet]"},{"issue":"1","key":"pcbi.1012768.ref018","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1186\/s13073-019-0667-1","article-title":"Improved precision of epigenetic clock estimates across tissues and its implication for biological ageing","volume":"11","author":"Q Zhang","year":"2019","journal-title":"Genome Med"},{"issue":"17","key":"pcbi.1012768.ref019","doi-asserted-by":"crossref","first-page":"8552","DOI":"10.18632\/aging.205046","article-title":"Fail-tests of DNA methylation clocks, and development of a noise barometer for measuring epigenetic pressure of aging and disease","volume":"15","author":"X Mei","year":"2023","journal-title":"Aging (Albany NY)"},{"issue":"1","key":"pcbi.1012768.ref020","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1186\/s13148-023-01528-3","article-title":"Stability selection enhances feature selection and enables accurate prediction of gestational age using only five DNA methylation sites","volume":"15","author":"KL Haftorn","year":"2023","journal-title":"Clin Epigenetics"},{"issue":"7","key":"pcbi.1012768.ref021","first-page":"1581","article-title":"Sperm epigenetic clock associates with pregnancy outcomes in the general population","volume":"37","author":"JR Pilsner","year":"2022","journal-title":"Hum Reprod"},{"issue":"24","key":"pcbi.1012768.ref022","doi-asserted-by":"crossref","first-page":"2901","DOI":"10.1097\/CM9.0000000000001723","article-title":"Epigenetic clocks in the pediatric population: when and why they tick?","volume":"134","author":"J Wang","year":"2021","journal-title":"Chin Med J (Engl)"},{"issue":"3","key":"pcbi.1012768.ref023","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1016\/j.biopsych.2020.01.025","article-title":"Schizophrenia and epigenetic aging biomarkers: increased mortality, reduced cancer risk, and unique clozapine effects.","volume":"88","author":"AT Higgins-Chen","year":"2020","journal-title":"Biol Psychiatry"},{"key":"pcbi.1012768.ref024","unstructured":"For Investigators | CERCH [Internet]. [cited 2024 Dec 25]. Available from: https:\/\/cerch.berkeley.edu\/investigators."},{"key":"pcbi.1012768.ref025","author":"Y Zeng","year":"2018"},{"key":"pcbi.1012768.ref026","author":"E Polley","year":"2018"},{"issue":"4","key":"pcbi.1012768.ref027","doi-asserted-by":"crossref","first-page":"1276","DOI":"10.1093\/ije\/dyad023","article-title":"Practical considerations for specifying a super learner","volume":"52","author":"RV Phillips","year":"2023","journal-title":"Int J Epidemiol"},{"key":"pcbi.1012768.ref028","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1007\/978-1-4939-3578-9_5","article-title":"The gene expression omnibus database","author":"E Clough","year":"2016","journal-title":"Methods Mol Biol Clifton NJ"},{"issue":"8","key":"pcbi.1012768.ref029","doi-asserted-by":"crossref","first-page":"1131","DOI":"10.4161\/epi.29446","article-title":"DNA methylation-associated colonic mucosal immune and defense responses in treatment-na\u00efve pediatric ulcerative colitis","volume":"9","author":"RA Harris","year":"2014","journal-title":"Epigenetics"},{"key":"pcbi.1012768.ref030","unstructured":"GEO Accession viewer [Internet]. [cited 2023 Nov 23]. Available from: https:\/\/www.ncbi.nlm.nih.gov\/geo\/query\/acc.cgi?acc=GSE80283."},{"issue":"9","key":"pcbi.1012768.ref031","doi-asserted-by":"crossref","first-page":"784","DOI":"10.1080\/15592294.2015.1062964","article-title":"DNA methylation provides insight into intergenerational risk for preterm birth in African Americans","volume":"10","author":"SE Parets","year":"2015","journal-title":"Epigenetics"},{"key":"pcbi.1012768.ref032","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1186\/s13072-016-0074-4","article-title":"DNA methylation signature of human fetal alcohol spectrum disorder","volume":"9","author":"E Portales-Casamar","year":"2016","journal-title":"Epigenetics Chromatin"},{"issue":"5","key":"pcbi.1012768.ref033","doi-asserted-by":"crossref","first-page":"e1004402","DOI":"10.1371\/journal.pgen.1004402","article-title":"Mosaic epigenetic dysregulation of ectodermal cells in autism spectrum disorder","volume":"10","author":"ER Berko","year":"2014","journal-title":"PLoS Genet"},{"issue":"4","key":"pcbi.1012768.ref034","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1101\/gr.125187.111","article-title":"Age-associated DNA methylation in pediatric populations","volume":"22","author":"RS Alisch","year":"2012","journal-title":"Genome Res"},{"issue":"1","key":"pcbi.1012768.ref035","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1093\/toxsci\/kfu210","article-title":"Prenatal arsenic exposure and the epigenome: identifying sites of 5-methylcytosine alterations that predict functional changes in gene expression in newborn cord blood and subsequent birth outcomes","volume":"143","author":"D Rojas","year":"2015","journal-title":"Toxicol Sci"},{"key":"pcbi.1012768.ref036","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1186\/s13073-015-0225-4","article-title":"Many obesity-associated SNPs strongly associate with DNA methylation changes at proximal promoters and enhancers","volume":"7","author":"S Voisin","year":"2015","journal-title":"Genome Med"},{"issue":"13","key":"pcbi.1012768.ref037","doi-asserted-by":"crossref","first-page":"2006","DOI":"10.1080\/15592294.2022.2102846","article-title":"Prenatal and birth associations of epigenetic gestational age acceleration in the Center for the Health Assessment of Mothers and Children of Salinas (CHAMACOS) cohort","volume":"17","author":"S Daredia","year":"2022","journal-title":"Epigenetics"},{"issue":"24","key":"pcbi.1012768.ref038","doi-asserted-by":"crossref","first-page":"25653","DOI":"10.18632\/aging.203776","article-title":"Maternal adverse childhood experiences before pregnancy are associated with epigenetic aging changes in their children","volume":"13","author":"JC Nwanaji-Enwerem","year":"2021","journal-title":"Aging (Albany NY)"},{"key":"pcbi.1012768.ref039","doi-asserted-by":"crossref","first-page":"101515","DOI":"10.1016\/j.eclinm.2022.101515","article-title":"Epigenetic profiling linked to multisystem inflammatory syndrome in children (MIS-C): a multicenter, retrospective study","volume":"50","author":"V Davalos","year":"2022","journal-title":"eClinicalMedicine"},{"issue":"1","key":"pcbi.1012768.ref040","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1186\/s13059-015-0600-x","article-title":"A coherent approach for analysis of the Illumina HumanMethylation450 BeadChip improves data quality and performance in epigenome-wide association studies","volume":"16","author":"B Lehne","year":"2015","journal-title":"Genome Biol"},{"issue":"1","key":"pcbi.1012768.ref041","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1186\/s13059-016-1041-x","article-title":"An integrated genetic-epigenetic analysis of schizophrenia: evidence for co-localization of genetic associations and differential DNA methylation","volume":"17","author":"E Hannon","year":"2016","journal-title":"Genome Biol"},{"key":"pcbi.1012768.ref042","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1186\/s13148-021-01207-1","article-title":"The ENmix DNA methylation analysis pipeline for Illumina BeadChip and comparisons with seven other preprocessing pipelines","volume":"13","author":"Z Xu","year":"2021","journal-title":"Clinical Epigenetics"},{"issue":"1","key":"pcbi.1012768.ref043","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1080\/15592294.2019.1565590","article-title":"Exposure to polybrominated biphenyl (PBB) associates with genome-wide DNA methylation differences in peripheral blood","volume":"14","author":"SW Curtis","year":"2019","journal-title":"Epigenetics"},{"key":"pcbi.1012768.ref044","author":"D Khodasevich"},{"issue":"5","key":"pcbi.1012768.ref045","doi-asserted-by":"crossref","first-page":"btae302","DOI":"10.1093\/bioinformatics\/btae302","article-title":"methscore: a comprehensive R function for DNA methylation-based health predictors","volume":"40","author":"Z Xu","year":"2024","journal-title":"Bioinformatics"},{"key":"pcbi.1012768.ref046","doi-asserted-by":"crossref","first-page":"116067","DOI":"10.1016\/j.envres.2023.116067","article-title":"Associations between prenatal phthalate exposure and childhood epigenetic age acceleration","volume":"231","author":"D Khodasevich","year":"2023","journal-title":"Environ Res"},{"issue":"1","key":"pcbi.1012768.ref047","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1186\/s12859-017-1511-5","article-title":"A comparison of reference-based algorithms for correcting cell-type heterogeneity in Epigenome-wide association studies","volume":"18","author":"AE Teschendorff","year":"2017","journal-title":"BMC Bioinformatics"}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012768","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T19:03:32Z","timestamp":1738868612000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012768"}},"subtitle":[],"editor":[{"given":"Wei","family":"Li,","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,2,6]]},"references-count":47,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2,6]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1012768","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,6]]}}}