A SuperLearner-based pipeline for the development of DNA methylation-derived predictors of phenotypic traits.
<h4>Background</h4>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 tra...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-02-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://doi.org/10.1371/journal.pcbi.1012768 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823856927904366592 |
|---|---|
| author | Dennis Khodasevich Nina Holland Lars van der Laan Andres Cardenas |
| author_facet | Dennis Khodasevich Nina Holland Lars van der Laan Andres Cardenas |
| author_sort | Dennis Khodasevich |
| collection | DOAJ |
| description | <h4>Background</h4>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.<h4>Methodology/findings</h4>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.<h4>Conclusions</h4>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. |
| format | Article |
| id | doaj-art-b482c4187e3d468db2def109da6b08fc |
| institution | Kabale University |
| issn | 1553-734X 1553-7358 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj-art-b482c4187e3d468db2def109da6b08fc2025-02-12T05:30:34ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582025-02-01212e101276810.1371/journal.pcbi.1012768A SuperLearner-based pipeline for the development of DNA methylation-derived predictors of phenotypic traits.Dennis KhodasevichNina HollandLars van der LaanAndres Cardenas<h4>Background</h4>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.<h4>Methodology/findings</h4>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.<h4>Conclusions</h4>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.https://doi.org/10.1371/journal.pcbi.1012768 |
| spellingShingle | Dennis Khodasevich Nina Holland Lars van der Laan Andres Cardenas A SuperLearner-based pipeline for the development of DNA methylation-derived predictors of phenotypic traits. PLoS Computational Biology |
| title | A SuperLearner-based pipeline for the development of DNA methylation-derived predictors of phenotypic traits. |
| title_full | A SuperLearner-based pipeline for the development of DNA methylation-derived predictors of phenotypic traits. |
| title_fullStr | A SuperLearner-based pipeline for the development of DNA methylation-derived predictors of phenotypic traits. |
| title_full_unstemmed | A SuperLearner-based pipeline for the development of DNA methylation-derived predictors of phenotypic traits. |
| title_short | A SuperLearner-based pipeline for the development of DNA methylation-derived predictors of phenotypic traits. |
| title_sort | superlearner based pipeline for the development of dna methylation derived predictors of phenotypic traits |
| url | https://doi.org/10.1371/journal.pcbi.1012768 |
| work_keys_str_mv | AT denniskhodasevich asuperlearnerbasedpipelineforthedevelopmentofdnamethylationderivedpredictorsofphenotypictraits AT ninaholland asuperlearnerbasedpipelineforthedevelopmentofdnamethylationderivedpredictorsofphenotypictraits AT larsvanderlaan asuperlearnerbasedpipelineforthedevelopmentofdnamethylationderivedpredictorsofphenotypictraits AT andrescardenas asuperlearnerbasedpipelineforthedevelopmentofdnamethylationderivedpredictorsofphenotypictraits AT denniskhodasevich superlearnerbasedpipelineforthedevelopmentofdnamethylationderivedpredictorsofphenotypictraits AT ninaholland superlearnerbasedpipelineforthedevelopmentofdnamethylationderivedpredictorsofphenotypictraits AT larsvanderlaan superlearnerbasedpipelineforthedevelopmentofdnamethylationderivedpredictorsofphenotypictraits AT andrescardenas superlearnerbasedpipelineforthedevelopmentofdnamethylationderivedpredictorsofphenotypictraits |