A comparison of feature selection methodologies and learning algorithms in the development of a DNA methylation-based telomere length estimator
Preprint
Abstract
The field of epigenomics holds great promise in understanding and treating disease with advances in machine learning (ML) and artificial intelligence being vitally important in this pursuit. Increasingly, research now utilises DNA methylation measures at cytosine-guanine dinucleotides (CpG) to detect disease and estimate biological traits such as aging. Given the high dimensionality of DNA methylation data, feature-selection techniques are commonly employed to reduce dimensionality and identify the most important subset of features. In this study, we test and compare a range of feature-selection methods and ML algorithms in the development of a novel DNA methylation-based telomere length (TL) estimator. We found that principal component analysis in advance of elastic net regression led to the overall best performing estimator when evaluated using a nested cross-validation analysis and two independent test cohorts. In contrast, the baseline model of elastic net regression with no prior feature reduction stage performed worst - suggesting a prior feature-selection stage may have important utility. The variance in performance across tested approaches shows that estimators are sensitive to data set heterogeneity and the development of an optimal DNA methylation-based estimator should benefit from the robust methodological approach used in this study. Additionally, we observed that different DNA methylation-based TL estimators, which have few common CpGs, are associated with many of the same biological entities. Moreover, our methodology which utilises a range of feature-selection approaches and ML algorithms could be applied to other biological markers and disease phenotypes, to examine their relationship with DNA methylation and predictive value.Keywords
All Related Versions
- Published version: BMC Bioinformatics, 24 (1), 1.
This publication has 56 references indexed in Scilit:
- Dynamic regulation of genome-wide pre-mRNA splicing and stress tolerance by the Sm-like protein LSm5 in ArabidopsisGenome Biology, 2014
- Genomic selection using regularized linear regression models: ridge regression, lasso, elastic net and their extensionsBMC Proceedings, 2012
- GuiTope: an application for mapping random-sequence peptides to protein sequencesBMC Bioinformatics, 2012
- High density DNA methylation array with single CpG site resolutionGenomics, 2011
- Biomarkers increase detection of active smoking and secondhand smoke exposure in critically ill patients*Critical Care Medicine, 2011
- Prevalence of Smoking Assessed Biochemically in an Urban Public Hospital: A Rationale for Routine Cotinine ScreeningAmerican Journal of Epidemiology, 2009
- A review of feature selection techniques in bioinformaticsBioinformatics, 2007
- Regularization and Variable Selection Via the Elastic NetJournal of the Royal Statistical Society Series B: Statistical Methodology, 2005
- A Direct Approach to False Discovery RatesJournal of the Royal Statistical Society Series B: Statistical Methodology, 2002
- Telomere Length as an Indicator of Biological AgingHypertension, 2001