Novel feature selection methods for construction of accurate epigenetic clocks

Abstract

Epigenetic clocks allow us to accurately predict the age and future health of individuals based on the methylation status of specific CpG sites in the genome and are a powerful tool to measure the effectiveness of longevity interventions. There is a growing need for methods to efficiently construct epigenetic clocks. The most common approach is to create clocks using elastic net regression modelling of all measured CpG sites, without first identifying specific features or CpGs of interest. The addition of feature selection approaches provides the opportunity to optimise the identification of predictive CpG sites. Here, we apply novel feature selection methods and combinatorial approaches including newly adapted neural network, genetic algorithms, and ‘chained’ combinations. Human whole blood methylation data of ~470,000 CpGs was used to develop clocks that predict age with R2 correlation scores of greater than 0.73, the most predictive of which uses 35 CpG sites for a R2 correlation score of 0.87. The five most frequent sites across all clocks were modelled to build a clock with a R2 correlation score of 0.83. These two clocks are validated on two external datasets where they maintain excellent predictive accuracy. When compared with three published epigenetic clocks (Hannum, Horvath, Weidner) also applied to these validation datasets, our clocks outperformed all three models. We identified gene regulatory regions associated with selected CpG as possible targets for future aging studies. Thus, our feature selection algorithms build accurate, generalizable clocks with a low number of CpG sites, providing important tools for the field.

G × E interactions as a basis for toxicological uncertainty

“…We would like to stress here, that epigenetic changes and transcriptome modifications are not necessarily correlated and thus need to be considered separately. Together they may contribute to the heritability of environmental influences, independent of the primary gene sequence alteration (Li et al 2022 ; Siwek et al 2020 ). N.B.…”

“…One of the most extreme results of the time effect is ageing. Biological ageing may be measured by progress on an epigenetic clock (Li et al 2022 ), i.e. a measureable alteration of the epigenetic state (G e ) over time.…”

Evaluation of DNAmAge in paired fresh, frozen, and formalin-fixed paraffin-embedded heart tissues

“…The potential role of epigenetics in forensic investigation lies in tissue identification of trace sample and age estimation of donor and has been described previously [ 9 , 10 ]. Prediction of age based on methylation levels in tissue is known as DNAmAge [ 11 , 12 ]. The DNAmAge may be calculated using various prediction tools and was originally proposed by Horvath in 2013 [ 13 ].…”

Editorial: Accelerated epigenetic ageing as a consequence of early environmental adversity

“…DNA methylation changes with age, and earlier work has shown that one such aggregated measure of DNA methylation forms a biomarker of chronological age (Horvath & Raj, 2018). Several ways of estimating such an 'epigenetic clock' have been developed, and enhanced epigenetic ageing has been observed in a variety of diseases, see for example Li et al (2022). Why epigenetic ageing is enhanced in such conditions, is not yet clear.…”

“…Several ways of estimating such an ‘epigenetic clock’ have been developed, and enhanced epigenetic ageing has been observed in a variety of diseases, see for example Li et al. (2022). Why epigenetic ageing is enhanced in such conditions, is not yet clear.…”