@article{12719,
  abstract     = {Background
Epigenetic clocks can track both chronological age (cAge) and biological age (bAge). The latter is typically defined by physiological biomarkers and risk of adverse health outcomes, including all-cause mortality. As cohort sample sizes increase, estimates of cAge and bAge become more precise. Here, we aim to develop accurate epigenetic predictors of cAge and bAge, whilst improving our understanding of their epigenomic architecture.

Methods
First, we perform large-scale (N = 18,413) epigenome-wide association studies (EWAS) of chronological age and all-cause mortality. Next, to create a cAge predictor, we use methylation data from 24,674 participants from the Generation Scotland study, the Lothian Birth Cohorts (LBC) of 1921 and 1936, and 8 other cohorts with publicly available data. In addition, we train a predictor of time to all-cause mortality as a proxy for bAge using the Generation Scotland cohort (1214 observed deaths). For this purpose, we use epigenetic surrogates (EpiScores) for 109 plasma proteins and the 8 component parts of GrimAge, one of the current best epigenetic predictors of survival. We test this bAge predictor in four external cohorts (LBC1921, LBC1936, the Framingham Heart Study and the Women’s Health Initiative study).

Results
Through the inclusion of linear and non-linear age-CpG associations from the EWAS, feature pre-selection in advance of elastic net regression, and a leave-one-cohort-out (LOCO) cross-validation framework, we obtain cAge prediction with a median absolute error equal to 2.3 years. Our bAge predictor was found to slightly outperform GrimAge in terms of the strength of its association to survival (HRGrimAge = 1.47 [1.40, 1.54] with p = 1.08 × 10−52, and HRbAge = 1.52 [1.44, 1.59] with p = 2.20 × 10−60). Finally, we introduce MethylBrowsR, an online tool to visualise epigenome-wide CpG-age associations.

Conclusions
The integration of multiple large datasets, EpiScores, non-linear DNAm effects, and new approaches to feature selection has facilitated improvements to the blood-based epigenetic prediction of biological and chronological age.},
  author       = {Bernabeu, Elena and Mccartney, Daniel L. and Gadd, Danni A. and Hillary, Robert F. and Lu, Ake T. and Murphy, Lee and Wrobel, Nicola and Campbell, Archie and Harris, Sarah E. and Liewald, David and Hayward, Caroline and Sudlow, Cathie and Cox, Simon R. and Evans, Kathryn L. and Horvath, Steve and Mcintosh, Andrew M. and Robinson, Matthew Richard and Vallejos, Catalina A. and Marioni, Riccardo E.},
  issn         = {1756-994X},
  journal      = {Genome Medicine},
  publisher    = {Springer Nature},
  title        = {{Refining epigenetic prediction of chronological and biological age}},
  doi          = {10.1186/s13073-023-01161-y},
  volume       = {15},
  year         = {2023},
}

@article{8133,
  abstract     = {The molecular factors which control circulating levels of inflammatory proteins are not well understood. Furthermore, association studies between molecular probes and human traits are often performed by linear model-based methods which may fail to account for complex structure and interrelationships within molecular datasets.In this study, we perform genome- and epigenome-wide association studies (GWAS/EWAS) on the levels of 70 plasma-derived inflammatory protein biomarkers in healthy older adults (Lothian Birth Cohort 1936; n = 876; Olink® inflammation panel). We employ a Bayesian framework (BayesR+) which can account for issues pertaining to data structure and unknown confounding variables (with sensitivity analyses using ordinary least squares- (OLS) and mixed model-based approaches). We identified 13 SNPs associated with 13 proteins (n = 1 SNP each) concordant across OLS and Bayesian methods. We identified 3 CpG sites spread across 3 proteins (n = 1 CpG each) that were concordant across OLS, mixed-model and Bayesian analyses. Tagged genetic variants accounted for up to 45% of variance in protein levels (for MCP2, 36% of variance alone attributable to 1 polymorphism). Methylation data accounted for up to 46% of variation in protein levels (for CXCL10). Up to 66% of variation in protein levels (for VEGFA) was explained using genetic and epigenetic data combined. We demonstrated putative causal relationships between CD6 and IL18R1 with inflammatory bowel disease and between IL12B and Crohn’s disease. Our data may aid understanding of the molecular regulation of the circulating inflammatory proteome as well as causal relationships between inflammatory mediators and disease.},
  author       = {Hillary, Robert F. and Trejo-Banos, Daniel and Kousathanas, Athanasios and Mccartney, Daniel L. and Harris, Sarah E. and Stevenson, Anna J. and Patxot, Marion and Ojavee, Sven Erik and Zhang, Qian and Liewald, David C. and Ritchie, Craig W. and Evans, Kathryn L. and Tucker-Drob, Elliot M. and Wray, Naomi R. and Mcrae, Allan F. and Visscher, Peter M. and Deary, Ian J. and Robinson, Matthew Richard and Marioni, Riccardo E.},
  issn         = {1756-994X},
  journal      = {Genome Medicine},
  number       = {1},
  publisher    = {Springer Nature},
  title        = {{Multi-method genome- and epigenome-wide studies of inflammatory protein levels in healthy older adults}},
  doi          = {10.1186/s13073-020-00754-1},
  volume       = {12},
  year         = {2020},
}