@article{18754,
  abstract     = {Exploring the molecular correlates of metabolic health measures may identify their shared and unique biological processes and pathways. Molecular proxies of these traits may also provide a more objective approach to their measurement. Here, DNA methylation (DNAm) data were used in epigenome-wide association studies (EWASs) and for training epigenetic scores (EpiScores) of six metabolic traits: body mass index (BMI), body fat percentage, waist-hip ratio, and blood-based measures of glucose, high-density lipoprotein cholesterol, and total cholesterol in >17,000 volunteers from the Generation Scotland (GS) cohort. We observed a maximum of 12,033 significant findings (p < 3.6 × 10−8) for BMI in a marginal linear regression EWAS. By contrast, a joint and conditional Bayesian penalized regression approach yielded 27 high-confidence associations with BMI. EpiScores trained in GS performed well in both Scottish and Singaporean test cohorts (Lothian Birth Cohort 1936 [LBC1936] and Health for Life in Singapore [HELIOS]). The EpiScores for BMI and total cholesterol performed best in HELIOS, explaining 20.8% and 7.1% of the variance in the measured traits, respectively. The corresponding results in LBC1936 were 14.4% and 3.2%, respectively. Differences were observed in HELIOS for body fat, where the EpiScore explained ∼9% of the variance in Chinese and Malay -subgroups but ∼3% in the Indian subgroup. The EpiScores also correlated with cognitive function in LBC1936 (standardized βrange: 0.08–0.12, false discovery rate p [pFDR] < 0.05). Accounting for the correlation structure across the methylome can vastly affect the number of lead findings in EWASs. The EpiScores of metabolic traits are broadly applicable across populations and can reflect differences in cognition.},
  author       = {Smith, Hannah M. and Ng, Hong Kiat and Moodie, Joanna E. and Gadd, Danni A. and Mccartney, Daniel L. and Bernabeu, Elena and Campbell, Archie and Redmond, Paul and Taylor, Adele and Page, Danielle and Corley, Janie and Harris, Sarah E. and Tay, Darwin and Deary, Ian J. and Evans, Kathryn L. and Robinson, Matthew Richard and Chambers, John C. and Loh, Marie and Cox, Simon R. and Marioni, Riccardo E. and Hillary, Robert F.},
  issn         = {1537-6605},
  journal      = {American Journal of Human Genetics},
  number       = {1},
  pages        = {106--115},
  publisher    = {Elsevier},
  title        = {{DNA methylation-based predictors of metabolic traits in Scottish and Singaporean cohorts}},
  doi          = {10.1016/j.ajhg.2024.11.012},
  volume       = {112},
  year         = {2025},
}

@article{14258,
  abstract     = {There is currently little evidence that the genetic basis of human phenotype varies significantly across the lifespan. However, time-to-event phenotypes are understudied and can be thought of as reflecting an underlying hazard, which is unlikely to be constant through life when values take a broad range. Here, we find that 74% of 245 genome-wide significant genetic associations with age at natural menopause (ANM) in the UK Biobank show a form of age-specific effect. Nineteen of these replicated discoveries are identified only by our modeling framework, which determines the time dependency of DNA-variant age-at-onset associations without a significant multiple-testing burden. Across the range of early to late menopause, we find evidence for significantly different underlying biological pathways, changes in the signs of genetic correlations of ANM to health indicators and outcomes, and differences in inferred causal relationships. We find that DNA damage response processes only act to shape ovarian reserve and depletion for women of early ANM. Genetically mediated delays in ANM were associated with increased relative risk of breast cancer and leiomyoma at all ages and with high cholesterol and heart failure for late-ANM women. These findings suggest that a better understanding of the age dependency of genetic risk factor relationships among health indicators and outcomes is achievable through appropriate statistical modeling of large-scale biobank data.},
  author       = {Ojavee, Sven E. and Darrous, Liza and Patxot, Marion and Läll, Kristi and Fischer, Krista and Mägi, Reedik and Kutalik, Zoltan and Robinson, Matthew Richard},
  issn         = {1537-6605},
  journal      = {American Journal of Human Genetics},
  number       = {9},
  pages        = {1549--1563},
  publisher    = {Elsevier},
  title        = {{Genetic insights into the age-specific biological mechanisms governing human ovarian aging}},
  doi          = {10.1016/j.ajhg.2023.07.006},
  volume       = {110},
  year         = {2023},
}

@article{12142,
  abstract     = {Theory for liability-scale models of the underlying genetic basis of complex disease provides an important way to interpret, compare, and understand results generated from biological studies. In particular, through estimation of the liability-scale heritability (LSH), liability models facilitate an understanding and comparison of the relative importance of genetic and environmental risk factors that shape different clinically important disease outcomes. Increasingly, large-scale biobank studies that link genetic information to electronic health records, containing hundreds of disease diagnosis indicators that mostly occur infrequently within the sample, are becoming available. Here, we propose an extension of the existing liability-scale model theory suitable for estimating LSH in biobank studies of low-prevalence disease. In a simulation study, we find that our derived expression yields lower mean square error (MSE) and is less sensitive to prevalence misspecification as compared to previous transformations for diseases with  =< 2% population prevalence and LSH of =< 0.45, especially if the biobank sample prevalence is less than that of the wider population. Applying our expression to 13 diagnostic outcomes of  =< 3% prevalence in the UK Biobank study revealed important differences in LSH obtained from the different theoretical expressions that impact the conclusions made when comparing LSH across disease outcomes. This demonstrates the importance of careful consideration for estimation and prediction of low-prevalence disease outcomes and facilitates improved inference of the underlying genetic basis of  =< 2% population prevalence diseases, especially where biobank sample ascertainment results in a healthier sample population.},
  author       = {Ojavee, Sven E. and Kutalik, Zoltan and Robinson, Matthew Richard},
  issn         = {0002-9297},
  journal      = {The American Journal of Human Genetics},
  keywords     = {Genetics (clinical), Genetics},
  number       = {11},
  pages        = {2009--2017},
  publisher    = {Elsevier},
  title        = {{Liability-scale heritability estimation for biobank studies of low-prevalence disease}},
  doi          = {10.1016/j.ajhg.2022.09.011},
  volume       = {109},
  year         = {2022},
}