Preprint · CC-BY
via OpenAlex
Variational autoencoders to predict DNA-methylation age and provide biological insights in age-related health and disease
Sandra Steyaert, Adriaan Verhelle, Wim Van Criekinge
medRxiv · 2023 · ▲ 2 citations
Abstract
Abstract Motivation Epigenetic ageing clocks based on age-associated changes in DNA-methylation (DNAm) profiles have shown great potential as predictors to quantify age-related health and disease. Most of these clocks are built using penalized linear regression models with the aim to predict chronological and/or biological age. However, the precise underlying biological mechanisms influencing these clocks remain unclear. In this work, we explored if a Variational Autoencoder (VAE) can be trained to model DNAm age, and whether this VAE captures biologically relevant features of ageing in the latent space. Results Our results indicate that VAEs present a promising framework to construct embeddings that capture complex interactions and that can be used to extract biological meaningful features upon predicting DNAm age. By using deep learning interpretation methods, we show it is possible to determine which genomic loci and pathways are important in making the predictions, both on a population and individual level, paving the way to unravel what makes the DNAm clock tick.
◌ CITATION ONLY
Full text is not openly licensed for redistribution here. Read it at the source:
Provenance
- Source
- OpenAlex
- DOI
- 10.1101/2023.07.07.23292381
- Canonical
- link ↗
- Fetched
- 2026-10-14 MST
Cite this
APA
Steyaert, S., Verhelle, A., & Criekinge, W.V. (2023). Variational autoencoders to predict DNA-methylation age and provide biological insights in age-related health and disease. <em>medRxiv</em>. https://doi.org/10.1101/2023.07.07.23292381
Vancouver
Steyaert S, Verhelle A, Criekinge WV. Variational autoencoders to predict DNA-methylation age and provide biological insights in age-related health and disease. medRxiv. 2023. doi:10.1101/2023.07.07.23292381.
BibTeX
@unpublished{sandra2023Variat,
title = {Variational autoencoders to predict DNA-methylation age and provide biological insights in age-related health and disease},
author = {Sandra Steyaert and Adriaan Verhelle and Wim Van Criekinge},
journal = {medRxiv},
year = {2023},
doi = {10.1101/2023.07.07.23292381},
}
Research neighborhood
References, citing works, and semantically nearest findings. Click a node to open it.
Related findings
Aging Cell 2024
Open access · CC-BY
DNA methylation and chromatin accessibility predict age in the domestic dog
Cells 2025
Open access · CC-BY
A Biophysics of Epigenetic Rejuvenation
The Eye Hospital of Wenzhou Medical University 2023
Open access · US-GOV
Predicting Biological Age Using Electronic Health Records: An AI-Based Approach
Scientific Reports 2024
Open access · CC-BY
Biologically informed deep learning for explainable epigenetic clocks
Innovation in Aging 2025
Open access · CC-BY
EnsembleAge Clock: A Reliable, Robust and Convenient Epigenetic Age Prediction Service for Promoting Healthy Aging
Aging Cell 2024
Open access · CC-BY