Decoding heterogeneous aging clocks and disease risk stratification using MetAgeFormer
- 1Department of Computer Science, Hong Kong Baptist University
Abstract
Metabolomic aging clocks estimate biological age by modeling metabolite concentrations, thereby capturing aging signals from healthspan and adverse outcomes. However, existing clocks generally assume homogeneous aging trajectories and yield only a single age acceleration metric, limiting their capacity to capture inter-individual metabolic heterogeneity and characterize nuanced individual-level representations. To address these limitations, we proposed MetAgeFormer, a transformer-based metabolomic model pre-trained on nuclear magnetic resonance (NMR) metabolomic profiles from over 430,000 participants in UK Biobank via self-supervised learning. This large-scale pre-training enables MetAgeFormer to learn a metabolomic representation space that captures the complex, nonlinear structure of systemic metabolism as reflected in NMR data. Building on MetAgeFormer, we developed a mortality-informed metabolomic aging clock by fine-tuning an attached survival module, deriving age acceleration that demonstrates significant associations with multiple age-related diseases and factors. We further validated zero-shot transfer in the independent Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. More importantly, we utilized embeddings generated by MetAgeFormer to identify 13 distinct metabolic subtypes and consolidated them into four meta-subtypes with markedly divergent susceptibility profiles for major age-related diseases, particularly type 2 diabetes and neurodegenerative disorders. This finding empirically demonstrated substantial metabolic heterogeneity across populations, persisting even at comparable levels of age acceleration. To enhance clinical applicability, we further employed contrastive learning to distill a lightweight model that approximates the learned metabolomic representation space using only 14 routine clinical blood test measurements as inputs. Both hold-out testing within UK Biobank and external validation in the China Health and Retirement Longitudinal Study replicated similar disease onset patterns across the identified subtypes, underscoring the robust generalizability of MetAgeFormer and supporting its translational potential as a scalable framework for metabolomic aging assessment and early disease risk stratification.
Related
- Interferon‐α–Driven Stratification of B Cells Reveals Metabolic Reprogramming of Double‐Negative, Naïve, and Transitional Cell Subsets and Refines Molecular Classification in Sjögren's Disease
- OmniRE-seq: A Dual-Method Framework for Decoding RNA Editing Dynamics in Disease and Therapy
- Heterogeneous Graph Contrastive Learning for Drug-Gene-Disease Motif Prediction
- Clinical variables and quantitative CT radiomics for mortality risk stratification after acute exacerbation of idiopathic inflammatory myopathy-associated interstitial lung disease
- A heterogeneous biomedical knowledge network framework for rare disease drug candidate prioritization: integrating Orphadata and DisGeNET via gene-bridge harmonization
BibTeX
@misc{xu2026decoding,
title = {{Decoding heterogeneous aging clocks and disease risk stratification using MetAgeFormer}},
author = {Y. Xu and B. Zou and G. Xie and T. Chen and W. Jia and L. Zhang},
howpublished = {bioRxiv},
year = {2026},
month = may,
doi = {10.64898/2026.05.18.725977},
url = {https://www.biorxiv.org/content/10.64898/2026.05.18.725977v2},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Decoding heterogeneous aging clocks and disease risk stratification using MetAgeFormer
AU - Y. Xu
AU - B. Zou
AU - G. Xie
AU - T. Chen
AU - W. Jia
AU - L. Zhang
PY - 2026
DA - 2026/05/18
PB - bioRxiv
DO - 10.64898/2026.05.18.725977
UR - https://www.biorxiv.org/content/10.64898/2026.05.18.725977v2
AB - Metabolomic aging clocks estimate biological age by modeling metabolite concentrations, thereby capturing aging signals from healthspan and adverse outcomes. However, existing clocks generally assume homogeneous aging trajectories and yield only a single age acceleration metric, limiting their capacity to capture inter-individual metabolic heterogeneity and characterize nuanced individual-level representations. To address these limitations, we proposed MetAgeFormer, a transformer-based metabolomic model pre-trained on nuclear magnetic resonance (NMR) metabolomic profiles from over 430,000 participants in UK Biobank via self-supervised learning. This large-scale pre-training enables MetAgeFormer to learn a metabolomic representation space that captures the complex, nonlinear structure of systemic metabolism as reflected in NMR data. Building on MetAgeFormer, we developed a mortality-informed metabolomic aging clock by fine-tuning an attached survival module, deriving age acceleration that demonstrates significant associations with multiple age-related diseases and factors. We further validated zero-shot transfer in the independent Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. More importantly, we utilized embeddings generated by MetAgeFormer to identify 13 distinct metabolic subtypes and consolidated them into four meta-subtypes with markedly divergent susceptibility profiles for major age-related diseases, particularly type 2 diabetes and neurodegenerative disorders. This finding empirically demonstrated substantial metabolic heterogeneity across populations, persisting even at comparable levels of age acceleration. To enhance clinical applicability, we further employed contrastive learning to distill a lightweight model that approximates the learned metabolomic representation space using only 14 routine clinical blood test measurements as inputs. Both hold-out testing within UK Biobank and external validation in the China Health and Retirement Longitudinal Study replicated similar disease onset patterns across the identified subtypes, underscoring the robust generalizability of MetAgeFormer and supporting its translational potential as a scalable framework for metabolomic aging assessment and early disease risk stratification.
ER -