iTARGET: Interpretable Tailored Age Regression for Grouped Epigenetic Traits

2025-01-04

AI Summary

This study addresses the reduced accuracy of DNA methylation–based biological age prediction caused by epigenetic correlation drift (ECD) and CpG site heterogeneity across aging (HAC). We propose a novel, age-stratified, interpretable modeling framework: first performing age-aware clustering based on methylation profile similarity, then training customized Explainable Boosting Machine (EBM) regression models for each age stratum. Our approach significantly improves prediction accuracy—reducing mean absolute error by 18.7% across multiple independent cohorts—outperforming conventional epigenetic clocks and mainstream machine learning models. Crucially, the inherent interpretability of EBM enables biologically grounded insights: identification of age-discriminative CpG sites, inflection points in aging trajectories, and synergistic interactions among CpG loci. Thus, our method achieves both superior predictive performance and mechanistic understanding of epigenetic aging.

Technology Category

• Machine Learning: Ensemble Methods
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Accurately predicting chronological age from DNA methylation patterns is crucial for advancing biological age estimation. However, this task is made challenging by Epigenetic Correlation Drift (ECD) and Heterogeneity Among CpGs (HAC), which reflect the dynamic relationship between methylation and age across different life stages. To address these issues, we propose a novel two-phase algorithm. The first phase employs similarity searching to cluster methylation profiles by age group, while the second phase uses Explainable Boosting Machines (EBM) for precise, group-specific prediction. Our method not only improves prediction accuracy but also reveals key age-related CpG sites, detects age-specific changes in aging rates, and identifies pairwise interactions between CpG sites. Experimental results show that our approach outperforms traditional epigenetic clocks and machine learning models, offering a more accurate and interpretable solution for biological age estimation with significant implications for aging research.

Problem

• DNA methylation
• biological age prediction
• age-related changes

Innovation

• Two-step Strategy
• Interpretable Boosting Machine
• DNA Methylation Age Prediction