iTARGET: Interpretable Tailored Age Regression for Grouped Epigenetic Traits

TL;DR

This paper introduces iTARGET, a two-phase, interpretable machine learning approach that improves age prediction accuracy from DNA methylation data by addressing epigenetic heterogeneity and revealing key aging biomarkers.

Contribution

The paper presents a novel two-phase algorithm combining similarity clustering and explainable boosting to enhance age prediction and interpretability in epigenetic data.

Findings

Outperforms traditional epigenetic clocks in accuracy

Reveals key age-related CpG sites and interactions

Detects age-specific changes in aging rates

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.