Graph-Based Biomarker Discovery and Interpretation for Alzheimer's Disease
Maryam Khalid, Fadeel Sher Khan, John Broussard, Arko Barman
TL;DR
The study tackles the challenge of early Alzheimer's disease (AD) detection and drug target discovery by developing BRAIN, a framework that ensembles $K=3$ machine learning models and bootstraps across $B$ iterations, aggregates feature importances via SHAP with the rule $S_i = rac{1}{TBK} \, \sum_{j=1}^{TBK} |s_i^j|$, and then constructs graph representations to reveal inter-biomarker relationships. By removing APOE-related biomarkers to mitigate confounding and addressing multicollinearity, BRAIN identifies a comprehensive set of discriminative biomarkers and three distinct sub-networks whose interactions differ between AD and control groups in the TARCC blood biomarker dataset. The graph-based representation enables interpretable visualization of holistic biomarker interdependencies and highlights potential targets for therapeutic intervention, while demonstrating how different models prioritize different biomarkers due to correlation structure. Overall, the approach advances cost-effective, population-level screening and mechanistic understanding of AD by coupling robust biomarker discovery with network-level interpretation and domain-aware validation.
Abstract
Early diagnosis and discovery of therapeutic drug targets are crucial objectives for the effective management of Alzheimer's Disease (AD). Current approaches for AD diagnosis and treatment planning are based on radiological imaging and largely inaccessible for population-level screening due to prohibitive costs and limited availability. Recently, blood tests have shown promise in diagnosing AD and highlighting possible biomarkers that can be used as drug targets for AD management. Blood tests are significantly more accessible to disadvantaged populations, cost-effective, and minimally invasive. However, biomarker discovery in the context of AD diagnosis is complex as there exist important associations between various biomarkers. Here, we introduce BRAIN (Biomarker Representation, Analysis, and Interpretation Network), a novel machine learning (ML) framework to jointly optimize the diagnostic accuracy and biomarker discovery processes to identify all relevant biomarkers that contribute to AD diagnosis. Using a holistic graph-based representation for biomarkers, we highlight their inter-dependencies and explain why different ML models identify different discriminative biomarkers. We apply BRAIN to a publicly available blood biomarker dataset, revealing three novel biomarker sub-networks whose interactions vary between the control and AD groups, offering a new paradigm for drug discovery and biomarker analysis for AD.