WIMOAD: Weighted Integration of Multi-Omics data with meta learning for Alzheimer's Disease diagnosis

BackgroundAlzheimer's disease (AD), the most prevalent subtype of dementia, is characterized by a gradual decline in brain cognitive function. Early detection is critical for initiating timely interventions that may delay the severe progression of the disease. Recent advances in next-generation sequencing (NGS) offer promising, non-invasive, and cost-effective strategies for AD screening. However, most current approaches rely on single-omics data, which fail to capture the complex biological heterogeneity among individuals.ObjectiveTo develop a user-friendly and efficient framework that incorporates blood-based multi-omics for stage-specific AD classification and detects genetic markers associated with disease pathology.MethodsWe introduce WIMOAD, a stacking ensemble and weighted multi-omics integration for AD diagnosis. It leverages paired gene expression and methylation data from ADNI and presents a meta learning framework for multi-cognitive stage classification during AD progression.ResultsAcross tasks, WIMOAD consistently outperforms single-omics models and representative integration baselines, and surpasses existing integration methods in AD diagnosis. Its interpretability also facilitates the detection of novel biomarkers across different omics layers. The code is freely available at https://github.com/wan-mlab/WIMOAD.ConclusionsThe study believes WIMOAD is an interpretable, cost-effective and promising integrative framework for accurate AD diagnosis and biomarker discovery across different cognitive stages utilizing blood-based data, which eventually will have consequential impacts on early treatment intervention and personalized therapy design for AD.