Integrative Multi-Omics Analysis for Etiology Classification and Biomarker Discovery in Stroke: Advancing towards Precision Medicine

Simple Summary Stroke is a devastating condition that leads to significant morbidity and mortality worldwide. To enhance our understanding of stroke pathophysiology and improve patient outcomes orldwides, it is crucial to explore high-throughput omics approaches and integrate multi-omics data. In this study, we propose a graph-based integrative approach to identify stroke-related gene expression changes using blood samples from ischemic stroke patients. Our goal is to discover biomarkers that can aid in the diagnosis, etiological classification, and management of stroke.Abstract Recent advancements in high-throughput omics technologies have opened new avenues for investigating stroke at the molecular level and elucidating the intricate interactions among various molecular components. We present a novel approach for multi-omics data integration on knowledge graphs and have applied it to a stroke etiology classification task of 30 stroke patients through the integrative analysis of DNA methylation and mRNA, miRNA, and circRNA. This approach has demonstrated promising performance as compared to other existing single technology approaches.