Speakers: Tayo Obafemi-Ajayi PhD,

Genetic Data-Driven Prioritization of Druggable Gene Targets for Alzheimer’s Disease

Identifying high-yield targets for drug repurposing in complex and heterogeneous diseases such as Alzheimer’s disease (AD) is challenging due to high dimensionality of genetic data and limited functional annotation of associated variants. This highlights the need for novel, biology-informed feature selection approaches to effectively guide drug target discovery. We hypothesize that gene and disease-specific network properties—learnable from these large-scale biomedical knowledge graphs—can inform implicit gene-AD connections and prioritize repurposable AD drug targets. We applied scalable random walk methods to learn unbiased gene and disease embeddings, representative of their topological and semantic network properties.  These embeddings were subsequently used to compute gene-AD similarity and derive network-based scores for each gene. We validated the scores by constructing AD classification models using Alzheimer’s Disease Sequencing Project dataset. Models were optimized for performance, model complexity, and high aggregate network-based scores. Network-based scores successfully prioritized diverse feature sets—many not previously associated with AD—that are enriched in biologically meaningful body parts such as brain, and pathways including neuronal signaling, potassium channels, and creatine metabolism. The results suggested that knowledge graphs and network-informed embeddings could aid a scalable and biologically interpretable framework for AD drug repurposing and discovery.