Abstract: Alzheimer’s disease is a neurodegenerative disorder that leads to progressive memory loss, cognitive decline, and behavioral changes. Despite ongoing research, its exact causes and effective treatments remain elusive. Traditional approaches have focused on symptom management, but breakthroughs in bioinformatics and high-throughput drug screening are offering new pathways to potential therapies. This review highlights our recent efforts to identify novel drug candidates for Alzheimer’s disease by leveraging computational methods and large-scale biological datasets. Our work introduces two key innovations in Alzheimer’s disease research: addressing sex-specific differences and leveraging drug repurposing for accelerated treatment discovery. By combining sex-stratified preclinical data with machine learning and in vivo validation, we improve translational relevance and support precision medicine. Using the TgF344-AD rat model, which mimics human Alzheimer’s disease spatial memory deficits and pathology, we explored the efficacy of various US Food and Drug Administration– approved and investigational drugs. These included ibudilast, timapiprant, RG2833, diazoxide/ dibenzoylmethane (combined), and BT-11, which targeted key Alzheimer’s disease–related molecular pathways such as amyloid-beta plaques, Tau tangles, and neuroinflammation. These drugs, at various stages of development, offer hope for not only managing symptoms but also addressing the underlying mechanisms of Alzheimer’s disease. This review underscores the need for a multifaceted approach to Alzheimer’s disease treatment, combining symptom relief with disease modification.

Key words: Alzheimer’s disease, BT-11, diazoxide, dibenzoylmethane, drug repurposing, highthroughput drug approach, ibudilast, RG2833, TgF344-AD rat model, timapiprant