Drug Repurposing in The Era of AI: A Review

Drug repurposing is the process of finding new therapeutic uses for already-approved medications. It has become very popular as a fast and less expensive replacement for usual drug development. The incorporation and analysis of large, various biomedical datasets, such as genomic, proteomic, clinical, and real-world evidence, have been made feasible by the evolution of artificial intelligence (AI), which has entirely transformed this discipline. Advanced machine learning and deep learning algorithms simplify the prediction of drug–target interactions, identification of novel disease–drug associations, and organizing repurposing prospects with unparalleled speed and accuracy. Natural language processing, network-based learning, and graph neural networks, like computational models are contributing significantly in AI driven drug repurposing. This review highlights the requirement of associative cooperation to achieve therapeutic success from the in-silico prediction while crucially evaluating issues with quality of date, model comprehensibility, validation, and ethical considerations. Case studies display AI-enabled repurposing during the COVID-19 pandemic and in oncology, neurology, and rare diseases indicate the shifting potential of this approach. This review provides a thorough understanding of changing paradigm in drug repurposing by AI and accelerating the journey from discovery to patient treatment by combining existing knowledge with potential future paths.