ABSTRACT
The development of new drugs is a lengthy and resource-intensive process, often spanning decades and requiring substantial financial investment and effort. With success rates typically low, hovering around 14%, the need to streamline this process, reduce costs, and enhance success rates is paramount. Drug repurposing emerges as a crucial strategy to achieve these goals by identifying novel therapeutic indications for existing drugs. Also known as drug repositioning or therapeutic switching, this approach leverages previous investments while mitigating the risks associated with clinical activities. Compared to traditional drug discovery methods, which are characterized by their high expenses, laborious nature, and significant risk of failure, drug repurposing offers a more efficient alternative. This review explores how leveraging machine learning techniques in drug repurposing can further expedite the drug development process while minimizing costs. By harnessing the power of computational algorithms, researchers can efficiently sift through vast datasets to identify promising candidates for repurposing, ultimately accelerating the delivery of new therapeutic solutions.
