AI

Drug discovery is one of the most resource-intensive endeavours in modern science, requiring over 12 years and USD 2.6 billion on average to bring a single drug to market, with a clinical failure rate exceeding 90%. Artificial Intelligence (AI) is fundamentally transforming this process. This review examines how AI technologies — including machine learning, deep learning, graph neural networks, generative models, and natural language processing — are being applied across every stage of the drug discovery pipeline, with particular focus on drug repurposing. Key real-world case studies are analysed, including DeepMind’s AlphaFold2, which predicted over 200 million protein structures; Insilico Medicine’s AI-designed pulmonary fibrosis candidate developed in approximately 30 months; and BenevolentAI’s identification of baricitinib as an FDA-approved COVID-19 treatment. Advantages including accelerated timelines and improved molecular design are considered alongside persistent limitations in data quality, model interpretability, and regulatory frameworks. The review concludes with implications for pharmacy education and future directions including foundation models, multimodal AI, and quantum-enhanced simulation.