AI- and ML-Driven Strategies for Drug Repurposing: Techniques, Applications, and Challenges

This chapter provides a comprehensive overview of the role of artificial intelligence (AI) and machine learning (ML) in drug repurposing, emphasizing their potential to uncover new therapeutic applications for existing drugs. It begins by categorizing drug repurposing methodologies into data-driven and approach-driven strategies, establishing a foundational framework for subsequent discussions. The chapter then explores fundamental AI/ML techniques, including classification, regression, clustering, and dimensionality reduction, with a focus on their applications in identifying drug-disease associations and optimizing drug properties. Building on this, advanced deep learning models, such as neural networks, generative adversarial networks (GANs), and graph neural networks (GNNs), and large language models (LLMs), are explained alongside tools such as AlphaFold for protein structure prediction based on amino acid sequences, showcasing the cutting-edge integration of AI with biological data. Critical challenges, including data integration, model interpretability, and scalability, are subsequently addressed, with potential solutions such as transfer learning and federated learning highlighted. Finally, the chapter discusses future directions, focusing on predicting adverse drug reactions (ADRs) and managing CYP450-mediated metabolism, underscoring the transformative potential of AI/ML in advancing drug repurposing.