Recent advances in molecular representation methods and their applications in scaffold hopping

The rapid evolution of molecular representation methods has significantly advanced the drug discovery process. Advances in language models, graph-based representations, and novel learning strategies have greatly improved the ability to characterize molecules. These AI-driven strategies extend beyond traditional structural data, facilitating exploration of broader chemical spaces and accelerating scaffold hopping. This review summarizes key advancements, discusses their advantages over conventional techniques, and highlights challenges in data quality and real-world applications.