Abstract
In modern pharmaceutical research and development (R&D), drug discovery remains a challenging process. Artificial intelligence (AI) has been extensively incorporated into various phases of drug discovery and development. AI enable effectively extract molecular structural features, perform in-depth analysis of drug-target interactions, and systematically model the relationships among drugs, targets, and diseases. These approaches improve prediction accuracy, accelerate discovery timelines, reduce costs from trial and error methods, and enhance success probabilities. This review summarizes recent advances in AI applications for drug design, including target identification, synthetic accessibility prediction, lead optimization, and ADMET property evaluation. Furthermore, it introduces various deep learning tools to guide researchers in selecting and implementing the most appropriate AI-driven strategies throughout the drug discovery process. We hope it can establish a conceptual framework intended to advance AI-driven methodologies in pharmaceutical research by comprehensively organizing novel perspectives and critical insights.