Despite GPCRs accounting for a significant proportion of all approved drugs, it is estimated that 60–85% of potentially therapeutic GPCRs remain untargeted, leaving substantial untapped opportunity within this receptor class. Historically, limited structural data has posed a major challenge to advancing GPCR-targeted drug discovery. However, recent breakthroughs in AI-driven modelling and machine learning are beginning to transform this landscape. From predicting receptor structures with greater precision to enhancing target identification and streamlining drug design, these technologies are rapidly accelerating discovery and enabling access to previously unreachable targets. This workshop will explore how the latest advancements in AI and ML are driving innovation in GPCR drug discovery, bridging the gap from target identification to clinical translation.

Key Takeaways:

• Utilise computer-based drug design to overcome structural gaps by supporting structure prediction, binding-site identification and functional conformation modelling, particularly for orphan and lipid-sensing receptors
• Enhance virtual screening and hit prioritisation by leveraging AI for molecular docking, chemical space exploration, and machine learning-driven scoring, ranking, and selection of tractable compounds
• Predict functional states and downstream signalling using AI models to gain deeper insights into receptor behaviour and distinguish between agonist and antagonist responses