With AI tools like AlphaFold3, Boltz-2, Chai-1, RFdiffusion and generative chemistry platforms moving rapidly into the drug discovery space, the question is no longer if AI belongs in structure-based drug design but how to apply it effectively. This workshop will equip attendees with practical insights on incorporating AI/ML into the structural biology workflow, ensuring models are reliable, interpretable, and complementary to experimental approaches.

Highlights include:

Understand the current capabilities and limitations of AI for protein structure prediction, binding mode analysis, and property optimization

Learn strategies to integrate AI predictions with X-ray crystallography, Cryo-EM, NMR, and biophysical assays to validate and refine outputs

Explore case studies demonstrating AI in action, from accelerating hit-to-lead optimization to enabling novel scaffold and biologics design

Discuss best practices for data quality, avoiding “garbage in, garbage out,” and building trust in AI models across discovery teams

This session is ideal for structural biologists, computational chemists, AI/ML specialists, and drug discovery scientists seeking to unlock the full potential of artificial intelligence as part of a cohesive, structure-driven design strategy.