1:30 pm | Workshop B | Benchmarking Generative AI for Biologics to Define Metrics & Deliver Meaningful Models
Time: 1:30 pm
day: Pre-Conference AI Validation Workshop Day
Details:
How do we know if a generative AI model for biologics is truly effective? With new models emerging daily, what metrics reflect biological relevance, therapeutic potential, or developability? And when experimental validation is limited, how can we confidently compare, benchmark, and trust these models to guide critical drug design decisions?
This workshop will gather experts to discuss:
- Identify and prioritize key benchmarking criteria for generative biologic models, including developability, stability, and target affinity
- Examine approaches for validating generative model outputs in the absence of large-scale experimental datasets
- Discuss emerging frameworks and community efforts for establishing shared standards in biologics AI benchmarking
