Applying Real-World Drug Discovery Experience in the OpenADMET ExpansionRx Blind Challenge

Join us for this webinar, where Jason Wang from Merck & Co and Davide Boldini from Merck KGaA, top performers in the recent OpenADMET ExpansionRx Blind Challenge, describe how they drew on years of experience in drug discovery programs to make critical decisions about model architecture, pre-training, data augmentation, and other factors.

Key Learnings Explored:

• Foundation models consistently outperform alternatives.
• Supervised pre-training on diverse multitask data is an effective strategy.
• Easy-to-use MLOps and SWE tooling are key to improve model quality and impact.