Bristol Myers, Takeda to pool data for AI-based drug discovery

By Sneha S K Oct 1 (Reuters) – Bristol Myers Squibb, Takeda Pharmaceuticals and Astex Pharmaceuticals are coming together to share proprietary data for training an artificial intelligence model to assist drug discovery and development. The companies are joining a consortium that includes AbbVie and Johnson & Johnson, and will contribute data from several thousand experimentally determined protein–small molecule structures to train an AI model called OpenFold3, life sciences company Apheris said on Wednesday. The initiative is based on a federated data sharing model, which enables collaboration without exposing sensitive data. Germany-based Apheris' computing platform enables the aggregation of diverse data sets from companies while ensuring each dataset remains securely in its original location. By pooling these datasets, the initiative aims to improve OpenFold3’s accuracy in predicting interactions of proteins and small molecules. The federated platform allows multiple companies to "advance predictive models for small molecule discovery in ways no single organization could achieve alone," said Payal Sheth, vice president, discovery biotherapeutics and lead discovery and optimization at Bristol. OpenFold3 is the flagship project of the industry-led AI Structural Biology Network, conducted in collaboration with the AlQuraishi Lab at Columbia University. This consortium really ties into our larger corporate goal of embedding AI throughout all of what we do; and also a nice example of how we can come together as pharma companies and do even more for patients than we could if we did it on our own, said Hans Bitter, head of computational sciences at Takeda. (Reporting by Sneha S K in Bengaluru; Editing by Sahal Muhammed)

(The article has been published through a syndicated feed. Except for the headline, the content has been published verbatim. Liability lies with original publisher.)