San Francisco-based Chai Discovery and Bristol Myers Squibb (NYSE: BMY) have announced a collaboration to apply Chai's generative AI antibody discovery platform across BMS's broader portfolio, with the stated goal of building an AI-powered, continuously learning discovery system at BMS. The deal covers antibody candidate identification across multiple undisclosed targets. Financial terms were not disclosed.
Under the agreement, BMS gains access to Chai's molecular folding and design models, which predict and reprogram molecular interactions to generate novel biomolecule designs from defined therapeutic criteria. The platform's current-generation system, Chai-3, is a multimodal diffusion-based architecture capable of designing complete antibody sequences and structures from scratch conditioned on a target protein and binding epitope, with the company reporting that its predecessor Chai-2 achieved experimental hit rates of approximately 16–20% in fully de novo antibody design compared with sub-1% rates for prior computational methods.
No upfront payment, milestones, royalties, territorial rights, or equity component were disclosed.