Chai Discovery has announced an expanded collaboration with GSK following a successful laboratory evaluation of its artificial intelligence-powered molecular design technology. The agreement will provide GSK with access to Chai's platform, including its protein folding and design models, to support drug discovery activities across its therapeutic pipeline.
The collaboration follows an evaluation in which Chai's AI models generated molecular designs against a diverse panel of GSK-selected therapeutic targets. The models operated in a zero-shot setting, meaning they produced designs without requiring additional training specific to individual targets.
GSK subsequently conducted internal wet-lab experiments to assess the generated molecules, identifying binders across all tested targets. The findings provided the basis for extending the companies' relationship into a broader collaboration.
Christopher Austin, SVP R&D Technologies at GSK, commented: “We evaluated their models across a panel of diverse targets and saw designs with strong binding affinities. Their technology complements our own internal models that we continuously retrain against our own wet-lab data, all helping to enable us to accelerate the discovery of potential new medicines.”
Chai Discovery develops AI models designed to predict molecular interactions and generate new molecular structures, with applications in preclinical drug discovery. Its latest model, Chai-3, focuses on protein structure prediction and molecular design, including approaches targeting biological mechanisms that have historically presented challenges for conventional drug discovery methods.
Joshua Meier, co-founder and CEO of Chai Discovery, stated: “The evaluation gave both teams an opportunity to assess Chai’s models against a range of therapeutic targets in the lab. We are excited to build on those results with GSK and support discovery efforts across its pipeline.”
Founded in 2024 and headquartered in San Francisco, Chai Discovery has pursued multiple pharmaceutical industry collaborations throughout 2026.
The agreement reflects increasing pharmaceutical interest in integrating generative AI into early-stage drug development. By combining computational molecular design with experimental validation, the collaboration aims to support the identification and assessment of potential therapeutic candidates while complementing GSK's existing internal AI capabilities.
Click here for the original news story.
