Roche Partners with Chai Discovery to Leverage AI Models in Drug Discovery Programmes

The collaboration will integrate Chai Discovery's computer-aided design platform for protein-based therapeutics into Roche's drug discovery programmes.

Swiss pharmaceutical giant Roche has partnered with US-based artificial intelligence company Chai Discovery to deploy its AI models and platform across multiple drug discovery programmes spanning Roche's therapeutic areas.

The collaboration will integrate Chai Discovery's computer-aided design platform for protein-based therapeutics into Roche's drug discovery programmes.

Sharing his thoughts, Boris L. Zaïtra, Head of Corporate Business Development at Roche, said, “Chai’s platform aligns well with our research strategy. We look forward to collaborating to advance drug discovery programs.”

The partnership will leverage Chai-3, Chai Discovery's latest AI model, which is designed to support protein-based therapeutic development by analysing biological structures and generating molecular designs.

The company said the model has demonstrated high target success rates and binding affinities, including against challenging biological targets.

Commenting on the collaboration, Joshua Meier, Co-founder and CEO of Chai Discovery, said, “We are delighted to see Chai's models being used by Roche in their portfolio. This expands the range of therapeutic programs that can benefit from AI-driven molecular design.”

Chai Discovery is a San Francisco-based AI biotechnology company founded in 2024. It develops computational models for protein structure prediction, molecular design, and therapeutic discovery, with a focus on applying AI to accelerate the development of new medicines.

The latest partnership follows Chai’s earlier announced collaboration with Bristol Myers Squibb to advance therapeutic antibody discovery using artificial intelligence (AI).

Under the agreement, BMS will leverage Chai's molecular folding and design models across its drug discovery portfolio to support the identification of antibody candidates and the development of an AI-powered, continuously learning discovery system.

Stay tuned for more such updates on Digital Health News