GSK has joined Chai Discovery’s growing roster of Big Pharma clients, signing up to access protein-folding and design models.
San Francisco-based Chai has established itself at the forefront of AI-enabled drug discovery this year, forming pacts with Bristol Myers Squibb, Eli Lilly, Novartis and Pfizer, as well as raising a $400 million series C round. Chai has shared details of its scientific progress in preprint papers, linking its second model to a 16% hit rate in fully de novo antibody design and showing its antibodies have drug-like properties.
GSK signed up to access Chai’s platform after evaluating the technology. The models “generated designs to GSK targets, zero-shot without target-specific training,” Chai said. GSK’s internal wet-lab testing of the designs uncovered binders to all tested targets.
“We evaluated their models across a panel of diverse targets and saw designs with strong binding affinities,” Christopher Austin, GSK’s senior vice president of R&D technologies, said in a statement. “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 has moved beyond the model with the 16% hit rate. The company designed its latest model, Chai-3, to achieve high target success rates and binding affinities, including to challenging targets. Chai showed its previous model, Chai-2, could design antibodies against six GPCRs.
The progress has attracted investors and large pharma companies. But the long timelines inherent to drug development mean evidence that Chai has a promising technology has yet to translate into clinical validation. With a who’s who of pharma companies using the platform, Chai has laid the foundations for exploring and validating the impact of the technology.
GSK CEO Luke Miels told journalists back in May that the “number one priority for the usage of AI is the innovation dimension.” Since then, the British Big Pharma has penned a $110 million deal with AI-focused biotech Relation focused on “generating large-scale human cellular perturbation data and deploying them into models.”
Where Big Pharma is placing its biggest bets is one of the hot topics being discussed at Fierce Biotech's high-impact event in London next month. Find out more information and register by clicking on the banner below:
