Edison Scientific will deploy its AI scientist, Kosmos, across Incyte’s drug discovery and development work.
The partnership will embed Kosmos across Incyte’s translational and clinical data to provide predictive models of therapeutic performance, according to a May 19 release. Initially, the work will focus on high-impact use cases within Incyte’s research workflows, with the potential to expand across the company’s broader R&D organization.
Incyte's Global Head of R&D Pablo Cagnoni, M.D., said in the release that he sees an opportunity for the company’s data to help train Kosmos, establishing a new model of collaboration in which AI not only analyzes data, but also learns from it to improve outcomes.
“This partnership aims to maximize our data’s value by integrating AI to guide experimental design and improve the quality and consistency of scientific and development decisions,” he said in the release.
The team-up with San Francisco-based Edison is just the latest example of biopharma’s embrace of AI to discover new drugs, identify patients for trials and even source future M&A deals. AstraZeneca reported last month that its Reinvent platform has halved the time needed to identify structures that could become new medicines, while its algorithm platform pinpoints patients most likely to respond to treatment.
Meanwhile, GSK CEO Luke Miels told journalists during a recent earnings call that the company is launching the AI in the earliest stages of R&D, with the aim of using it to design medicines. Bristol Myers Squibb is focused on broadening the use of AI, particularly to streamline clinical operations, shorten development timelines and improve quality oversight.
Partnerships have been a central strategy, with Novo Nordisk, Sanofi and Eli Lilly all inking deals with OpenAI, while Merck & Co. selected Google Cloud as its AI partner.
The collaboration between Edison and Incyte continues this trend, with an emphasis on improving the AI model’s performance while working toward the discovery of new medicines. Incyte's commercial portfolio includes marketing the Novartis-partnered blockbuster myelofibrosis drug Jakafi in the U.S., while its pipeline includes JAK2 inhibitors and CDK2 inhibitors.
“Most AI efforts in pharma treat data as something to analyze,” Edison CEO Sam Rodriques, Ph.D., said in today's release.
“What we are building treats data as something to learn from continuously,” Rodriques added. “The result is a system that compounds—where every experiment, every clinical readout and every decision improves the underlying models.”