LONDON, October 15, 2026 — AstraZeneca is expanding its use of artificial intelligence in pharmaceutical research through a new partnership with California-based biotechnology company Insitro, targeting difficult-to-treat diseases affecting the liver and heart.

The agreement provides Insitro with an initial payment of $40 million. Additional payments tied to development and commercial achievements could reach approximately $1.46 billion, alongside royalties representing a single-digit percentage of future product sales.

The collaboration will concentrate on metabolic dysfunction-associated steatohepatitis (MASH), a serious liver condition, and cardiomyopathies, which affect the heart muscle. AstraZeneca said progress against both disease categories has been hindered by difficulties identifying the underlying biological mechanisms that drive them.

Insitro plans to apply its “Virtual Human” technology, which combines laboratory-grown cellular models with machine-learning systems, to investigate disease processes and identify promising therapeutic targets. AstraZeneca will select targets for the research, while Insitro will work to advance them toward development-candidate status. AstraZeneca will subsequently finance and oversee clinical trials under the multiyear arrangement.

The deal adds to Insitro’s growing relationships with major pharmaceutical companies. The biotechnology firm has broadened its work with Bristol Myers Squibb on potential treatments for amyotrophic lateral sclerosis (ALS). It has also partnered with Eli Lilly to develop AI models capable of forecasting how small-molecule compounds behave pharmacologically in living organisms.

AstraZeneca executive Sharon Barr, who leads biopharmaceutical research and development, said identifying worthwhile targets remains one of the most challenging aspects of bringing new medicines into development.

“Choosing the new targets that we ​want to put into ​our discovery pipeline is ⁠one of the hardest things we do across research and development,” Sharon Barr, executive vice president of biopharmaceuticals R&D at AstraZeneca, ​told Reuters.

Barr emphasized that researchers can lose a competitive advantage when potential targets become widely known through scientific publications.

“By the time we read about a new pathway or ​target (in major ⁠scientific journals), it is no longer novel. It’s in the public domain and we’re already a few steps too late. But when we identify these unique connections early and test them ⁠in ​cellular systems, we’re ahead of the game.”

She added that combining artificial intelligence with scientific expertise could help AstraZeneca screen fewer compounds experimentally, limit reliance on guesswork and identify effective treatments more efficiently.

The partnership reflects the pharmaceutical industry’s broader push to use AI to improve early-stage drug research. By helping scientists identify disease mechanisms and prioritize potential treatments, these technologies could make laboratory research more targeted, although prospective medicines must still undergo clinical testing to establish their safety and effectiveness.