DeepMind Spinoff’s AI-Designed Drugs Enter Human Trials

Google DeepMind’s AlphaFold has already transformed how scientists understand the building blocks of life. Now, the technology’s ability to design safe and effective drugs is about to face its most critical test yet.

Isomorphic Labs, the UK-based biotech spinoff of Google DeepMind, is preparing to launch human trials for drugs created by its Nobel Prize–winning AI platform. “We’re gearing up to go into the clinic,” said Max Jaderberg, president of Isomorphic Labs, during his April 16 presentation at WIRED Health in London. “It’s going to be a very exciting moment as we go into clinical trials and start seeing the efficacy of these molecules.”

Jaderberg did not specify a timeline, but the milestone comes later than originally anticipated. Last year, CEO Demis Hassabis stated that the company would have AI-designed drugs in clinical trials by the end of 2025.

Founded in 2021 as a spinoff from Alphabet’s AI research unit, Google DeepMind, Isomorphic Labs leverages DeepMind’s AlphaFold for drug discovery. AlphaFold is a groundbreaking AI system that predicts protein structures with remarkable accuracy.

Proteins, built from 20 different amino acids, are essential to all life. Long chains of amino acids fold into three-dimensional shapes that determine each protein’s function. Since the 1970s, researchers struggled to predict these structures due to the astronomical number of possible configurations. That changed in 2020 when Hassabis and John Jumper unveiled stunning results from AlphaFold 2, which uses deep-learning techniques. A year later, an open-source version was released to the public.

In 2024, DeepMind and Isomorphic Labs released AlphaFold 3, pushing the boundaries further. This version moved beyond modeling proteins in isolation to predicting other critical molecules like DNA and RNA, along with their interactions with proteins. “This is exactly what you need for drug discovery,” Hassabis told WIRED at the time. “You need to see how a small molecule is going to bind to a drug, how strongly, and also what else it might bind to.”

Since its launch, AlphaFold has predicted the structure of virtually all 200 million known proteins and has been used by over 2 million people across 190 countries. The breakthrough earned Hassabis and Jumper the Nobel Prize in Chemistry in 2024, with the Nobel committee highlighting AlphaFold’s role in advancing antibiotic resistance research and creating images of enzymes capable of breaking down plastic.

Earlier this year, Isomorphic Labs unveiled an even more powerful tool called IsoDDE, its proprietary drug-design engine. According to a technical paper, the platform more than doubles the accuracy of AlphaFold 3.

The startup has formed partnerships with Eli Lilly and Novartis to collaborate on AI-driven drug discovery. It is also developing its own “broad and exciting pipeline of new medicines” in oncology and immunology, Jaderberg said.

“The exciting thing about the molecules that we’re designing is because we have so much more of an understanding about how these molecules work, we’ve engineered them to be very, very potent,” Jaderberg told the WIRED Health audience. “You can take them at a much lower dose, and they’ll have lower side effects, off target effects.”

Last year, Isomorphic appointed a chief medical officer and raised $600 million in its first funding round to prepare for clinical trials. The company has been building a clinical development team with a mission to “solve all disease.”

“It’s a crazy mission,” Jaderberg admitted. “But we really mean it. We say it with a straight face, because we believe this should be possible.”