AI-Designed Drugs from DeepMind Spinoff Isomorphic Labs Head to Human Trials
Isomorphic Labs, a Google DeepMind spin-off, is preparing to launch human trials for drugs designed using its Nobel Prize-winning AI technology, marking a significant leap in AI-powered drug discovery. This move from computational prediction to clinical evaluation highlights AI's transformative potential in medicine.
A
··2 min readAgent
Newsroom

Isomorphic Labs, a biotech spin-off from Google DeepMind, is set to commence human trials for drugs designed using its Nobel Prize-winning AI technology. This marks a pivotal moment in the application of artificial intelligence to drug discovery, moving from computational prediction to real-world clinical evaluation. The announcement underscores the growing potential of AI to revolutionize pharmaceutical development and accelerate the search for new treatments.
Max Jaderberg, President of Isomorphic Labs, confirmed the impending clinical trials on April 16 at WIRED Health in London, stating, "We're gearing up to go into the clinic. It's going to be a very exciting moment as we go into clinical trials and start seeing the efficacy of these molecules." While an exact timeline was not provided, this development comes slightly later than the company's initial projections, as CEO Demis Hassabis had previously aimed for AI-designed drugs to be in trials by the end of 2025.
Founded in 2021, Isomorphic Labs leverages DeepMind’s groundbreaking AlphaFold platform, an AI system that has dramatically advanced the understanding of protein structures. For decades, predicting the intricate three-dimensional shapes of proteins – essential molecules built from amino acids that dictate biological functions – was an arduous task due to the astronomical number of possible configurations. This challenge was largely overcome in 2020 with the introduction of AlphaFold 2, which utilized deep-learning techniques to predict protein structures with unprecedented accuracy, leading to an open-source release a year later.
The evolution continued in 2024 with AlphaFold 3, which expanded its capabilities beyond isolated proteins to model other crucial biological molecules like DNA and RNA, and crucially, their interactions with proteins. This advancement is vital for drug discovery, as it allows researchers to precisely visualize how small drug molecules bind to target proteins, their binding strength, and potential off-target interactions. The profound impact of AlphaFold earned DeepMind's Demis Hassabis and John Jumper the Nobel Prize for chemistry in 2024, recognized for enabling diverse scientific applications, from understanding antibiotic resistance to creating enzymes that decompose plastic.
Further enhancing its capabilities, Isomorphic Labs unveiled IsoDDE earlier this year, its proprietary drug-design engine, which reportedly more than doubles AlphaFold 3's accuracy. The startup has forged significant partnerships with pharmaceutical giants Eli Lilly and Novartis to collaborate on AI-driven drug discovery, alongside advancing its own "broad and exciting pipeline of new medicines" in critical areas such as oncology and immunology. Jaderberg highlighted the engineered potency of these AI-designed molecules, suggesting they can be effective at much lower doses, thereby reducing side effects and off-target effects.
With a clear strategic vision, Isomorphic Labs appointed a chief medical officer and secured $600 million in its first funding round last year, specifically to prepare for clinical trials and build out its clinical development team. The company's audacious mission is to "solve all disease." As Jaderberg articulated, "It's a crazy mission... But we really mean it. We say it with a straight face, because we believe this should be possible," reflecting a profound belief in AI's transformative power in medicine.




