AI-Designed Drugs by a DeepMind Spinoff Are Headed to Human Trials

Google DeepMind’s AlphaFold There has already been a revolution in scientists’ understanding of proteins. Now, the platform’s ability to design safe and effective medicines is about to be tested.

Isomorphic Labs, the UK-based biotech spinoff of Google DeepMind, will soon begin human trials of drugs designed by its Nobel Prize-winning AI technology. “We are preparing to go into the clinic,” Max Jederberg, president of Isomorphic Labs, said at WIRED Health in London on April 16. “This is going to be a very exciting moment as we move into clinical trials and begin to see the efficacy of these molecules.”

Jaderberg didn’t elaborate on the timeline, but it’s after the company had planned to begin human studies. Last year, CEO Demis Hassabis said there would be AI-designed drugs in clinical trials by the end of 2025.

Isomorphic Labs was founded in 2021 as a spinoff of Alphabet’s AI research subsidiary, Google DeepMind. The company uses DeepMind’s AlphaFold, a groundbreaking AI platform that predicts protein structures, for drug discovery.

Composed of 20 different amino acids, proteins are essential for all living organisms. Long chains of amino acids join together and fold to form the three-dimensional structure of a protein, which determines the protein’s function. Researchers have tried to predict protein structures since the 1970s, but it was a laborious process given the astronomically high number of possible shapes of protein chains.

That changed in 2020, when DeepMind’s Hassabis and John Jumper presented surprising results from AlphaFold 2, which uses deep-learning techniques. A year later, the company released an open-source version of AlphaFold that was available to anyone.

In 2024, DeepMind and Isomorphic Labs released AlphaFold 3, which further advanced scientists’ understanding of the protein. It moved beyond modeling proteins in isolation to predicting their interactions with other important molecules and proteins, such as DNA and RNA.

“This is exactly what you need for drug discovery: You need to see how a small molecule binds to a drug, how strongly, and also what it can bind to,” Hassabis told WIRED at the time.

Since its release, the AlphaFold platform has been able to predict the structure of nearly all 200 million proteins known to researchers and has been used by more than 2 million people in 190 countries. The breakthrough earned Hassabis and Jumper the Nobel Prize for Chemistry in 2024, with the Nobel committee saying AlphaFold has enabled numerous scientific applications, including a better understanding of antibiotic resistance and the creation of images of enzymes that can decompose plastics.

Earlier this year, Isomorphic Labs announced an even more powerful tool, what it calls its proprietary drug-design engine, IsoDDE. In a technical paper, the company says the platform doubles the accuracy of AlphaFold 3.

Jederberg said the startup has partnered with Eli Lilly and Novartis to work together on AI drug discovery and is also advancing its “broad and exciting pipeline of new medicines” in oncology and immunology.

“The exciting thing about the molecules we’re designing is that as we have so much understanding of how these molecules work, we’ve engineered them to be very, very powerful,” Jederberg told the audience at WIRED Health. “You can take them at much lower doses, and they’ll have fewer side effects, other than off-target.”

Last year, Isomorphic appointed a chief medical officer and announced it had raised $600 million in its first funding round to prepare for clinical trials. Meanwhile, the company is building a clinical development team. Its mission is to “solve all ills”.

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



<a href

Leave a Comment