AlphaFold by Google DeepMind has already revolutionized scientists’ knowledge of proteins. Now the platform’s ability to design protected and effective drugs will soon be put to the test.
Isomorphic Labs, the British biotechnology subsidiary of Google DeepMind, will soon begin human trials of drugs developed using Nobel Prize-winning artificial intelligence technology. “We are preparing to enter the clinic,” said Isomorphic Labs CEO Max Jaderberg on April 16 at WIRED Health in London. “It will be a very exciting moment when we start clinical trials and start to see the effectiveness of these molecules.”
Jaderberg did not provide a detailed timeline, but it is later than the company had planned to start human trials. Last year, CEO Demis Hassabis he said by the end of 2025, drugs designed by artificial intelligence would undergo clinical trials.
Isomorphic Labs was founded in 2021 as a subsidiary of Alphabet’s artificial intelligence research subsidiary Google DeepMind. The company leverages DeepMind’s AlphaFold, a breakthrough artificial intelligence platform that predicts protein structures, for drug discovery.
Proteins, made of 20 different amino acids, are imperative for all living organisms. Long chains of amino acids connect and fold together to form the three-dimensional structure of the protein, which determines its function. Scientists have been trying to predict protein structures since the 1970s, but this has been a tedious process given the astronomically huge number of possible shapes a protein chain can take.
That changed in 2020, when Hassabis and John Jumper of DeepMind presented stunning results from AlphaFold 2, which uses deep learning techniques. A year later, the company released an open-source version of AlphaFold, available to anyone.
In 2024, DeepMind and Isomorphic Labs released AlphaFold 3, which further deepened scientists’ understanding of proteins. They went beyond modeling isolated proteins and began to predict other essential molecules, such as DNA and RNA, and their interactions with proteins.
“That’s what you need in drug discovery: you have to see how the small molecule will bind to the drug, how strongly it can bind, and what else it can bind to,” Hassabis told WIRED at the time.
Since launch, the AlphaFold platform has been able to predict the structure of virtually all 200 million proteins known to researchers and is used by over 2 million people in 190 countries. The breakthrough earned Hassabis and Jumper an award Nobel Prize in Chemistry in 2024, and the Nobel Committee noted that AlphaFold enabled a range of scientific applications, including a better understanding of antibiotic resistance and creating images of enzymes that break down plastic.
Earlier this year, Isomorphic Labs announced an even more powerful tool it calls IsoDDE, its proprietary drug design engine. In technical paperthe company touts that the platform more than doubles the accuracy of AlphaFold 3.
The startup has partnered with Eli Lilly and Novartis to work together on AI-powered drug discovery, and is also working on its own “broad and exciting pipeline of new medicines” in oncology and immunology, Jaderberg said.
“What’s exciting about the molecules we’re designing is that we have so much more knowledge about how these molecules work, so we designed them to be very, very powerful,” Jaderberg told the WIRED Health audience. “You can take them at a much lower dose and the side effects will be smaller, off-target.”
Last year, Isomorphic appointed a chief medical officer and announced in its first round of financing, it raised $600 million to prepare for clinical trials. Meanwhile, the company was building a clinical development team. Its mission is to “solve all diseases.”
“It’s a crazy mission,” Jaderberg said. “But we really mean it. We mean it because we believe it should be possible.”