First human trials of AI-designed cancer drugs scheduled to start soon

Alphabet's drug discovery subsidiary Isomorphic Labs is preparing to begin the first human clinical trials of medicines designed entirely by artificial intelligence, marking a potential turning point in pharmaceutical development after years of AI-assisted research.

Colin Murdoch, president of Isomorphic Labs and chief business officer at Google DeepMind, told Fortune that the company is "getting very close" to dosing patients with its AI-created drugs. The trials represent a crucial test of whether AI can deliver on promises to accelerate drug discovery and reduce the industry's notoriously high failure rates.

Preparing for Human Testing

"There are people sitting in our office in King's Cross, London, working, and collaborating with AI to design drugs for cancer," Murdoch said during an interview in Paris. "That's happening right now."

The company is currently staffing up for the trials, focusing initially on oncology candidates, according to Clinical Trials Arena. Isomorphic has been developing drug candidates in oncology and immunology fields for future licensing.

The trials will test drugs created using AlphaFold, the Nobel Prize-winning AI system that can predict protein structures and model how proteins interact with other molecules like DNA and drugs. Traditional pharmaceutical companies invest millions in drug development with only about a 10 percent success rate in trials.

Technology and Partnerships

Isomorphic Labs, spun out from DeepMind in 2021, has established partnerships with pharmaceutical giants Novartis and Eli Lilly. In April 2025, the company raised $600 million in its first external funding round led by Thrive Capital.

"This funding will further turbocharge the development of our next-generation AI drug design engine, help us advance our own programs into clinical development," said Isomorphic founder and CEO Sir Demis Hassabis.

The company's AI models can analyze vast amounts of biological data to identify drug targets and design new compounds, potentially reducing development timelines from the traditional 15 years to 18 months.

The AlphaFold Foundation

Isomorphic's approach stems from AlphaFold, developed by John Jumper and Demis Hassabis, who won the 2024 Nobel Prize in Chemistry. The system evolved from predicting individual protein structures to modeling complex molecular interactions.

"This was the inspiration for Isomorphic Labs," Murdoch explained. "It really demonstrates that we could do something very foundational in AI that could help unlock drug discovery."

The company envisions a future where researchers can identify a disease and computationally generate treatment designs. "One day we hope to be able to say — well, here's a disease, and then click a button and out pops the design for a drug to address that disease," Murdoch said.