Isomorphic Labs, the spin-out of Google AI DeepMind’s London-based drug discovery-focused R&D division, announced today that it has entered into strategic partnerships with two pharmaceutical giants, Eli Lilly and Novartis, to apply AI to discover new drugs to treat diseases. .
The deals have a total value of about $3 billion. Isomorphic will receive $45 million upfront from Eli Lilly and potentially up to $1.7 billion based on performance milestones, excluding royalties. Novartis, meanwhile, will pay $37.5 million upfront, in addition to funding “selected” research expenses, and up to $1.2 billion (once again excluding royalties) in performance-based incentives over next year.
“We are excited to begin this partnership and implement our proprietary technology platform,” DeepMind co-founder and Isomorphic CEO Demis Hassambis said in a press release. “Our shared focus on advancing innovative approaches to drug design and appreciation of cutting-edge science does [these] partnership[s] particularly exciting.”
Fiona Marshall, president of biomedical research at Novartis, added in a statement: “Cutting-edge AI technologies … have the potential to transform the way we discover new medicines and accelerate our ability to deliver life-changing medicines to patients . This collaboration leverages our companies’ unique strengths, from artificial intelligence and data science to medicinal chemistry and deep disease expertise, to realize new possibilities in AI-driven drug discovery.”
Isomorphic, which Hassabis launched in 2021 under DeepMind’s parent company Alphabet, is based on DeepMind’s AlphaFold 2 AI technology that can be used to predict the structure of proteins in the human body. By uncovering these structures, the hope is that researchers can identify new target pathways to deliver drugs to fight disease.
Technology isn’t perfect. Recent article in the magazine Nature pointed out that AlphaFold occasionally makes obvious mistakes and, in many cases, is more useful as a “hypothesis generator” than as a replacement for experimental data. But the scale at which the model can generate reasonably accurate protein predictions is beyond most of the resulting methods.
Researchers recently used AlphaFold to design and synthesize a potential drug to treat hepatocellular carcinoma, the most common type of primary liver cancer. And DeepMind is working with the Geneva-based Drugs for Neglected Diseases initiative, a pharmaceutical nonprofit, to apply AlphaFold to formulating treatments for Chagas disease and leishmaniasis, two of the deadliest diseases in the developing world.
The latest version of AlphaFold can generate predictions for almost all molecules in the Protein Data Bank, the world’s largest open-access database of biological molecules, DeepMind announced in October. The model can also accurately predict the structures of ligands – molecules that bind to ‘receptor’ proteins and cause changes in the way cells communicate – as well as nucleic acids (molecules that contain key genetic information) and post-translational modifications (chemical changes that occur after a protein is made).
Already, Isomorphic is applying the new AlphaFold model – which it co-designed with DeepMind – to therapeutic drug design, helping to characterize different types of molecular structures important for treating diseases.
The pressure is on for Isomorphic to start turning a profit. In 2021, the company recorded a loss of £2.4 million (~$3 million) as it ramped up hiring ahead of the opening of its second office location in Lausanne, Switzerland.
