Complementary cancer collaboration

MENLO PARK, Calif. & OXFORD, U.K.—Drug discovery is a key element of the production of new medicines, but it can be an incredibly lengthy and expensive process, taking an average of five years. A new collaboration will use two organizations’ proprietary technologies to accelerate the discovery of selective molecules while aiming at a high-value oncology target.

Exscientia, a clinical-stage artificial intelligence (AI) drug-discovery company in the U.K., and SRI International (SRI) entered into a drug-discovery collaboration agreement in May. Under the terms of the agreement, the companies will implement a new approach to drug discovery by integrating AI design with automated compound synthesis.

Specifically, the companies will combine SRI’s fully automated SynFini synthetic-chemistry system with Exscientia’s Centaur Chemist AI platform to automate the design, reaction screening and optimization (RSO), and production of those molecules.

According to Mark Swindells, chief commercial officer at Exscientia, the partnership between SRI and Exscientia evolved because, “Both Exscientia and SRI have developed significant, complementary new approaches for drug discovery. Upon meeting, we quickly agreed that the best way to test our systems and explore how they might work together would be to embark upon a real project with real-life goals.”

“Both the SynFini and Centaur Chemist platforms have demonstrated ability to overcome key drug discovery challenges,” said Dr. Nathan Collins, chief strategy officer of SRI’s Biosciences Division and head of the SynFini program. “We believe there is tremendous potential to further accelerate the oncology drug-discovery process by combining these novel and proven technologies.”

The end-to-end SynFini platform from SRI was developed to bring new drugs to the clinic more quickly and affordably by accelerating chemical discovery and development. The SynFini closed-loop system includes three components that work seamlessly together: a software platform (SynRoute), a reaction screening platform (SynJet) and a multi-step flow chemistry automation and development platform (AutoSyn).

Swindells noted that Exscientia is the first company to successfully apply AI technologies to design small-molecule compounds that have reached the clinic. The molecules generated by Exscientia’s Centaur Chemist platform are highly optimized to satisfy the multiple pharmacology criteria required to enter a compound into the clinic and to achieve these goals in a rapid time scale. By using Centaur Chemist, researchers can transform drug discovery into a formalized set of moves while also enabling the system to learn strategy from human experts.

“The opportunity to apply AI drug design through our Centaur Chemist system with SynFini automated chemistry offers an exciting opportunity to accelerate drug discovery timelines through scientific innovation and automation,” commented Andrew Hopkins, CEO of Exscientia.

SRI International is a non-profit research institute founded in 1946. SRI Biosciences, a division of SRI International, integrates basic biomedical research with drug and diagnostics discovery and preclinical and clinical development. It has produced several marketed drugs and advanced more than 100 drugs to clinical trials. Focused on novel platforms and programs in a variety of therapeutic areas targeting high unmet medical needs, SRI Biosciences collaborates with a broad range of partners from small and virtual biotechnology companies to top 10 pharmaceutical companies and other leading industry partners.

Exscientia’s Centaur Chemist transforms drug discovery into a formalized set of moves while also enabling the system to learn strategy from human experts. Combining the power of the original AI-design with the experience of seasoned drug hunters, the platform enables the discovery of optimized molecules with extremely high productivity. In tandem, Exscientia’s Centaur Biologist platform drives the flexible analysis and prioritization of discovery targets across all pharmaceutically relevant disease space.

“Progress will be assessed by our ability to achieve real-life drug discovery milestones, transitioning from hit to lead and candidate in a timely manner,” Swindells remarked, concluding that “We are optimistic about the commercial potential of bringing together the automation of both compound design and synthesis. Drug discovery is one of the few industries remaining where key workflows are still largely human tasks. We want to automate these tasks where possible, so that we can free up the creative time of human researchers to concentrate on delivering the best overall discovery strategy.”