Spotlight: AI in drug discovery first

Earlier this year, Exscientia announced what was said to be the first AI-designed immuno-oncology drug to enter clinical trials. Lu Rahman talks to CEO Andrew Hopkins about the company’s work and use of AI in drug discovery.

LR:  How AI has been used in this process and what benefits has it created?

AH: AI was used to generate all the compound structures made and tested to discover EXS21546. AI was combined with advanced GPCR biophysical assays to drive the optimisation process for this programme.  The process used to bring this drug candidate to trial centred on the thoughtful application of AI and machine learning techniques. It is Exscientia’s ambition to find quicker, smarter, more precise ways of discovering and developing new drugs so that we can meet the medical needs of more people living longer lives. By empowering our researchers to interact strategically with AI design systems, we are able to design well-balanced molecules that deliver across competing properties meaning that they are less likely to fail during the drug development phases.

The drug candidate has potential for best-in-class characteristics, with high selectivity for the target receptor, bringing together potential benefits of reduced systemic sides effects as well as minimal brain exposure to avoid undesired psychological side effects.

LR: What were the challenges in the process?

AH: Designing any new molecule in drug discovery is a challenge. For this particular project there were existing patents as A2a had previously been the subject of research for Parkinson’s disease. At the same time we wanted a molecule that did not cross into the brain and also with high specificity for A2a over A2b and other family members. Hence the challenges were designing novelty, in a well-known space, high selectivity and reducing CNS side effects.

LR: Why the focus on immuno-oncology?

AH: Exscientia’s core internal therapeutic interests are focused transformative medicines in the areas of oncology, immunology and the interface between the two. Oncology represents a major area of unmet medical need and as such is a significant focus area for Exscientia. Immuno-oncology medicines are bringing benefit to a range of cancer patients. Our selective A2a receptor antagonist addresses a next-generation immuno-oncology strategy to empower the human immune system by reversing the effects of high adenosine concentrations.

LR: What did the collaboration with Evotec bring to the process and why was it so important?

AH: We combined Exscientia’s AI and biophysics capabilities with Evotec’s experimental platform. On this particular project the combination of our platforms allowed us to discover the drug candidate within only eight months from starting the project, synthesising and testing less than 200 compounds. The ongoing success of this partnership has been the basis for an expanded and deepened research collaboration. This clinical trial represents a major milestone emanating from our discovery collaboration with Evotec.

LR: The candidate was found in eight months – how was this process different to a more conventional one?

AH: It is not unusual for discovery times to take three to five years using conventional approaches. We’re using AI and machine learning techniques combined with advanced experimental techniques to confront and overcome that. AI has the potential to advance and improve the drug discovery and development process by enabling better decision-making and doing the right experiments at the right time which results in better molecules, delivered faster. We want to accelerate human achievement. We can do this by using AI to improve and expand cognitive bandwidth. It’s our aim to bring as many new precisely engineered medicines to the clinic as we possibly can.

LR: Where do you see opportunities for AI in drug discovery?

AH: We want to apply the power of our AI machine learning capabilities across the entire process of drug discovery and development from hypothesis generation to drug design to patient selection to therapeutic areas with the greatest unmet needs. We are focused on oncology and immunology but through our partnerships we have projects across a range of therapy areas including autoimmunity, Covid-19, psychiatric and rare diseases. We recently announced that our drug candidate for the treatment of Alzheimer’s disease psychosis has entered Phase I clinical trials in the US. This is now the third drug design by our platform to enter into clinical testing.

Volume 22, Issue 3 – Summer 2021

About the author

Andrew Hopkins is the founder and CEO of the global pharma-tech company, Exscientia, with offices in Oxford, Miami Osaka and Dundee. At Exscientia, Dr Hopkins has overseen the discovery of the world’s first precision engineered drugs generated by AI to enter Phase I human clinical trials.

Related Articles

Join FREE today and become a member
of Drug Discovery World

Membership includes:

  • Full access to the website including free and gated premium content in news, articles, business, regulatory, cancer research, intelligence and more.
  • Unlimited App access: current and archived digital issues of DDW magazine with search functionality, special in App only content and links to the latest industry news and information.
  • Weekly e-newsletter, a round-up of the most interesting and pertinent industry news and developments.
  • Whitepapers, eBooks and information from trusted third parties.
Join For Free