The Financial Times has this week reported the scheduled start of human clinical trials for the first ever ‘drug molecule’ invented in its entirety by AI. For a couple of years now, the lightning fast developments in the progression of AI, and its practical application, has promised a potential revolution in medicine discovery. The new compound, developed by Oxford-based pharmaceuticals and AI start-up Exscientia, in partnership and collaboration with Japanese pharma giant Sumitomo Dainippon Pharma, is now on the cusp of representing the first fruit to be borne from those leaps forward.
One of the most promising qualities of Exscientia’s breakthrough is the speed with which it has brough the drug to the stage where human clinical trials can begin – just 12 months. The usual timeframe would be expected to be somewhere between 2.5 and 5 years. And not only does machine learning AI promise to accelerate the discovery and time to market period for new drugs, the new technology is also expected to slash costs, which average around $2.6 billion using traditional methods.
The influence of machine learning algorithms in medicine has so far been to increase the number and types of patients who can be categorised as likely to benefit from existing medicines. The algos, fed on large quantities of data, have helped pinpoint combinations of factors that indicate a patient, or category of patients, may well benefit from a treatment that might otherwise not have been prescribed.
However, it is only now that AI has reached the stage of being effectively applied to the actual development of medicines. John Bell, Regius professor of medicine at Oxford University commented for the Financial Times:
“The design and development of molecules through medicinal chemistry has always been a slow and laborious process. Exscientia can do this in many fewer steps, which is really impressive, and it comes from very sound scientific principles. I think they are a real asset to have in the UK.”
Exscientia’s used a suite of algorithms to arrive at the optimal chemical structure for the compound. For now, known as DSP-1181, the compound has been designed to treat OCD by targeting a specific brain receptor. The algorithms first ‘brainstormed’ tens of millions of potential molecules before creating a shortlist of those that looked to hold the most potential for synthesis and testing.
Exscientia’s AI platform used a suite of algorithms to decide on the best chemical structure for the new compound, which is known as DSP-1181 and is targeted at a specific receptor in the brain involved in OCD. Together the algorithms were able to generate tens of millions of potential molecules, sift through the candidates and make a decision about which ones to synthesise and test.
Andrew Hopkins, the molecular biologist who is Exscientia’s CEO explains:
“The AI can learn faster than conventional approaches, so we had to make and test only 350 compounds, a fifth of the normal number of compound candidates, which is record-breaking productivity. The algorithms . . . can be applied to any drug targets, against a huge range of diseases in oncology, cardiovascular and rare diseases.”
As well as the Japanese partner with which it has developed DSP-1181, the start-up, which currently employs a team of approximately 60, is working on other projects with partners including Bayer and Sanofi. Research is underway on the design of new drugs to treat a range of conditions including metabolic disease.
Bristol-Myers Squibb is a major investor in Exscientia, having injected $43 million in funding.
This article is for information purposes only.
Please remember that financial investments may rise or fall and past performance does not guarantee future performance in respect of income or capital growth; you may not get back the amount you invested.
There is no obligation to purchase anything but, if you decide to do so, you are strongly advised to consult a professional adviser before making any investment decisions.