AI Drug Discovery

CENTAUR CHEMIST™

Exscientia’s unique Centaur Chemist™ approach transforms drug discovery into a formalized set of moves and a system to learn strategy from human experts.

We were the first to demonstrate that AI algorithms can outperform expert human drug designers in the search for optimised drug compounds.

Algorithms and machine learning methods are very powerful in finding solutions to defined tasks. However the rules of drug discovery are very complex - not all are known and some are not readily describable as a finite set of moves. Therefore it is very challenging to devise a pure machine process for drug discovery.

The origin of the term Centaur lies in the first man vs. machine events in chess invented by grandmaster Garry Kasparov after proposing the cooperation of human chess player and machine. The result was a combination of human and machine able to beat both human experts and machines alone. Ultimately, the deciding factor is the process used to combine human and machine.

However the rules of drug discovery are very complex - not all are known and some are not readily describable as a finite set of moves. Therefore it is very challenging to devise a pure machine process for drug discovery.

At Exscientia the Centaur Chemist™  platform controls the entire process, not single tasks. Through this, learnings about drug discovery moves & rules improve with each project and cycle. This encoded knowledge helps the system become more efficient, and through this approach the technology platform workflows define and execute these design tasks allowing the Centaur designers to define workflows and concentrate on strategy.

View the Nature 26 Sep, 2017 Report

View the Nature 12 Dec, 2012 Report