A partnership between a large British drugmaker and a startup that discovers drugs using artificial intelligence has borne fruit.

Oxford, UK-based Exscientia said Wednesday that it had delivered the first drug candidate to be found using its AI collaboration with GlaxoSmithKline, a potential therapy for chronic obstructive pulmonary disorder, or COPD.

The company said it was developed through application of its Centaur Chemist AI-driven automated drug discovery platform. The system was able to find the molecule with fewer compounds synthesized in comparison with drugs discovered through conventional means. The partnership between GSK and Exscientia dates back to July 2017.

“Our AI platform and approach have advanced significantly over the past few years and have been constantly refined and optimized through real-world projects for our pharma partners,” said Andy Bell, Exscientia’s chief research officer, in a statement. “With the productivity improvements we are now seeing, we believe that our Centaur Chemist approach is proving itself to be the industry’s leading AI drug-discovery platform by achieving far superior results to what conventional discovery techniques have historically delivered.”

The exploration of AI and machine learning in drug discovery and development has drawn considerable interest from drugmakers in recent years, though it remains in its infancy, and it could be some time before integration of the two fields becomes fully mainstreamed.

Still, a number of companies large and small have been exploring the idea of AI/ML in developing new drugs, in particular because of its potential to speed along the process of drug development and even find new druggable targets that conventional methods would miss. For example, AI/ML combined with cryo-electron microscopy can allow researchers to correctly infer three-dimensional structures of molecules and then map them at the atomic level in ways not possible using traditional X-ray crystallography.

In January, the large contract research organization Charles River Labs and Atomwise announced a partnership to provide AI services in drug discovery. A partnership announced last June between Swiss drugmaker Novartis and chipmaker Intel is using AI to cut the amount of time required to analyze microscopic images from 11 hours to 31 minutes. Also in July, Salt Lake City-based Recursion Pharmaceuticals got the go-ahead from the Food and Drug Administration to start a Phase I study of REC-994, a drug candidate discovered through machine learning that it is developing for the genetic disease cerebral cavernous malformation. However, there has not been a public update on that program since.

Photo: MF3d, Getty Images