A drug developed using artificial intelligence will enter clinical trials for the first time, opening up the possibility of using machine learning to slash costs and time needed to create medicines.
The compound targeting obsessive-compulsive disorder was developed by U.K.-based Exscientia in partnership with Japanese drugmaker Sumitomo Dainippon Pharma. The research exploratory phase of development took less than 12 months, a fraction of the typical 4.5 years that conventional research techniques need, the companies said.
The potential of AI to revolutionize industries from healthcare to finance to manufacturing and education has led investors to pour record amounts of cash into startups leveraging the technology. Last year, 1,356 AI-related startups in the U.S. raised a record $18.5 billion, according to the National Venture Capital Association. Exscientia, founded in 2012, has raised $43.7 million from investors, according to Crunchbase.
Excscientia’s AI might cut the cost of bringing a drug to market by 30%, CEO Andrew Hopkins said. Such savings may revolutionize the industry, as the Food and Drug Administration has said the average cost to research and develop each successful drug is estimated to be $2.6 billion, when money spent on failures are taken into account.
The company’s AI used a suite of algorithms to decide the best chemical structure for the compound known as DSP-1181. The technology sorted through tens of millions of potential molecules and chose the ones most likely to be effective, saving vast amounts of time. Only 350 compounds needed to be made and tested, a fifth of the normal number of candidates, Hopkins told the Financial Times.
Paul Workman, CEO of the Institute of Cancer Research, said he believed DSP-1181 is the first drug candidate entering human trials that was created using AI in a major way. “Success stories like this will provide us with the hard evidence that AI really will deliver on its transformative potential,” he said in a Pharmaphorum article.