Created by British start-up Exscientia and Japanese pharmaceutical firm Sumitomo Dainippon Pharma a drug molecule “artificial” by artificial intelligence (AI) will be utilized in human trails in a world-first for machine learning in the field of medicine.
Especially to be put to the use of treating patients who have obsessive-compulsive disorder (OCD), Exscienta CEO Prof Andrew Hopkins even describes it as a “key milestone in drug discovery”.
The molecule- known as DSP-1181 – was made by utilizing algorithms that filtered through potential compounds, checking them against an enormous database of parameters. Normally, drug development takes around five years to finally ‘get to trail’, but surprisingly enough the AI drug took only a year.
Hopkins told the BBC: “We have seen AI for diagnosing patients and for analyzing patient data and scans, but this is the direct use of AI in the creation of new medicine. There are billions of decisions needed to find the right molecules and it is a huge decision to precise engineer a drug, but the beauty of the algorithm is that they are agnostic, so can be applied to any disease,”
The first drug will enter stage one trails in Japan which, if effective, will be then followed by more tests globally.
The firm is now dealing with potential medications for the treatment of cancer and cardiovascular disease and would like to have another molecule prepared for clinical trials before the year’s end.
“This year was the first to have an AI-designed drug but by the end of the decade all new drugs could potentially be created by AI,” said Prof Hopkins.
Paul Workman, chief executive of The Institute of Cancer Research, who was not involved in the research, said of the breakthrough: “I think AI has huge potential to enhance and accelerate drug discovery.
And later adds, “I’m excited to see what I believe is the first example of a new drug now entering human clinical trials that were created by scientists using AI in a major way to guide and speed up discovery.”