Development of a New Drug for Artificial Intelligence to Begin Clinical Trials

2020-02-03

Exscientia, an AI startup, has developed a new drug that will soon undergo clinical trials in Japan. This is one of the few examples where AI has been applied to clinical development, bringing us closer to widespread use of AI in drug development and deployment. Unlike traditional drug development, this AI-developed drug, developed in collaboration with Sumitomo Dainippon Pharma, will begin clinical trials in less than a year after project initiation, whereas typical drug development takes around 4.5 years. Exscientia utilized an AI platform to develop this drug, which generated millions of potential molecular combinations using various algorithms. The AI then filtered and narrowed down the generated molecules to the best candidates that should be synthesized and tested. The clinical trials come at a time when investments in AI-driven drug development are increasing. AI has the potential to expedite and reduce the cost of drug discovery, with the average cost of drug development being approximately $2.6 billion. This means that new approaches to treating diseases such as heart disease and cancer can be generated more quickly. This drug is known as DSP-1181. Andrew Hopkins, CEO and molecular biologist at Exscientia, explained to the Financial Times that researchers only need to test around 350 compounds, which is one-fifth of the usual number of compounds tested in the drug development process. While not directly involved in this research, Professor John Bell, a medical professor at the University of Oxford, explained the impact of this recent advancement to the Financial Times: "The process of drug design and development has always been slow and difficult. Exscientia can achieve this with fewer steps, which is truly impressive. It comes from very reliable scientific principles, so it is convincing." Exscientia scientists will collaborate with other pharmaceutical companies such as Sanofi and Bayer in an attempt to find new methods for treating diseases. While some claim that DSP-1181 is the first AI-designed drug to undergo clinical trials, ScienceMag reports that many other new drugs have already been tested on humans, including some for Parkinson's disease and stroke. Despite Exscientia's impressive achievements, there are still some challenges on the path to promoting AI drug development. While AI can assist in discovering and developing drugs, it cannot guarantee that the drugs discovered by AI will be particularly useful. It is possible that the discovered drugs are extremely similar to molecules that have already been studied by humans. Additionally, the effective utilization of drugs depends on scientists' understanding of the nature of the diseases they are trying to treat, so AI drug development strategies may not completely revolutionize the field of medicine as some hope.

RECENT AI NEWS

RECENT AI TOOLS