Connect with us

Artificial Intelligence

For the first time, a drug created by an artificial intelligence will be tested in humans

Amelia Fort

Published

on

In recent months, we have seen some interesting advances in the field of artificial intelligence and health, such as Google’s AI capable of detecting breast or lung cancer . However, the potential of this incipient technology goes much further, and a proof of this is DSP-1181 , a molecule developed entirely by an artificial intelligence whose resulting drug will be tested in humans.

To put us in context, the BBC states that the development process of a drug takes around five years, although the Higher Council for Scientific Research ( CSIC ) is less optimistic, lengthening the process to between ten and 12 years on average from that the therapeutic target is sought until it reaches the market. And why is this important? Because the artificial intelligence that concerns us today has needed less than 12 months .

A drug for obsessive-compulsive disorder

The DSP-1181 molecule has been developed by the British start-up Exscientia and the Japanese company Sumitomo Dainippon Pharma, being the first molecule developed by an AI that enters the human trials phase. As explained by the company , the molecule has been developed as a “potent long-acting agonist of the serotonin 5-HT1A receptors “, which is linked to the treatment of OCD.

From the company they explain that obsessive-compulsive disorder affects one million Japanese and three million Americans and that, although “the mechanism of OCD has not yet been clarified,” “dysfunction in the orbitofrontal cortex, the anterior cingulate cortex and the striatum have been more strongly involved. “

To develop it, the company used artificial intelligence to choose the most appropriate chemical structure . They explain in the Financial Times that these algorithms were able to “generate tens of millions of potential molecules, filter among all the candidates and make the decision of which molecule to synthesize and test”. Something similar, saving the distances, was done to develop the structure of the Biobot .The drug will enter phase 1 of the clinical trial in Japan and, if successful, further testing will be done globally

According to Andre Hopkings, CEO of Exscientia, “AI can learn faster than conventional approaches, so we had to make and test only 350 compounds , a fifth of the normal number of compound candidates, which is record productivity. “. It also highlights that “the algorithms […] can be applied to any pharmacological target, against a wide range of diseases in oncology, cardiovascular and rare diseases.”

The drug will enter phase 1 of the clinical trial in Japan and, if successful, will undergo further testing around the world. In this first phase is when people are involved for the first time and the objective is to verify their safety, side effects and optimal doses. The number of people who participate in this phase varies, but usually ranges between 20 and 100 volunteers , both healthy and affected by the disease or disorder to be treated.