Scientists from the Zelinsky Institute of Organic Chemistry of the Russian Academy of Sciences have developed a digital assistant based on artificial intelligence that can reduce the time it takes to search for new reactions by 180 times—from 3.5 years to one week. With the help of AI, it has already been possible to discover previously unknown reactions that are promising for the creation of cancer drugs, the Russian Science Foundation (RSF) press service reported.
The digital assistant takes on the difficult and voluminous work of primary analysis, and the person makes creative decisions on an already worked-out data space. Our research demonstrates that even without expensive robotic laboratories, it is possible to significantly accelerate the discovery of new reactions, relying on available computing tools and expert experience.
As an example, the authors of the system created a computer algorithm trained in the rules by which the cycloaddition reaction proceeds. The AI assistant searches for and studies reactions in which molecules are "stitched" into rings. Such ring structures are often used in the creation of antibiotics and other drugs.
Earlier it was reported that the legislative framework for the introduction of artificial intelligence in medicine is being developed at VolSU. Lawyers want to close existing gaps regarding AI in legislation: for example, it is necessary to determine who is responsible if AI makes a mistake in diagnosis or treatment, as well as to establish rules of interaction in the "doctor - algorithm - patient" chain.