It could take years for the pharmaceutical industry to develop medicines that can treat or cure human ailments, but new research suggests the use of generative artificial intelligence could greatly accelerate the drug development process. is suggested.
Today, most drug discovery is done by human chemists who rely on their knowledge and experience to select the appropriate molecules necessary to become the safe and efficient medicines we depend on. Synthesize. To identify synthetic routes, scientists often use a technique called retrosynthesis. – A method of back-calculating from the required molecule to create a potential drug, I’m looking for a chemical reaction to produce it.
But sifting through millions of potential chemical reactions would be a very difficult and time-consuming task, so researchers at Ohio State University G.2retro To Automatically generate reactions for any molecule. New research shows that, compared to current manual planning methods, this framework covers a huge range of possible chemical reactions, allowing us to accurately and precisely determine which reactions are the best to generate a particular drug molecule. shown to be readily identifiable.
“Using AI for things that are important to save lives, such as healthcare, is what we really want to focus on,” he said. Xia Ning First author of the study and Associate Professor Computer Science and Engineering at Ohio State University. “Our aim was to use AI to accelerate the drug design process. We have found that it provides drug candidates with potentially unique properties.” 
The work builds on Ning’s previous work, in which her team developed a method called Modof that can generate molecular structures that exhibit desirable properties over any existing molecule. “The question becomes how to make such a product molecule, and that’s where this new work shines,” said Ning, who is also an associate professor of biomedical informatics at the medical school.
The study was published today in a journal communication chemistry.
Ning’s team trained G.2A retro dataset containing 40,000 chemical reactions collected between 1976 and 2016. This framework “learns” from a graph-based representation of a given molecule and uses deep neural networks to generate structures for potential reactants that can be used in their synthesis. Its generative power is so impressive that, according to Ning, Given a molecule G,2Retro can come up with hundreds of nPredict new reactions in just minutes.
“Our Generative AI Method G2Retro can have multiple supplies It’s a way to rank different synthetic routes and options, and even different options per molecule,” Ning said. “While this will not replace current lab-based experiments, it will provide more and better drug options, allowing us to prioritize experiments and focus more quickly. ”
To further test the effectiveness of AI, Ning’s team conducted a case study to G.2Retro was able to accurately predict four newly released drugs already in circulation. mitapivata drug used to treat hemolytic anemia. tapinaroffused in the treatment of various skin diseases. Mavakamten, a drug to treat systemic heart failure.and Oteseconazole, used to treat fungal infections in women. G.2Ning said Retro was able to produce exactly the same patented synthetic route for these drugs and also provided a viable and synthetically viable alternative synthetic route.
Putting such dynamic and effective devices at the scientists’ disposal could enable industry to produce more potent drugs at a faster pace.But despite the potential for edge AI for scientists in the lab, Ning emphasizes pharmaceuticals G.2retro Or you still need to validate what the generative AI created – the process by which the produced molecule is produced It was tested in animal models and then clinically tested in humans.
“We are very excited about generative AI for medicine and are committed to using AI responsibly to improve human health,” said Ning.
This research was supported by the Ohio Presidential Research Excellence Program and the National Science Foundation. Other co-authors from Ohio State University were Ziqi Chen, Oluwatosin Ayinde, James Fuchs, and Huan Sun.
