Graphical Abstract. Credit: Journal of Chemical Information and Modeling (2024). DOI: 10.1021/acs.jcim.4c01451
Scientists have devised a free AI algorithm that they believe will make drug discovery much more efficient.
DrugSynthMC can generate thousands of brand new virtual drug molecules for screening and testing in seconds. It adapts to an input “target” molecule, creates a library of drug candidates to test against this target, and then further optimizes the best ones to make the drug even better. Available in open source, it can generate 10,000 molecules that match a specific target in 0.75 seconds.
The research team believes that the software could be readily used by pharmaceutical companies and university research scientists.
Dr Olivier Pardo from the Department of Surgery and Oncology, who led the study, said: “We are very excited. This is a fairly simple algorithm, but it is much more efficient than the more complex ones tested or published so far, and will be extremely useful for AI-driven drug discovery for bespoke therapeutic targets.”
The results of this research have been published in the Journal of Chemical Information and Modeling.
Further information: Milo Roucairol et al., “DrugSynthMC: Atom-Based Generation of Drug-Like Molecules via Monte Carlo Exploration.” Journal of Chemical Information and Modeling (2024). DOI: 10.1021/acs.jcim.4c01451
Courtesy of Imperial College London
Source: AI for Drug Discovery: DrugSynthMC Makes Drug Discovery More Efficient (September 20, 2024) Retrieved September 22, 2024 from https://phys.org/news/2024-09-ai-drug-discovery-drugsynthmc-medication.html
This document is subject to copyright. It may not be reproduced without written permission, except for fair dealing for the purposes of personal study or research. The content is provided for informational purposes only.
