AI for drug discovery: DrugSynthMC to make finding new medication more efficient

Editors' notes

This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

fact-checked

peer-reviewed publication

trusted source

proofread

Scientists have devised a free AI algorithm that they believe will make finding new medicines far more efficient.

DrugSynthMC can generate thousands of brand new, virtual drug molecules in seconds for screening and testing. It can adapt to whatever "target" molecule is inputted, creating a library of drug candidates to test against this target, before optimizing the ones that work to make them still better. Available via Open Source, it can generate 10,000 molecules to fit a particular target in 0.75 seconds.

The team believes the software is immediately usable by scientists working in pharmaceutical companies or in university research.

Dr. Olivier Pardo in the Department of Surgery & Cancer, who led the work, said, "We're very excited. Even though this is a fairly simple algorithm, it's far more efficient than anything more complex that has been tested or published out there, and will become very useful in AI-driven drug discovery for bespoke therapeutic targets."

The findings are published in the Journal of Chemical Information and Modeling.

More information: Milo Roucairol et al, DrugSynthMC: An Atom-Based Generation of Drug-like Molecules with Monte Carlo Search, Journal of Chemical Information and Modeling (2024). DOI: 10.1021/acs.jcim.4c01451

Journal information: Journal of Chemical Information and Modeling

Provided by Imperial College London