DrugSynthMC aims to make the search for new drugs more efficient

Scientists have developed a free AI algorithm that they believe will make the search for new drugs much more efficient.

DrugSynthMC can generate thousands of brand new, virtual drug molecules for screening and testing in seconds. It can adapt to any input “target molecule” and create a library of drug candidates that can be tested against that target before tweaking the effective molecules to make them even better. It is available as open source and can generate 10,000 molecules that match a given target in 0.75 seconds.

The team is convinced that the software can be used immediately by scientists in pharmaceutical companies or in university research.

Dr Olivier Pardo of the Department of Surgery and Cancer, who led the work, said: “We are very excited. Even though it is a fairly simple algorithm, it is far more efficient than anything more complex that has been tested or published to date and will be very useful in AI-driven drug discovery for tailored therapeutic targets.”

The results are published in Journal of Chemical Information and Modelling.