AI steps up in fight against resistance

2 minute read


It’s not all doom and gloom on the advanced technology front.


Regular followers of this digital rectangle could be forgiven for thinking your Back Page scrawler is not the world’s biggest fan of artificial intelligence.

Fair enough too, because we have in the past readily availed ourselves of the opportunity to highlight some of the over-hyped technology’s more transparent shortcomings.

So today we are going to break the mould somewhat and focus on something that shows AI might also be a force for good – something positive for humanity, as opposed to an existential threat.

Because, dear reader, it is entirely possible for AI to be both those things simultaneously.

Take the issue of antimicrobial resistance, for instance. While not a peril akin to a nuclear holocaust perhaps, those pesky bacterial pathogens do hold the potential to wreak significant health havoc if things get too far out of hand.

Could AI play a role in helping us non-artificial folks combat this menace?

You betcha it can, if a recent study published by Wiley in the journal Advanced Science, is to be believed.

According to boffins from Imperial College in London, their study shows diverse AI models can be successful in identifying already approved drugs that can be repurposed against drug-resistant bacterial pathogens, such as Streptococcus pneumoniae.

Using a dataset of molecules shown to be active against S. pneumoniae and a larger dataset of molecules inactive against another drug-resistant bacteria, the scientists trained three different AI models to test nearly 7000 candidate drugs for inhibition of the bacteria.

Of those tested, 11 were selected for experimental validation and nine were found to be able to inhibit the growth of S. pneumoniae, with one of the two most potent repurposed drugs even effective even against the drug-resistant strains of the pathogen.

“AI-guided drug repurposing has become a powerful strategy for combating antimicrobial resistance, particularly for pathogens for which some active molecules are already known and can be leveraged as a training or fine-tuning dataset,” senior study author Dr Pedro Ballester told media.

So mark one up for the AI White Hats. If only everyone’s intentions were as noble …

The naturally intelligent thing to do is send your story tips to Holly@medicalrepublic.com.au.

End of content

No more pages to load

Log In Register ×