Artificial intelligence has helped researchers to design antibiotics that can tackle hard-to-treat infections gonorrhoea and MRSA.
A team at Massachusetts Institute of Technology used AI algorithms to design more than 36 million possible compounds and screen them for antimicrobial properties.
The top candidates appeared to be different from any existing antibiotics, and researchers say they work through mechanisms that disrupt bacterial cell membranes.
The use of AI allowed scientists to generate and test compounds that had never been seen before.
Senior author of the study Professor James Collins said the team is “excited” about the new possibilities opened up by this project.
“Our work shows the power of AI from a drug design standpoint, and enables us to exploit much larger chemical spaces that were previously inaccessible,” he said.
The team used generative AI algorithms to design molecules based on a specific chemical fragment that showed antimicrobial activity, but they then also let the algorithms freely generate molecules that didn’t require that specific fragment.
Bacterial resistance to many antibiotics is also increasing – nearly five million deaths each year are caused by drug-resistant bacterial infections.
“We wanted to get rid of anything that would look like an existing antibiotic, to help address the antimicrobial resistance crisis in a fundamentally different way,” lead author Aarti Krishnan said.
“By venturing into underexplored areas of chemical space, our goal was to uncover novel mechanisms of action.”
It is rare that new antibiotics are discovered and later approved by health authorities.
Follow STV News on WhatsApp
Scan the QR code on your mobile device for all the latest news from around the country
