AI-Designed Antibiotics Show Efficacy Against Drug-Resistant Gonorrhea and MRSA in MIT Study

Cambridge, MA – Researchers at the Massachusetts Institute of Technology (MIT) have successfully designed novel antibiotics using artificial intelligence (AI) that show promise against two difficult-to-treat infections: drug-resistant Neisseria gonorrhoeae and multi-drug-resistant Staphylococcus aureus (MRSA). This breakthrough marks a significant step in addressing the growing global threat of antimicrobial resistance (AMR), as highlighted by a recent social media announcement.

"With help from artificial intelligence, MIT researchers have designed novel antibiotics that can combat two hard-to-treat infections: drug-resistant Neisseria gonorrhoeae and multi-drug-resistant Staphylococcus aureus (MRSA)," stated a tweet from James Pethokoukis.

The MIT team, including senior author Professor James Collins and lead authors Aarti Krishnan, Melis Anahtar, and Jacqueline Valeri, utilized generative AI algorithms to create more than 36 million potential compounds. Unlike traditional drug discovery that screens existing libraries, this approach allowed them to design entirely new molecules. The top candidates identified are structurally distinct from current antibiotics and appear to function by novel mechanisms, primarily disrupting bacterial cell membranes.

Two experimental compounds, named NG1 for drug-resistant gonorrhoea and DN1 for MRSA, have shown strong efficacy in laboratory dishes and mouse models. NG1 effectively killed Neisseria gonorrhoeae and interacts with a previously untapped protein target, LptA, involved in bacterial outer membrane synthesis. DN1 successfully cleared MRSA skin infections in mouse models, also interfering with bacterial cell membranes.

This research, published in the journal Cell, is part of MIT’s Antibiotics-AI Project and aims to usher in a "second golden age" of antibiotic discovery. Drug-resistant bacterial infections contributed to an estimated 4.71 million deaths globally in 2021, underscoring the urgent need for new treatments. While these compounds are still years away from patient use, they represent a potent proof-of-concept for AI's role in creating new weapons against lethal pathogens.

The scientists are now collaborating with Phare Bio, a non-profit biotech company, to further refine NG1 and DN1 for additional testing. If successful, these drug candidates could eventually advance to clinical trials, offering new hope in the ongoing battle against superbugs.