Researchers at MIT have harnessed generative artificial intelligence to design novel antibiotic molecules effective against drug-resistant Neisseria gonorrhoeae and multi-drug-resistant Staphylococcus aureus. Their approach involved generating over 36 million compounds and computationally screening them for antimicrobial activity. The leading candidates exhibited novel structures distinct from existing antibiotics and appear to disrupt bacterial membranes by new mechanisms. This study, published in Cell, illustrates AI’s capability to expand accessible chemical space for antibiotic discovery, a critical advance amid escalating antimicrobial resistance.