A team of MIT scientists used AI to discover a new class of antibiotics that can kill methicillin-resistant Staphylococcus aureus (MRSA), a bacterium that causes deadly infections.

The discovery, published in Nature, is a significant advance in the fight against antibiotic resistance. MRSA infects more than 800,000 people in the United States alone each year, and can cause skin infections, pneumonia and sepsis.

The research team trained a deep learning model with a database of 39,000 compounds. The model was able to predict the antibacterial activity and toxicity of the compounds, which allowed the researchers to identify promising candidates.

Laboratory tests showed that the discovered compounds killed the MRSA bacteria by disrupting their ability to maintain an electrochemical gradient across their cell membranes. These results were corroborated in mouse models.

Researchers have yet to conduct further studies to evaluate the safety and efficacy of the new antibiotics in humans. However, the discovery represents a promising advance in the fight against antibiotic resistance.