New antibiotics AI breakthrough

A team of researchers at the laboratory of James Collins of the Broad Institute of the Massachusetts Institute of Technology and Harvard University has made a significant breakthrough in the field of antibiotic discovery using artificial intelligence (AI). They used a type of AI known as deep learning to screen millions of compounds for antibiotic activity[1][2].

The researchers tested 283 promising compounds in mice and found several that were effective against methicillin-resistant Staphylococcus aureus (MRSA) and vancomycin-resistant enterococci, which are among the most stubbornly hard-to-kill pathogens[1]. The AI model used in this research is “explainable,” meaning it’s possible to understand the biochemistry behind its reasoning[1][10].

This development is significant because antibiotic resistance is among the biggest global threats to human health, responsible for an estimated 1.27 million deaths in 2019 and contributing to nearly five million more[1][3]. The problem has worsened during the COVID-19 pandemic, and no new classes of antibiotics have been developed for decades[1][3].

The compounds discovered by the researchers also show very low toxicity against human cells, making them particularly good drug candidates[2]. The researchers have shared their findings with Phare Bio, a nonprofit started by Collins and others as part of…