Deep Learning Algorithms Discover Potent New Antibiotics

New machine learning techniques applied to drug discovery has led to the identification of a number of powerful new antibiotics.

One of these is Halicin, a completely novel antibiotic which researchers at MIT have shown to work against a number of previously untreatable strains of bacteria, in mice.

The researchers from MIT then screened over 107 million molecular structures in a database called ZINC15. From a shortlist of 23, physical tests identified 8 with antibacterial activity. Of these, two had potent activity against a broad range of pathogens, and could overcome even antibiotic-resistant strains of E. coli.

This study is “a great example of the growing body of work using computational methods to discover and predict properties of potential drugs”

Bob Murphy, Computational Biologist. Source: Nature