AI Helped Discover New Antibiotic Compounds

By using machine learning algorithms, researchers at the Massachusetts Institute of Technology (MIT) have discovered new antibiotic compounds that can kill one of the most dangerous bacteria in the world.

According to laboratory tests, the new drug was able to kill the bacteria that cause tuberculosis as well as strains of enterobacteria that are resistant to antibiotics, and also cleared infections in mice.

A team of scientists led by Regina Barzilay, a senior project researcher, and James Collins, a bioengineer at MIT, used artificial intelligence to test millions of molecules for antibacterial activity. They discovered nine new antibiotics with the help of a trained “deep learning” algorithm that was aimed at identifying molecules that kill antibiotic-resistant bacteria.

“In terms of antibiotic discovery, this is absolutely a first,” said Regina Barzilay.

James Collins added, “I think this is one of the more powerful antibiotics that has been discovered to date. It has remarkable activity against a broad range of antibiotic-resistant pathogens.”

Neural networks scanned a database of over 6,000 chemical compounds and identified a new one called halicin in a matter of hours. It was named after Hal, the AI from the 2001: A Space Odyssey movie.

The computer model was designed to screen millions of chemical compounds and reveal potential antibiotics that work differently than existing ones.

“We wanted to develop a platform that would allow us to harness the power of artificial intelligence to usher in a new age of antibiotic drug discovery. Our approach revealed this amazing molecule which is arguably one of the more powerful antibiotics that has been discovered,” stated James Collins, who is also a co-senior author of the paper published by the researchers.

The importance of this discovery lies in the fact that very few new antibiotics have been developed in recent decades.