By the mid-1940s the use of antibiotics became widely accessible to the general public, which undoubtedly saved thousands of lives. There is, however, a downside to the overuse of antibiotics in recent decades, with harmful bacterias evolving to the point where current antibiotics will soon become redundant.
To prevent this from happening, researchers from MIT turned to artificial intelligence to identify a new compound capable of killing off a variety of antibiotic-resistant superbugs, including a particular bacteria that has been resistant to all known antibiotics.
They managed to achieve this by training a computer algorithm to identify certain compounds that contained bacteria-killing properties from a sample size of over 100,000,000 chemical compounds over a number of days, along with looking for new ones. This resulted in the algorithm picking out a molecule that didn’t resemble any existing antibiotics.
Researchers then tested their new bacteria-killing molecule on what they described as “the world’s most problematic disease-causing bacteria, including some strains that are resistant to all known antibiotics”, and to the surprise of everyone working on the research, it killed all but one of the drug-resistant bacterias.
#Halicin, a first in AI and Biology history !
Using a #AI/ML, @MIT researchers have discovered a powerful new drug that can kill many species of highly antibiotic-resistant bacteria.
James J. Collins, PhD. Professor of Medical Engineering & Science at MIT https://t.co/XhMr0e0Xnm
— Frederic Rombaut (@FredericRombaut) February 24, 2020
According to James Collins of MIT’s Institute for Medical Engineering and Science, “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.”
Researchers have dubbed their algorithm Halicin, after the supercomputer found in ‘2001: A Space Odyssey.’