Team Sociating
by on February 24, 2020

Scientists from MIT have succeeded in finding a new type of antibiotic with artificial intelligence. Through machine learning a molecule was identified which seemed to have some significant antibiotic properties. In the researchers' first tests the molecule may be effective against certain resistant bacteria.

To make this discovery, the software first had to learn how certain drugs are effective against existing diseases. With the use of artificial intelligence 2,500 molecules were analyzed and 1,700 types of working drugs. “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,” says James Collins, the Termeer Professor of Medical Engineering and Science in MIT’s Institute for Medical Engineering and Science (IMES) and Department of Biological Engineering. “Our approach revealed this amazing molecule which is arguably one of the more powerful antibiotics that has been discovered."

The software had to scan a large library of molecules in order to be able to learn finding new potential drugs. Artificial intelligence then discovered a molecule that could become a potential antibiotic. “The machine learning model can explore, in silico, large chemical spaces that can be prohibitively expensive for traditional experimental approaches,” says Regina Barzilay, the Delta Electronics Professor of Electrical Engineering and Computer Science in MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL). This groundbreaking machine-learning approach has established powerful new antibiotic forms from a pool of over 100 million molecules — including one that works against a wide range of bacteria like tuberculosis and strains that are considered untreatable.

The molecule is called Halicin by the scientists and has been tested in the lab for a dozen bacteria. The bacteria hardly became resistant to Halicin, which is good news for combatting certain resistant bacteria. Halicin has also been tested on mice with the highly resistant hospital bacterium Acinetobacter baumannii. The molecule turned out to be very effective. Halicin has not yet been tested as a medicine on humans. So it remains to be seen whether it can actually be used as a medicine.

Bacterial resistance to antibiotics is increasing rapidly around the world and researchers estimate that resistant infections could kill ten million people per year by 2050 unless new drugs are developed urgently. Many potentially dangerous bacteria have developed drug resistance due to overuse of antibiotics, making them extremely difficult to handle. Currently in the US, the Centers for Disease Control and Prevention estimates that at least 2.8 million people receive an antibiotic-resistant infection every year and more than 35,000 people die from one.

Ernst Snijder
Source: MITCell

Join our Artificial Intelligence community
Read the reseach paper A Deep Learning Approach to Antibiotic Discovery

Like (1)