top of page

Are Drug-Resistant Infections Becoming a Thing of the Past?

microscopic view of purple round organisms

Photo courtesy of MIT Biology

Antibiotic resistance is killing more than 1.2 million people per year. Very few new classes of antibiotics have been discovered in the last 60 years.

According to the Centers for Disease Control and Prevention (CDC), antimicrobial resistance happens when germs like bacteria and fungi develop the ability to defeat the drugs designed to kill them. That means the germs are not killed and continue to grow.

Resistant infections can be difficult, and sometimes impossible, to treat. Only a few recently identified antibiotic classes effectively combat Methicillin-resistant Staphylococcus aureus (MRSA) and vancomycin-resistant Enterococci (VRE). Unfortunately, resistance to these compounds has been on the rise.

Leveraging trained artificial intelligence (AI) models, Felix Wong and his colleagues at the Broad Institute of MIT and Harvard in Massachusetts analyzed more than 12 million compounds via computer simulations. This led them to identify 3,646 compounds with desirable drug-like properties. Additionally, employing AI deep learning, they pinpointed compounds with high predicted antibiotic activity and low anticipated cytotoxicity.

By comparing substructures within various compounds, the researchers pinpointed new classes of potential antibiotics. Eventually, they discovered two non-toxic compounds that effectively eliminate MRSA and vancomycin-resistant Enterococci.

James Collins, the Termeer Professor of Medical Engineering and Science at MIT’s Institute for Medical Engineering and Science (IMES), along with his team, has initiated deep learning to explore the discovery of new antibiotics. Their efforts have resulted in potential drugs effective against Acinetobacter baumannii, a bacterium commonly present in hospitals, and other drug-resistant bacteria.

Dr. Wong and Collins are using similar methods with chemical structures to create compounds and find new antibiotics for different types of germs.



Trafton, Ann, Using AI, MIT researchers identify a new class of antibiotic candidates, MIT News, December 20, 2023.


7 views0 comments


bottom of page