Machine Learning Insights into Antibiotic Lethality

The discovery of penicillin transformed modern-day medicine. But as its use has spread, beginning in the 1940s, so too have penicillin-resistant organisms. Today, the Centers for Disease Control and Prevention calls the accelerating mutation of drug-resistant bacteria “one of the biggest public health challenges of our time.” In order to combat it, researchers are looking for answers. Among them are Allison Lopatkin and Jason Yang, postdoctoral research scientists in the Institute for Medical Engineering and Science at MIT.

“The rise of antibiotic-resistant pathogens is a growing global threat,” says Lopatkin, “and the rate at which we can bring antibiotics to market is significantly slower than the rate at which bacteria can acquire resistance to these drugs. It’s been predicted that if we don’t do something drastic about it, mortality from infectious diseases will skyrocket, potentially reaching 10 million people by the year 2050, becoming the leading global cause of death.” She adds: “We need to take a few steps back and learn more about how antibiotics function, to design things in the future to work better.”

In this MIT Alumni Association Faculty Forum Online, Lopatkin and Yang discuss a “white-box” machine-learning approach they developed to discover a mechanism that helps certain antibiotics kill bacteria.

The webinar was moderated by Aviva Hope Rutkin SM ’13, data and math editor at the Conversation US.

Watch the video above, then catch up on previous talks from the Faculty Forum Online.