Scientists are using AI to target ‘sleeper’ bacteria.

WhatsApp Group Join Now
Telegram Group Join Now
Instagram Group Join Now

This article has been reviewed in accordance with Science X’s editorial practices and policies. The editors have highlighted the following attributes to ensure the credibility of the content:

Reality check

Peer-reviewed publication

Trusted source

Proof read


A time-lapse microscopy video of E. coli cells treated with semapimod in the presence of SYTOX Blue. Credit: Massachusetts Institute of Technology

× Close


A time-lapse microscopy video of E. coli cells treated with semapimod in the presence of SYTOX Blue. Credit: Massachusetts Institute of Technology

Since the 1970s, modern antibiotic discovery has experienced a slowdown. Now the World Health Organization has named the antimicrobial resistance crisis as one of the 10 global public health threats.

When an infection is treated repeatedly, clinicians run the risk of bacteria becoming resistant to antibiotics. But why would the infection return after appropriate antibiotic treatment? A well-documented possibility is that the bacteria are becoming metabolically inactive, escaping detection by conventional antibiotics that respond only to metabolic activity. When the threat is over, the bacteria re-emerge and the infection reappears.

“Resistance builds over time, and recurrent infections are caused by this sleeplessness,” says Jackie Valery, a former MIT-Takeda Fellow at the MIT Abdul Latif Jameel Clinic for Machine Learning in Health. Center) who recently completed his Ph.D. . in biological engineering from the Collins Lab. Valerie is the first author of a recent paper published in Cell Chemical Biology which demonstrates how machine learning can help screen compounds that are lethal to inactive bacteria.

Stories of bacteria’s “sleeper-like” resilience are hardly news to the scientific community—ancient bacterial strains dating back 100 million years have been discovered alive in an energy-sapping state on the Pacific ocean floor in recent years.

James J. Collins, chair of the Life Sciences Faculty at the MIT Jamel Clinic, a term professor of medical engineering and science in MIT’s Institute for Medical Engineering and Science and Department of Biological Engineering, recently described a new class of antibiotics. Make headlines for using AI to discover, part of the group’s larger mission to use AI to dramatically improve existing antibiotics.

According to a paper published by The LancetIn 2019, 1.27 million deaths could have been prevented if the infections were susceptible to the drug, and one of the many challenges facing researchers is finding antibiotics that are able to target metabolically inactive bacteria.


A time-lapse microscopy video of E. coli cells treated with semapimod in the presence of SYTOX Blue. Credit: Massachusetts Institute of Technology

In this case, researchers in the Collins lab employed AI to speed up the process of finding antibiotic properties in known drug compounds. With millions of molecules, the process can take years, but the researchers were able to identify a compound called cemapimod in a weekend, thanks to AI’s ability to perform high-throughput screening.

Semapimod is an anti-inflammatory drug commonly used for Crohn’s disease, and the researchers discovered that it is also effective against stationary-phase Escherichia coli and Acinetobacter baumannii.

More information:
Erica J. Zeng et al., Discovery of antibiotics that selectively kill metabolically inactive bacteria, Cell Chemical Biology (2023). DOI: 10.1016/j.chembiol.2023.10.026

Journal Information:
Cell Chemical Biology

The Lancet

WhatsApp Group Join Now
Telegram Group Join Now
Instagram Group Join Now

Leave a Comment