Sign In

Communications of the ACM

ACM Careers

AI Helps Scientists Develop New Antibiotic To Kill Superbug

View as: Print Mobile App Share:
Acinetobacter bacteria

Researchers trained a neural network and performed in silico predictions for new molecules with activity against A. baumannii.

Credit: CDC

Scientists from McMaster University and the Massachusetts Institute of Technology used machine learning to find a new antibiotic to kill Acinetobacter baumannii, a bacteria often found in hospitals that can cause serious infections, according to a study published in Nature Chemical Biology.

Acinetobacter baumannii, commonly transmitted via the hands of healthcare workers, has become resistant to most antibiotics and was deemed a "critical" threat by the World Health Organization, which said in 2017 that new antibiotics were "urgently needed" to fight it. 

AI may help achieve that goal. In this case, the scientists screened 7,500 molecules to find a new antibacterial compound named abaucin, which was shown to treat infected wounds on mice. 

The researchers call it a "promising lead" that "highlights the utility of machine learning in antibiotic discovery."

From Decrypt
View Full Article


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account