May 25, 2023
C3.ai DTI COVID Co-PIs Regina Barzilay and Tommi Jaakkola, both professors of electrical engineering and computer science at the Massachusetts Institute of Technology, were part of a team using AI to discover a drug that could help combat drug-resistant infections. The machine-learning algorithm identified a compound that kills Acinetobacter baumannii, a bacterium found in many hospital settings.
The two researchers served as Co-PIs on a 2020 DTI-funded COVID-19 project led by Ziv Bar-Joseph of Carnegie Mellon University that studied lung cells infected with SARS-CoV-2 virus and identified 18 FDA-approved drugs to halt the coronavirus infection.
The study announced this spring used AI to identify a new antibiotic that, if developed for use in patients, could help combat A. baumannii, a species of bacteria that can lead to pneumonia, meningitis, and other serious infections, according to the May 25 MIT News story.
Researchers identified the new drug from a library of nearly 7,000 potential drug compounds using a machine-learning model that they trained to evaluate whether a chemical compound will inhibit the growth of A. baumannii.
Several years ago, Professor Barzilay set out with colleagues to combat the growing problem of drug-resistant bacteria using machine learning to identify new antibiotics whose chemical structures are different from any existing drugs.
The computer model, which can screen more than a hundred million chemical compounds in a matter of days, was designed to pick out potential antibiotics that kill bacteria using different mechanisms than those of existing drugs.
“The machine learning model can explore, in silico, large chemical spaces that can be prohibitively expensive for traditional experimental approaches,” said Barzilay in a February 2020 MIT News story.