Researchers at Massachusetts Institute of Technology (MIT) have identified a powerful antibiotic using a machine-learning algorithm.
The MIT team said the compound is able to kill some of the most dangerous drug-resistant bacteria in the world. The Artificial Intelligence (AI)-created drug, named halicin, was able to wipe out antibiotic-resistant strains of bacteria, such as Acinetobacter baumannii and Enterobacteriaceae – two of three high-priority pathogens that the World Health Organisation (WHO) ranks as critical for new antibiotics to target.
The AI-powered technology is able to screen more than 100 million chemical compounds in a matter of days. The model has been trained to identify potential antibiotics that kill bacteria using different mechanisms than those of existing drugs. It was specifically trained to find molecules known for being effective against E.coli growth.
Once the model was trained, the researchers tested it on the Broad Institute’s Drug Repurposing Hub, a library of about 6,000 compounds.After identifying halicin, they used the model to screen more than 100 million molecules selected from the ZINC15 database, an online collection of about 1.5 billion chemical compounds.
The process took only three days and identified 23 candidates that were structurally dissimilar from existing antibiotics and predicted to be nontoxic to human cells.
MIT professor James Collins explained: “We wanted to develop a platform that would allow us to harness the power of artificial intelligence to usher in a new age of antibiotic drug discovery.
“Our approach revealed this amazing molecule which is arguably one of the more powerful antibiotics that has been discovered. It has remarkable activity against a broad range of antibiotic-resistant pathogens.”
- Reports of Cyber-Flashing on Trains Are on the Rise
- Cyber Attack Exposes Data of 10.6 Million Guests at MGM Resorts
- Japanese Scientists Create Robot Child That Can ‘Feel’ Pain
The researchers also identified a number of other “promising” antibiotic candidates, which they plan to test further.
“The machine learning model can explore, in silico, large chemical spaces that can be prohibitively expensive for traditional experimental approaches,” said MIT computing science professor, Regina Barzilay.
Collins added: “We’re facing a growing crisis around antibiotic resistance, and this situation is being generated by both an increasing number of pathogens becoming resistant to existing antibiotics, and an anemic pipeline in the biotech and pharmaceutical industries for new antibiotics.”