Trending Science: AI discovers powerful antibiotic to combat drug resistance

In a major development in the fight against drug resistance, MIT researchers used a type of AI to discover new antibiotics. They methodically trained the AI algorithm with samples of effective and ineffective drugs, as well as drugs that are known to be safe in humans.

AI technologies in battle against drug resistance

Their algorithm identified a formidable new antibiotic compound that’s capable of killing some of the world’s most challenging disease-causing bacteria. They published their findings in the journal ‘Cell’.

“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,” said bioengineer and MIT team member James Collins in an MIT news release.

“In terms of antibiotic discovery, this is absolutely a first,” Regina Barzilay, a specialist in machine learning at MIT and senior project researcher, told ‘The Guardian’. “I think this is one of the more powerful antibiotics that has been discovered to date,” added Collins. “It has remarkable activity against a broad range of antibiotic-resistant pathogens.”

The search for new antibiotics

The computer model screened more than a hundred million chemical compounds in just a few days. The algorithm analysed the atomic and molecular features of 2 500 drugs and other natural compounds to find those with the most antibacterial qualities that could kill E. coli. The researchers then chose and tested about 100 candidates before discovering a molecule called halicin, originally developed for treating diabetes. This newly discovered compound was able to kill 35 types of potentially deadly bacteria. They treated numerous drug-resistant infections with halicin. It proved effective against E. coli, which didn’t develop any resistance to it during treatment in mice. Halicin was also potent against more deadly pathogens, including those that cause tuberculosis.

“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,” Collins told the UK’s ‘Independent’. “Our approach revealed this amazing molecule which is arguably one of the more powerful antibiotics that has been discovered.”

The researchers used a database with about 1.5 billion chemical compounds to search for more drugs. The AI model identified 23 potential antibiotics, 2 of which appear to be powerful. Doing so in the lab would have been impossible. “Being able to perform these experiments in the computer dramatically reduces the time and cost to look at these compounds,” first author Jonathan Stokes said in the same ‘The Guardian’ article.

The MIT team would like to continue investigating halicin in the hopes of developing it for use in humans. It also plans to use the AI model to design new antibiotics and optimise existing molecules.