AI Algorithm Discovers One of World’s Most Powerful Antibiotics

228
Sourced from Science History Images

An AI algorithm created at MIT has just discovered a powerful new antibiotic that kills some of the world’s most dangerous drug-resistant bacteria.

“In terms of antibiotic discovery, this is absolutely a first,” said Regina Barzilay, a senior researcher on the project and specialist in machine learning at MIT

The drug itself works in a way that is different from any other existing antibacterials and is the first-ever drug of its kind to be discovered by setting an AI upon a vast digital library of pharmaceutical compounds, reports The Guardian.

The new AI-found drug was tested and seen to have completely wiped out an entire range of antibiotic-resistant strains, including Acinetobacter baumannii and Enterobacteriaceae. Who make up two of the three highest priority “critical” bacteria that urgently need antibiotics.

“I think this is one of the more powerful antibiotics that has been discovered to date,” added James Collins, a bioengineer on the team at MIT. “It has remarkable activity against a broad range of antibiotic-resistant pathogens.”

In their quest to find new antibiotics, a “deep learning” algorithm was trained to identify the sorts of molecules that kill bacteria – the program was therefore given information on the atomic and molecular features of about 2500 drugs and natural compound using E-Coli as a benchmark to test how well or not the substances blocked the spread of bacteria.

Once the algorithm was well-versed in what makes a good antibiotic good, the team then began feeding the programme information from a library of over 6000 compounds under investigation for treating various human diseases, with a focus on compounds, unlike any existing antibiotics. This would boost the chances that any drugs found would bypass any resistance developed by bugs in a radical way.

It took only a matter of hours before the algorithm came up with a few promises antibiotics – a particularly potent compound was named ‘Halicin” by the researchers after the AI super-computer HAL from Ridley Scott’s 2001: A Space Odyssey.

The researchers began tests on halicin, and found that the new antibiotic killed Mycobacterium tuberculosis and other strains of bacteria known to be resistant to powerful antibiotics like Enterobacteriaceae. Halicin also cleared C-difficile and multi-drug resistant Acinetobacter baumannii infections in mice.

“The work really is remarkable,” said Jacob Durrant, who works on computer-aided drug design at the University of Pittsburgh. “Their approach highlights the power of computer-aided drug discovery. It would be impossible to physically test over 100m compounds for antibiotic activity.”

“Given typical drug-development costs, in terms of both time and money, any method that can speed early-stage drug discovery has the potential to make a big impact,” he added.

How do bacteria become resistant to antibiotics?

The antibiotic resistance of bacteria arises when they mutate and evolve an ability to bypass the mechanisms within antibiotics that kill them.

New antibiotics need to be discovered and tested constantly as without them more than 10 million lives around the world would be put at risk from new infections by 2050, a review on antimicrobial resistance warns.

Edited by Luis Monzon

Follow Luis Monzon on Twitter

Follow IT News Africa on Twitter