Artificial intelligence has invented a new antibiotic: it will solve the problem that doctors could not cope with for decades

A machine learning algorithm has identified a compound that kills Acinetobacter baumannii, a superbug found in many hospitals. The publication told in more detail Scitech Daily.

Photo: IStock

Using an artificial intelligence algorithm, researchers at MIT and McMaster University have identified a new antibiotic capable of killing the type of bacteria responsible for many drug-resistant infections.

If developed for use in patients, the drug could help fight Acinetobacter baumannii, a type of bacteria commonly found in hospitals that can lead to pneumonia, meningitis and other serious infections. The microbe is the leading cause of infections among wounded soldiers in Iraq and Afghanistan.

“Acinetobacter survives on doorknobs and hospital equipment for a long time, and also absorbs antibiotic resistance genes from the environment. It is now very common to find isolates of A. baumannii that are resistant to almost all antibiotics,” says Jonathan Stokes, a former MIT doctor who is now an assistant professor of biochemistry and biomedical sciences at McMaster University.

The researchers identified a new drug from a library of nearly 7000 potential drug compounds using a machine learning model they trained to evaluate whether a chemical compound would inhibit the growth of A. baumannii.

“This discovery further supports the idea that AI can significantly speed up and expand our search for new antibiotics,” explains James Collins, Termeer Professor of Medical Engineering and Science at MIT's Institute of Medical Engineering and Science (IMES). “I’m pleased that this work shows that we can use AI to combat problematic pathogens such as A. baumannii.”

On the subject: Scientists have created a robotic pill: it can be a lifesaver for diabetics and cope with antibiotic-resistant bacteria

Collins and Stokes are the lead authors of the new study, which was published May 25 in the journal Nature Chemical Biology. The lead authors of the paper are McMaster PhD students Gary Liu and Denise Katakutan, and recent McMaster graduate Khushi Rathod.

Drug discovery

Over the past few decades, many pathogenic bacteria have become more resistant to existing antibiotics, while very few new antibiotics have been developed.

A few years ago, Collins, Stokes, and MIT professor Regina Barzilai set out to tackle this problem using machine learning. It is a type of artificial intelligence that can learn to recognize patterns in a vast expanse of data volumes. Collins and Barzilai hope this approach can be used to identify new antibiotics that have a chemical structure different from any existing drugs.

The researchers first trained an algorithm to identify chemical structures that could inhibit the growth of E. coli. After testing over 100 million compounds, this algorithm yielded a molecule that the researchers named halicin, after the fictional AI system from 2001: A Space Odyssey. They showed that this molecule could kill not only E. coli but also several other types of drug-resistant bacteria.

“After this article, when we showed that these machine learning approaches can work well for complex antibiotic discovery tasks, we turned our attention to what I consider public enemy #1 for multidrug-resistant bacterial infections, namely Acinetobacter ', says Stokes.

To get training data for their computational model, the researchers first exposed lab-grown A. baumannii to about 7500 different chemicals to see which ones might inhibit the microbe's growth. They then entered the structure of each molecule into the model. They told the model whether each structure could inhibit bacterial growth or not. This allowed the algorithm to study the chemistry associated with growth inhibition.

Once the model was trained, the researchers used it to analyze a set of 6680 compounds it had not seen before, obtained from the Broad Institute's Drug Repurposing Center. This analysis, which took less than two hours, produced several hundred results. Of these, the researchers selected 240 for experimental testing in the laboratory, focusing on compounds with structures different from those of existing antibiotics or molecules from the training data.

These tests yielded nine antibiotics, including one that was very potent. This compound, which was initially investigated as a potential treatment for diabetes, proved to be extremely effective in killing A. baumannii, but had no effect on other bacterial species, including Pseudomonas aeruginosa, Staphylococcus aureus, and carbapenem-resistant Enterobacteriaceae.

This "narrow spectrum" killing ability is a desirable characteristic of antibiotics because it minimizes the risk of rapid spread of drug resistance in bacteria. Another advantage is that the drug is likely to help suppress opportunistic infections such as Clostridium difficile.

New mechanism

In a mouse study, the researchers found that the drug, which they named abaucin, could treat infections caused by A. baumannii. In addition, they found in laboratory tests that it works against various drug-resistant strains of A. baumannii isolated from human patients.

Further experiments showed that the drug killed cells by interfering with a process known as lipoprotein transfer, which cells use to transport proteins from the inside of the cell to the cell wall. In particular, the drug inhibits the LolE protein involved in this process.

You may be interested in: top New York news, stories of our immigrants and helpful tips about life in the Big Apple - read it all on ForumDaily New York

All gram-negative bacteria express this enzyme, so the researchers were surprised to find that abaucin was so selective in A. baumannii. They suggest that small differences in how A. baumannii performs this task may explain the drug's selectivity.

“We have not yet completed the collection of experimental data, but we think that this is due to the fact that A. baumannii delivers lipoproteins a little differently than other gram-negative species. We think that's why we get narrow-spectrum activity,” Stokes notes.

The Stokes lab is currently working with other researchers to optimize the compound's medicinal properties in hopes of developing it for possible use in patients.

The researchers plan to use their modeling approach to identify potential antibiotics for other types of drug-resistant infections, including those caused by Staphylococcus aureus and Pseudomonas aeruginosa.

Read also on ForumDaily:

Hidden gems: seven high-end products you can buy at Aldi for pennies

How much bad habits cost us: alcohol and fast food hurt the budget

Who to study in college to make good money: popular specialties lead to low wages

Costco vs Aldi: Price Comparison of Five Popular Products

Do you want more important and interesting news about life in the USA and immigration to America? — support us donate! Also subscribe to our page Facebook. Select the “Priority in display” option and read us first. Also, don't forget to subscribe to our РєР ° РЅР ° Р »РІ Telegram  and Instagram- there is a lot of interesting things there. And join thousands of readers ForumDaily New York — there you will find a lot of interesting and positive information about life in the metropolis.