Scientists have harnessed the capabilities of artificial intelligence (AI) to make a groundbreaking discovery in the field of antibiotics.

By utilizing AI, researchers were able to efficiently narrow down a vast array of potential chemical compounds to a select few that could undergo laboratory testing. The outcome of this process yielded a potent and experimental antibiotic named abaucin, which will undergo further examination before its potential application.

Experts from Canada and the United States have highlighted the immense potential of AI in revolutionizing the drug discovery process by significantly expediting the identification of new medications. This recent achievement serves as a prime illustration of how artificial intelligence tools can have a transformative impact on scientific and medical advancements.

Antibiotics play a crucial role in combating bacterial infections. Nevertheless, there has been a dearth of new antibiotic drugs for several decades, leading to the emergence of antibiotic-resistant bacteria that are increasingly challenging to treat.

Estimates suggest that over a million individuals lose their lives annually due to infections that are resistant to existing antibiotics. To address this urgent problem, the researchers focused their efforts on tackling one of the most troublesome bacterial species known as Acinetobacter baumannii.

This particular superbug has been identified by the World Health Organization as a “critical” threat and poses a significant challenge as it readily develops resistance to multiple antibiotics. It frequently affects wounds and can cause pneumonia, making it a prevalent concern in hospitals and care facilities, where it can persist on surfaces and medical equipment.

Dr Jonathan Stokes, from McMaster University, describes the bug as “public enemy number one” as it’s “really common” to find cases where it is “resistant to nearly every antibiotic”.

In order to discover a new antibiotic, the researchers commenced by training the AI. They conducted manual tests on thousands of drugs with known chemical structures against Acinetobacter baumannii to identify those that could impede or eliminate the bacterium’s growth.

This data was then fed into the AI, enabling it to learn the specific chemical characteristics of drugs capable of targeting the problematic bacterium.

Subsequently, the AI was deployed to analyze a list of 6,680 compounds with unknown efficacy. The findings, published in Nature Chemical Biology, revealed that the AI generated a shortlist within a mere hour and a half.

The researchers proceeded to conduct laboratory experiments on 240 compounds, identifying nine potential antibiotics, one of which was the remarkably potent abaucin.

Further laboratory tests demonstrated abaucin’s ability to treat infected wounds in mice and successfully eliminate A. baumannii strains obtained from patients.

Nonetheless, Dr. Stokes cautioned, “This is when the work starts.”

The subsequent phase involves refining the drug through laboratory processes and subsequently conducting clinical trials. Dr. Stokes anticipates that the first AI-derived antibiotics may not be available for prescription until around 2030.

Interestingly, this experimental antibiotic exhibited no impact on other bacterial species, exclusively targeting A. baumannii.

While numerous antibiotics tend to indiscriminately kill bacteria, the researchers believe that abaucin’s precision will make it more challenging for drug resistance to develop and potentially lead to reduced side effects.

In principle, the AI could screen tens of millions of potential compounds – something that would be impractical to do manually.

“AI enhances the rate, and in a perfect world decreases the cost, with which we can discover these new classes of antibiotic that we desperately need,” Dr Stokes told me.

The researchers tested the principles of AI-aided antibiotic discovery in E. coli in 2020, but have now used that knowledge to focus on the big nasties. They plan to look at Staphylococcus aureus and Pseudomonas aeruginosa next.

“This finding further supports the premise that AI can significantly accelerate and expand our search for novel antibiotics,” said Prof James Collins, from the Massachusetts Institute of Technology.

He added: “I’m excited that this work shows that we can use AI to help combat problematic pathogens such as A. baumannii.”

Prof Dame Sally Davies, the former chief medical officer for England and government envoy on anti-microbial resistance, told Radio 4’s The World Tonight: “We’re onto a winner.”

She said the idea of using AI was “a big game-changer, I’m thrilled to see the work he (Dr Stokes) is doing, it will save lives”.