For the last several decades, doctors and scientists have warned that we will get to the point where antibiotics will no longer work to treat serious infections. That time has come.
Independent medical journal, The Lancet, published a report in January 2022 saying that more than one million people worldwide, died of antibiotic-resistant bacterial infections in 2019. This number is almost more than the annual death toll from both malaria (640,000) and AIDS (860,000) combined.
Researchers estimated that up to 4.95 million people died in 2019 from illnesses related to antibiotic-resistant infections. That’s over and above the 1.2 million who died as a direct result of the drug-resistant bacterial infections.
Overuse and misuse of antibiotics in humans, as well as in agriculture, has led to the currently discovered and used antibiotics becoming less effective, and in many cases, ineffective, against serious infections.
CDC estimates that up to 50% of antibiotics prescribed in the outpatient setting are either inappropriately prescribed (wrong antibiotic, dosage, duration) or completely unnecessary (being prescribed for non-bacterial infections.)
According to the Lancet report, the six leading bacteria for deaths associated with resistance were Escherichia coli (E. coli), Staphylococcus aureus, Klebsiella pneumonia, Streptococcus pneumonia, Pseudomonas aeruginosa and Acinetobacter baumannii.
With a seemingly new worldwide epidemic just on the horizon threatening to wipe out a substantial portion of the global population, there is some good news in the fight against drug-resistant bacterial infections.
A team of scientists from McMaster University and the Massachusetts Institute of Technology have employed the use of AI to discover an antibiotic that could be used to treat the extremely resistant Acinetobacter baumannii bacteria.
The researchers shared their findings about the new antibacterial treatment, which they named abaucin, in a study published in the journal Nature Chemical Biology on May 25th, 2023.
Jon Stokes, an assistant professor in the department of biochemistry and biomedical sciences at McMaster University, and a lead author of the research paper, said: “In my opinion, it [Acinetobacter baumannii] is public enemy No. 1 for antibiotic resistance,” which he went on to say was largely due to it being often found in hospital settings, its ability to survive on surfaces for prolonged periods of time and the ability of the bacterial pathogen to pick up DNA from other species of bacteria in its environment, which can encode antibiotic-resistance genes. A. baumannii causes pneumonia, meningitis and infects wounds, all of which can lead to death if not properly treated.
AI Is The New Powertool in the Medical Research Toolbox
The researchers tested roughly 7,500 molecules with different structures in a lab to see which of them were able to demonstrate growth inhibiting properties of A. baumannii and which of them were not.
Then, the research team trained an AI model to understand what chemical features resulted in molecules that demonstrated those properties. Once the model was trained, they were able to show the AI model new molecules it had never seen and based on what it had learned from its training datasets, it was able to predict which chemicals would most likely be effective against the drug-resistant pathogen.
Once the most likely molecular candidates were identified by the AI model, the researchers then tested those molecules to see how well they could fight off A. baumannii.
The AI did not discover the new treatment for the highly drug-resistant bacteria, but it sped up the process to find it exponentially. Instead of having to test thousands or even tens of thousands of molecules, only a few hundred were tested.
“We ended up finding this one molecule that was potent at inhibiting the growth of Acinetobacter in the laboratory — and it was structurally unique relative to every other known antibiotic we have. So, this AI model helped us rather efficiently pull out an interesting molecule with antibacterial properties against the bug we were trying to kill,” said Stokes.
He further commented that their research offers proof that the application of AI methods can “meaningfully influence” the discovery of new antibiotics for other challenging bacterial pathogens. “I’m not saying that AI is a panacea — it’s not going to solve all of our problems for us — but it’s a very powerful tool in our toolbox with which we use to find new medicines for people.”
The team hopes to employ AI, using the same process to discover treatments for other, drug-resistant bacteria.
