A new type of antibiotics has been found through artificial intelligence (AI) machine learning, a significant advancement that could aid in tackling the worldwide issue of antimicrobial resistance (AMR).
The new drug, halicin, is effective against drug-resistant Staphylococcus aureus (MRSA) bacteria, one of the most stubbornly hard-to-kill pathogens that can cause life-threatening infections. The discovery was made possible by using more transparent deep learning models, a type of AI that can learn to recognize patterns in vast amounts of data.
“The insight here was that we could see what was being learned by the models to make their predictions that certain molecules would make for good antibiotics,” James Collins, professor of Medical Engineering and Science at the Massachusetts Institute of Technology (MIT) and one of the study’s authors, said in a statement.”Our work provides a framework that is time-efficient, resource-efficient, and mechanistically insightful, from a chemical-structure standpoint, in ways that we haven’t had to date”.
The researchers, from MIT and Harvard University, utilized AI to sift through millions of chemical compounds, seeking those capable of eliminating bacteria without causing harm to human cells. The method pinpointed multiple compounds that proved effective against methicillin-resistant Staphylococcus aureus (MRSA) and vancomycin-resistant enterococci, two of the most perilous superbugs.
The researchers tested halicin in mice infected with A. baumannii, a bacterium found in many hospitals that can lead to pneumonia, septic shock, and other complications.
“Acinetobacter can survive on hospital doorknobs and equipment for long periods, and it can take up antibiotic resistance genes from its environment. It’s really common now to find A. baumannii isolates that are resistant to nearly every antibiotic,” said Jonathan Stokes, a postdoctoral researcher at MIT and the lead author of the study, published in the journal Nature.
The researchers utilized AI to develop new versions of salicin, which demonstrated enhanced effectiveness against certain bacteria. They intend to continue refining the medication and conducting tests in additional animal models, prior to progressing to human trials.
The development builds on previous research by this group and others, who have used AI to find new antibiotics and optimize existing ones. Unlike a typical AI model, which operates as an inscrutable “black box,” it was possible to follow this model’s reasoning and understand the biochemistry behind it.
The researchers found the new drug from a pool of nearly 7,000 potential compounds using a machine-learning model that they trained to determine if a chemical compound would inhibit the growth of A. baumannii.
“This finding further supports the premise that AI can significantly accelerate and expand our search for novel antibiotics,” says James Collins, the Termeer Professor of Medical Engineering and Science in MIT’s Institute for Medical Engineering and Science (IMES) and Department of Biological Engineering. “I’m excited that this work shows that we can use AI to help combat problematic pathogens such as A. baumannii.”
The finding of this new type of antibiotics is a major advancement in combating drug-resistant infections, which according to the World Health Organization, cause about 700,000 deaths globally annually. It paves the way for AI utilization in drug discovery and design, providing hope for the creation of improved treatments for various illnesses.
Relevant articles:
– Scientists discover the first new antibiotics in over 60 years using AI
– AI Discovers First New Antibiotic in Over 60 Years
– Scientists discover the first new antibiotics in over 60 years using AI
– Using AI, scientists find a drug that could combat drug-resistant …