AI's Medical Breakthrough: Tackling Antibiotic Resistance
Antibiotic-resistant bacteria are among the most perilous microorganisms to humans. However, this may soon change, as scientists at McMaster University and MIT are employing AI to discover new, potent antibiotics.
Scientists from McMaster University in Canada and the Massachusetts Institute of Technology in the United States have joined forces to address an urgent medical challenge: the creation of antibacterial drugs that can combat drug-resistant microorganisms. They're using AI to identify molecules that can effectively destroy these resistant pathogens, which cause severe, and often fatal, illnesses.
Jonathan Stokes, Associate Professor of Biochemistry and Biomedical Sciences at McMaster University Source: https://brighterworld.mcmaster.ca
The team's research has particularly focused on the bacterium Acinetobacter baumannii, which the World Health Organization has classified as one of the world's most drug-resistant microorganisms. This bacterium is typically found in medical facilities and, due to its unique characteristics, can survive standard treatment methods, leading to extensive drug resistance.
A. baumannii, a bacterium capable of surviving on surfaces for an extended period and accumulating DNA from other pathogens, typically infects seriously ill or weakened patients in clinical settings. It leads to various conditions including wound infections, pneumonia, urological diseases, meningitis, and sepsis, many of which can be fatal.
Discovering new antibiotics against A. baumannii has proven challenging through conventional screening approaches. Fortunately, machine learning methods allow for the rapid exploration of chemical space, increasing the probability of discovering new antibacterial molecules,the researchers note in an article in the scientific journal Nature Chemical Biology.
The lead author of the study, Jonathan Stokes, an Associate Professor of Biochemistry and Biomedical Sciences at McMaster University, collaborated with James J. Collins, a Professor of Medical Engineering and Science at MIT, and graduate students Gary Liu and Denize Catacutan from McMaster University.
The team screened about 7,500 molecules for potential inhibitors of A. baumannii's growth in an artificial environment (in vitro). Using the data they collected, they trained a neural network to create novel molecules capable of suppressing the bacterium. Through computer modeling (in silico), they developed Abaucin, a narrow-spectrum antibiotic that specifically targets A. baumannii.
The authors of the study suggest that Abaucin's selective effect makes it a promising candidate for further development. Broad-spectrum antibiotics often lose their efficacy as microorganisms adapt to them. Moreover, these drugs not only kill disease-causing agents but also beneficial bacteria in the gut, leading to an increase in harmful microorganisms and severe infections. However, the targeted action of abaucin minimizes the chances of A. baumannii developing drug resistance and prevents potential complications.
AI methods afford us the opportunity to vastly increase the rate at which we discover new antibiotics, and we can do it at a reduced cost. This is an important avenue of exploration for new antibiotic drugs,Stokes confidently states.
