The team's discovery could lead to more effective treatments for a dangerous hospital superbug called Acinetobacter baumannii.
A. baumannii is classified by the World Health Organization as one of the world’s most dangerous types of antibiotic-resistant bacteria. It poses a severe threat to vulnerable hospital patients, as it can cause life-threatening conditions, such as pneumonia, meningitis, and wound infections.
The bacteria, notorious for its ability to survive on surfaces for extended periods, has the capability to acquire antibiotic-resistance genes from other bacteria species in its environment.
Conventional methods of discovering antibiotics to combat A. baumannii have proven challenging, time-consuming, and expensive. In response to the urgent need for new drugs, the research team turned to AI to expedite the process.
By employing an AI algorithm, they were able to predict new structural classes of antibacterial molecules. Their efforts yielded the discovery of a new antibacterial compound, which they have named abaucin.
Modern algorithmic approaches can access hundreds of millions, possibly billions, of molecules with antibacterial properties.
“This work validates the benefits of machine learning in the search for new antibiotics,” says Jonathan Stokes, lead author on the paper and an Assistant Professor in McMaster’s Department of Biomedicine & Biochemistry, who conducted the work with James J. Collins, a Professor of medical engineering and science at MIT, and McMaster graduate students, Gary Liu and Denise Catacutan.
“Using AI, we can rapidly explore vast regions of chemical space, significantly increasing the chances of discovering fundamentally new antibacterial molecules,” says Stokes, who belongs to McMaster’s Global Nexus School for Pandemic Prevention and Response.
“AI approaches to drug discovery are here to stay and will continue to be refined,” says Collins, Life Sciences faculty lead at the MIT Abdul Latif Jameel Clinic for Machine Learning in Health. “We know algorithmic models work, now it’s a matter of widely adopting these methods to discover new antibiotics more efficiently and less expensively.”
What makes abaucin particularly promising is the fact that it exclusively targets A. baumannii, reducing the likelihood of the bacteria being able to develop drug resistance rapidly.
Broad-spectrum antibiotics indiscriminately kill bacteria, which disrupts the gut microbiome, opening the door to a host of serious infections, including C difficile. abaucin's precision, in contact, could therefore lead to more targeted and effective treatments.
“We know broad-spectrum antibiotics are suboptimal and that pathogens have the ability to evolve and adjust to every trick we throw at them,” says Stokes.
“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.”
As the battle against antibiotic resistance continues, researchers plan to expand their AI-driven antibiotic discovery efforts to tackle other challenging pathogens, such as Staphylococcus aureus and Pseudomonas aeruginosa.
The application of AI in this field holds great promise, offering a new frontier in the fight against infectious diseases and the development of life-saving treatments.