In a bid to combat the pressing challenge of antibiotic resistance, researchers have unveiled a novel approach utilizing generative artificial intelligence (AI) to develop potential treatments for antibiotic-resistant bacteria.
Generative AI Formulates Potential Drugs Against Antibiotic-Resistant Bacteria
With antibiotic-resistant strains contributing to nearly 5 million deaths annually worldwide, the urgency for innovative solutions has never been greater.
A collaborative effort between Stanford Medicine and McMaster University has yielded promising results as they harness generative AI to formulate six new drugs targeting resistant strains of Acinetobacter baumannii, a primary pathogen driving antibiotic resistance-related fatalities.
The newly introduced model, SyntheMol, may represent a significant advancement in the fight against antibiotic resistance, offering a ray of hope in the battle against these resilient bacterial strains.
James Zou, Ph.D., an associate professor of biomedical data science and co-senior author of the study, underscores the critical need for expedited antibiotic development, emphasizing AI's potential to design novel molecules to address this pressing issue.
"There's a huge public health need to develop new antibiotics quickly," Zou said in a press release statement.
"Our hypothesis was that there are a lot of potential molecules out there that could be effective drugs, but we haven't made or tested them yet. That's why we wanted to use AI to design entirely new molecules that have never been seen in nature."
SyntheMol's Framework
Prior methodologies relied on algorithms to sift through existing drug libraries, but these approaches merely scratched the surface of the vast chemical space potentially harboring antibacterial properties.
SyntheMol's innovative framework leverages a diverse library of over 130,000 molecular building blocks and a repository of validated chemical reactions to craft potential drugs.
It not only presents the final compound but also delineates the synthetic steps required for its production, streamlining the drug development pipeline.
To ensure practical viability, the model underwent training on existing antibacterial data and was guided to generate compounds distinct from existing ones, mitigating the risk of bacterial resistance.
Collaborating with the Ukrainian chemical company Enamine, researchers successfully synthesized 58 of the 70 selected compounds identified by SyntheMol. Among these, six demonstrated efficacy against resistant strains of A. baumannii in laboratory tests.
These compounds exhibited promising antibacterial activity against other antibiotic-resistant bacteria, including E. coli, Klebsiella pneumoniae, and MRSA, underscoring their broad potential impact.
Exploring a New Part of Chemical Space
While the precise mechanisms of action remain elusive, further research aims to elucidate these details and uncover general principles applicable to antibiotic development.
"This AI is really designing and teaching us about this entirely new part of the chemical space that humans just haven't explored before," Zou said.
Zou and Swanson are further enhancing SyntheMol's capabilities and expanding its scope by collaborating with other research teams. They aim to utilize the model in drug discovery efforts targeting heart disease and in the development of novel fluorescent molecules for laboratory experimentation.
The findings of the research team were published in the journal Nature Machine Intelligence.
Related Article : World's First Genetically Edited Pig Kidney Transplanted Into a Living Human Patient
