Hundreds of thousands of potential new antibiotics have been uncovered in the natural world using artificial intelligence, marking a significant breakthrough in the fight against deadly drug-resistant infections. An international research team has leveraged machine learning to identify 863,498 promising antimicrobial peptides (AMPs), each with the potential to combat formidable infections like MRSA (methicillin-resistant Staphylococcus aureus) and VRSA (vancomycin-resistant Staphylococcus aureus).
The study, recently published in the journal Cell, highlights the importance of innovative approaches in addressing the growing crisis of antimicrobial resistance (AMR). This issue has gained renewed attention as the number of infections resistant to existing antibiotics continues to rise at an alarming rate. “There is an urgent need for new methods for antibiotic discovery,” says computational biologist Professor Luis Pedro Coelho of the Queensland University of Technology (QUT) in Australia. “It is one of the top public health threats, killing 1.27 million people each year.”
Professor Coelho emphasizes the role of artificial intelligence in revolutionizing public health research. “Using artificial intelligence to understand and harness the power of the global microbiome will hopefully drive innovative research for better public health outcomes,” he explains. Without significant intervention, AMR could lead to an estimated 10 million deaths annually by 2050, underscoring the dire need for new antibiotics.
From his lab at the QUT Center for Microbiome Research, Professor Coelho and his team tested 100 of the more than 800,000 peptides against clinically significant pathogens. The machine learning predictions were validated in pre-clinical models of infected mice, where the peptides showed promising results. The treatment produced effects comparable to polymyxin B, a commercially available antibiotic used to treat severe infections like meningitis, pneumonia, sepsis, and urinary tract infections.
The study also revealed that an additional 79 peptides disrupted bacterial membranes, while 63 specifically targeted antibiotic-resistant bacteria such as Staphylococcus aureus and Escherichia coli. “Moreover, some peptides helped to eliminate infections in mice; two in particular reduced bacteria by up to four orders of magnitude,” Coelho reports, highlighting the significant impact these peptides could have on treating resistant infections.
The peptides were sourced from over one million organisms analyzed by the research team. These organisms came from diverse environments, including marine and soil ecosystems, as well as the guts of humans and animals. This extensive analysis has culminated in the creation of AMPSphere, a publicly available and open-access database comprising the newly discovered peptides. This resource is expected to accelerate the development of new antibiotics and provide a valuable tool for researchers worldwide.
The findings of this study represent a pivotal moment in the ongoing battle against AMR. The integration of artificial intelligence in antibiotic discovery offers a powerful avenue for identifying novel treatments that can address the urgent need for effective antibiotics. As researchers continue to explore the potential of these antimicrobial peptides, the hope is that they will pave the way for innovative therapies that can save countless lives and curb the threat of drug-resistant infections.
Recommended For You
