A newly designed AI-powered tool is effective in developing treatments that attack antibiotic-resistant bacteria by destroying their outer defenses, according to a new study from Houston Methodist.
This research nature communications Led by Eleftherios Milonakis, M.D., chair of the Houston Methodist Charles W. Duncan Jr. School of Medicine, it details how researchers used this tool to identify antimicrobial peptides (small proteins that are part of the body’s innate immune system) that effectively target bacteria such as methicillin-resistant Staphylococcus aureus (MRSA) in clinical tests.
“Antibiotic-resistant bacteria are a major global health threat, causing an estimated 2.8 million infections and more than 35,000 deaths in the United States each year. It is important that we address this challenge,” said Mylonakis.
Antimicrobial peptides offer a promising approach to target difficult-to-treat bacteria while reducing the potential for resistance. However, precisely designing these molecules has traditionally been complex and time-consuming. To overcome this, we have developed an AI-powered platform that allows us to identify and design the most effective peptides against MRSA and other pathogens. ”
Eleftherios Milonakis, Houston Methodist
First authors Fadi Shehadeh and Biswajit Mishra, along with their collaborators, designed CAMPER (Constraint-driven AMP Engineering with Rank), an AI-based platform that integrates machine learning and biologically-informed features. CAMPER evaluates and ranks libraries of candidate peptides based on their physical and chemical properties and predicted performance. Using this approach, the research team identified a promising candidate, WP-CAMPER1, which showed potent activity against MRSA at low concentrations and revealed potential to treat antibiotic-resistant infections.
“Ultimately, our study reports and validates the CAMPER methodology and demonstrates its ability to generate peptides that demonstrate efficacy against difficult-to-treat and persistent infections. This represents an important step toward a scalable platform for developing therapeutics targeting complex pathogens,” Mylonakis said.
Other collaborators on this study include Luis Oscar Felix; Charilaos Delis Narchonai Ganesan and Zhang Liyang From Houston Methodist. Raquel Ferrer-Espada Andrew Mertens, Yulian Gulev, and Johan Poulsson from Harvard Medical School; Mr. Anindya Basu of Rajiv Gandhi Institute of Technology. Michael B. Sherman of the University of Texas at Galveston School of Medicine; Mandal Naik of Brown University and Paul Sotiriadis of the National Institute of Technology of Athens and the Center for Archimedes and Athena Research.
sauce:
Reference magazines:
Shehadeh, F. others. (2026) CAMPER: Mechanical artificial intelligence to design peptides targeting MRSA persisters. nature communications. DOI: 10.1038/s41467-026-70348-9. https://www.nature.com/articles/s41467-026-70348-9.
