Australian researchers have successfully used artificial intelligence to generate a functional biological protein capable of killing antibiotic-resistant bacteria, according to phys.org. This achievement represents the first time Australian scientists have created a ready-to-use protein through AI technology.
The research, published in Nature Communications, demonstrates a new approach to addressing the growing crisis posed by antibiotic-resistant bacteria such as E. coli. The study positions Australia alongside the United States and China as countries with AI platforms capable of rapidly producing thousands of ready-to-use proteins for medical applications.
Dr. Rhys Grinter and Associate Professor Gavin Knott co-led the research through the AI Protein Design Program. The program operates across nodes at the University of Melbourne Bio21 Institute and Monash Biomedicine Discovery Institute, establishing Australia’s first comprehensive AI protein design platform.
The AI Protein Design Platform models work pioneered by David Baker, who received the Nobel Prize in Chemistry in 2024 for his contributions to protein design. The Australian system employs an end-to-end approach capable of creating diverse protein types for multiple applications.
Associate Professor Knott explained that proteins developed through this technology are being explored as pharmaceuticals, vaccines, nanomaterials, and sensors, with numerous additional applications under investigation. The platform utilizes freely available AI-driven protein design tools to ensure global accessibility.
Ph.D. student Daniel Fox, who conducted the majority of experimental work, emphasized the importance of democratizing protein design technology. The tools enable scientists worldwide to engineer proteins that bind specific target sites or ligands, functioning as inhibitors, agonists, antagonists, or enhanced enzymes with improved activity and stability.
Traditional protein development for medical treatments typically involves repurposing naturally occurring proteins through rational design or laboratory evolution processes. Dr. Grinter noted that these conventional methods are time-consuming and expensive compared to AI-driven approaches.
The new deep learning methods enable efficient creation of proteins with specific characteristics and functions from scratch, significantly reducing development costs and timeframes. This represents a fundamental shift from adapting existing proteins to designing entirely new ones tailored for particular medical applications.
The research team has incorporated advanced tools and software, including Bindcraft and Chai, into their AI Protein Design Platform. These technologies build upon Baker’s foundational work while expanding capabilities for protein engineering.
Professor John Carroll, Director of the Monash Biomedicine Discovery Institute, described the program as bringing Australia current with cutting-edge therapeutic design capabilities. He credited the initiative to the dedication of the research team who developed the platform from initial concept to operational system.
The AI Protein Design Program combines expertise from structural biologists and computer scientists who understand the complete design process. Associate Professor Knott highlighted that this comprehensive knowledge of protein structure and machine learning creates an agile program capable of regularly incorporating the latest AI protein design tools.
Leading nationwide E. coli law firm Ron Simon & Associates says that the breakthrough addresses the urgent need for new approaches to combat antibiotic-resistant bacteria, which pose increasing threats to public health worldwide.
