AI Breakthrough: New Protein Design Targets Antibiotic-Resistant E. coli

In a significant advancement against antibiotic-resistant bacteria, Australian researchers have employed artificial intelligence (AI) to design a novel protein capable of neutralizing Escherichia coli (E. coli). This breakthrough, detailed in the July 9, 2025, issue of Nature Communications, marks a pivotal moment in the application of AI to biomedical research.

The AI-generated protein, named "de novo-1," targets the bacterial transporter protein ChuA, which E. coli utilizes to extract iron from human hemoglobin—a process essential for its survival and proliferation. By binding to ChuA, de novo-1 effectively obstructs this iron uptake, leading to the bacterium's demise. This innovative approach offers a promising new strategy in the global fight against antimicrobial resistance (AMR).

AMR poses a significant global health threat, with an estimated 4.95 million deaths associated with bacterial AMR in 2019 alone. Projections indicate that AMR-related deaths could reach 8.2 million by 2050. E. coli, a major contributor to this crisis, causes hundreds of millions of serious intestinal infections annually and is the most common cause of urinary tract infections. The increasing antibiotic resistance of E. coli underscores the urgent need for new therapeutic strategies.

The research was conducted by scientists from the University of Melbourne's Bio21 Institute and Monash University's Biomedicine Discovery Institute. Dr. Rhys Grinter, a laboratory head in the Department of Biochemistry and Pharmacology at the University of Melbourne, emphasized the significance of this development:

"These new methods in deep learning enable efficient de novo design of proteins with specific characteristics and functions, lowering the cost and accelerating the development of novel protein binders and engineered enzymes."

The AI Protein Design Program, a collaborative initiative between the University of Melbourne and Monash University, played a crucial role in this achievement. Associate Professor Gavin Knott, a laboratory head in the Department of Biochemistry at Monash University's Biomedicine Discovery Institute, highlighted the program's capabilities:

"The Program, based at Monash University and the University of Melbourne, is run by a team of talented structural biologists and computer scientists who understand the design process from end-to-end. This in-depth knowledge of protein structure and machine learning makes us a highly agile program capable of regularly onboarding cutting-edge tools in AI-protein design."

The study focused on the heme uptake pathway in pathogenic E. coli, which is crucial for the bacterium's metabolism and growth during infection. The researchers identified that E. coli uses the transporter protein ChuA to bind hemoglobin and extract heme, importing it into the bacterial cell. Utilizing AI-based methods, the team developed de novo-1, a protein designed to bind to ChuA and inhibit its function. Experimental results demonstrated that de novo-1 effectively prevents E. coli growth when heme from hemoglobin is the only available iron source, with high potency at low concentrations.

This study provides strong proof of concept for the use of AI-designed proteins as next-generation antimicrobials. The rapid and targeted design of these proteins could revolutionize the treatment of bacterial infections, addressing the growing challenge of antibiotic resistance. The research team plans to further develop heme-uptake inhibitors as therapeutics for E. coli infections, focusing on improving potency, stability, and testing for safety and effectiveness in pre-clinical models.

The successful application of AI in designing therapeutic proteins marks a significant advancement in biomedical research. It highlights Australia's growing expertise in this field and contributes to global efforts to combat antibiotic-resistant bacteria. The development of AI-designed proteins could lead to more affordable and accessible treatments, potentially transforming patient care and public health outcomes.

This breakthrough underscores the potential of AI in rapidly developing new therapeutic proteins, offering a promising avenue in the ongoing battle against antibiotic-resistant bacteria.