In what stands as a promising development for the production of safe, efficacious antibiotics, a team of researchers at The University of Texas at Austin has harnessed artificial intelligence, specifically a large language model akin to ChatGPT, for the crafting of a drug capable of combating antibiotic-resistant bacteria. The findings, indicating success in animal trials, were published in Nature Biomedical Engineering, as reported by University of Texas News.
Amidst, a backdrop where the emergence of antibiotic-resistant strains has become a pressing concern, and drug development has seen a standstill— the utilization of AI in drug discovery, demonstrates a significant leap forward. Claus Wilke, a professor at UT and a co-senior author of the study, emphasized the potential of these tools, stating, "We have found that large language models are a major step forward for machine learning applications in protein and peptide engineering." Many use cases that weren’t feasible with prior approaches are now starting to work. Wilke predicted an increased reliance on AI for the development of therapeutics moving forward.
The crux of this research lies in the AI's ability to modify an existing antibiotic named Protegrin-1, which is naturally originated in pigs and potent against bacteria but poses toxicity risks to humans. Scientists at UT applied a previously established high-throughput method to generate more than 7,000 variants of the antibiotic, pinpointing segments for potential modification that does not compromise its antibacterial properties.
Subsequently, through the protein LLM, the researchers analyzed millions of permutations analyzing three crucial traits— the tendency to exclusively target bacterial membranes, potency in eradicating bacteria, and, safety with regards to human red blood cells. The endeavor culminated in a refined drug variant, bacterially selective Protegrin-1.2 (bsPG-1.2), which showed substantial efficacy in mice infected with multidrug-resistant bacteria. Bryan Davies, another co-senior author of the paper, articulated the significance of machine learning, stating, "It’s going to point out new molecules that could have potential to help people, and it’s going to show us how we can take those existing antibiotic molecules and make them better and focus our work to more quickly get those to clinical practice."
The advancement portrays an evolving landscape where AI intersects with medical research to address complex health challenges. With the designation of 2024 as the Year of AI by UT, this study is a testament to the university's commitment to leveraging cutting-edge technology in the pursuit of societal benefits. The project also received backing from diverse sources, including the National Institutes of Health, The Welch Foundation, the Defense Threat Reduction Agency, and Tito’s Handmade Vodka, underlining a collective effort toward combating the looming threat of antibiotic resistance.
