AI Opens Door to Safe, Effective New Antibiotics to Combat Resistant Bacteria

In a hopeful sign for demand for more safe, effective antibiotics for humans, researchers at The University of Texas at Austin have leveraged artificial intelligence (AI) to develop a new drug that already is showing promise in animal trials.

Publishing their results in Nature Biomedical Engineering, the scientists describe using a large language model - an AI tool like the one that powers ChatGPT - to engineer a version of a bacteria-killing drug that was previously toxic in humans, so that it would be safe to use.

The prognosis for patients with dangerous bacterial infections has worsened in recent years as antibiotic-resistant bacterial strains spread and the development of new treatment options has stalled. However, UT researchers say AI tools are game-changing.

"We have found that large language models are a major step forward for machine learning applications in protein and peptide engineering," said Claus Wilke, professor of integrative biology and statistics and data sciences, and co-senior author of the new paper. "Many use cases that weren't feasible with prior approaches are now starting to work. I foresee that these and similar approaches are going to be used widely for developing therapeutics or drugs going forward."

Large language models, or LLMs, were originally designed to generate and explore sequences of text, but scientists are finding creative ways to apply these models to other domains. For example, just as sentences are made up of sequences of words, proteins are made up of sequences of amino acids. LLMs cluster together words that share common attributes (such as cat, dog and hamster) in what’s known as an “embedding space” with thousands of dimensions. Similarly, proteins with similar functions, like the ability to fight off dangerous bacteria without hurting the people who host said bacteria, may cluster together in their own version of an AI embedding space.

"The space containing all molecules is enormous," said Davies, co-senior author of the new paper. "Machine learning allows us to find the areas of chemical space that have the properties we're interested in, and it can do it so much more quickly and thoroughly than standard one-at-a-time lab approaches."

For this project, the researchers employed AI to identify ways to reengineer an existing antibiotic called Protegrin-1 that is great at killing bacteria, but toxic to people. Protegrin-1, which is naturally produced by pigs to combat infections, is part of a subtype of antibiotics called antimicrobial peptides (AMPs). AMPs generally kill bacteria directly by disrupting cell membranes, but many target both bacterial and human cell membranes.

First, the researchers used a high-throughput method they had previously developed to create more than 7,000 variations of Protegrin-1 and quickly identify areas of the AMP which could be modified without losing its antibiotic activity.

Next, they trained a protein LLM on these results so that the model could evaluate millions of possible variations for three features: selectively targeting bacterial membranes, potently killing bacteria and not harming human red blood cells to find those that fell in the sweet spot of all three. The model then helped guide the team to a safer, more effective version of Protegrin-1, which they dubbed bacterially selective Protegrin-1.2 (bsPG-1.2).

Mice infected with multidrug-resistant bacteria and treated with bsPG-1.2 were much less likely to have detectable bacteria in their organs six hours after infection, compared to untreated mice. If further testing offers similarly positive results, the researchers hope eventually to take a version of the AI-informed antibiotic drug into human trials.

"Machine learning's impact is twofold," Davies said. "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."

This project highlights how academic researchers are advancing artificial intelligence to meet societal needs, a key theme this year at UT Austin, which has declared 2024 the Year of AI.

The study's other authors are research associate Justin Randall and graduate student Luiz Vieira, both at UT Austin.

Funding for this research was provided by the National Institutes of Health, The Welch Foundation, the Defense Threat Reduction Agency and Tito's Handmade Vodka.

Randall JR, Vieira LC, Wilke CO, Davies BW.
Deep mutational scanning and machine learning for the analysis of antimicrobial-peptide features driving membrane selectivity.
Nat Biomed Eng. 2024 Jul 31. doi: 10.1038/s41551-024-01243-1

Most Popular Now

Most Advanced Artificial Touch for Brain…

For the first time ever, a complex sense of touch for individuals living with spinal cord injuries is a step closer to reality. A new study published in Science, paves...

From Text to Structured Information Secu…

Artificial intelligence (AI) and above all large language models (LLMs), which also form the basis for ChatGPT, are increasingly in demand in hospitals. However, patient data must always be protected...

Deep Learning Model Helps Detect Lung Tu…

A new deep learning model shows promise in detecting and segmenting lung tumors, according to a study published in Radiology, a journal of the Radiological Society of North America (RSNA)...

New Study Reveals AI's Transformati…

Intensive care units (ICUs) face mounting pressure to effectively manage resources while delivering optimal patient care. Groundbreaking research published in the INFORMS journal Information Systems Research highlights how a novel...

One of the Largest Global Surveys of Soc…

As leaders gather for the World Economic Forum Annual Meeting 2025 in Davos, Leaps by Bayer, the impact investing arm of Bayer, and Boston Consulting Group (BCG) announced the launch...

New Computer Models Open Door to Far Mor…

With antibiotic resistance a growing problem, University of Virginia School of Medicine researchers have developed cutting-edge computer models that could give the disease-fighting drugs a laser-like precision to target only...

New Biomarkers to Detect Colorectal Canc…

Machine learning and artificial intelligence (AI) techniques and analysis of large datasets have helped University of Birmingham researchers to discover proteins that have strong predictive potential for colorectal cancer. In a...

Sam Neville Joins the Highland Marketing…

Leading chief nursing information officer Sam Neville is joining the Highland Marketing advisory board. Sam brings a passion for nursing and safety to the board, which debates the big issues...

AI Model Identifies Potential Risk Genes…

Researchers from the Cleveland Clinic Genome Center have successfully applied advanced artificial intelligence (AI) genetics models to Parkinson's disease. Researchers identified genetic factors in progression and FDA-approved drugs that can...

AI Tool that may Assist Underserved Hosp…

As the fields of healthcare and technology increasingly evolve and intersect, researchers are collaborating on the best ways to use emerging technologies such as artificial intelligence (AI) to care for...

AI-Supported Breast Cancer Screening - N…

The new findings are published in The Lancet Digital Health. The initial results of the Mammography Screening with Artificial Intelligence (MASAI) study* - a randomised trial to evaluate whether AI...

AI Improves Personalized Cancer Treatmen…

Personalized medicine aims to tailor treatments to individual patients. Until now, this has been done using a small number of parameters to predict the course of a disease. However, these...