As of 2024, over 40 million people in the world are diagnosed with human immunodeficiency virus (HIV)-a chronic, life-threatening infection that remains one of the leading global causes of death. Even decades after its discovery, HIV continues to take lives and challenge global health systems, in part because scientists haven't been able to quickly determine which experimental vaccine approaches are working due to significant volumes of data.
Scripps Research scientists recently received $1.1 million from the Scripps Consortium for HIV/AIDS Vaccine Development (CHAVD) to purchase high-performance computing equipment to address this global health challenge. The equipment will be used to accelerate the identification of more effective HIV vaccine candidates through enhanced computational infrastructure, reduced data-processing bottlenecks, and state-of-the-art artificial intelligence (AI) technology. Support for CHAVD is provided by the National Institutes of Health.
Over the last 10 years, we've been able to accelerate data generation, but we don't have a good way of analyzing that data to understand if these vaccines are working well. This new AI technology will supercharge our ability to evaluate up to millions of potential vaccine designs in the time it used to take to study a few dozen-bringing us closer to finding more promising vaccine approaches."
Bryan Briney, associate professor at Scripps Research and co-principal investigator on the project
Developing an effective HIV vaccine remains extraordinarily difficult. To work, it must train the immune system to produce antibodies-protective proteins capable of neutralizing more than 90% of HIV strains in more than 90% of people. In other words, it's an exceptionally high bar that no vaccine has yet achieved. The challenge is driven by HIV's remarkable ability to mutate, constantly changing its form and making it difficult for the immune system to recognize and destroy the virus.
The Scripps Research team hopes to eventually develop a long-lasting vaccine that adapts to mutations of the virus and can be delivered in a single dose. In the meantime, however, Briney and the collaborators aim to develop a series of multiple vaccines that adapt to the virus' changes over time. To meet the challenge of protecting against more than 90% of HIV strains, the team needs real-time feedback from clinical trials-data that reveals how the vaccine is performing and informs the design of the next version in the series.
"We're shifting from trial-and-error to smart prediction," says Andrew Ward, professor in the Department of Integrative Structural and Computational Biology and co-principal investigator on the project. "Instead of spending months testing every design idea in the laboratory, we can screen hundreds of thousands of possibilities computationally, identify the best candidates and focus our experimental work where it matters most."
Supercharging science with AI
Ward, Briney and their labs will use the funds to purchase new AI technology that doubles the computational power available at Scripps Research and operates at speeds four-to-five times faster than existing systems. This new computational bandwidth will allow the team to rapidly analyze the antibodies produced by people who receive experimental vaccines in clinical trials and determine if they are on the right track with molecular precision.
"This new resource leverages a ton of hard work and creativity from the scientists in our labs and I am excited to see how far they can extend the technology," says Ward.
When a vaccine is administered, it can train the immune system to produce antibodies that neutralize a broad range of HIV strains-also known as broadly neutralizing antibodies. The team will then evaluate these vaccine-induced antibodies, test multiple scenarios simultaneously, and model how they interact with the virus at the molecular level, all while reducing analysis time from weeks to days. The antibodies identified to work exceptionally well against the virus are known as "antibody candidates," which make up the next iteration of the vaccine. This added processing power will also support the work of other Scripps Research teams working on different aspects of HIV, such as protein engineering-helping drive discovery from multiple angles.
The teams will first train the AI system on historical clinical trial data from previous vaccines to develop a comprehensive computational model that can quickly identify the best antibody candidates. In the lab, researchers often sift through data manually and apply their own thinking to determine which antibody may work best. The AI model, however, has proven to identify promising candidates that the researchers had initially dismissed.
To further develop this AI framework, the group will leverage a method called StepwiseDesign which, like its name implies, mimics how the immune system gradually learns to develop more efficient antibodies through small, optimized iterations.
The approach has already proven remarkably successful: the team used their AI system to analyze about 2,000 antibodies from people who had never been infected with HIV, searching for rare candidates that might have the potential to fight the virus. They discovered an antibody that could actually neutralize HIV-the first time anyone has found such an antibody in an uninfected person. This finding is significant because it demonstrates that some people naturally carry the genetic starting material for broadly protective antibodies, even though they've never encountered HIV.
A successful vaccine would need to activate and train these rare precursor antibodies to mature into full-strength virus fighters. The discovery also validates that this computational approach can identify these extremely rare candidates-essentially finding needles in biological haystacks-which gives scientists confidence the methods will work even better for evaluating antibodies that have already been partially trained by experimental vaccines.
The timing is also ideal: Several HIV vaccine candidates are currently being tested in human trials, producing a flood of new data. With the ability to rapidly analyze these responses and refine follow-up vaccines, researchers could significantly shorten the path to an effective HIV vaccine.
A new model for vaccine development
The implications extend far beyond HIV. Ward and Briney hope that this computational approach could be applied to a variety of challenging vaccine targets, like influenza and malaria.
"This project demonstrates the power of collaboration by combining the expertise at Scripps Research and CHAVD," added Briney. "We hope this project leads to a resource that can be used by HIV researchers around the world-eventually leading to better health outcomes for those living with or who are susceptible to HIV."
T cells drive vaccine effectiveness against porcine reproductive and respiratory syndrome virus