A team of researchers at the University of Washington has used artificial intelligence (AI) to design synthetic proteins that neutralise lethal snake venom faster, more effectively, and at a lower cost than traditional anti-venom, according to Nvidia. Led by computational biologist Susana Vazquez Torres in Nobel laureate David Baker's lab, the team developed these proteins using deep learning models. Their study, published in Nature, demonstrates that AI-designed proteins successfully protected animals from fatal venom toxins in laboratory tests.
Also Read: AI Designed for Speech Recognition Deciphers Earthquake Signals
AI’s Role in Snakebite Treatment
"For over a century, anti-venom production has relied on animal immunisation, requiring thousands of snake milkings and plasma extractions. Torres and her team hope to replace this with AI-driven protein design, compressing years of work into weeks," Nvidia said in a blog post on February 7, 2025.
Faster, Cheaper, and More Effective
Using Nvidia Ampere architecture and L40 GPUs, and deep learning models like RFdiffusion and ProteinMPNN, the Baker Lab generated millions of potential antitoxin structures 'in silico,' or in computer simulations. Instead of screening a vast number of these proteins in a lab, they used AI tools to predict how the designer proteins would interact with snake venom toxins, rapidly homing in on the most promising designs, Nvidia explained.
Also Read: Nvidia and Partners Develop AI Model to Predict Future Glucose Levels in Individuals
The researchers created proteins that bind tightly to deadly three-finger toxins (3FTx), neutralising their effects. Lab tests confirmed their stability, and mouse studies showed an 80-100 percent survival rate after exposure to lethal neurotoxins. Unlike conventional anti-venom, these AI-designed proteins were small, heat-resistant, and easy to manufacture without cold storage.
Snakebites kill over 100,000 people annually, with another 300,000 suffering severe injuries, particularly in rural communities in Africa, South Asia, and Latin America. Many victims cannot afford or access traditional antivenom, pushing families deeper into poverty.
"Unlike traditional antivenoms, which cost hundreds of dollars per dose, it may be possible to mass-produce these AI-designed proteins at low cost, making life-saving treatment available where it’s needed most," Nvidia said.
Also Read: Nvidia Accelerates AI Integration in Medical Imaging with MONAI
AI's Potential in Drug Development
"This research isn't just about snakebites. The same AI-driven approach could be used to design precision treatments for viral infections, autoimmune diseases and other hard-to-treat conditions, according to the researchers. By replacing trial-and-error drug development with algorithmic precision, researchers using AI to design proteins are working to make life-saving medicines more affordable and accessible worldwide," the blog post emphasised.
Clinical Trials and Mass Production
Torres and her collaborators — including researchers from the Technical University of Denmark, University of Northern Colorado and Liverpool School of Tropical Medicine — are now working to advance these proteins toward clinical trials and large-scale production. "If successful, this AI-driven advancement could save lives, and uplift families and communities around the world," Nvidia concluded.
