When it comes to responding to global emergencies like pandemics or biothreats, speed is critical.

A new artificial intelligence project from the Defense Advanced Research Projects Agency (DARPA) could transform how the world prepares for such crises.

Abhishek Singharoy, an associate professor in Arizona State University’s School of Molecular Sciences, is currently on special assignment with DARPA, where he is leading the development of NODES (Network of Optimal Dynamic Energy Signatures) an AI platform designed to predict the function of every known protein in about an hour.

NODES blends physics with advanced AI to study how proteins the molecules that drive disease spread and shape immune responses — move and shift their form. While scientists have mapped the sequence and structure of hundreds of millions of proteins, only a fraction of their functions are understood. By focusing on proteins in motion rather than static structures, NODES can generate high-confidence predictions about what these proteins actually do.

“If successful, NODES will revolutionize our ability to evaluate threats from new and unknown protein sequences,” said Singharoy, who also serves as an associate faculty member at ASU’s Biodesign Center for Applied Structural Discovery. “It will speed up the translation of scientific discoveries into real-world solutions, deepen our understanding of complex diseases, bolster defenses against infections and biothreats, and ultimately, save lives.”

Advancing speed and precision
Traditional computational models rely on static protein snapshots, which limits accuracy and restricts analysis to small datasets. NODES changes the game by capturing protein motion, scaling up processing power, and evaluating roughly 300 million proteins in just one hour  with more than 90% confidence.

Put simply, current models are like trying to understand a movie from a single still frame. NODES, in contrast, watches the entire film at high speed showing scientists how proteins move and interact and does so for hundreds of millions of proteins in record time.

“Abhishek’s work is a perfect example of the cutting-edge, interdisciplinary research we champion at the School of Molecular Sciences,” said Tijana Rajh, professor and director of the school. “By combining scientific expertise with AI, his team is expanding the frontiers of discovery and advancing human health.”

With its speed and scale, NODES could be vital in crises from identifying biothreats to rapidly responding to emerging infectious diseases. It also has potential to reduce risks in biotechnology, accelerate drug discovery, and unlock treatments for complex conditions.

“For me, having this program supported by DARPA reflects not just my own work, but the collaboration and inspiration from colleagues at ASU and beyond,” said Singharoy. “It’s a reminder of why innovation matters and a motivation to keep pursuing advances in molecular biophysics that can truly protect lives.”

Source: https://news.asu.edu/20250925-science-and-technology-ai-program-could-help-guard-against-pandemics-and-biowarfare