Overcoming Barriers in Computational Enzyme Design Through Improved Sequence Structure Ensemble Modeling

The Genesis Mission is a national initiative to mobilize government, industry, academia, nonprofits and international partners to advance AI for science and technology. Using the Department of Energy-built American Science and Security Platform, collaborators work together on shared infrastructure that connects researchers with data, compute and AI tools to accelerate scientific discovery. Partners are focusing on the most critical challenges facing our nation in energy, national security, scientific discovery, health, space and more.

Recipients of the Genesis Phase II Awards were notified last week.  One such award, led by the University of Washington is Overcoming Barriers in Computational Enzyme Design: Using SI and advanced X-ray tools to design new enzymes that could help create cleaner chemicals and materials.

The goal of this project is to improve the reliability of AI-generated enzymes by drawing lessons from designs that work as well as those that fail. The researchers will pair AI-driven protein design with high-throughput functional assays and structural biology to assemble extensive datasets that link enzyme sequence, structure, and function. These results will then be used to retrain the AI models to improve successive rounds of design.

The Project Contact at the Advanced Photon Source is Bob Fischetti (GM/CA).  NE-CAT will be acting as a partner along with Velocity Bio Inc. and SLAC National Accelerator Laboratory.