NSF Expands Efforts to Advance AI in Protein Design Research

The National Science Foundation (NSF) is seeking to promote further research and innovation in the application of AI in protein design, according to media reports. The NSF hopes that the program will, to some extent, democratize these capabilities, enabling individuals with a need for proteins and specific applications to utilize these tools more easily.

“One of the two areas we're really focusing on is enzymes, because enzymes are a type of protein that are really key to any number of types of chemical reactions that can enable a lot of different applications,” David Tennenhouse, Senior Advisor in the NSF’s Technology, Innovation, and Partnerships Directorate, told the media. 

Through deep learning and predictive modeling, AI algorithms expedite protein structure prediction, protein-protein interactions, and drug design.

This accelerates drug discovery, enhances therapeutic efficacy, and advances fields like personalized medicine, bolstering healthcare and biotechnological innovation.

In February, NSF announced a new funding opportunity worth US$ 40 million aimed at expediting the translation of AI-driven methods into protein design.

This initiative, titled Use-Inspired Acceleration of Protein Design (USPRD), aims to propel advancements in protein design, particularly focusing on enzyme design, over the next three years.

Earlier this year, the NSF also partnered with AI companies such as NVIDIA, OpenAI, and Google, among others, to launch the National Artificial Intelligence Research Resource (NAIRR) pilot program.

Other big names joining the NAIRR pilot include Microsoft, IBM, Amazon, Intel, Anthropic, Hugging Face, IBM Meta and Palantir. Also, federal agencies such as the Defense Advanced Research Projects Agency (DARPA), National Aeronautics and Space Administration (NASA), National Institutes of Health (NIH) and National Institute of Standards and Technology (NIST), among others are part of the pilot.