ARPA-H Funds $28.6 Million AI Protein Research Project

Oct 12, 2026
The NATIVE-ID project will combine AI, cell experiments and protein data to predict harmful changes linked to neurodegenerative diseases.
ARPA-H Funds $28.6 Million AI Protein Research Project

ARPA-H will provide up to $28.6 million for a research project that uses AI to predict protein changes linked to neurodegenerative diseases, the Stowers Institute said in a press release. The NATIVE-ID project is led by the Innovative Genomics Institute at the University of California, Berkeley.

Randal Halfmann's laboratory at the Stowers Institute for Medical Research will receive about $4.1 million over two years. The lab plans to produce more than 10 billion measurements of protein aggregation across 50,000 proteins and more than 1 million samples. Researchers will use the data to train AI models to predict how disordered proteins change shape and clump together.

The team will initially study frontotemporal lobar degeneration, which shares genetic and biological features with ALS. Other participants include Brown University, Emory University, Johns Hopkins University, Parallel Squared Technology Institute and Texas A&M University. The first two year phase will focus on datasets and models, while a planned second phase will test possible treatments and methods for detecting protein dysfunction earlier.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Life AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Life AI Weekly

Weekly coverage of AI applications in healthcare, drug development, biotechnology research, and genomics breakthroughs.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.