A researcher at A-Alpha Bio. (A-Alpha Bio Photo)

A-Alpha Bio will receive $14.5 million from the Department of Defense (DOD) to expand a project with a national lab to help prepare for future biological threats using the company’s machine learning tools.

The partnership brings together A-Alpha Bio, a Seattle-based spinout of the Institute for Protein Design at the University of Washington, and the federally funded Lawrence Livermore National Laboratory (LLNL), with support from the DOD.

The project is generating data and training computational models preemptively so that they’re primed and ready for a rapid response when a future disease or other biothreat emerges. The effort began in response to the devastating impacts of the COVID-19 pandemic.

A-Alpha Bio’s technology offers a systematic approach powered by machine learning for the discovery of new antibodies that fight disease. It uses pools of single-celled yeast engineered to express various proteins or protein fragments. When two proteins interact, the yeast fuse and the interacting proteins are identified using experimental and computational methods. The approach can identify protein interactions such as an antibody sticking tightly to a viral protein.

Researchers at A-Alpha Bio working at the bench. (A-Alpha Bio Photo)

The project with LLNL initially focused on coronaviruses, and then added other specific pathogen families of concern. Through the effort, A-Alpha Bio’s AlphaSeq platform has been used to measure the interactions between nearly 10 million antibody-antigen combinations across three pathogen families, leading to improvements in machine learning models.

A-Alpha Bio received $1 million for this work from LLNL in 2022, and last year DOD provided $2.4 million for the project. Both tranches of defense dollars are from the DOD Joint Program Executive Office for Chemical, Biological, Radiological and Nuclear Defense’s Generative Unconstrained Intelligent Drug Engineering (GUIDE) program.

“The past two years of collaboration with LLNL on the GUIDE program have seen remarkable success in training predictive machine learning models with high-throughput antibody-antigen binding data, and we are excited to expand our partnership,” said Randolph Lopez, A-Alpha Bio’s chief technical officer, in a statement.

A-Alpha Bio launched in 2017 and has raised a total of $65.5 million, which includes the new DOD funding, roughly $46 million from investors, and grant dollars. The startup has partnerships with drug companies including Bristol Myers Squibb and Gilead Sciences.

Like what you're reading? Subscribe to GeekWire's free newsletters to catch every headline

Job Listings on GeekWork

Find more jobs on GeekWork. Employers, post a job here.