Seattle biotech startup A-Alpha Bio raised $22.4 million to boost development of its machine learning platform that analyzes protein-protein interactions.
A-Alpha Bio, a spinout of the Institute for Protein Design at the University of Washington, combines computational tools with yeast experiments to identify potentially therapeutic proteins. It partners with drug companies to help them find the best agents to test on a range of conditions.
The startup has inked a number of partnerships: with Bristol Myers Squibb for protein interaction research; with Lawrence Livermore National Laboratory for antibody development in biothreats; and with Gilead Sciences for HIV therapeutic exploration.
A-Alpha Bio is among a growing flock of startups using AI as a tool to help scientists forge proteins into drugs, industrial enzymes, biosensors, food products and more.
The startup is betting that AI will “fundamentally improve” the speed and quality in which therapeutics are developed, giving an advantage to healthcare companies with access to proprietary datasets, CEO David Younger told GeekWire.
A-Alpha Bio holds a database of almost 500 million protein-protein interaction measurements.
Its technology relies on 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.
A-Alpha Bio’s computational tools, AlphaSeq and AlphaBind, work together to measure and analyze protein-protein interactions. AlphaSeq uses genetic engineering and DNA sequencing to generate its massive dataset. This feeds into AlphaBind, which uses machine learning to predict new protein sequences with desired binding properties.
“Machine learning successes across the industry (like AlphaFold) are valuable proof-points for the power of machine learning applied to biological problems and drive considerable interest into companies like ours,” Younger said. “Additionally, we benefit from advances in machine learning — as many of the techniques used by others (large language models, etc.) can also be applied to biological data.”
Younger said the Series A extension will help the company capitalize on “significant growth” and provide additional runway to hit certain milestones before raising more funding.
The startup was co-founded in 2017 by Younger and CTO Randolph Lopez, using the technology they helped to develop while graduate researchers at the UW.
A-Alpha Bio employs 45 people, up from 13 during its $20 million Series A round in 2021. Despite a funding slowdown pushing many other digital health companies to reduce staff, A-Alpha has avoided layoffs, Younger said.
The extended Series A was led by existing investor Perceptive Xontogeny Ventures, with participation from Madrona Venture Group and other previous backers. New investor Breakout Ventures joined the round, and its managing director, Lindy Fishburne, will serve as an observer on A-Alpha’s board.
The startup previously raised non-dilutive capital from The Bill and Melinda Gates Foundation, National Science Foundation, and the Joint Program Executive Office for Chemical, Biological, Radiological and Nuclear Defense. Total funding to date is $51 million.
