A-Alpha Bio Announces Industry-First Data Consortium to Solve AI Protein Engineering's Experimental Data Bottleneck. Founding members include GSK, Boltz, Cradle, and Dyno Therapeutics.
Consortium members will steer the experimental design with A-Alpha Bio to generate the large-scale, standardized antibody-antigen affinity and structural datasets needed to advance AI antibody engineering.
Seattle, WA, July 22, 2026 (GLOBE NEWSWIRE) -- A-Alpha Bio, a synthetic biology and machine learning biotechnology company that measures and engineers protein-protein interactions, today announced the founding members of its Atlas Consortium: an industry-first collaborative model for generating and sharing standardized experimental antibody-antigen data. The Atlas Consortium launches with five founding members, including GSK, Boltz, Cradle, and Dyno Therapeutics.
The founding members bring together organizations from across the AI-enabled drug discovery landscape: a global pharmaceutical leader, a genetic biotechnology company and two prominent model builders in AI-driven antibody design and optimization. In a field where experimental data is among the most closely guarded assets, the participation of such diverse teams reflects broad interest in a new cooperative model for generating experimental structural and affinity data that meet the needs of modern AI workflows.
"The next generation of AI-enabled drug discovery depends on training models with experimental data at a quality and a scale that does not currently exist,” said Christopher Austin, MD, SVP of R&D Technologies at GSK. “This data Consortium provides a first-of-its-kind solution to help remove this bottleneck and thus potentially accelerate protein discovery at GSK and boost innovation and collaboration across the industry.”
Until now, most collaborative initiatives around data have focused on federated learning, allowing organizations to improve shared AI models while keeping their underlying data private. The Atlas Consortium introduces a fundamentally different approach: through a subscription, members design new experimental datasets every quarter that are purpose built to address major objectives for AI-driven antibody engineering, including generalizable models for de novo design and zero-shot optimization.
Datasets are generated by A-Alpha Bio under standard conditions through its AlphaSeq platform. All data generated in the Consortium, including A-Alpha Bio’s own contributed designs, are pooled and released quarterly, giving every member millions of highly interoperable data points for training and benchmarking models. Members will help to shape future datasets designed by A-Alpha Bio through collaborative development of a data roadmap focused on major industry challenges. Current roadmap datasets include the generation of highly diverse antibody-antigen structural data for de novo design, as well as the generation of affinity landscapes for accelerating zero-shot antibody optimization.
"The next wave of protein foundation models requires experimental datasets that are not only larger, but also consistently generated and quantitatively comparable,” said Gabriele Corso, PhD, Co-Founder and CEO of Boltz. “Access to abundant and high-quality structural and affinity data, as we develop our models, lets us push de novo antibody design forward faster.”
“Building better AI for protein engineering requires experimental data that spans the full design lifecycle—from hit ID through preclinical readiness," said Stef van Grieken, Co-Founder and CEO of Cradle. "High-quality, quantitative affinity datasets help models learn the principles that govern molecular function, enabling scientists to design and engineer better therapeutic proteins at every stage of development."
One of the defining advantages of the Atlas Consortium is that every new member increases the value of participation for every existing member. As organizations contribute new experimental designs, the collective dataset expands in both breadth and diversity. At launch, with five founding members, each member will receive approximately 28 million affinity measurements per year; as the Consortium grows to 20 members, that number will increase to 100 million measurements annually.
“Better data and better models make it faster and cheaper for our partners to develop the transformative therapies patients most need," said Eric Kelsic, PhD, Co-Founder and CEO of Dyno Therapeutics. “The Atlas Consortium’s datasets compound in scale and value with every experiment and every new member, creating a shared resource no single organization could build alone. This collaborative approach accelerates our work building AI technologies that bring genetic agency within reach for every patient.”
“We see our Atlas Consortia as a unique and economical way to generate and distribute the quantity and quality of data required to accelerate AI-enabled protein engineering," said David Younger, PhD, Co-Founder and CEO of A-Alpha Bio. "We’re excited to see organizations who approach industry challenges from very different perspectives all come together around a shared vision, and equally excited to see what they will do with an abundance of data at their fingertips.”
The Atlas Consortium is part of A-Alpha Bio’s broader Atlas ecosystem of scalable affinity and structural data. To learn more, visit atlas.aalphabio.com
About A-Alpha Bio
A-Alpha Bio is a biotechnology platform company that measures, predicts, and engineers protein-protein interactions at scale. Its experimental platform, AlphaSeq, enables the rapid and quantitative measurement of millions of protein-protein binding affinities simultaneously. Its AI platform, AlphaBind, is trained on the world’s largest protein-protein interaction database and predicts binding strength from sequence. A-Alpha Bio works with pharmaceutical and biotechnology companies through both strategic partnerships and streamlined services, leveraging AlphaSeq and AlphaBind to engineer next-generation dual-specific and molecular glue therapeutics, discover and optimize differentiated biologics, and generate protein binding and structural data at scale to power AI models. A-Alpha Bio is based in Seattle and was founded in 2017 at the University of Washington’s Institute for Protein Design. To learn more, please visit: https://www.aalphabio.com/
Media Contact:
Drew Duglan
Director, Scientific Communications, A-Alpha Bio
858-247-9110
Doug Freeman Jones-Dilworth, Inc 512-826-7674 doug@jones-dilworth.com
Legal Disclaimer:
EIN Presswire provides this news content "as is" without warranty of any kind. We do not accept any responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this article. If you have any complaints or copyright issues related to this article, kindly contact the author above.
