Biotech Firms Launched Antibody Developability Consortium
Companies have united to build a 10,000-antibody dataset using Apheris infrastructure and Ginkgo Datapoints technology.
Updated on Sept. 29, 2026 in Biotech
Live Poll
Do you support pharmaceutical companies sharing private research data to improve AI drug development?
Apheris and Ginkgo Datapoints have launched the Antibody Developability Consortium to create a standardized dataset of 10,000 antibodies. Founding members AbbVie, argenx, Lundbeck, and Takeda will contribute proprietary sequences to train AI models while maintaining data ownership.
Why it matters
Current predictive models for drug development often struggle due to data that is fragmented and inconsistent. This consortium aims to overcome these technical hurdles by using federated infrastructure to pool resources safely.
The project aims to compile a massive database of 10,000 antibodies to power AI-driven drug discovery. Ginkgo Datapoints will manage high-throughput wet-lab characterization, while Apheris provides the federated infrastructure for privacy-preserving data access.
The players
AbbVie
This global biopharmaceutical company is a founding member of the new consortium.
Apheris
The company provides the federated infrastructure necessary for training AI models on private data.
Ginkgo Datapoints
This entity oversees antibody production and high-throughput wet-lab characterization for the project.
Charlotte Deane
She serves as one of two primary figures providing independent scientific oversight for the project.
Peter Tessier
He provides independent scientific oversight for the antibody consortium project.
The details
Participating pharmaceutical companies retain full ownership of their contributed proprietary data while benefiting from the collective intelligence of the shared network. Independent scientific oversight is provided by Charlotte Deane and Peter Tessier to ensure rigorous standards throughout the production and analysis phases.
Timeline
The Antibody Developability Consortium officially launched on September 29, 2026.
The consortium expects to deliver its initial dataset to members by early 2027.
The Tech Race
This effort represents a significant shift from siloed research toward collaborative AI-training environments in the life sciences. It mirrors the broader industry trend of adopting the federated learning framework for biomedical data to overcome historical barriers to drug discovery.
While not a consumer-facing tool, the project aims to accelerate the timeline for bringing next-generation therapeutics to market. By creating more accurate predictive models, researchers hope to reduce the failures often seen in early-stage drug development.
The takeaway
Collaborative data-sharing initiatives are increasingly becoming the standard for solving complex biological problems that exceed the capacity of individual firms. Researchers and industry stakeholders can anticipate higher-quality predictive models as these large-scale dataset projects reach maturity.
What happens next
The consortium plans to deliver the initial 10,000-antibody dataset to its founding members in early 2027.
Further reading
Explore the latest industry developments in Biotech.
Source note: This article includes information reported by Tech.
Live Poll
Do you support pharmaceutical companies sharing private research data to improve AI drug development?
