Ginkgo Datapoints and Apheris Welcome AbbVie, argenx, Lundbeck, and Takeda as Founding Members of the Antibody Developability Consortium
The Antibody Developability Consortium has launched with founding members AbbVie, argenx, Lundbeck, and Takeda. Together they are building the field's largest standardized antibody developability dataset: 10,000 antibodies plus a foundation model, delivered through Apheris' federated infrastructure.
Ginkgo Datapoints and Apheris have announced the launch of the Antibody Developability Consortium, an industry collaboration that helps pharma and biotech teams spot manufacturability and developability risks earlier. The founding members are AbbVie, argenx, Lundbeck, and Takeda, and the consortium remains open to additional members.
Why it matters
Today's predictive models are held back by small, fragmented, and inconsistent datasets. The consortium closes that gap with a purpose-built, standardized, diverse training set and the AI models trained on it.
How it works
- 10,000 antibodies: each member contributes proprietary sequences, and Ginkgo fills the remaining capacity from public sources.
- One lab, one standard: Ginkgo Datapoints designs the sequence selection, oversees production, and runs high-throughput characterization across core developability endpoints.
- Foundation model: Ginkgo trains a foundation developability model inside Apheris' secure environment.
- Federated fine-tuning: Apheris delivers that model into each member's environment for fine-tuning on proprietary data. No raw sequences are exposed to other members, and each member keeps ownership of the sequences and assay data it contributes.
- Timeline: the initial dataset is targeted for delivery to members by early 2027.
What they're saying
"We are building the largest, most standardized antibody developability dataset the industry has ever seen, along with the predictive models trained on it." — Rich Cohen, Senior Director, Ginkgo Datapoints
"For AI to impact developability decisions in a drug program, it has to perform on a pharma's own molecules." — Robin Röhm, CEO and co-founder, Apheris
"Pooling standardized developability data across the industry can create stronger predictive models than any one company could build alone." — Yves Fomekong Nanfack, Head of AI/ML Research, Takeda
Read the full press release on Business Wire
Interested in joining? Contact us.