The new Antibody Developability Consortium will pool proprietary data without exposing members’ sequences, aiming to improve predictions of which antibody drugs can make it to the clinic.
Ginkgo Datapoints and Berlin-based Apheris today announced that the Antibody Developability Consortium has kicked off with its founding members.
The Consortium is a new industry collaboration designed to help pharmaceutical and biotech companies predict manufacturability and developability risks earlier by building the field’s largest standardised antibody developability dataset.
Apheris powers the largest federated data networks in drug discovery, used by leading pharmaceutical and biotech companies across domains including co-folding, binding and structure prediction, ADMET, in vivo PK, antibody developability, and virtual cell modelling.
Members provide privacy-preserving access to their proprietary data and, in return, receive higher-performing models with a broader applicability domain. Apheris’ expertise lies in driving the adoption of AI models within pharmaceutical drug programs, customising and fine-tuning them on each company’s proprietary chemistry and biology so they perform where public data cannot reach.
Developability challenges can prevent otherwise promising antibody candidates from progressing efficiently toward patients. Antibody developability encompasses the biophysical properties that influence whether a candidate antibody can be manufactured, formulated, and successfully advanced into a clinical product. Predicting these barriers early could support more informed candidate selection and reduce avoidable development time and investment. However, existing predictive models have been limited by small, fragmented, and inconsistent datasets, while even large internal datasets are constrained in sequence diversity.
The Antibody Developability Consortium was created to address this gap by unifying efforts to produce a standardised, purpose-built, diverse dataset and corresponding AI models at scale.
The founding members of the consortium include AbbVie (United States),argenx (Netherlands), Lundbeck (Denmark), and Takeda (Japan), and it remains open to additional pharmaceutical and biotech companies.
Each founding member will contribute proprietary antibody sequences, with Ginkgo Datapoints filling any remaining capacity from publicly available sources to reach 10,000 antibodies in total.
Using Apheris’s infrastructure, members can train, benchmark, and refine AI models using the full consortium dataset, without raw proprietary sequences being exposed to other members.
The consortium is designed so that members can develop models trained on the full consortium dataset, and apply resulting models and their own fine-tuned derivatives internally while retaining ownership of the proprietary sequences and assay data they contribute.
Ginkgo Datapoints leads the scientific design and execution of the consortium: designing the sequence selection approach, overseeing antibody production, and conducting high-throughput wet-lab characterisation across core developability endpoints.
Ginkgo also trains a foundation antibody developability model on the resulting dataset within Apheris’s secure environment.
Charlotte Deane, Professor of Structural Bioinformatics at the University of Oxford and Peter Tessier, Professor of Pharmaceutical Sciences and Chemical Engineering at the University of Michigan, will provide independent scientific oversight.
Together, the consortium provides pharmaceutical partners with a broader portfolio-level developability capability without having to build the data or infrastructure themselves. The consortium plans to deliver its initial dataset to members by early 2027.
The consortium will also explore adding more complex antibody formats over time to enable new drug classes and other key properties that enable early predictions of which drugs will succeed or fail.
“For AI to impact developability decisions in a drug program, it has to perform on a pharma’s own molecules,” said Robin Röhm, CEO and co-founder of Apheris.
“The Antibody Developability Consortium delivers the largest standardised antibody dataset and the foundation model trained on it. Apheris’ federated infrastructure brings that model to each member and lets them fine-tune it on their proprietary molecules inside their own environment.”
“We are building the largest, most standardised antibody developability dataset the industry has ever seen, along with the predictive models trained on it,” said Rich Cohen, Senior Director at Ginkgo Datapoints.
Lead image: magnific.