Ginkgo Datapoints and Apheris have launched an antibody developability consortium with AbbVie, argenx, Lundbeck and Takeda as founding members. The group plans to assemble a standardized dataset of 10,000 antibodies and use it to train models that assess potential manufacturing and development difficulties.
Each pharmaceutical member will contribute proprietary antibody sequences. Ginkgo Datapoints, part of Ginkgo Bioworks, will use publicly available sequences to fill any remaining capacity needed to reach the target. The consortium aims to give participants access to a more diverse dataset than individual companies may hold.
Ginkgo will design the sequence selection process, oversee antibody production and conduct laboratory tests of properties relevant to developability. It will also train a model using the resulting data.
Apheris will provide infrastructure that lets members train, test and refine models using the consortium dataset without exposing their raw proprietary sequences to other members. Companies will retain ownership of the sequences and assay data they contribute and can adapt the models using their own data.
The consortium expects to deliver an initial dataset to members by early 2027. It remains open to additional pharmaceutical and biotechnology companies and may later expand its work to more complex antibody formats.
Charlotte Deane, a professor at the University of Oxford, and Peter Tessier, a professor at the University of Michigan, will provide independent scientific oversight.
Subscribe to our e-Newsletters
Stay up to date with the latest news, articles, and events. Plus, get special offers
from American Pharmaceutical Review – all delivered right to your inbox!
Sign up now!