The Open Molecular Software Foundation (OMSF) today announced a new research fellowship between the OpenFold Consortium and the University of Washington Institute for Protein Design (IPD). Nobel Laureate David Baker is the Director of the IPD, a professor of biochemistry, and HHMI Investigator at UW Medicine. This fellowship is aimed at accelerating the development of open-source artificial intelligence tools for protein structure prediction and design ultimately to be used for new drug discovery.
The fellowship will support graduate students and postdoctoral scholars in the Baker Lab. With funding from the OpenFold Consortium fellows will focus on creating new state-of-the-art AI models for antibody-antigen design and structure prediction. Following an approach shared by OpenFold and the IPD, all resulting code from this collaboration will be released under permissive licenses for use by researchers and companies worldwide.
“The AI revolution in biology is built on a foundation of openness — researchers sharing data, code, and ideas freely so that others can build on them,” said Baker. “We’re excited to continue this tradition with OpenFold.”
“This collaboration with the Baker Lab marks a defining moment for open biomolecular AI,” said Dr. Woody Sherman, Chair of the OpenFold Consortium Executive Committee and Chief Innovation Officer at PsiThera. “This collaboration brings extraordinary depth across protein design, structure prediction, and large-scale experimental data generation. By building these capabilities as open, shared infrastructure, OpenFold is laying the foundation for a new era of biological discovery where AI models become community resources that accelerate innovation, enable entirely new classes of therapeutics, and deliver impact far beyond what any single organization could achieve.”
As part of this collaboration, the Baker Lab will conduct AI model development. To enhance the longevity and ease-of-use of new software, OpenFold engineers will provide technical support for packaging, documentation, and maintenance. All finished models developed with OMSF fellowship support will be shared publicly under permissive licenses.
