DAVIS, California–(BUSINESS WIRE)–A number of leading academic and industry partners announce the creation of: Unfold, a non-profit artificial intelligence (AI) research consortium of organizations with the goal of developing free and open source software tools for biology and drug discovery. OpenFold is a project of the Open Molecular Software Foundation (OMSF), a nonprofit organization that advances molecular sciences by building communities for the development of open source research software.
The founding members of OpenFold are the Columbia University Laboratory of Mohammed AlQuraishi, Ph.D.† Arzeda† Cyrus Biotechnology† Genentech’s forward-looking designand Exceed Organic† The consortium, whose membership is open to other organizations, is hosted by OMSF and supported by Amazon Web Services (AWS) as part of the AWS Open Data Sponsorship Program† OMSF also organizes OpenFreeEnergy and OpenForceField†
Brian Weitzner, Ph.D. Associate Director of Computational and Structural Biology at Outpace and co-founder of OpenFold said, “In biology, structure and function are inextricably linked, so a deep understanding of structure is required to elucidate molecular mechanisms and develop biological systems. We believe that open collaboration and access to powerful AI-powered structural biology tools will transform biotechnology and life sciences by enabling researchers and educators from life science companies, technology companies and academia to access the use and extending these tools to accelerate discovery and develop life-changing technologies.”
The first major area of research for the consortium is to create advanced AI-based protein modeling tools that can predict molecular structures with atomic accuracy. The OpenFold consortium is modeled after open source consortia in the precompetitive technology industry, such as: Linux and OpenAI†
First consortium-released AI model to predict protein structure, with impressive results
The founders of OpenFold also officially announced today the full release of their first AI model for predicting protein structure, developed in the lab of Dr. AlQuraishi, first publicly recognized on Twitter on June 22, 2022† The model is based on groundbreaking work at Google DeepMind and the Institute for Protein Design at the University of Washington. The software is available under a free and open source license from The Apache Software Foundation Bee https://github.com/aqlaboratory/openfold† Training data can be found on the Register of Open Data on AWS† A formal preprint and publication will follow.
Yih-En Andrew Ban, Ph.D., VP of Computing at Arzeda and co-founder of OpenFold said, “This first OpenFold AI model is already producing highly accurate predictions of protein crystal structures as benchmarked on the Continuous Automated Model Evaluation (CAMEO)and delivered on average higher accuracy and faster run times than DeepMind AlphaFold2† An example output from OpenFold, with comparison to experimental data, is included in the figure.
CAMEO is a project developed by the protein structure prediction scientific community to evaluate the accuracy and reliability of predictions.
Lucas Nivon, Ph.D., CEO at Cyrus and co-founder of OpenFold, said, “The initial release of the OpenFold software includes not only inference code and model parameters, but full training code, a complete package that has not been released by any other entity in space. It will make it possible to train a full set of derivative models for specialized use in drug discovery from biologics, small molecules and other modalities.”
Researchers around the world will be able to use, improve and contribute to what the consortium founders describe as their “predictive molecular microscope.” Current and future work will extend these derived models to integrate with other software in the field and to be more specific for protein design and biologic drug discovery.
Richard Bonneau, Ph.D., Executive Director at Genentech’s Prescient Design said, “OpenFold is a lot for us, a code, a forum, a bunch of great minds to discuss our favorite topics! It’s been a great experience so far and we are very excited to work out the next phases of the roadmap!”
Multiple other corporate and non-profit organizations are currently joining the OpenFold consortium as full members, and the founders are inviting biotech, pharma, technology and other research organizations to join. The consortium is currently evaluating proposals for new AI protein projects from academic groups around the world.
OpenFold is a non-profit artificial intelligence (AI) research consortium of academic and industry partners with the goal of developing free and open source software tools for biology and drug discovery, hosted as an Open Molecular Software Foundation project . For more information, visit: OpenFold Consortium