Biomolecular design through latent reasoning with RFD4-Proteina
Year: 2026
Type: preprint
Abstract: Biomolecular design requires finding chemically and geometrically compatible arrangements of interacting atoms and molecules. The complexity of problems which can be tackled by deep learning design models is limited by both the molecular landscape they encompass and their ability to explore that landscape effectively. Here we introduce RFD4-Proteina, which addresses these limitations through intrinsic and extrinsic reasoning within a shared chemical and conformational latent space. The latent space encompasses standard and modified amino acids, sugars, DNA, and RNA, with force-field supervision favoring physically plausible atomic reconstructions. Within this space, intrinsic reasoning uses recurrent refinement to adaptively allocate computation, while extrinsic reasoning guides search with arbitrary constraints such as energetic or geometric criteria. Across in silico protein design benchmarks, RFD4-Proteina achieves higher design success rates at greater generation throughput than all previous methods evaluated, with further gains from conformational flexibility, recurrent refinement, and search. The same model performs equivalently to or better than state-of-the-art specialist methods for side-chain packing, sequence design, conformational sampling, and design refinement. We demonstrate the power and versatility of RFD4-Proteina experimentally by designing specific and cross-reactive binders to therapeutically relevant targets, recognizing phosphorylations, controlling glycosylation, and creating enzymes that catalyze both bond-breaking and bond-forming reactions, including a first proof-of-concept demonstration of a de novo designed enzyme for active pharmaceutical ingredient synthesis. By unifying diverse chemistry, conformational flexibility, and scalable reasoning in a single physically grounded latent space, RFD4-Proteina expands the frontier of biomolecular design.
Authors: Nathaniel Corley, Kieran Didi, Maxwell W. Kazman, Rafael I. Brent, Magnus S. Bauer, Riti Biswas, Julia E. Bonzanini, Adam M. Chazin-Gray, Jie Chen, Andrew Favor, Maximilian Gantz, Henry A. Jones, Paul Kim, Margaret C. Lunn-Halbert, Nora K. McNamara-Bordewick, Saman Salike, DeJenae L. See, Shajesh Sharma, Eric Sun, Preetham Venkatesh, Seth M. Woodbury, Kejia Wu, Yuyang Zhang, Joel D. Allen, Jasper Butcher, Lemuel Chang, Yehlin Cho, Alexis Courbet, Brian Coventry, Christian Dallago, Elliot S. Delfosse, Helen E. Eisenach, Mariana Garcia Sanchez, Tomas Geffner, Inna Goreshnik, Per Greisen, Andrew C. Hunt, David E. Kim, Donghyo Kim, Brianne R. King, Rohith Krishna, Yanjing Li, Zi Ming Li, Aiko Muraishi, Edin Muratspahic, Oliver Nagl, Griffin H. Rangel, Antonia Ruder, Hojeong Shin, Zefei Xu, Yuwei Yang, Max Crispin, Neil P. King, Frank DiMaio, Gaurav Bhardwaj, Michael Bronstein, Karsten Kreis, Donald Hilvert, Anthony P. Green, Arash Vahdat, David Baker
Institutions: University of Washington, University of Oxford, Nvidia (United States), Max Planck Institute for Terrestrial Microbiology, University of Manchester, Howard Hughes Medical Institute, Tsinghua University, University of Southampton, Duke University, ETH Zurich, Austrian Academy of Sciences, AITHYRA GmbH- Research Institute for Biomedical Artificial Intelligence (Austria), Laboratory of Organic Chemistry
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W7233594777
Cites:
Cited by:
Related to:
