RNA design has been hindered by the limited accuracy of three-dimensional (3D) structure prediction. In this study, we show that intricate RNA structures can be generated with current deep learning tools through accurate de novo design of pseudoknot secondary structures. In an Eterna competition involving 57 pseudoknots, generative artificial intelligence (AI) methods matched experienced human designers in solving most blind challenges, evaluated by single nucleotide-resolution chemical mapping, compensatory mutagenesis, and cryo-electron microscopy. AI-generated molecules with accurate secondary structures formed well-ordered 3D folds stabilized by noncanonical tertiary interactions not modeled during design. Success was guided by an RNet foundation model trained on prior chemical mapping data, suggesting that some difficult RNA design tasks may be tractable without first solving RNA 3D structure prediction.
J. Townley, W. Kladwang, David Baker et al.· Science· 1 citation
Protein kinases are critical regulators of cellular signaling, but precise modulation of their activity remains challenging due to their high structural conservation. Here, we present de novo designed genetically encoded miniproteins capable of activating or inhibiting focal adhesion kinase (FAK) by directly targeting the kinase domain itself. Among 96 binders designed to stabilize distinct conformational states of FAK, 33 modulated kinase activity. Biochemical characterization of the four most potent modulators revealed that two designs inhibit FAK with low-nanomolar IC50 values while the remaining two potentiated FAK activity by more than two-fold. When expressed in cells, the modulators preserved the same inhibitory and activating effects observed in vitro, establishing that designed conformational binders can directly tune FAK signaling in living cells. Taking advantage of the high similarity between kinases, we redesigned the FAK inhibitors to inhibit Src kinase. Our approach establishes a versatile platform for selective and genetically encoded kinase control as a way to rewire cell signaling and as a starting point for the discovery of novel modulatory sites of kinases.
Magnus S. Bauer, Saurav Kumar, Mia S. Donald-Paladino et al.· bioRxiv· 0 citations
Biomolecular interactions, including protein–protein interactions, protein–nucleic acid recognition, and protein–small molecule binding, underlie a wide range of biological processes and therapeutic mechanisms. Although recent de novo design methods can generate candidate binders for diverse molecular targets, practical design campaigns remain limited by low filter-passing rates and model-specific biases that arise when designs are optimized against a single predictor. Here, we present RFOptimization (RFO), a training-free framework for all-atom biomolecular binder optimization. RFO formulates binder improvement as a residue-wise mutational search problem, sampling candidate substitutions alternately based on gradient-guided sequence optimization using all-atom structure prediction models and a cycling-based sequence redesign strategy that alternates structure generation with an orthogonal predictor and MPNN-based sequence design to improve the in silico success rate of RFdiffusion-generated binders within minutes of computation. To reduce overfitting to any individual structure model, candidate mutations are further evaluated with orthogonal AlphaFold3 metrics as final filters. We demonstrate the generality of RFO across diverse design settings, including classical protein binder design, ligand-binding biosensor design, cyclic peptide design, and active site-aware enzyme design.
Odin Zhang, Jia-Qi Wang, T. Thompson et al.· bioRxiv· 0 citations
Protein kinases are critical regulators of cellular signaling, but precise modulation of their activity remains challenging due to their high structural conservation. Here, we present de novo designed genetically encoded miniproteins capable of activating or inhibiting focal adhesion kinase (FAK) by directly targeting the kinase domain itself. Among 96 binders designed to stabilize distinct conformational states of FAK, 33 modulated kinase activity. Biochemical characterization of the four most potent modulators revealed that two designs inhibit FAK with low-nanomolar IC50 values while the remaining two potentiated FAK activity by more than two-fold. When expressed in cells, the modulators preserved the same inhibitory and activating effects observed in vitro, establishing that designed conformational binders can directly tune FAK signaling in living cells. Taking advantage of the high similarity between kinases, we redesigned the FAK inhibitors to inhibit Src kinase. Our approach establishes a versatile platform for selective and genetically encoded kinase control as a way to rewire cell signaling and as a starting point for the discovery of novel modulatory sites of kinases.
Magnus S. Bauer, Saurav Kumar, Mia S. Donald-Paladino et al.· bioRxiv· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
