Preetham Venkatesh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Preetham Venkatesh has a total of 106 co-authors. Here are the top co-authors by number of shared publications:
- David Baker
Institute for Protein Design, University of Washington, Seattle, WA, USA
4 shared publications - Xinting Li
Department of Biochemistry, University of Washington, Seattle, WA, USA
3 shared publications - Brian Coventry
Institute for Protein Design, University of Washington, Seattle, WA, USA
2 shared publications - Donald Hilvert
Laboratory of Organic Chemistry, ETH Zurich, Zurich, Switzerland
2 shared publications - Donghyo Kim
Department of Biochemistry, University of Washington, Seattle, USA
2 shared publications - Frank DiMaio
Institute for Protein Design, University of Washington, Seattle, WA, USA
2 shared publications
Latest Publications
- Open Access
Biomolecular design through latent reasoning with RFD4-Proteina
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.
Open AccessBiomolecular design through latent reasoning with RFD4-Proteina
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.
- Open Access
Computational design of metalloproteases
De novo design of enzymes that cleave amide bonds represents a major challenge 1–2 . Here we use RFdiffusion methods 3–4 to de novo design proteins with water activating zinc based active sites adjacent to a peptide substrate binding pocket. Of 135 designs tested, 36% catalyze cleavage of their cognate peptide substrates at the targeted scissile bond. The best design accelerates peptide-bond hydrolysis by more than 10 8 -fold relative to the uncatalyzed reaction; four substitutions increase this acceleration to over 10 10 -fold by improving active-site preorganization 5 . We use this approach to design metalloproteases that selectively cleave the human disease associated proteins TDP-43, amyloid-β, and serum amyloid A, with rate enhancements of up to 10 9 -fold. We further design caged cytokines and receptor antagonists that are selectively activated by the designed proteases, enabling bioorthogonal control of cell state. Thus, de novo design can yield highly active, programmable proteases with applications in therapeutics, biotechnology, and bioremediation.
Open AccessComputational design of metalloproteases
De novo design of enzymes that cleave amide bonds represents a major challenge 1–2 . Here we use RFdiffusion methods 3–4 to de novo design proteins with water activating zinc based active sites adjacent to a peptide substrate binding pocket. Of 135 designs tested, 36% catalyze cleavage of their cognate peptide substrates at the targeted scissile bond. The best design accelerates peptide-bond hydrolysis by more than 10 8 -fold relative to the uncatalyzed reaction; four substitutions increase this acceleration to over 10 10 -fold by improving active-site preorganization 5 . We use this approach to design metalloproteases that selectively cleave the human disease associated proteins TDP-43, amyloid-β, and serum amyloid A, with rate enhancements of up to 10 9 -fold. We further design caged cytokines and receptor antagonists that are selectively activated by the designed proteases, enabling bioorthogonal control of cell state. Thus, de novo design can yield highly active, programmable proteases with applications in therapeutics, biotechnology, and bioremediation.
- Top Cited Papers
- 19 April 2024
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 384 (6693) , eadl2528
Generalized biomolecular modeling and design with RoseTTAFold All-Atom
Deep-learning methods have revolutionized protein structure prediction and design but are presently limited to protein-only systems. We describe RoseTTAFold All-Atom (RFAA), which combines a residue-based representation of amino acids and DNA bases with an atomic representation of all other groups to model assemblies that contain proteins, nucleic acids, small molecules, metals, and covalent modifications, given their sequences and chemical structures. By fine-tuning on denoising tasks, we developed RFdiffusion All-Atom (RFdiffusionAA), which builds protein structures around small molecules. Starting from random distributions of amino acid residues surrounding target small molecules, we designed and experimentally validated, through crystallography and binding measurements, proteins that bind the cardiac disease therapeutic digoxigenin, the enzymatic cofactor heme, and the light-harvesting molecule bilin.
- 19 April 2024
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 384 (6693) , eadl2528
Top Cited PapersGeneralized biomolecular modeling and design with RoseTTAFold All-Atom
Deep-learning methods have revolutionized protein structure prediction and design but are presently limited to protein-only systems. We describe RoseTTAFold All-Atom (RFAA), which combines a residue-based representation of amino acids and DNA bases with an atomic representation of all other groups to model assemblies that contain proteins, nucleic acids, small molecules, metals, and covalent modifications, given their sequences and chemical structures. By fine-tuning on denoising tasks, we developed RFdiffusion All-Atom (RFdiffusionAA), which builds protein structures around small molecules. Starting from random distributions of amino acid residues surrounding target small molecules, we designed and experimentally validated, through crystallography and binding measurements, proteins that bind the cardiac disease therapeutic digoxigenin, the enzymatic cofactor heme, and the light-harvesting molecule bilin.
- Open Access
De novo design of high-affinity protein binders to bioactive helical peptides
Many peptide hormones form an alpha-helix upon binding their receptors 1–4 , and sensitive detection methods for them could contribute to better clinical management. De novo protein design can now generate binders with high affinity and specificity to structured proteins 5,6 . However, the design of interactions between proteins and short helical peptides is an unmet challenge. Here, we describe parametric generation and deep learning-based methods for designing proteins to address this challenge. We show that with the RF diffusion generative model, picomolar affinity binders can be generated to helical peptide targets either by noising and then denoising lower affinity designs generated with other methods, or completely de novo starting from random noise distributions; to our knowledge these are the highest affinity designed binding proteins against any protein or small molecule target generated directly by computation without any experimental optimization. The RF diffusion designs enable the enrichment of parathyroid hormone or other bioactive peptides in human plasma and subsequent detection by mass spectrometry, and bioluminescence-based protein biosensors. Capture reagents for bioactive helical peptides generated using the methods described here could aid in the improved diagnosis and therapeutic management of human diseases. 7,8
Open AccessDe novo design of high-affinity protein binders to bioactive helical peptides
Many peptide hormones form an alpha-helix upon binding their receptors 1–4 , and sensitive detection methods for them could contribute to better clinical management. De novo protein design can now generate binders with high affinity and specificity to structured proteins 5,6 . However, the design of interactions between proteins and short helical peptides is an unmet challenge. Here, we describe parametric generation and deep learning-based methods for designing proteins to address this challenge. We show that with the RF diffusion generative model, picomolar affinity binders can be generated to helical peptide targets either by noising and then denoising lower affinity designs generated with other methods, or completely de novo starting from random noise distributions; to our knowledge these are the highest affinity designed binding proteins against any protein or small molecule target generated directly by computation without any experimental optimization. The RF diffusion designs enable the enrichment of parathyroid hormone or other bioactive peptides in human plasma and subsequent detection by mass spectrometry, and bioluminescence-based protein biosensors. Capture reagents for bioactive helical peptides generated using the methods described here could aid in the improved diagnosis and therapeutic management of human diseases. 7,8