@article{pmid40016259,

title = {Rapid and accurate prediction of protein homo-oligomer symmetry using Seq2Symm},

author = {Meghana Kshirsagar and Artur Meller and Ian R Humphreys and Samuel Sledzieski and Yixi Xu and Rahul Dodhia and Eric Horvitz and Bonnie Berger and Gregory R Bowman and Juan Lavista Ferres and David Baker and Minkyung Baek},

url = {https://www.nature.com/articles/s41467-025-57148-3, Nature Communications

https://www.bakerlab.org/wp-content/uploads/2025/03/s41467-025-57148-3.pdf, PDF},

doi = {10.1038/s41467-025-57148-3},

year  = {2025},

date = {2025-02-27},

urldate = {2025-02-27},

journal = {Nature Communications},

abstract = {The majority of proteins must form higher-order assemblies to perform their biological functions, yet few machine learning models can accurately and rapidly predict the symmetry of assemblies involving multiple copies of the same protein chain. Here, we address this gap by finetuning several classes of protein foundation models, to predict homo-oligomer symmetry. Our best model named Seq2Symm, which utilizes ESM2, outperforms existing template-based and deep learning methods achieving an average AUC-PR of 0.47, 0.44 and 0.49 across homo-oligomer symmetries on three held-out test sets compared to 0.24, 0.24 and 0.25 with template-based search. Seq2Symm uses a single sequence as input and can predict at the rate of ~80,000 proteins/hour. We apply this method to 5 proteomes and ~3.5 million unlabeled protein sequences, showing its promise to be used in conjunction with downstream computationally intensive all-atom structure generation methods such as RoseTTAFold2 and AlphaFold2-multimer. Code, datasets, model are available at: https://github.com/microsoft/seq2symm .},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{VázquezTorres2025,

title = {De novo designed proteins neutralize lethal snake venom toxins},

author = {Susana Vázquez Torres and Melisa Benard Valle and Stephen P. Mackessy and Stefanie K. Menzies and Nicholas R. Casewell and Shirin Ahmadi and Nick J. Burlet and Edin Muratspahić and Isaac Sappington and Max D. Overath and Esperanza Rivera-de-Torre and Jann Ledergerber and Andreas H. Laustsen and Kim Boddum and Asim K. Bera and Alex Kang and Evans Brackenbrough and Iara A. Cardoso and Edouard P. Crittenden and Rebecca J. Edge and Justin Decarreau and Robert J. Ragotte and Arvind S. Pillai and Mohamad Abedi and Hannah L. Han and Stacey R. Gerben and Analisa Murray and Rebecca Skotheim and Lynda Stuart and Lance Stewart and Thomas J. A. Fryer and Timothy P. Jenkins and David Baker},

url = {https://www.nature.com/articles/s41586-024-08393-x, Nature

https://www.bakerlab.org/wp-content/uploads/2025/03/s41586-024-08393-x-1.pdf, PDF},

doi = {10.1038/s41586-024-08393-x},

year  = {2025},

date = {2025-01-15},

urldate = {2025-01-15},

journal = {Nature},

publisher = {Springer Science and Business Media LLC},

abstract = {Snakebite envenoming remains a devastating and neglected tropical disease, claiming over 100,000 lives annually and causing severe complications and long-lasting disabilities for many more1,2. Three-finger toxins (3FTx) are highly toxic components of elapid snake venoms that can cause diverse pathologies, including severe tissue damage3 and inhibition of nicotinic acetylcholine receptors, resulting in life-threatening neurotoxicity4. At present, the only available treatments for snakebites consist of polyclonal antibodies derived from the plasma of immunized animals, which have high cost and limited efficacy against 3FTxs5,6,7. Here we used deep learning methods to de novo design proteins to bind short-chain and long-chain α-neurotoxins and cytotoxins from the 3FTx family. With limited experimental screening, we obtained protein designs with remarkable thermal stability, high binding affinity and near-atomic-level agreement with the computational models. The designed proteins effectively neutralized all three 3FTx subfamilies in vitro and protected mice from a lethal neurotoxin challenge. Such potent, stable and readily manufacturable toxin-neutralizing proteins could provide the basis for safer, cost-effective and widely accessible next-generation antivenom therapeutics. Beyond snakebite, our results highlight how computational design could help democratize therapeutic discovery, particularly in resource-limited settings, by substantially reducing costs and resource requirements for the development of therapies for neglected tropical diseases.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{King2024,

title = {Computational Stabilization of a Non‐Heme Iron Enzyme Enables Efficient Evolution of New Function},

author = {Brianne R. King and Kiera H. Sumida and Jessica L. Caruso and David Baker and Jesse G. Zalatan},

url = {https://onlinelibrary.wiley.com/doi/full/10.1002/anie.202414705, Angew Chem Int Ed

https://www.bakerlab.org/wp-content/uploads/2025/02/Angew-Chem-Int-Ed-2024-King-Computational-Stabilization-of-a-Non‐Heme-Iron-Enzyme-Enables-Efficient-Evolution-of-New.pdf, PDF},

doi = {10.1002/anie.202414705},

issn = {1521-3773},

year  = {2024},

date = {2024-10-12},

urldate = {2025-01-10},

journal = {Angew Chem Int Ed},

publisher = {Wiley},

abstract = {Deep learning tools for enzyme design are rapidly emerging, and there is a critical need to evaluate their effectiveness in engineering workflows. Here we show that the deep learning-based tool ProteinMPNN can be used to redesign Fe(II)/αKG superfamily enzymes for greater stability, solubility, and expression while retaining both native activity and industrially relevant non-native functions. This superfamily has diverse catalytic functions and could provide a rich new source of biocatalysts for synthesis and industrial processes. Through systematic comparisons of directed evolution trajectories for a non-native, remote C(sp3)−H hydroxylation reaction, we demonstrate that the stabilized redesign can be evolved more efficiently than the wild-type enzyme. After three rounds of directed evolution, we obtained a 6-fold activity increase from the wild-type parent and an 80-fold increase from the stabilized variant. To generate the initial stabilized variant, we identified multiple structural and sequence constraints to preserve catalytic function. We applied these criteria to produce stabilized, catalytically active variants of a second Fe(II)/αKG enzyme, suggesting that the approach is generalizable to additional members of the Fe(II)/αKG superfamily. ProteinMPNN is user-friendly and widely accessible, and our results provide a framework for the routine implementation of deep learning-based protein stabilization tools in directed evolution workflows for novel biocatalysts.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Humphreys2024,

title = {Protein interactions in human pathogens revealed through deep learning},

author = {Ian R. Humphreys and Jing Zhang and Minkyung Baek and Yaxi Wang and Aditya Krishnakumar and Jimin Pei and Ivan Anishchenko and Catherine A. Tower and Blake A. Jackson and Thulasi Warrier and Deborah T. Hung and S. Brook Peterson and Joseph D. Mougous and Qian Cong and David Baker},

url = {https://www.nature.com/articles/s41564-024-01791-x, Nature Microbiology [Open Access]},

doi = {10.1038/s41564-024-01791-x},

issn = {2058-5276},

year  = {2024},

date = {2024-09-18},

urldate = {2024-09-18},

journal = {Nature Microbiology},

publisher = {Springer Science and Business Media LLC},

abstract = {Identification of bacterial protein–protein interactions and predicting the structures of these complexes could aid in the understanding of pathogenicity mechanisms and developing treatments for infectious diseases. Here we developed RoseTTAFold2-Lite, a rapid deep learning model that leverages residue–residue coevolution and protein structure prediction to systematically identify and structurally characterize protein–protein interactions at the proteome-wide scale. Using this pipeline, we searched through 78 million pairs of proteins across 19 human bacterial pathogens and identified 1,923 confidently predicted complexes involving essential genes and 256 involving virulence factors. Many of these complexes were not previously known; we experimentally tested 12 such predictions, and half of them were validated. The predicted interactions span core metabolic and virulence pathways ranging from post-transcriptional modification to acid neutralization to outer-membrane machinery and should contribute to our understanding of the biology of these important pathogens and the design of drugs to combat them.



},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{An2024,

title = {Binding and sensing diverse small molecules using shape-complementary pseudocycles},

author = {Linna An and Meerit Said and Long Tran and Sagardip Majumder and Inna Goreshnik and Gyu Rie Lee and David Juergens and Justas Dauparas and Ivan Anishchenko and Brian Coventry and Asim K. Bera and Alex Kang and Paul M. Levine and Valentina Alvarez and Arvind Pillai and Christoffer Norn and David Feldman and Dmitri Zorine and Derrick R. Hicks and Xinting Li and Mariana Garcia Sanchez and Dionne K. Vafeados and Patrick J. Salveson and Anastassia A. Vorobieva and David Baker},

url = {https://www.science.org/doi/10.1126/science.adn3780, Science},

doi = {10.1126/science.adn3780},

year  = {2024},

date = {2024-07-19},

urldate = {2024-07-19},

journal = {Science},

publisher = {American Association for the Advancement of Science (AAAS)},

abstract = {We describe an approach for designing high-affinity small molecule–binding proteins poised for downstream sensing. We use deep learning–generated pseudocycles with repeating structural units surrounding central binding pockets with widely varying shapes that depend on the geometry and number of the repeat units. We dock small molecules of interest into the most shape complementary of these pseudocycles, design the interaction surfaces for high binding affinity, and experimentally screen to identify designs with the highest affinity. We obtain binders to four diverse molecules, including the polar and flexible methotrexate and thyroxine. Taking advantage of the modular repeat structure and central binding pockets, we construct chemically induced dimerization systems and low-noise nanopore sensors by splitting designs into domains that reassemble upon ligand addition.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Goverde2024,

title = {Computational design of soluble and functional membrane protein analogues},

author = {Casper A. Goverde and Martin Pacesa and Nicolas Goldbach and Lars J. Dornfeld and Petra E. M. Balbi and Sandrine Georgeon and Stéphane Rosset and Srajan Kapoor and Jagrity Choudhury and Justas Dauparas and Christian Schellhaas and Simon Kozlov and David Baker and Sergey Ovchinnikov and Alex J. Vecchio and Bruno E. Correia},

url = {https://www.nature.com/articles/s41586-024-07601-y, Nature [Open Access]

},

doi = {10.1038/s41586-024-07601-y},

issn = {1476-4687},

year  = {2024},

date = {2024-06-19},

urldate = {2024-06-19},

journal = {Nature},

publisher = {Springer Science and Business Media LLC},

abstract = {De novo design of complex protein folds using solely computational means remains a substantial challenge. Here we use a robust deep learning pipeline to design complex folds and soluble analogues of integral membrane proteins. Unique membrane topologies, such as those from G-protein-coupled receptors, are not found in the soluble proteome, and we demonstrate that their structural features can be recapitulated in solution. Biophysical analyses demonstrate the high thermal stability of the designs, and experimental structures show remarkable design accuracy. The soluble analogues were functionalized with native structural motifs, as a proof of concept for bringing membrane protein functions to the soluble proteome, potentially enabling new approaches in drug discovery. In summary, we have designed complex protein topologies and enriched them with functionalities from membrane proteins, with high experimental success rates, leading to a de facto expansion of the functional soluble fold space.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Krishna2024,

title = {Generalized biomolecular modeling and design with RoseTTAFold All-Atom},

author = {Rohith Krishna and Jue Wang and Woody Ahern and Pascal Sturmfels and Preetham Venkatesh and Indrek Kalvet and Gyu Rie Lee and Felix S. Morey-Burrows and Ivan Anishchenko and Ian R. Humphreys and Ryan McHugh and Dionne Vafeados and Xinting Li and George A. Sutherland and Andrew Hitchcock and C. Neil Hunter and Alex Kang and Evans Brackenbrough and Asim K. Bera and Minkyung Baek and Frank DiMaio and David Baker},

url = {https://www.science.org/stoken/author-tokens/ST-1739/full, Science [Full Access Link]

https://www.bakerlab.org/wp-content/uploads/2024/03/science.adl2528.pdf, PDF},

doi = {10.1126/science.adl2528},

year  = {2024},

date = {2024-03-07},

urldate = {2024-03-07},

journal = {Science},

publisher = {American Association for the Advancement of Science (AAAS)},

abstract = {Deep learning methods have revolutionized protein structure prediction and design but are currently 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 containing proteins, nucleic acids, small molecules, metals, and covalent modifications given their sequences and chemical structures. By fine tuning on denoising tasks we obtain RFdiffusionAA, which builds protein structures around small molecules. Starting from random distributions of amino acid residues surrounding target small molecules, we design and experimentally validate, through crystallography and binding measurements, proteins that bind the cardiac disease therapeutic digoxigenin, the enzymatic cofactor heme, and the light harvesting molecule bilin.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid38109936,

title = {De novo design of high-affinity binders of bioactive helical peptides},

author = {Susana Vázquez Torres and Philip J Y Leung and Preetham Venkatesh and Isaac D Lutz and Fabian Hink and Huu-Hien Huynh and Jessica Becker and Andy Hsien-Wei Yeh and David Juergens and Nathaniel R Bennett and Andrew N Hoofnagle and Eric Huang and Michael J MacCoss and Marc Expòsit and Gyu Rie Lee and Asim K Bera and Alex Kang and Joshmyn De La Cruz and Paul M Levine and Xinting Li and Mila Lamb and Stacey R Gerben and Analisa Murray and Piper Heine and Elif Nihal Korkmaz and Jeff Nivala and Lance Stewart and Joseph L Watson and Joseph M Rogers and David Baker},

url = {https://www.nature.com/articles/s41586-023-06953-1, Nature [Open Access]},

doi = {10.1038/s41586-023-06953-1},

issn = {1476-4687},

year  = {2023},

date = {2023-12-01},

urldate = {2023-12-01},

journal = {Nature},

abstract = {Many peptide hormones form an alpha-helix upon binding their receptors, and sensitive detection methods for them could contribute to better clinical management of disease. De novo protein design can now generate binders with high affinity and specificity to structured proteins. However, the design of interactions between proteins and short peptides with helical propensity is an unmet challenge. Here, we describe parametric generation and deep learning-based methods for designing proteins to address this challenge. We show that by extending RFdiffusion to enable binder design to flexible targets, and to refining input structure models by successive noising and denoising (partial diffusion), picomolar affinity binders can be generated to helical peptide targets both by refining 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 optimisation. The RFdiffusion designs enable the enrichment and subsequent detection of parathyroid hormone and glucagon by mass spectrometry, and the construction of bioluminescence-based protein biosensors. The ability to design binders to conformationally variable targets, and to optimise by partial diffusion both natural and designed proteins, should be broadly useful.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Watson2023,

title = {De novo design of protein structure and function with RFdiffusion},

author = {Watson, Joseph L.

and Juergens, David

and Bennett, Nathaniel R.

and Trippe, Brian L.

and Yim, Jason

and Eisenach, Helen E.

and Ahern, Woody

and Borst, Andrew J.

and Ragotte, Robert J.

and Milles, Lukas F.

and Wicky, Basile I. M.

and Hanikel, Nikita

and Pellock, Samuel J.

and Courbet, Alexis

and Sheffler, William

and Wang, Jue

and Venkatesh, Preetham

and Sappington, Isaac

and Torres, Susana Vázquez

and Lauko, Anna

and De Bortoli, Valentin

and Mathieu, Emile

and Ovchinnikov, Sergey

and Barzilay, Regina

and Jaakkola, Tommi S.

and DiMaio, Frank

and Baek, Minkyung

and Baker, David},

url = {https://www.nature.com/articles/s41586-023-06415-8, Nature

https://www.bakerlab.org/wp-content/uploads/2023/07/s41586-023-06415-8_reference.pdf, PDF (29MB)},

doi = {10.1038/s41586-023-06415-8},

year  = {2023},

date = {2023-07-11},

journal = {Nature},

abstract = {There has been considerable recent progress in designing new proteins using deep learning methods1–9. Despite this progress, a general deep learning framework for protein design that enables solution of a wide range of design challenges, including de novo binder design and design of higher order symmetric architectures, has yet to be described. Diffusion models10,11 have had considerable success in image and language generative modeling but limited success when applied to protein modeling, likely due to the complexity of protein backbone geometry and sequence-structure relationships. Here we show that by fine tuning the RoseTTAFold structure prediction network on protein structure denoising tasks, we obtain a generative model of protein backbones that achieves outstanding performance on unconditional and topology-constrained protein monomer design, protein binder design, symmetric oligomer design, enzyme active site scaffolding, and symmetric motif scaffolding for therapeutic and metal-binding protein design. We demonstrate the power and generality of the method, called RoseTTAFold Diffusion (RFdiffusion), by experimentally characterizing the structures and functions of hundreds of designed symmetric assemblies, metal binding proteins and protein binders. The accuracy of RFdiffusion is confirmed by the cryo-EM structure of a designed binder in complex with Influenza hemagglutinin which is nearly identical to the design model. In a manner analogous to networks which produce images from user-specified inputs, RFdiffusion enables the design of diverse functional proteins from simple molecular specifications.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Bennett2023,

title = {Improving de novo protein binder design with deep learning},

author = {Bennett, Nathaniel R.

and Coventry, Brian

and Goreshnik, Inna

and Huang, Buwei

and Allen, Aza

and Vafeados, Dionne

and Peng, Ying Po

and Dauparas, Justas

and Baek, Minkyung

and Stewart, Lance

and DiMaio, Frank

and De Munck, Steven

and Savvides, Savvas N.

and Baker, David},

url = {https://www.nature.com/articles/s41467-023-38328-5, Nature Communications (Open Access)},

doi = {10.1038/s41467-023-38328-5},

year  = {2023},

date = {2023-05-06},

journal = {Nature Communications},

abstract = {Recently it has become possible to de novo design high affinity protein binding proteins from target structural information alone. There is, however, considerable room for improvement as the overall design success rate is low. Here, we explore the augmentation of energy-based protein binder design using deep learning. We find that using AlphaFold2 or RoseTTAFold to assess the probability that a designed sequence adopts the designed monomer structure, and the probability that this structure binds the target as designed, increases design success rates nearly 10-fold. We find further that sequence design using ProteinMPNN rather than Rosetta considerably increases computational efficiency.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Kim2023,

title = {De novo design of small beta barrel proteins},

author = {Kim, David E.

and Jensen, Davin R.

and Feldman, David

and Tischer, Doug

and Saleem, Ayesha

and Chow, Cameron M.

and Li, Xinting

and Carter, Lauren

and Milles, Lukas

and Nguyen, Hannah

and Kang, Alex

and Bera, Asim K.

and Peterson, Francis C.

and Volkman, Brian F.

and Ovchinnikov, Sergey

and Baker, David},

url = {https://www.pnas.org/doi/10.1073/pnas.2207974120, PNAS (Open Access)},

doi = {10.1073/pnas.2207974120},

year  = {2023},

date = {2023-03-10},

urldate = {2023-03-10},

journal = {Proceedings of the National Academy of Sciences},

abstract = {Small beta barrel proteins are attractive targets for computational design because of their considerable functional diversity despite their very small size (<70 amino acids). However, there are considerable challenges to designing such structures, and there has been little success thus far. Because of the small size, the hydrophobic core stabilizing the fold is necessarily very small, and the conformational strain of barrel closure can oppose folding; also intermolecular aggregation through free beta strand edges can compete with proper monomer folding. Here, we explore the de novo design of small beta barrel topologies using both Rosetta energy–based methods and deep learning approaches to design four small beta barrel folds: Src homology 3 (SH3) and oligonucleotide/oligosaccharide-binding (OB) topologies found in nature and five and six up-and-down-stranded barrels rarely if ever seen in nature. Both approaches yielded successful designs with high thermal stability and experimentally determined structures with less than 2.4 Å rmsd from the designed models. Using deep learning for backbone generation and Rosetta for sequence design yielded higher design success rates and increased structural diversity than Rosetta alone. The ability to design a large and structurally diverse set of small beta barrel proteins greatly increases the protein shape space available for designing binders to protein targets of interest.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Yeh2023,

title = {De novo design of luciferases using deep learning},

author = {Yeh, Andy Hsien-Wei

 Norn, Christoffer

 Kipnis, Yakov

 Tischer, Doug

 Pellock, Samuel J.

 Evans, Declan

 Ma, Pengchen

 Lee, Gyu Rie

 Zhang, Jason Z.

 Anishchenko, Ivan

 Coventry, Brian

 Cao, Longxing

 Dauparas, Justas

 Halabiya, Samer

 DeWitt, Michelle

 Carter, Lauren

 Houk, K. N.

 Baker, David},

url = {https://www.nature.com/articles/s41586-023-05696-3, Nature (Open Access)},

doi = {10.1038/s41586-023-05696-3},

year  = {2023},

date = {2023-02-22},

journal = {Nature},

abstract = {De novo enzyme design has sought to introduce active sites and substrate-binding pockets that are predicted to catalyse a reaction of interest into geometrically compatible native scaffolds1,2, but has been limited by a lack of suitable protein structures and the complexity of native protein sequence–structure relationships. Here we describe a deep-learning-based ‘family-wide hallucination’ approach that generates large numbers of idealized protein structures containing diverse pocket shapes and designed sequences that encode them. We use these scaffolds to design artificial luciferases that selectively catalyse the oxidative chemiluminescence of the synthetic luciferin substrates diphenylterazine3 and 2-deoxycoelenterazine. The designed active sites position an arginine guanidinium group adjacent to an anion that develops during the reaction in a binding pocket with high shape complementarity. For both luciferin substrates, we obtain designed luciferases with high selectivity; the most active of these is a small (13.9 kDa) and thermostable (with a melting temperature higher than 95 °C) enzyme that has a catalytic efficiency on diphenylterazine (kcat/Km = 106 M−1 s−1) comparable to that of native luciferases, but a much higher substrate specificity. The creation of highly active and specific biocatalysts from scratch with broad applications in biomedicine is a key milestone for computational enzyme design, and our approach should enable generation of a wide range of luciferases and other enzymes.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Wicky2022,

title = {Hallucinating symmetric protein assemblies},

author = {B. I. M. Wicky and L. F. Milles and A. Courbet and R. J. Ragotte and J. Dauparas and E. Kinfu and S. Tipps and R. D. Kibler and M. Baek and F. DiMaio and X. Li and L. Carter and A. Kang and H. Nguyen and A. K. Bera and D. Baker},

url = {https://www.science.org/doi/abs/10.1126/science.add1964, Science

https://www.bakerlab.org/wp-content/uploads/2022/09/Wicky_etal_Science2022_Hallucinating_symmetric_protein_assemblies.pdf, PDF

},

doi = {10.1126/science.add1964},

year  = {2022},

date = {2022-09-15},

journal = {Science},

abstract = {Deep learning generative approaches provide an opportunity to broadly explore protein structure space beyond the sequences and structures of natural proteins. Here we use deep network hallucination to generate a wide range of symmetric protein homo-oligomers given only a specification of the number of protomers and the protomer length. Crystal structures of 7 designs are very close to the computational models (median RMSD: 0.6 Å), as are 3 cryoEM structures of giant 10 nanometer rings with up to 1550 residues and C33 symmetry; all differ considerably from previously solved structures. Our results highlight the rich diversity of new protein structures that can be generated using deep learning, and pave the way for the design of increasingly complex components for nanomachines and biomaterials.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Dauparas2022,

title = {Robust deep learning–based protein sequence design using ProteinMPNN},

author = {Dauparas, J.

and Anishchenko, I.

and Bennett, N.

and Bai, H.

and Ragotte, R. J.

and Milles, L. F.

and Wicky, B. I. M.

and Courbet, A.

and de Haas, R. J.

and Bethel, N.

and Leung, P. J. Y.

and Huddy, T. F.

and Pellock, S.

and Tischer, D.

and Chan, F.

and Koepnick, B.

and Nguyen, H.

and Kang, A.

and Sankaran, B.

and Bera, A. K.

and King, N. P.

and Baker, D.},

url = {https://www.science.org/doi/abs/10.1126/science.add2187, Science

https://www.bakerlab.org/wp-content/uploads/2022/09/Dauparas_etal_Science2022_Sequence_design_via_ProteinMPNN.pdf, PDF},

doi = {10.1126/science.add2187},

year  = {2022},

date = {2022-09-15},

journal = {Science},

abstract = {While deep learning has revolutionized protein structure prediction, almost all experimentally characterized de novo protein designs have been generated using physically based approaches such as Rosetta. Here we describe a deep learning–based protein sequence design method, ProteinMPNN, with outstanding performance in both in silico and experimental tests. On native protein backbones, ProteinMPNN has a sequence recovery of 52.4%, compared to 32.9% for Rosetta. The amino acid sequence at different positions can be coupled between single or multiple chains, enabling application to a wide range of current protein design challenges. We demonstrate the broad utility and high accuracy of ProteinMPNN using X-ray crystallography, cryoEM and functional studies by rescuing previously failed designs, made using Rosetta or AlphaFold, of protein monomers, cyclic homo-oligomers, tetrahedral nanoparticles, and target binding proteins},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Wang2022,

title = {Scaffolding protein functional sites using deep learning},

author = {Jue Wang and Sidney Lisanza and David Juergens and Doug Tischer and Joseph L. Watson and Karla M. Castro and Robert Ragotte and Amijai Saragovi and Lukas F. Milles and Minkyung Baek and Ivan Anishchenko and Wei Yang and Derrick R. Hicks and Marc Expòsit and Thomas Schlichthaerle and Jung-Ho Chun and Justas Dauparas and Nathaniel Bennett and Basile I. M. Wicky and Andrew Muenks and Frank DiMaio and Bruno Correia and Sergey Ovchinnikov and David Baker },

url = {https://www.science.org/doi/abs/10.1126/science.abn2100, Science

https://www.ipd.uw.edu/wp-content/uploads/2022/07/science.abn2100.pdf, Download PDF},

doi = {10.1126/science.abn2100},

year  = {2022},

date = {2022-07-21},

urldate = {2022-07-21},

journal = {Science},

abstract = {The binding and catalytic functions of proteins are generally mediated by a small number of functional residues held in place by the overall protein structure. Here, we describe deep learning approaches for scaffolding such functional sites without needing to prespecify the fold or secondary structure of the scaffold. The first approach, “constrained hallucination,” optimizes sequences such that their predicted structures contain the desired functional site. The second approach, “inpainting,” starts from the functional site and fills in additional sequence and structure to create a viable protein scaffold in a single forward pass through a specifically trained RoseTTAFold network. We use these two methods to design candidate immunogens, receptor traps, metalloproteins, enzymes, and protein-binding proteins and validate the designs using a combination of in silico and experimental tests. Protein design has had success in finding sequences that fold into a desired conformation, but designing functional proteins remains challenging. Wang et al. describe two deep-learning methods to design proteins that contain prespecified functional sites. In the first, they found sequences predicted to fold into stable structures that contain the functional site. In the second, they retrained a structure prediction network to recover the sequence and full structure of a protein given only the functional site. The authors demonstrate their methods by designing proteins containing a variety of functional motifs. —VV Deep-learning methods enable the scaffolding of desired functional residues within a well-folded designed protein.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Sen2022,

title = {Characterizing and explaining the impact of disease-associated mutations in proteins without known structures or structural homologs},

author = {Sen, Neeladri

and Anishchenko, Ivan

and Bordin N

and Sillitoe, Ian

and Velankar, Sameer

and Baker, David

and Orengo, Christine},

url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9294430/},

doi = {10.1093/bib/bbac187},

year  = {2022},

date = {2022-07-18},

journal = {Briefings in Bioinformatics},

abstract = {Mutations in human proteins lead to diseases. The structure of these proteins can help understand the mechanism of such diseases and develop therapeutics against them. With improved deep learning techniques, such as RoseTTAFold and AlphaFold, we can predict the structure of proteins even in the absence of structural homologs. We modeled and extracted the domains from 553 disease-associated human proteins without known protein structures or close homologs in the Protein Databank. We noticed that the model quality was higher and the Root mean square deviation (RMSD) lower between AlphaFold and RoseTTAFold models for domains that could be assigned to CATH families as compared to those which could only be assigned to Pfam families of unknown structure or could not be assigned to either. We predicted ligand-binding sites, protein-protein interfaces and conserved residues in these predicted structures. We then explored whether the disease-associated missense mutations were in the proximity of these predicted functional sites, whether they destabilized the protein structure based on ddG calculations or whether they were predicted to be pathogenic. We could explain 80% of these disease-associated mutations based on proximity to functional sites, structural destabilization or pathogenicity. When compared to polymorphisms, a larger percentage of disease-associated missense mutations were buried, closer to predicted functional sites, predicted as destabilizing and pathogenic. Usage of models from the two state-of-the-art techniques provide better confidence in our predictions, and we explain 93 additional mutations based on RoseTTAFold models which could not be explained based solely on AlphaFold models.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Lovelock2022,

title = {The road to fully programmable protein catalysis},

author = {Sarah L. Lovelock and Rebecca Crawshaw and Sophie Basler and Colin Levy and David Baker and Donald Hilvert and Anthony P. Green 

},

url = {https://www.nature.com/articles/s41586-022-04456-z, Nature

https://www.bakerlab.org/wp-content/uploads/2022/06/s41586-022-04456-z.pdf, Download PDF},

doi = {10.1038/s41586-022-04456-z},

year  = {2022},

date = {2022-06-01},

journal = {Nature},

abstract = {The ability to design efficient enzymes from scratch would have a profound effect on chemistry, biotechnology and medicine. Rapid progress in protein engineering over the past decade makes us optimistic that this ambition is within reach. The development of artificial enzymes containing metal cofactors and noncanonical organocatalytic groups shows how protein structure can be optimized to harness the reactivity of nonproteinogenic elements. In parallel, computational methods have been used to design protein catalysts for diverse reactions on the basis of fundamental principles of transition state stabilization. Although the activities of designed catalysts have been quite low, extensive laboratory evolution has been used to generate efficient enzymes. Structural analysis of these systems has revealed the high degree of precision that will be needed to design catalysts with greater activity. To this end, emerging protein design methods, including deep learning, hold particular promise for improving model accuracy. Here we take stock of key developments in the field and highlight new opportunities for innovation that should allow us to transition beyond the current state of the art and enable the robust design of biocatalysts to address societal needs.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Linder2022,

title = {Interpreting neural networks for biological sequences by learning stochastic masks},

author = {Linder, Johannes and La Fleur, Alyssa and Chen, Zibo and Ljubetič, Ajasja and Baker, David and Kannan, Sreeram and Seelig, Georg},

url = {https://www.nature.com/articles/s42256-021-00428-6, Nature Machine Intelligence},

doi = {10.1038/s42256-021-00428-6},

year  = {2022},

date = {2022-01-25},

urldate = {2022-01-25},

journal = {Nature Machine Intelligence},

abstract = {Sequence-based neural networks can learn to make accurate predictions from large biological datasets, but model interpretation remains challenging. Many existing feature attribution methods are optimized for continuous rather than discrete input patterns and assess individual feature importance in isolation, making them ill-suited for interpreting nonlinear interactions in molecular sequences. Here, building on work in computer vision and natural language processing, we developed an approach based on deep learning—scrambler networks—wherein the most important sequence positions are identified with learned input masks. Scramblers learn to predict position-specific scoring matrices where unimportant nucleotides or residues are scrambled by raising their entropy. We apply scramblers to interpret the effects of genetic variants, uncover nonlinear interactions between cis-regulatory elements, explain binding specificity for protein–protein interactions, and identify structural determinants of de novo-designed proteins. We show that scramblers enable efficient attribution across large datasets and result in high-quality explanations, often outperforming state-of-the-art methods.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Baek2022,

title = {Deep learning and protein structure modeling},

author = {Minkyung Baek and David Baker},

url = {https://www.nature.com/articles/s41592-021-01360-8, Nature Methods

https://www.bakerlab.org/wp-content/uploads/2022/01/Baek_Baker_NatureMethods2022_Deep_Learning_and_Protein_Structure_Modeling.pdf, Download PDF

},

doi = {10.1038/s41592-021-01360-8},

year  = {2022},

date = {2022-01-22},

urldate = {2022-01-22},

journal = {Nature Methods},

abstract = {Deep learning has transformed protein structure modeling. Here we relate AlphaFold and RoseTTAFold to classical physically based approaches to protein structure prediction, and discuss the many areas of structural biology that are likely to be affected by further advances in deep learning.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Du2021,

title = {The trRosetta server for fast and accurate protein structure prediction},

author = {Du, Zongyang

and Su, Hong

and Wang, Wenkai

and Ye, Lisha

and Wei, Hong

and Peng, Zhenling

and Anishchenko, Ivan

and Baker, David

and Yang, Jianyi},

url = {https://www.nature.com/articles/s41596-021-00628-9

https://www.bakerlab.org/wp-content/uploads/2022/01/Du_etal_NatProt2021_trRosetta_server.pdf},

doi = {10.1038/s41596-021-00628-9},

year  = {2021},

date = {2021-12-01},

urldate = {2021-12-01},

journal = {Nature Protocols},

abstract = {The trRosetta (transform-restrained Rosetta) server is a web-based platform for fast and accurate protein structure prediction, powered by deep learning and Rosetta. With the input of a protein’s amino acid sequence, a deep neural network is first used to predict the inter-residue geometries, including distance and orientations. The predicted geometries are then transformed as restraints to guide the structure prediction on the basis of direct energy minimization, which is implemented under the framework of Rosetta. The trRosetta server distinguishes itself from other similar structure prediction servers in terms of rapid and accurate de novo structure prediction. As an illustration, trRosetta was applied to two Pfam families with unknown structures, for which the predicted de novo models were estimated to have high accuracy. Nevertheless, to take advantage of homology modeling, homologous templates are used as additional inputs to the network automatically. In general, it takes ~1 h to predict the final structure for a typical protein with ~300 amino acids, using a maximum of 10 CPU cores in parallel in our cluster system. To enable large-scale structure modeling, a downloadable package of trRosetta with open-source codes is available as well. A detailed guidance for using the package is also available in this protocol. The server and the package are available at https://yanglab.nankai.edu.cn/trRosetta/ and https://yanglab.nankai.edu.cn/trRosetta/download/, respectively.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}