Improved protein structure refinement guided by deep learning based accuracy estimation
Open accessPublished version of a preprint
Abstract
We develop a deep learning framework (DeepAccNet) that estimates per-residue accuracy and residue-residue distance signed error in protein models and uses these predictions to guide Rosetta protein structure refinement. The network uses 3D convolutions to evaluate local atomic environments followed by 2D convolutions to provide their global contexts and outperforms other methods that similarly predict the accuracy of protein structure models. Overall accuracy predictions for X-ray and cryoEM structures in the PDB correlate with their resolution, and the network should be broadly useful for assessing the accuracy of both predicted structure models and experimentally determined structures and identifying specific regions likely to be in error. Incorporation of the accuracy predictions at multiple stages in the Rosetta refinement protocol considerably increased the accuracy of the resulting protein structure models, illustrating how deep learning can improve search for global energy minima of biomolecules.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
RoseTTAFold has been evaluated since May 15th, 2021 on CAMEO; over the 69 medium and hard targets released during this time, it outperformed all other servers evaluated including Robetta, IntFold6-TS, BestSingleTemplate, and SWISS-MODEL.
“RoseTTAFold has been evaluated since May 15th, 2021 on CAMEO; over the 69 medium and hard targets released during this time (May 15th, 2021 ~ June 19th, 2021), it outperformed all other servers evaluated in the experiment including Robetta (3), IntFold6-TS (8), BestSingleTemplate (9), and SWISS-MODEL (10) (Fig. 1C).”
From Accurate prediction of protein structures and interactions using a 3-track network (2021) · cites this paper as [10]
Split into 2 atoms — 0 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 2 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
<i>Phaser</i> crystallographic software
McCoy, A. J., Grosse-Kunstleve, R. W., Adams, P. D., Winn, M. D., Storoni, L. C., & Read, R. J. (2007) · Journal of Applied Crystallography · doi:10.1107/s0021889807021206 · Cited by 20,612 · see citing works
Kabsch, W., & Sander, C. (1983) · Biopolymers · doi:10.1002/bip.360221211 · Cited by 15,320 · see citing works
Amino acid substitution matrices from protein blocks.
Henikoff, S., & Henikoff, J. G. (1992) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.89.22.10915 · Cited by 6,218 · see citing works
TM-align: a protein structure alignment algorithm based on the TM-score
Zhang, Y. (2005) · Nucleic Acids Research · doi:10.1093/nar/gki524 · Cited by 3,774 · see citing works
Improved protein structure prediction using potentials from deep learning
Senior, A. W., Evans, R., Jumper, J., Kirkpatrick, J., Sifre, L., Green, T., Qin, C., Žídek, A., Nelson, A. W. R., Bridgland, A., et al. (2020) · Nature · doi:10.1038/s41586-019-1923-7 · Cited by 3,378 · see citing works
The Rosetta All-Atom Energy Function for Macromolecular Modeling and Design
Alford, R. F., Leaver-Fay, A., Jeliazkov, J. R., O’Meara, M. J., DiMaio, F. P., Park, H., Shapovalov, M. V., Renfrew, P. D., Mulligan, V. K., Kappel, K., et al. (2017) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.7b00125 · Cited by 1,532 · see citing works
Self-citationImproved protein structure prediction using predicted interresidue orientations
Yang, J., Anishchenko, I., Park, H., Peng, Z., Ovchinnikov, S., & Baker, D. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1914677117 · Cited by 1,421 · see citing works
Self-citationMariani, V., Biasini, M., Barbato, A., & Schwede, T. (2013) · Bioinformatics · doi:10.1093/bioinformatics/btt473 · Cited by 1,138 · see citing works
High-Resolution Comparative Modeling with RosettaCM
Song, Y., DiMaio, F., Wang, R. Y., Kim, D. E., Miles, C., Brunette, T., Thompson, J., & Baker, D. A. (2013) · Structure · doi:10.1016/j.str.2013.08.005 · Cited by 1,079 · see citing works
Self-citationLGA: a method for finding 3D similarities in protein structures
Zemla, A. (2003) · Nucleic Acids Research · doi:10.1093/nar/gkg571 · Cited by 1,069 · see citing works
QMEAN: A comprehensive scoring function for model quality assessment
Benkert, P., Tosatto, S. C. E., & Schomburg, D. (2007) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.21715 · Cited by 1,011 · see citing works
Critical assessment of methods of protein structure prediction (CASP) — round x
Moult, J., Fidelis, K. A., Kryshtafovych, A., Schwede, T. F., & Tramontano, A. L. (2013) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.24452 · Cited by 673 · see citing works
Park, H., Bradley, P. H., Greisen, P. J., Liu, Y., Mulligan, V. K., Kim, D. E., Baker, D. A., & DiMaio, F. (2016) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.6b00819 · Cited by 564 · see citing works
Self-citationCritical assessment of methods of protein structure prediction (CASP)—Round XIII
Kryshtafovych, A., Schwede, T., Topf, M., Fidelis, K., & Moult, J. (2019) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.25823 · Cited by 506 · see citing works
ProtTrans: Towards Cracking the Language of Life’s Code Through Self-Supervised LearningPreprint
Elnaggar, A., Heinzinger, M., Dallago, C., Rehawi, G., Wang, Y., Jones, L., Gibbs, T., Feher, T., Angerer, C., Steinegger, M., et al. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.07.12.199554 · Cited by 409 · see citing works
Relaxation of backbone bond geometry improves protein energy landscape modeling
Conway, P., Tyka, M. D., DiMaio, F., Konerding, D. E., & Baker, D. A. (2013) · Protein Science · doi:10.1002/pro.2389 · Cited by 408 · see citing works
Self-citationDistance-based protein folding powered by deep learning
Xu, J. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1821309116 · Cited by 401 · see citing works
Meiler, J., Zeidler, A., Schm�schke, F., & M�ller, M. (2001) · Journal of Molecular Modeling · doi:10.1007/s008940100038 · Cited by 271 · see citing works
Improved model quality assessment using ProQ2
Ray, A., Lindahl, E. R., & Wallner, B. (2012) · BMC Bioinformatics · doi:10.1186/1471-2105-13-224 · Cited by 191 · see citing works
Assessment of template based protein structure predictions in CASP9
Mariani, V., Kiefer, F., Schmidt, T., Haas, J., & Schwede, T. (2011) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.23177 · Cited by 185 · see citing works
VoroMQA: Assessment of protein structure quality using interatomic contact areas
Olechnovič, K., & Venclovas, Č. (2017) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.25278 · Cited by 181 · see citing works
Haas, J., Barbato, A., Behringer, D., Studer, G., Roth, S., Bertoni, M., Mostaguir, K., Gumienny, R., & Schwede, T. (2018) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.25431 · Cited by 168 · see citing works
ProQ3D: improved model quality assessments using deep learning
Uziela, K., Menéndez-Hurtado, D., Shu, N., Wallner, B., & Elofsson, A. (2016) · Bioinform. · doi:10.1093/bioinformatics/btw819 · Cited by 164 · see citing works
ProQ3: Improved model quality assessments using Rosetta energy terms
Uziela, K., Shu, N., Wallner, B., & Elofsson, A. (2016) · Scientific Reports · doi:10.1038/srep33509 · Cited by 102 · see citing works
Deep convolutional networks for quality assessment of protein folds
Derevyanko, G., Grudinin, S., Bengio, Y., & Lamoureux, G. (2018) · Bioinformatics · doi:10.1093/bioinformatics/bty494 · Cited by 101 · see citing works
Protein model quality assessment using 3D oriented convolutional neural networks
Pagès, G., Charmettant, B., & Grudinin, S. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz122 · Cited by 94 · see citing works
Experimental accuracy in protein structure refinement via molecular dynamics simulations
Heo, L., & Feig, M. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1811364115 · Cited by 86 · see citing works
Computational protein structure refinement: almost there, yet still so far to go
Feig, M. (2017) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.1307 · Cited by 83 · see citing works
Protein homology model refinement by large-scale energy optimization
Park, H., Ovchinnikov, S., Kim, D. E., DiMaio, F., & Baker, D. A. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1719115115 · Cited by 61 · see citing works
Self-citationWon, J., Baek, M., Monastyrskyy, B., Kryshtafovych, A., & Seok, C. (2019) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.25804 · Cited by 57 · see citing works
Self-citationAssessment of refinement of template‐based models in CASP11
Modi, V., & Dunbrack, R. L. (2016) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.25048 · Cited by 43 · see citing works
High‐accuracy refinement using Rosetta in CASP13
Park, H., Lee, G. R., Kim, D. E., et al. (2019) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.25784 · Cited by 39 · see citing works
Self-citationDriven to near‐experimental accuracy by refinement via molecular dynamics simulations
Heo, L., Arbour, C. F., & Feig, M. (2019) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.25759 · Cited by 36 · see citing works
refineD: improved protein structure refinement using machine learning based restrained relaxation
Bhattacharya, D. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz101 · Cited by 34 · see citing works
Evaluation of model refinement in CASP13
Read, R. J., Sammito, M. D., Kryshtafovych, A., & Croll, T. I. (2019) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.25794 · Cited by 29 · see citing works
Axiomatic attribution for multilinear functions
Sun, Y. J., & Sundararajan, M. (2011) · ACM Conference on Electronic Commerce (EC) · doi:10.1145/1993574.1993601 · Cited by 24 · see citing works
Estimating the Quality of 3D Protein Models Using the ModFOLD7 Server
Maghrabi, A. H. A., & McGuffin, L. J. (2020) · Methods in molecular biology · doi:10.1007/978-1-0716-0708-4_4 · Cited by 18 · see citing works
Bittrich, S., Heinke, F., & Labudde, D. (2016) · Communications in computer and information science · doi:10.1007/978-3-319-34099-9_32 · Cited by 7 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Varadi, M., Anyango, S., Deshpande, M., Nair, S., Natassia, C., Yordanova, G., Yuan, D., Stroe, O., Wood, G., Laydon, A., et al. (2022) · Nucleic Acids Research · doi:10.1093/nar/gkab1061 · Cited by 7,850 · see citing works
Accurate prediction of protein structures and interactions using a 3-track network
Baek, M., DiMaio, F., Anishchenko, I., Dauparas, J., Ovchinnikov, S., Lee, G. R., Wang, J., Cong, Q., Kinch, L. N., Schaeffer, R. D., et al. (2021) · doi:10.1101/2021.06.14.448402 · Cited by 5,542 · see citing works
Self-citationHarnessing protein folding neural networks for peptide–protein docking
Tsaban, T., Varga, J. K., Avraham, O., Ben-Aharon, Z., Khramushin, A., & Schueler-Furman, O. (2022) · Nature Communications · doi:10.1038/s41467-021-27838-9 · Cited by 1,205 · see citing works
Improving de novo protein binder design with deep learning
Bennett, N. R., Coventry, B., Goreshnik, I., Huang, B., Allen, A., Vafeados, D., Peng, Y. P., Dauparas, J., Baek, M., Stewart, L., et al. (2023) · Nature Communications · doi:10.1038/s41467-023-38328-5 · Cited by 402 · see citing works
Self-citationState-of-the-Art Estimation of Protein Model Accuracy Using AlphaFold
Roney, J. P., & Ovchinnikov, S. (2022) · Physical Review Letters · doi:10.1103/physrevlett.129.238101 · Cited by 281 · see citing works
Implications of <i>AlphaFold</i> 2 for crystallographic phasing by molecular replacement
McCoy, A. J., Sammito, M. D., & Read, R. J. (2022) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798321012122 · Cited by 104 · see citing works
Putting <i>AlphaFold</i> models to work with <i>phenix.process_predicted_model</i> and <i>ISOLDE</i>
Oeffner, R. D., Croll, T. I., Millán, C., Poon, B. K., Schlicksup, C. J., Read, R. J., & Terwilliger, T. C. (2022) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798322010026 · Cited by 63 · see citing works
Barbarin-Bocahu, I., & Graille, M. (2022) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798322002157 · Cited by 52 · see citing works
Protein sequence‐to‐structure learning: Is this the end(‐to‐end revolution)?
Laine, E., Eismann, S., Elofsson, A., & Grudinin, S. (2021) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.26235 · Cited by 44 · see citing works
Evaluation of model refinement in <scp>CASP14</scp>
Simpkin, A. J., Sánchez Rodríguez, F., Mesdaghi, S., Kryshtafovych, A., & Rigden, D. J. (2021) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.26185 · Cited by 28 · see citing works
Protein oligomer modeling guided by predicted interchain contacts in <scp>CASP14</scp>
Baek, M., Anishchenko, I., Park, H., Humphreys, I. R., & Baker, D. (2021) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.26197 · Cited by 18 · see citing works
Self-citationPhysical-aware model accuracy estimation for protein complex using deep learning method
Wang, H., Sun, M., Xie, L., Liu, D., & Zhang, G. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.01.017 · Cited by 5 · see citing works
“The voxelization features project the protein structure into voxelized grids to describe the local structural information of residues [26,27] while USR [13,28 – 31] can quickly capture the topological information of protein structures by using three sets of interatomic distances.”
- Authors
- Hiranuma, N., Park, H., Baek, M., Anishchenko, I., Dauparas, J., & Baker, D.
- Affiliations
- University of Washington (US)
- Howard Hughes Medical Institute (US)
- Corresponding author
- Baker, David
- Venue
- Nature Communications
- Published
- 2021-02-26
- Volume
- 12
- Issue
- 1
- Pages
- 1340-1340
- ISSN
- 2041-1723 (ISSN-L)
- PMC
- PMC7910447
- OpenAlex
- W3132153121
- Cited by
- 243
- References
- 39
- Citations by year
- 2026: 14 · 2025: 39 · 2024: 32 · 2023: 45 · 2022: 62 · 2021: 46 · 2020: 5
- FWCI
- 14.52
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Nature Communications (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Howard Hughes Medical Institute
- Washington Research Foundation
- Open Philanthropy Project
- National Institute of Allergy and Infectious Diseases (HHSN272201700059C)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
- Physical Sciences › Materials Science › Materials Chemistry › Enzyme Structure and Function
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Computational Drug Discovery Methods
- Keywords
- protein structure refinement, Rosetta, 3D convolutional neural networks, protein structure model, X-ray crystallography, cryo-EM structure, model accuracy assessment
- MeSH terms
- Deep Learning, Algorithms, Models, Biological, Models, Molecular, Protein Conformation, Proteins, Software, Computational Biology, Caspases
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
