Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Improved protein structure prediction by deep learning irrespective of co-evolution information

Abstract

Predicting the tertiary structure of a protein from its primary sequence has been greatly improved by integrating deep learning and co-evolutionary analysis, as shown in CASP13 and CASP14. We describe our latest study of this idea, analysing the efficacy of network size and co-evolution data and its performance on both natural and designed proteins. We show that a large ResNet (convolutional residual neural networks) can predict structures of correct folds for 26 out of 32 CASP13 free-modelling targets and L/5 long-range contacts with precision over 80%. When co-evolution is not used, ResNet can still predict structures of correct folds for 18 CASP13 free-modelling targets, greatly exceeding previous methods that do not use co-evolution either. Even with only the primary sequence, ResNet can predict the structures of correct folds for all tested human-designed proteins. In addition, ResNet may fare better for the designed proteins when trained without co-evolution than with co-evolution. These results suggest that ResNet does not simply de-noise co-evolution signals, but instead may learn important protein sequence–structure relationships. This has important implications for protein design and engineering, especially when co-evolutionary data are unavailable.

A preprint version of the article is available at bioRxiv.

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.

from$8.99

All prices are NET prices.

Fig. 1: Contact prediction accuracy by various ResNet models on 31 CASP13 FM targets.
Fig. 2: 3D modelling accuracy (TMscore) on the 32 CASP13 FM targets.
Fig. 3: 3D modelling accuracy on the human-designed proteins.

Data availability

The PDB IDs of the human-designed proteins are available in Supplementary Data 4. The domain sequences determined by our own CASP13 server for the CASP13 targets are available in Supplementary Data 5. The official domain sequences of the CASP13 targets and their corresponding PDB IDs are available at the CASP13 web site, https://predictioncenter.org/casp13/index.cgi. The training data, including the multiple sequence alignment and ground truth files, are available at https://zenodo.org/record/4679643.

Code availability

The source code is available at https://github.com/j3xugit/RaptorX-3DModeling/ or https://doi.org/10.5281/zenodo.4642250 and the server is available at http://raptorx.uchicago.edu/. In addition to template-free protein structure prediction, this package also supports comparative protein structure modelling, that is, building protein 3D models from templates by deep learning.

References

  1. 1.

    De Juan, D., Pazos, F. & Valencia, A. Emerging methods in protein co-evolution. Nat. Rev. Genet. 14, 249–261 (2013).

    Article  Google Scholar 

  2. 2.

    Shrestha, R. et al. Assessing the accuracy of contact predictions in CASP13. Proteins 87, 1058–1068 (2019).

    Article  Google Scholar 

  3. 3.

    Abriata, L. A., Tamo, G. E. & Dal Peraro, M.A further leap of improvement in tertiary structure prediction in CASP13 prompts new routes for future assessments. Proteins 87, 1100–1112 (2019).

    Article  Google Scholar 

  4. 4.

    Wang, S. et al. Accurate de novo prediction of protein contact map by ultra-deep learning model. PLoS Comput. Biol. 13, e1005324 (2017).

    Article  Google Scholar 

  5. 5.

    Wang, S., Sun, S. Q. & Xu, J. B. Analysis of deep learning methods for blind protein contact prediction in CASP12. Proteins 86, 67–77 (2018).

    Article  Google Scholar 

  6. 6.

    Xu, J. Distance-based protein folding powered by deep learning. Proc. Natl Acad. Sci. USA 116, 16856–16865 (2019).

    Article  Google Scholar 

  7. 7.

    Xu, J. B. & Wang, S. Analysis of distance-based protein structure prediction by deep learning in CASP13. Proteins 87, 1069–1081 (2019).

    Article  Google Scholar 

  8. 8.

    Wang, S. et al. Folding membrane proteins by deep transfer learning. Cell Syst. 5, 202–211 (2017).

    Article  Google Scholar 

  9. 9.

    Zhu, J. W. et al. Protein threading using residue co-variation and deep learning. Bioinformatics 34, 263–273 (2018).

    Article  Google Scholar 

  10. 10.

    Senior, A. W. et al. Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13). Proteins 87, 1141–1148 (2019).

    Article  Google Scholar 

  11. 11.

    Ding, W. Z. & Gong, H. P. Predicting the real-valued inter-residue distances for proteins. Adv. Sci 7, 2001314 (2020).

    Article  Google Scholar 

  12. 12.

    Yang, J. Y. et al. Improved protein structure prediction using predicted interresidue orientations. Proc. Natl Acad. Sci. USA 117, 1496–1503 (2020).

    Article  Google Scholar 

  13. 13.

    Greener, J. G., Kandathil, S. M. & Jones, D. T. Deep learning extends de novo protein modelling coverage of genomes using iteratively predicted structural constraints. Nat. Commun. 10, 3977 (2019).

    Article  Google Scholar 

  14. 14.

    Ovchinnikov, S. et al. Protein structure determination using metagenome sequence data. Science 355, 294–297 (2017).

    Article  Google Scholar 

  15. 15.

    Li, Y. et al. Ensembling multiple raw coevolutionary features with deep residual neural networks for contact-map prediction in CASP13. Proteins 87, 1082–1091 (2019).

    Article  Google Scholar 

  16. 16.

    Kandathil, S. M., Greener, J. G. & Jones, D. T. Prediction of interresidue contacts with DeepMetaPSICOV in CASP13. Proteins 87, 1092–1099 (2019).

    Article  Google Scholar 

  17. 17.

    Marks, D. S., Hopf, T. A. & Sander, C. Protein structure prediction from sequence variation. Nat. Biotechnol. 30, 1072 (2012).

    Article  Google Scholar 

  18. 18.

    Kamisetty, H., Ovchinnikov, S. & Baker, D. Assessing the utility of coevolution-based residue–residue contact predictions in a sequence- and structure-rich era. Proc. Natl Acad. Sci. USA 110, 15674–15679 (2013).

    Article  Google Scholar 

  19. 19.

    Seemayer, S., Gruber, M. & Söding, J. CCMpred—fast and precise prediction of protein residue–residue contacts from correlated mutations. Bioinformatics 30, 3128–3130 (2014).

    Article  Google Scholar 

  20. 20.

    Liu, Y. et al. Enhancing evolutionary couplings with deep convolutional neural networks. Cell Syst. 6, 65–74 (2018).

    Article  Google Scholar 

  21. 21.

    AlQuraishi, M. End-to-end differentiable learning of protein structure. Cell Syst. 8, 292–301 (2019).

    Article  Google Scholar 

  22. 22.

    Chaudhury, S., Lyskov, S. & Gray, J. J. PyRosetta: a script-based interface for implementing molecular modeling algorithms using Rosetta. Bioinformatics 26, 689–691 (2010).

    Article  Google Scholar 

  23. 23.

    Jones, D. T. et al. MetaPSICOV: combining coevolution methods for accurate prediction of contacts and long range hydrogen bonding in proteins. Bioinformatics 31, 999–1006 (2015).

    Article  Google Scholar 

  24. 24.

    Eickholt, J. & Cheng, J. Predicting protein residue–residue contacts using deep networks and boosting. Bioinformatics 28, 3066–3072 (2012).

    Article  Google Scholar 

  25. 25.

    Steinegger, M. & Soding, J. Clustering huge protein sequence sets in linear time. Nat. Commun. 9, 2542 (2018).

    Article  Google Scholar 

  26. 26.

    Kim, D. E., Chivian, D. & Baker, D. Protein structure prediction and analysis using the Robetta server. Nucleic Acids Res. 32, W526–W531 (2004).

    Article  Google Scholar 

  27. 27.

    Xu, C. F. et al. Computational design of transmembrane pores. Nature 585, 129–134 (2020).

    Article  Google Scholar 

  28. 28.

    Lu, P. L. et al. Accurate computational design of multipass transmembrane proteins. Science 359, 1042–1046 (2018).

    Article  Google Scholar 

  29. 29.

    Pan, X. J. et al. Expanding the space of protein geometries by computational design of de novo fold families. Science 369, 1132–1136 (2020).

    Article  Google Scholar 

  30. 30.

    Chen, I. M. A. et al. The IMG/M data management and analysis system v.6.0: new tools and advanced capabilities. Nucleic Acids Res. 49, D751–D763 (2021).

    Article  Google Scholar 

  31. 31.

    Steinegger, M., Mirdita, M. & Soding, J. Protein-level assembly increases protein sequence recovery from metagenomic samples manyfold. Nat. Methods 16, 603–606 (2019).

    Article  Google Scholar 

  32. 32.

    Mitchell, A. L. et al. MGnify: the microbiome analysis resource in 2020. Nucleic Acids Res. 48, D570–D578 (2020).

    Google Scholar 

  33. 33.

    Rives, A. et al. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc. Natl Acad. Sci. USA 118, e2016239118 (2021).

    Article  Google Scholar 

  34. 34.

    Wang, G. L. & Dunbrack, R. L. PISCES: a protein sequence culling server. Bioinformatics 19, 1589–1591 (2003).

    Article  Google Scholar 

  35. 35.

    Remmert, M. et al. HHblits: lightning-fast iterative protein sequence searching by HMM-HMM alignment. Nat. Methods 9, 173–175 (2012).

    Article  Google Scholar 

  36. 36.

    Zhang, Y. & Skolnick, J. TM-align: a protein structure alignment algorithm based on the TM-score. Nucleic Acids Res. 33, 2302–2309 (2005).

    Article  Google Scholar 

  37. 37.

    Mirdita, M. et al. Uniclust databases of clustered and deeply annotated protein sequences and alignments. Nucleic Acids Res. 45, D170–D176 (2017).

    Article  Google Scholar 

  38. 38.

    Johnson, L. S., Eddy, S. R. & Portugaly, E. Hidden Markov model speed heuristic and iterative HMM search procedure. BMC Bioinformatics 11, 431 (2010).

    Article  Google Scholar 

  39. 39.

    Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. In 7th International Conference on Learning Representations (ICLR, 2019).

  40. 40.

    Zhao, F. & Xu, J. A position-specific distance-dependent statistical potential for protein structure and functional study. Structure 20, 1118–1126 (2012).

    Article  Google Scholar 

  41. 41.

    Zhou, H. Y. & Zhou, Y. Q. Distance-scaled, finite ideal-gas reference state improves structure-derived potentials of mean force for structure selection and stability prediction. Protein Sci. 11, 2714–2726 (2002); erratum 12, 2121 (2003).

    Article  Google Scholar 

  42. 42.

    Shen, M. Y. & Sali, A. Statistical potential for assessment and prediction of protein structures. Protein Sci. 15, 2507–2524 (2006).

    Article  Google Scholar 

  43. 43.

    Zhang, Y. & Skolnick, J. SPICKER: a clustering approach to identify near-native protein folds. J. Comput. Chem. 25, 865–871 (2004).

    Article  Google Scholar 

  44. 44.

    Xu, J. R. & Zhang, Y. How significant is a protein structure similarity with TM-score = 0.5? Bioinformatics 26, 889–895 (2010).

    Article  Google Scholar 

Download references

Acknowledgements

We thank J. Yang and I. Anishchanka for their very helpful discussions, providing trRosetta results and helping with PyRosetta. We thank I. Anishchanka for providing the MSAs built by the Baker human group for the CASP14 targets. This work is supported by National Institutes of Health grant no. R01GM089753 (J.X.) and National Science Foundation grant no. DBI1564955 (J.X.). The funders had no role in study design, data collection and analysis, decision to publish or preparation of the manuscript.

Author information

Affiliations

Authors

Contributions

J.X. conceived the whole project, implemented and tested the code, and wrote the manuscript. M.M. studied the gradient-based energy minimization algorithm and revised the manuscript. J.L. studied the deep learning algorithms, trained some ResNet models and generated the RGN results.

Corresponding author

Correspondence to Jinbo Xu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Peer review information Nature Machine Intelligence thanks Jeffrey Gray, Sai Pooja Mahajan and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Extended data

Extended Data Fig. 1 Distance matrices predicted for T0969-D1 by deep ResNet.

Distance matrices predicted for T0969-D1 by deep ResNet when co-evolution is not used (left) and used (right). Only distance predictions less than 15Å are displayed in color. In each picture, native distance and predicted distance are shown below and above the diagonal, respectively.

Supplementary information

Supplementary Information

Supplementary Fig. 1 and Table 1.

Reporting Summary

Supplementary Data 1

Data for the ablation study of contact prediction accuracy on CASP13 FM targets.

Supplementary Data 2

Detailed 3D modelling accuracy on CASP13 FM targets.

Supplementary Data 3

Data for the ablation study of 3D modelling accuracy on CASP13 FM targets.

Supplementary Data 4

Detailed 3D modelling accuracy on human-designed proteins.

Supplementary Data 5

CASP13 FM domain sequences defined by the RaptorX server in the CASP13 session.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Xu, J., McPartlon, M. & Li, J. Improved protein structure prediction by deep learning irrespective of co-evolution information. Nat Mach Intell (2021). https://doi.org/10.1038/s42256-021-00348-5

Download citation

Search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing