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.

  • Article
  • Published:

AmoebaContact and GDFold as a pipeline for rapid de novo protein structure prediction

Nature Machine Intelligence volume 2, pages 25–33 (2020)Cite this article

Subjects

A preprint version of the article is available at arXiv.

Abstract

Predicting the structures of proteins from amino acid sequences is of great importance. Recently, the accuracy of de novo protein structure prediction has been substantially improved when assisted by information about the contact between residues, which is also predictable from the sequence. Here, we present a novel pipeline for rapid protein structure prediction, which consists of a residue contact predictor, AmoebaContact, and a contact-assisted folder, GDFold. Unlike mainstream contact predictors that utilize simple, regularized neural networks, AmoebaContact adopts a set of network architectures that are optimized for contact prediction through automatic searching, and it predicts contacts at a series of cutoffs. Unlike conventional contact-assisted folders that only use top-scored contact pairs, GDFold considers all residue pairs from the prediction results of AmoebaContact in a differentiable loss function and optimizes atom coordinates using the gradient descent algorithm. The combination of AmoebaContact and GDFold allows quick modelling of the protein structure with acceptable model quality.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: General flow chart of the AmoebaContact and GDFold pipeline.
Fig. 2: Model evolution in the AmoebaNet architecture searching process.
Fig. 3: The performance of augmented models.
Fig. 4: Detailed comparison of AmoebaContact and GDFold against RaptorX-Contact.
Fig. 5: Case study.

Similar content being viewed by others

Data availability

The data required for running this pipeline for all proteins in the test sets are available on Code Ocean (https://doi.org/10.24433/CO.4945300.v1)49.

Code availability

All source codes and models of AmoebaContact and GDFold are openly available on Code Ocean (https://doi.org/10.24433/CO.4945300.v1)49. The codes for extracting protein features, for training the modified AmoebaNet pipeline and for optimizing the chosen network models are available on GitHub (https://github.com/THU-gonglab/AmoebaContact). An online server for AmoebaContact and GDFold has been prepared and is available at http://structpred.life.tsinghua.edu.cn/amoebacontact.html.

References

  1. Ekeberg, M., Lövkvist, C., Lan, Y., Weigt, M. & Aurell, E. Improved contact prediction in proteins: using pseudolikelihoods to infer Potts models. Phys. Rev. E 87, 012707 (2013).

    Article  Google Scholar 

  2. Jones, D. T., Buchan, D. W., Cozzetto, D. & Pontil, M. PSICOV: precise structural contact prediction using sparse inverse covariance estimation on large multiple sequence alignments. Bioinformatics 28, 184–190 (2011).

    Article  Google Scholar 

  3. 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 

  4. Weigt, M., White, R. A., Szurmant, H., Hoch, J. A. & Hwa, T. Identification of direct residue contacts in protein–protein interaction by message passing. Proc. Natl Acad. Sci. USA 106, 67–72 (2009).

    Article  Google Scholar 

  5. Wang, S., Sun, S., Li, Z., Zhang, R. & Xu, J. Accurate de novo prediction of protein contact map by ultra-deep learning model. PLoS Comput. Biol. 13, e1005324 (2017).

    Article  Google Scholar 

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

    Article  Google Scholar 

  7. 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 

  8. Li, Y., Zhang, C., Bell, E. W., Yu, D. J. & Zhang, Y. Ensembling multiple raw coevolutionary features with deep residual neural networks for contact-map prediction in CASP13. Proteins 87, 1092–1099 (2019).

    Article  Google Scholar 

  9. Fariselli, P., Olmea, O., Valencia, A. & Casadio, R. Prediction of contact maps with neural networks and correlated mutations. Protein Eng. 14, 835–843 (2001).

    Article  Google Scholar 

  10. Andreani, J. & Söding, J. bbcontacts: prediction of β-strand pairing from direct coupling patterns. Bioinformatics 31, 1729–1737 (2015).

    Article  Google Scholar 

  11. Mao, W., Wang, T., Zhang, W. & Gong, H. Identification of residue pairing in interacting β-strands from a predicted residue contact map. BMC Bioinformatics 19, 146 (2018).

    Article  Google Scholar 

  12. Elsken, T., Metzen, J. H. & Hutter, F. Neural architecture search: a survey. J. Mach. Learn. Res. 20, 1–21 (2019).

    MathSciNet  MATH  Google Scholar 

  13. Zhong, Z., Yan, J., Wu, W., Shao, J. & Liu, C.-L. Practical block-wise neural network architecture generation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2423–2432 (2018).

  14. Zoph, B., Vasudevan, V., Shlens, J. & Le, Q. V. Learning transferable architectures for scalable image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 8697–8710 (2018).

  15. Chrabaszcz, P., Loshchilov, I. & Hutter, F. A downsampled variant of ImageNet as an alternative to the CIFAR datasets. Preprint at https://arxiv.org/abs/1707.08819 (2017).

  16. Domhan, T., Springenberg, J. T. & Hutter, F. Speeding up automatic hyperparameter optimization of deep neural networks by extrapolation of learning curves. Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence 3460-3468 (2015).

  17. Klein, A., Falkner, S., Bartels, S., Hennig, P. & Hutter, F. Fast Bayesian optimization of machine learning hyperparameters on large datasets. Preprint at https://arxiv.org/abs/1605.07079 (2016).

  18. Real, E., Aggarwal, A., Huang, Y. & Le, Q. V. Regularized evolution for image classifier architecture search. Preprint at https://arxiv.org/abs/1802.01548 (2018).

  19. Zela, A., Klein, A., Falkner, S. & Hutter, F. Towards automated deep learning: efficient joint neural architecture and hyperparameter search. Preprint at https://arxiv.org/pdf/1807.06906.pdf (2018).

  20. Bergstra, J., Yamins, D. & Cox, D. D. Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures. Proceedings of the 30th International Conference on Machine Learning 28, 115–123 (2013).

  21. Mendoza, H., Klein, A., Feurer, M., Springenberg, J. T. & Hutter, F. Towards automatically-tuned neural networks. Proceedings of the Workshop on Automatic Machine Learning 64, 58–65 (2016).

  22. Elsken, T., Metzen, J. H. & Hutter, F. Efficient multi-objective neural architecture search via Lamarckian evolution. Preprint at https://arxiv.org/abs/1804.09081 (2018).

  23. Real, E. et al. Large-scale evolution of image classifiers. Proceedings of the 34th International Conference on Machine Learning 70, 2902–2911 (2017).

  24. Baker, B., Gupta, O., Naik, N. & Raskar, R. Designing neural network architectures using reinforcement learning. Preprint at https://arxiv.org/abs/1611.02167 (2016).

  25. Zoph, B. & Le, Q. V. Neural architecture search with reinforcement learning. Preprint at https://arxiv.org/abs/1611.01578 (2016).

  26. Liu, H., Simonyan, K. & Yang, Y. Darts: differentiable architecture search. Preprint at https://arxiv.org/abs/1806.09055 (2018).

  27. Zheng, W. et al. Deep-learning contact-map guided protein structure prediction in CASP13. Proteins 87, 1049–1164 (2019).

    Google Scholar 

  28. Adhikari, B., Bhattacharya, D., Cao, R. & Cheng, J. CONFOLD: residue–residue contact‐guided ab initio protein folding. Proteins 83, 1436–1449 (2015).

    Article  Google Scholar 

  29. Adhikari, B. & Cheng, J. CONFOLD2: improved contact-driven ab initio protein structure modeling. BMC Bioinformatics 19, 22 (2018).

    Article  Google Scholar 

  30. Senior, A. W. et al. Protein structure prediction using multiple deep neural networks in CASP13. Proteins 87, 1041–1148 (2019).

    Article  Google Scholar 

  31. He, K., Zhang, X., Ren, S. & Sun, J. Identity mappings in deep residual networks. In European Conference on Computer Vision 630–645 (2016).

  32. Schaarschmidt, J., Monastyrskyy, B., Kryshtafovych, A. & Bonvin, A. Assessment of contact predictions in CASP12: co-evolution and deep learning coming of age. Proteins 86(Suppl. 1), 51–66 (2018).

    Article  Google Scholar 

  33. Sillitoe, I. et al. CATH: comprehensive structural and functional annotations for genome sequences. Nucleic Acids Res. 43, D376–D381 (2014).

    Article  Google Scholar 

  34. Deming, W. E. Statistical Adjustment of Data (Wiley, 1943).

  35. Xiang, Z. & Honig, B. Jackal: A Protein Structure Modeling Package. (Columbia University and Howard Hughes Medical Institute: 2002). http://honig.c2b2.columbia.edu/jackal.

  36. Xiang, Z. & Honig, B. Extending the accuracy limits of prediction for side-chain conformations. J. Mol. Biol. 311, 421–430 (2001).

    Article  Google Scholar 

  37. Moult, J., Fidelis, K., Kryshtafovych, A., Schwede, T. & Tramontano, A. Critical assessment of methods of protein structure prediction: progress and new directions in round XI. Proteins 84, 4–14 (2016).

    Article  Google Scholar 

  38. Moult, J., Fidelis, K., Kryshtafovych, A., Schwede, T. & Tramontano, A. Critical assessment of methods of protein structure prediction (CASP)—round XII. Proteins 86, 7–15 (2018).

    Article  Google Scholar 

  39. Kryshtafovych, A., Schwede, T., Topf, M., Fidelis, K. & Moult, J. Critical assessment of methods of protein structure prediction (CASP)—round XIII. Proteins 87, 1011–1020 (2019).

    Article  Google Scholar 

  40. Dawson, N. L. et al. CATH: an expanded resource to predict protein function through structure and sequence. Nucleic Acids Res. 45, D289–D295 (2016).

    Article  Google Scholar 

  41. Remmert, M., Biegert, A., Hauser, A. & Söding, J. HHblits: lightning-fast iterative protein sequence searching by HMM–HMM alignment. Nat. Methods 9, 173 (2012).

    Article  Google Scholar 

  42. Apweiler, R. et al. UniProt: the universal protein knowledgebase. Nucleic Acids Res. 32, D115–D119 (2004).

    Article  Google Scholar 

  43. Gloor, G. B., Martin, L. C., Wahl, L. M. & Dunn, S. D. Mutual information in protein multiple sequence alignments reveals two classes of coevolving positions. Biochemistry 44, 7156–7165 (2005).

    Article  Google Scholar 

  44. Wang, S., Peng, J., Ma, J. & Xu, J. Protein secondary structure prediction using deep convolutional neural fields. Sci. Rep. 6, 18962 (2016).

    Article  Google Scholar 

  45. Wang, S., Weng, S., Ma, J. & Tang, Q. DeepCNF-D: predicting protein order/disorder regions by weighted deep convolutional neural fields. Int. J. Mol. Sci. 16, 17315–17330 (2015).

    Article  Google Scholar 

  46. Heffernan, R., Yang, Y., Paliwal, K. & Zhou, Y. Capturing non-local interactions by long short-term memory bidirectional recurrent neural networks for improving prediction of protein secondary structure, backbone angles, contact numbers and solvent accessibility. Bioinformatics 33, 2842–2849 (2017).

    Article  Google Scholar 

  47. Ioffe, S. & Szegedy, C. Batch normalization: accelerating deep network training by reducing internal covariate shift. Preprint at https://arxiv.org/abs/1502.03167 (2015).

  48. Ulyanov, D., Vedaldi, A. & Lempitsky, V. Instance normalization: the missing ingredient for fast stylization. Preprint at https://arxiv.org/abs/1607.08022 (2016).

  49. Mao, W., Ding, W., Xing, Y. & Gong, H. AmoebaContact and GDFold as a New Pipeline for Rapid De Novo Protein Structure Prediction (Code Ocean, 2019); https://doi.org/10.24433/CO.4945300.v1

Download references

Acknowledgements

This work has been supported by the National Natural Science Foundation of China (31670723, 91746119, 81861138009 and 31621092) and by the Beijing Advanced Innovation Center for Structural Biology.

Author information

Authors and Affiliations

  1. MOE Key Laboratory of Bioinformatics, School of Life Sciences, Tsinghua University, Beijing, China

    Wenzhi Mao, Wenze Ding, Yaoguang Xing & Haipeng Gong

  2. Beijing Advanced Innovation Center for Structural Biology, Tsinghua University, Beijing, China

    Wenzhi Mao, Wenze Ding, Yaoguang Xing & Haipeng Gong

Authors
  1. Wenzhi Mao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wenze Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yaoguang Xing
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Haipeng Gong
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

W.M. contributed to the methodology, experimental design, software, formal analysis and writing of the original draft. W.D. contributed to the web server and was involved in data analysis. Y.X. contributed to model optimization and was involved in data analysis. H.G. contributed to the experimental design and was responsible for supervision, writing (review and revision) as well as funding acquisition. All authors reviewed the final manuscript.

Corresponding author

Correspondence to Haipeng Gong.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

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

Supplementary information

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mao, W., Ding, W., Xing, Y. et al. AmoebaContact and GDFold as a pipeline for rapid de novo protein structure prediction. Nat Mach Intell 2, 25–33 (2020). https://doi.org/10.1038/s42256-019-0130-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42256-019-0130-4

This article is cited by

Search

Advanced 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