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
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$29.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 digital issues and online access to articles
$119.00 per year
only $9.92 per issue
Buy this article
- Purchase on Springer Link
- Instant access to full article PDF
Prices may be subject to local taxes which are calculated during checkout
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
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).
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).
Seemayer, S., Gruber, M. & Söding, J. CCMpred—fast and precise prediction of protein residue–residue contacts from correlated mutations. Bioinformatics 30, 3128–3130 (2014).
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).
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).
Xu, J. Distance-based protein folding powered by deep learning. Proc. Natl Acad. Sci. USA 116, 16856–16865 (2019).
Kandathil, S. M., Greener, J. G. & Jones, D. T. Prediction of interresidue contacts with DeepMetaPSICOV in CASP13. Proteins 87, 1092–1099 (2019).
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).
Fariselli, P., Olmea, O., Valencia, A. & Casadio, R. Prediction of contact maps with neural networks and correlated mutations. Protein Eng. 14, 835–843 (2001).
Andreani, J. & Söding, J. bbcontacts: prediction of β-strand pairing from direct coupling patterns. Bioinformatics 31, 1729–1737 (2015).
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).
Elsken, T., Metzen, J. H. & Hutter, F. Neural architecture search: a survey. J. Mach. Learn. Res. 20, 1–21 (2019).
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).
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).
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).
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).
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).
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).
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).
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).
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).
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).
Real, E. et al. Large-scale evolution of image classifiers. Proceedings of the 34th International Conference on Machine Learning 70, 2902–2911 (2017).
Baker, B., Gupta, O., Naik, N. & Raskar, R. Designing neural network architectures using reinforcement learning. Preprint at https://arxiv.org/abs/1611.02167 (2016).
Zoph, B. & Le, Q. V. Neural architecture search with reinforcement learning. Preprint at https://arxiv.org/abs/1611.01578 (2016).
Liu, H., Simonyan, K. & Yang, Y. Darts: differentiable architecture search. Preprint at https://arxiv.org/abs/1806.09055 (2018).
Zheng, W. et al. Deep-learning contact-map guided protein structure prediction in CASP13. Proteins 87, 1049–1164 (2019).
Adhikari, B., Bhattacharya, D., Cao, R. & Cheng, J. CONFOLD: residue–residue contact‐guided ab initio protein folding. Proteins 83, 1436–1449 (2015).
Adhikari, B. & Cheng, J. CONFOLD2: improved contact-driven ab initio protein structure modeling. BMC Bioinformatics 19, 22 (2018).
Senior, A. W. et al. Protein structure prediction using multiple deep neural networks in CASP13. Proteins 87, 1041–1148 (2019).
He, K., Zhang, X., Ren, S. & Sun, J. Identity mappings in deep residual networks. In European Conference on Computer Vision 630–645 (2016).
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).
Sillitoe, I. et al. CATH: comprehensive structural and functional annotations for genome sequences. Nucleic Acids Res. 43, D376–D381 (2014).
Deming, W. E. Statistical Adjustment of Data (Wiley, 1943).
Xiang, Z. & Honig, B. Jackal: A Protein Structure Modeling Package. (Columbia University and Howard Hughes Medical Institute: 2002). http://honig.c2b2.columbia.edu/jackal.
Xiang, Z. & Honig, B. Extending the accuracy limits of prediction for side-chain conformations. J. Mol. Biol. 311, 421–430 (2001).
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).
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).
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).
Dawson, N. L. et al. CATH: an expanded resource to predict protein function through structure and sequence. Nucleic Acids Res. 45, D289–D295 (2016).
Remmert, M., Biegert, A., Hauser, A. & Söding, J. HHblits: lightning-fast iterative protein sequence searching by HMM–HMM alignment. Nat. Methods 9, 173 (2012).
Apweiler, R. et al. UniProt: the universal protein knowledgebase. Nucleic Acids Res. 32, D115–D119 (2004).
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).
Wang, S., Peng, J., Ma, J. & Xu, J. Protein secondary structure prediction using deep convolutional neural fields. Sci. Rep. 6, 18962 (2016).
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).
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).
Ioffe, S. & Szegedy, C. Batch normalization: accelerating deep network training by reducing internal covariate shift. Preprint at https://arxiv.org/abs/1502.03167 (2015).
Ulyanov, D., Vedaldi, A. & Lempitsky, V. Instance normalization: the missing ingredient for fast stylization. Preprint at https://arxiv.org/abs/1607.08022 (2016).
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
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
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
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
About this article
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
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1038/s42256-019-0130-4
This article is cited by
-
Deep transfer learning for inter-chain contact predictions of transmembrane protein complexes
Nature Communications (2023)
-
Prediction of inter-chain distance maps of protein complexes with 2D attention-based deep neural networks
Nature Communications (2022)
-
Complementing sequence-derived features with structural information extracted from fragment libraries for protein structure prediction
BMC Bioinformatics (2021)
-
The trRosetta server for fast and accurate protein structure prediction
Nature Protocols (2021)
-
Machine learning methods to model multicellular complexity and tissue specificity
Nature Reviews Materials (2021)