Abstract
The fast motions of proteins at the picosecond to nanosecond timescale, known as fast dynamics, are closely related to protein conformational entropy and rearrangement, which in turn affect catalysis, ligand binding and protein allosteric effects. The most used NMR approach to study fast protein dynamics is the model free method, which uses order parameter S2 to describe the amplitude of the internal motion of local group. However, to obtain order parameter through NMR experiments is quite complex and lengthy. In this paper, we present a machine learning approach for predicting backbone 1H-15N order parameters based on protein NMR structure ensemble. A random forest model is used to learn the relationship between order parameters and structural features. Our method achieves high accuracy in predicting backbone 1H-15N order parameters for a test dataset of 10 proteins, with a Pearson correlation coefficient of 0.817 and a root-mean-square error of 0.131.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Alzubaidi L et al (2021) Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data 8:53
Andersen CAF, Palmer AG, Brunak S, Rost B (2002) Continuum secondary structure captures protein flexibility. Structure (London) 10:175–184
Berjanskii M, Wishart DS (2006) NMR: prediction of protein flexibility. Nat Protoc 1:683–688
Biau G, Scornet E (2016) A random forest guided tour. TEST 25:197–227
Biological Magnetic Resonance Data Bank. https://bmrb.io/
Bockting CL, van Dis EAM, Bollen J, van Rooij R, Zuidema W (2023) ChatGPT: five priorities for research. Nature 614:224–226
Breiman L (2001) Random forests. Mach Learn 45:5–32
Cala O, Guilliere F, Krimm I (2014) NMR-based analysis of protein-ligand interactions. Anal Bioanal Chem 406:943–956
Chao F-A, Zhang Y, Byrd RA (2022) Facilitating spectral analyses, simplification, and new tools through deep neural networks. Magnet Reson Lett 2:56–58
Cilia E, Pancsa R, Tompa P, Lenaerts T, Vranken WF (2013) From protein sequence to dynamics and disorder with DynaMine. Nat Commun 4:2741
Clore GM et al (1990) Deviations from the simple two-parameter model-free approach to the interpretation of nitrogen-15 nuclear magnetic relaxation of proteins. J Am Chem Soc 112:4989–4991
Fowler NJ, Sljoka A, Williamson MP (2020) A method for validating the accuracy of NMR protein structures. Nature Communications 11:6321
Gáspári Z, Perczel A (2010) Chapter 2 – Protein dynamics as reported by NMR. In: Webb GA (eds) Annual reports on NMR spectroscopy, vol 71. Academic Press, pp 35–75
Gobl C, Madl T, Simon B, Sattler M (2014) NMR approaches for structural analysis of multidomain proteins and complexes in solution. Prog Nucl Magnet Reson Spectrosc 80:26–63
Grimaldo M, Roosen-Runge F, Zhang F, Schreiber F, Seydel T (2019) Dynamics of proteins in solution. Quart Rev Biophys 52:e7
Hu Y, Jin C (2022) Conformational dynamics in GPCR signaling by NMR. Magnet Reson Lett 2:139–146
Huang S-W, Shih C-H, Lin C-P, Hwang J-K (2008) Prediction of NMR order parameters in proteins using weighted protein contact-number model. Theor Chem Acc 121:197–200
Jarymowycz VA, Stone MJ (2006) Fast time scale dynamics of protein backbones: NMR relaxation methods, applications, and functional consequences. Chem Rev 106:1624–1671
Jumper J et al (2021) Highly accurate protein structure prediction with AlphaFold. Nature 596:583–589
Kabsch W, Sander C (1983) Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features. Biopolymers: Orig Res Biomol 22:2577–2637
Kleckner IR, Foster MP (2011) An introduction to NMR-based approaches for measuring protein dynamics. Biochimica Et Biophysica Acta-Prot Proteomics 1814:942–968
Kovermann M, Rogne P, Wolf-Watz M (2016) Protein dynamics and function from solution state NMR spectroscopy. Quart Rev Biophys 49:e6
Lipari G, Szabo A (1982) Model-free approach to the interpretation of nuclear magnetic resonance relaxation in macromolecules. 1. Theory and range of validity. J Am Chem Soc 104:4546–4559
Lipari G, Szabo A (1982) Model-free approach to the interpretation of nuclear magnetic resonance relaxation in macromolecules 2. Analysis of experimental results. J Am Chem Soc 104:4559–4570
Ma PY, Li DW, Bruschweiler R (2023) Predicting protein flexibility with AlphaFold. Prot Struct Funct Bioinformatics 91:847–855
Ming DM, Bruschweiler R (2006) Reorientational contact-weighted elastic network model for the prediction of protein dynamics: comparison with NMR relaxation. Biophys J 90:3382–3388
Ortega G, Pons M, Millet O (2013) Chapter Six – Protein functional dynamics in multiple timescales as studied by NMR spectroscopy. In: T Karabencheva-Christova (ed) Advances in protein chemistry and structural biology, vol 92. Academic Press, pp 219–251
Peti W, Meiler J, Brüschweiler R, Griesinger C (2002) Model-free analysis of protein backbone motion from residual dipolar couplings. J Am Chem Soc 124:5822–5833
RCSB Protein Data Bank. https://www.rcsb.org/
Sekhar A, Kay LE (2019) An NMR View of protein dynamics in health and disease. In: Dill KA (eds) Annual review of biophysics, vol 48, pp 297–319
Trott O, Siggers K, Rost B, Palmer AG III (2008) Protein conformational flexibility prediction using machine learning. J Magnet Reson 192:37–47
Tzeng SR, Kalodimos CG (2011) Protein dynamics and allostery: an NMR view. CurrOpin Struct Biol 21:62–67
Vera R, Synsmir-Zizzamia M, Ojinnaka S, Snyder DA (2018) Prediction of protein flexibility using a conformationally restrained contact map. Prot Struct Funct Bioinformatics 86:1111–1116
Zhang FL, Bruschweiler R (2002) Contact model for the prediction of NMR N-H order parameters in globular proteins. J Am Chem Soc 124:12654–12655
Zhang H et al (2009) On the relation between residue flexibility and local solvent accessibility in proteins. Prot: Struct Funct Bioinformatics 76:617–636
Zhou ZH (2021) Machine learning. Springer Nature
Acknowledgements
This work was supported by the National Key Research and Development Program of China (2018YFA0704002, 2018YFE0202300), National Natural Science Foundation of China (21991081, 21921004, 21974149, 22327901), and the Strategic Priority Research Program of the Chinese Academy of Sciences (XDB0540301).
Author information
Authors and Affiliations
Contributions
Q. Wang, Z. Miao, X. Xiao and B. Jiang wrote codes, scripts, and main manuscript. Q. Wang and Z. Miao prepared figures. B. Jiang and M. Liu instructed the whole research. X. Zhang and D. Yang gave some valuable suggestion. All authors reviewed the manuscript.
Corresponding authors
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
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wang, Q., Miao, Z., Xiao, X. et al. Prediction of order parameters based on protein NMR structure ensemble and machine learning. J Biomol NMR (2024). https://doi.org/10.1007/s10858-024-00435-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10858-024-00435-w