Abstract
Precisely inferring the affinities of protein-protein interaction is essential for evaluating different methods of protein-protein docking and their outputs and also opens a door to inferring real status of cellular protein-protein complex. Accumulation of measured affinities of determined protein complex structures with high resolution facilitate the realization of this ambitious goal. Previous physical model based scoring functions failed to predict the affinities of diverse protein complexes. Therefore, accurate method for binding affinity prediction is still extremely challenging. Machine learning methods are promising to address this problem. However, current machine learning methods are not compatible to this task, which obstructs the effective application of these methods. We propose a Wavelet Package Transform (WPT) combined with two-layer support vector regression (TLSVR-WPT) model to implicitly capture binding contributions that are hard to model explicitly. Wavelet package transform greatly reduced the dimension of input features into machine learning model. The TLSVR circumvents both the descriptor compatibility problem and the need for problematic modeling assumptions. Input features for TLSVR first layer are eight features transformed by Wavelet Transform Package from scores of 2209 interacting atom pairs within each distance bin. The output of the first layer is combined by the next layer to infer the final affinities. A satisfactory result of R = 0.81 and SD = 1.40 was achieved when 2209 features were reduced to eight ones by 3-level Wavelet Package Transform. Results demonstrate that wavelet package transform greatly reduced the dimension of the input features into SVR without reducing the accuracy in predicting the protein binding affinity.
M. Zhu and X. Li—Co-first authors.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Li, X., Zhao, Y., Tian, B., Jamaluddin, M., Mitra, A., Yang, J., Rowicka, M., Brasier, A.R., Kudlicki, A.: Modulation of gene expression regulated by the transcription factor NF-κB/RelA. J. Biol. Chem. 289, 11927–11944 (2014)
Li, X., Zhu, M., Brasier, A.R., Kudlicki, A.S.: Inferring genome-wide functional modulatory network: a case study on NF-κB/RelA transcription factor. J. Comput. Biol. 22, 300–312 (2015)
Yang, J., Zhao, Y., Kalita, M., Li, X., Jamaluddin, M., Tian, B., Edeh, C.B., Wiktorowicz, J.E., Kudlicki, A., Brasier, A.R.: Systematic determination of human cyclin dependent kinase (CDK)-9 interactome identifies novel functions in RNA splicing mediated by the DEAD box (DDX)-5/17 RNA helicases. Mol. Cell. Proteomics 14, 2701–2721 (2015)
Li, X., Huang, M., Cao, H., Zhao, J., Yang, M.: Study of low molecular weight effectors on the binding between cell membrane receptor IGF-1R and its substrate protein IRS-1 by SPR biosensor. Sens. Actuators B Chem. 124, 227–236 (2007)
Li, X., Fong, C.-C., Huang, M., Cao, H., Zhao, J., Yang, M.: Measurement of binding kinetics between PI3-K and phosphorylated IGF-1R using a surface plasmon resonance biosensor. Microchim. Acta 162, 253–260 (2008)
Li, X.-L., Huang, M.-H., Cao, H.-M., Chen, Y., Zhao, J.-L., Yang, M.-S.: Phosphorylation of receptor-mimic tyrosine peptide on surface plasmon resonance sensor chip and its interaction with downstream proteins. Chin. J. Anal. Chem. 36, 1327–1332 (2008)
Zhang, J.S., Maslov, S., Shakhnovich, E.I.: Constraints imposed by non-functional protein-protein interactions on gene expression and proteome size. Molecular Syst. Biol. 4, 210 (2008)
Li, X., Zhu, M., Li, X., Wang, H.-Q., Wang, S.: Protein-Protein binding affinity prediction based on an SVR ensemble. In: Huang, D.-S., Jiang, C., Bevilacqua, V., Figueroa, J.C. (eds.) ICIC 2012. LNCS, vol. 7389, pp. 145–151. Springer, Heidelberg (2012). doi:10.1007/978-3-642-31588-6_19
Li, X.-L., Zhu, M., Li, X.-L., Wang, H.-Q., Wang, S.: Protein-Protein interaction affinity prediction based on interface descriptors and machine learning. In: Huang, D.-S., Ma, J., Jo, K.-H., Gromiha, M.M. (eds.) ICIC 2012. LNCS, vol. 7390, pp. 205–212. Springer, Heidelberg (2012). doi:10.1007/978-3-642-31576-3_27
Li, X.-L., Hou, M.-L., Wang, S.-L.: A residual level potential of mean force based approach to predict protein-protein interaction affinity. In: Huang, D.-S., Zhao, Z., Bevilacqua, V., Figueroa, J.C. (eds.) ICIC 2010. LNCS, vol. 6215, pp. 680–686. Springer, Heidelberg (2010). doi:10.1007/978-3-642-14922-1_85
Wolpert, D.H.: Stacked Generalization. Neural Netw. 5, 241–259 (1992)
Teramoto, R., Kashima, H.: Prediction of protein-ligand binding affinities using multiple instance learning. J. Molecular Graphics Modelling 29, 492–497 (2010)
Ballester, P.J., Mitchell, J.B.O.: A machine learning approach to predicting protein-ligand binding affinity with applications to molecular docking. Bioinformatics 26, 1169–1175 (2010)
Li, X.L., Wang, S.L., Hou, M.L.: Specificity of transporter associated with antigen processing protein as revealed by feature selection method. Protein Pept. Lett. 17, 1129–1135 (2010)
Li, X.-L., Wang, S.-L.: A comparative study on feature selection in regression for predicting the affinity of TAP binding peptides. In: Huang, D.-S., Zhang, X., Reyes García, C.A., Zhang, L. (eds.) ICIC 2010. LNCS, vol. 6216, pp. 69–75. Springer, Heidelberg (2010). doi:10.1007/978-3-642-14932-0_9
Wang, R.X., Fang, X.L., Lu, Y.P., Yang, C.Y., Wang, S.M.: The PDBbind database: methodologies and updates. J. Med. Chem. 48, 4111–4119 (2005)
Wang, R.X., Fang, X.L., Lu, Y.P., Wang, S.M.: The PDBbind database: collection of binding affinities for protein-ligand complexes with known three-dimensional structures. J. Med. Chem. 47, 2977–2980 (2004)
Wang, G., Dunbrack Jr., R.L.: PISCES: recent improvements to a PDB sequence culling server. Nucleic Acids Res. 33, W94–W98 (2005)
Su, Y., Zhou, A., **a, X.F., Li, W., Sun, Z.R.: Quantitative prediction of protein-protein binding affinity with a potential of mean force considering volume correction. Protein Sci. 18, 2550–2558 (2009)
Zhang, S., Wang, S., Li, X.: Palmprint linear feature extraction and identification based on ridgelet transforms and rough sets. In: Huang, D.-S., Wunsch, D.C., Levine, D.S., Jo, K.-H. (eds.) ICIC 2008. LNCS, vol. 5227, pp. 1101–1108. Springer, Heidelberg (2008). doi:10.1007/978-3-540-85984-0_132
Coifman, R.R., Wickerhauser, M.V.: Entropy-based algorithms for best basis selection. IEEE Trans. Inf. Theory 38, 713–718 (1992)
Vapnik, V.N.: Statistical Learning Theory. Springer, New York (1998)
Zhang, C., Liu, S., Zhu, Q., Zhou, Y.: A knowledge-based energy function for protein-ligand, protein-protein, and protein-DNA complexes. J. Med. Chem. 48, 2325–2335 (2005)
Kastritis, P.L., Bonvin, A.M.J.J.: Are scoring functions in protein-protein docking ready to predict interactomes? Clues from a novel binding affinity benchmark. J. Proteome Res. 9, 2216–2225 (2010)
Acknowledgements
This work was supported by the National Science Foundation of China, Nos. 31371340, 61273324 & 31271412, Anhui Provincial Natural Science Foundation Grant 1208085MF96, and the Knowledge Innovation Program of Chinese Academy of Sciences, No. 0823A16121.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Zhu, M., Li, X., Sun, B., Nie, J., Wang, S., Li, X. (2017). Protein-Protein Binding Affinity Prediction Based on Wavelet Package Transform and Two-Layer Support Vector Machines. In: Huang, DS., Jo, KH., Figueroa-García, J. (eds) Intelligent Computing Theories and Application. ICIC 2017. Lecture Notes in Computer Science(), vol 10362. Springer, Cham. https://doi.org/10.1007/978-3-319-63312-1_35
Download citation
DOI: https://doi.org/10.1007/978-3-319-63312-1_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-63311-4
Online ISBN: 978-3-319-63312-1
eBook Packages: Computer ScienceComputer Science (R0)