Abstract
Protein classification is the first step to functional annotation; SCOP and Pfam databases are currently the most relevant protein classification schemes. However, the disproportion in the number of three dimensional (3D) protein structures generated versus their classification into relevant superfamilies/families emphasizes the need for automated classification schemes. Predicting function of novel proteins based on sequence information alone has proven to be a major challenge.
The present study focuses on the use of physicochemical parameters in conjunction with machine learning algorithms (Naive Bayes, Decision Trees, Random Forest and Support Vector Machines) to classify proteins into their respective SCOP superfamily/Pfam family, using sequence derived information. Spectrophores™, a 1D descriptor of the 3D molecular field surrounding a structure was used as a benchmark to compare the performance of the physicochemical parameters. The machine learning algorithms were modified to select features based on information gain for each SCOP superfamily/Pfam family. The effect of combining physicochemical parameters and spectrophores on classification accuracy (CA) was studied.
Machine learning algorithms trained with the physicochemical parameters consistently classified SCOP superfamilies and Pfam families with a classification accuracy above 90%, while spectrophores performed with a CA of around 85%. Feature selection improved classification accuracy for both physicochemical parameters and spectrophores based machine learning algorithms. Combining both attributes resulted in a marginal loss of performance. Physicochemical parameters were able to classify proteins from both schemes with classification accuracy ranging from 90–96%. These results suggest the usefulness of this method in classifying proteins from amino acid sequences.
Similar content being viewed by others
References
Altschul, S.F., Gish, W., Miller, W., Myers, E.W., Lipman, D.J. 1990. Basic local alignment search tool. J Mol Biol 215, 403–410.
Ankerst, M., Kastenmüller, G., Kriegel, H.P., Seidl, T., et al., 1999. Nearest neighbor classification in 3d protein databases. In Proceedings of the Seventh International Conference on Intelligent Systems for Molecular Biology, 34–43.
Arumugam, G., Nair, A.G., Hariharaputran, S., Ramanathan, S. 2013. Rebelling for a reason: Protein structural outliers. PloS one 8, e74416.
Ashby, C., Johnson, D., Walker, K., Kanj, I.A., Xia, G., Huang, X. 2013. New enumeration algorithm for protein structure comparison and classification. BMC Genomics 14, S1.
Atsushi, I. 1980. Thermostability and aliphatic index of globular proteins. J Biochem 88, 1895–1898.
Bhasin, M., Raghava, G. 2004. Eslpred: Svm-based method for subcellular localization of eukaryotic proteins using dipeptide composition and psi-blast. Nucleic Acids Res 32, W414–W419.
Blomberg, N., Nilges, M. 1997. Functional diversity of ph domains: an exhaustive modelling study. Fold Des 2, 343–355.
Bultinck, P., Langenaeker, W., Lahorte, P., De Proft, F., Geerlings, P., Waroquier, M., Tollenaere, J. 2002. The electronegativity equalization method I: Parametrization and validation for atomic charge calculations. J Phys Chem A 106, 7887–7894.
Casbon, J., Saqi, M. 2006. Functional diversity within proteins superfamilies. Journal of Integrative Bioinformatics 3.
Chan, H.S., Dill, K.A. 1994. Transition states and folding dynamics of proteins and heteropolymers. J Chem Phys 100, 9238.
Demšar, J., Zupan, B., Leban, G., Curk, T. 2004. Orange: From experimental machine learning to interactive data mining. Springer, Berlin, Heidelberg, pp 537–539.
Dhir, C., Iqbal, N., Lee, S.Y. 2007. Efficient feature selection based on information gain criterion for face recognition. In Information Acquisition, 2007. ICIA’07. International Conference on. IEEE, 523–527.
Dyda, F., Klein, D.C., Hickman, A.B. 2000. Gcn5-related n-acetyltransferases: a structural overview. Annu Rev Bioph Biom 29, 81–103.
Elofsson, A., Heijne, G.V. 2007. Membrane protein structure: prediction versus reality. Annu Rev Biochem 76, 125–140.
Erdmann, M.A. 2005. Protein similarity from knot theory: geometric convolution and line weavings. J Comput Biol 12, 609–637.
Esposito, F., Malerba, D., Semeraro, G., Kay, J. 1997. A comparative analysis of methods for pruning decision trees. IEEE T Pattern Anal 19, 476–491.
Frank, E., Hall, M., Pfahringer, B. 2002. Locally weighted naive bayes. In Proceedings of the Nineteenth conference on Uncertainty in Artificial Intelligence. Morgan Kaufmann Publishers Inc., 249–256.
Gonnet, G.H., Cohen, M.A., Benner, S.A. 1992. Exhaustive matching of the entire protein sequence database. Science 256, 1443–1445.
Hand, D.J., Yu, K. 2001. Idiot’s bayes not so stupid after all? Int Stat Rev 69, 385–398.
Henikoff, S., Henikoff, J.G. 1992. Amino acid substitution matrices from protein blocks. P Natl Acad Sci USA 89, 10915–10919.
Hobohm, U., Sander, C. 1995. A sequence property approach to searching protein databases. J Mol Biol 251, 390–399.
Holm, L., Sander, C. 1996. The fssp database: fold classification based on structure-structure alignment of proteins. Nucleic Acids Res 24, 206–209.
Idicula-Thomas, S., Balaji, P.V. 2005. Understanding the relationship between the primary structure of proteins and its propensity to be soluble on overexpression in escherichia coli. Protein Sci 14, 582–592.
Jain, P., Hirst, J.D. 2010. Automatic structure classification of small proteins using random forest. BMC bioinformatics 11, 364.
Kim, Y.J., Patel, J.M. 2006. A framework for protein structure classification and identification of novel protein structures. BMC bioinformatics 7, 456.
Livingston, F. 2005. Implementation of breiman’s random forest machine learning algorithm. ECE591Q Machine Learning Journal Paper.
Lu, Z., Szafron, D., Greiner, R., Lu, P., Wishart, D.S., Poulin, B., Anvik, J., Macdonell, C., Eisner, R. 2004. Predicting subcellular localization of proteins using machine-learned classifiers. Bioinformatics 20, 547–556.
Ma, B., Elkayam, T., Wolfson, H., Nussinov, R. 2003. Protein-protein interactions: Structurally conserved residues distinguish between binding sites and exposed protein surfaces. P Natl Acad Sci USA 100, 5772–5777.
Mohan, A., Anishetty, S., Gautam, P. 2010. Global metal-ion binding protein fingerprint: A method to identify motif-less metal-ion binding proteins. J Bioinform Comput Biol 8, 717–726.
Momany, F. 1978. Determination of partial atomic charges from ab initio molecular electrostatic potentials. Application to formamide, methanol, and formic acid. J Phys Chem 82, 592–601.
Murzin, A.G., Brenner, S.E., Hubbard, T., Chothia, C. 1995. Scop: a structural classification of proteins database for the investigation of sequences and structures. J Mol Biol 247, 536–540.
Ooms, F., Wouters, J., Collin, S., Durant, F., Jegham, S., George, P. 1998. Molecular lipophilicity potential by clip, a reliable tool for the description of the 3d distribution of lipophilicity: application to 3-phenyloxazolidin-2-one, a prototype series of reversible maoa inhibitors. Bioorg Med Chem Lett 8, 1425–1430.
Pearson, W.R. 1991. Searching protein sequence libraries: comparison of the sensitivity and selectivity of the smith-waterman and fasta algorithms. Genomics 11, 635–650.
Rasoul, S., David, L. 1991. A survey of decision tree classifier methodology. IEEE Trans Syst Man Cybern 21, 660–674.
Rice, P., Longden, I., Bleasby, A. 2000. Emboss: the european molecular biology open software suite. Trends Genet 16, 276–277.
Røgen, P., Fain, B. 2003. Automatic classification of protein structure by using gauss integrals. P Natl Acad Sci USA 100, 119–124.
Santini, G., Soldano, H., Pothier, J. 2012. Automatic classification of protein structures relying on similarities between alignments. BMC bioinformatics 13, 233.
Shen, J., Zhang, J., Luo, X., Zhu, W., Yu, K., Chen, K., Li, Y., Jiang, H. 2007. Predicting protein-protein interactions based only on sequences information. P Natl Acad Sci USA 104, 4337–4341.
Shirota, M., Ishida, T., Kinoshita, K. 2008. Effects of surface-to-volume ratio of proteins on hydrophilic residues: Decrease in occurrence and increase in buried fraction. Protein Sci 17, 1596–1602.
Söding, J., Biegert, A., Lupas, A.N. 2005. The hhpred interactive server for protein homology detection and structure prediction. Nucleic Acids Res 33, W244–W248.
Sun, X.D., Huang, R.B. 2006. Prediction of protein structural classes using support vector machines. Amino Acids 30, 469–475.
Thijs, G., Langenaeker, W., De Winter, H. 2011. Application of spectrophores to map vendor chemical space using self-organising maps. J Cheminformatics 3, 1–1.
Vasanthanathan, P., Taboureau, O., Oostenbrink, C., Vermeulen, N.P.E., Olsen, L., Jrgensen, F.S. 2009. Classification of cytochrome p450 1a2 inhibitors and noninhibitors by machine learning techniques. Drug Metab Dispos 37, 658–664.
Wang, G., Lochovsky, F.H. 2004. Feature selection with conditional mutual information maximin in text categorization. In Proceedings of the thirteenth ACM international conference on Information and knowledge management. ACM, 342–349.
Wildman, S.A., Crippen, G.M. 1999. Prediction of physicochemical parameters by atomic contributions. J Chem Inf Comp Sci 39, 868–873.
Wu, C.H., Huang, H., Yeh, L.S.L., Barker, W.C. 2003. Protein family classification and functional annotation. Comput Biol Chem 27, 37–47.
Author information
Authors and Affiliations
Corresponding author
Additional information
Equal contribution
Rights and permissions
About this article
Cite this article
Mohan, A., Divya Rao, M., Sunderrajan, S. et al. Automatic classification of protein structures using physicochemical parameters. Interdiscip Sci Comput Life Sci 6, 176–186 (2014). https://doi.org/10.1007/s12539-013-0199-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12539-013-0199-0