Abstract
Prediction of epitope has great importance in the development of vaccine, drug and peptide libraries and immunologic research. There are very few methods for the prediction of patches containing conformational epitopes, and ninety percent of the epitopes are of conformational type. In this paper, an attempt has been made to propose soft support vector machine model based on the evaluation of different combinations of six scoring functions to predict patches containing conformational epitope. These scoring functions are based on structural properties. The model is implemented on antigen antibody complexes taken from the RCSB protein data bank. This model gives area under curve (AUC) value of 0.6524 which is greater than the AUC value of the existing methods. On evaluation of scoring functions, all scoring functions together give the best results with the highest accuracy of 61.456 for soft SVM and 57.738 for ordinary SVM. This difference in accuracy is due to uncertainty present in the data which ordinary SVM is not able to handle properly. The soft set-based approach incorporates the uncertainty due to parameters in the soft SVM model and leads to improvement in the accuracy of results. These combinations also show the highest sensitivity and Matthews’s correlation coefficient value and F score for soft SVM as compared to ordinary SVM. On the basis of results, it is concluded that the solvation potential, accessible surface area and planarity score have a major correlation with conformational epitope and the combination is recommended for building soft SVM model for prediction of patches containing conformational epitope.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Alix AJ (1999) Predictive estimation of protein linear epitopes by using the program PEOPLE. Vaccine 18(3):311–314
Connolly ML (1983) Solvent-accessible surfaces of proteins and nucleic acids. Science 221(4612):709–713
Gao J, Faraggi E, Zhou Y, Ruan J, Kurgan L (2012) BEST: improved prediction of B-cell epitopes from antigen sequences. PLoS ONE 7(6):e40104
Jones S, Thornton JM (1997) Analysis of protein–protein interaction sites using surface patches. J Mol Biol 272(1):121–132
Kulkarni-Kale U, Bhosle S, Kolaskar AS (2005) CEP: a conformational epitope prediction server. Nucleic Acids Res 33:W168–W171
Larsen JE, Lund O, Nielsen M (2006) Improved method for predicting linear B-cell epitopes. Immunome Res 2(1):2
Liang S, Zheng D, Zhang C, Zacharias M (2009) Prediction of antigenic epitopes on protein surfaces by consensus scoring. BMC Bioinform 10:302
Liang S, Zheng D, Standley DM, Yao B, Zacharias M, Zhang C (2010) EPSVR and EPMeta: prediction of antigenic epitopes using support vector regression and multiple server results. BMC Bioinform 11(1):381
Molodtsov D (1999) Soft set theory—first results. Comput Math Appl 37(4–5):19–31
Murakami Y, Jones S (2006) SHARP2: protein–protein interaction predictions using patch analysis. Struct Bioinform 22(14):1794–1795
Pellequer JL, Westhof E (1993) PREDITOP: a program for antigenicity prediction. J Mol Graph 11(3):204–210, 191–192
Ponomarenko J, Bui HH, Li W, Fusseder N, Bourne PE, Sette A, Peters B (2008) ElliPro: a new structure-based tool for the prediction of antibody epitopes. BMC bioinformatics 9(1):514
Rubinstein ND, Mayrose I, Martz E, Pupko T (2009) Epitopia: a web-server for predicting B-cell epitopes. BMC Bioinform 10:287
Saha S, Raghava GPS (2004) BcePred: prediction of continuous B-cell epitopes in antigenic sequences using physico-chemical properties. In artificial immune systems. Springer, Berlin, pp 197–204
Saha S, Raghava GP (2006) Prediction of continuous B-cell epitopes in an antigen using recurrent neural network. Proteins 65(1):40–48
Scott YHL, Cheng CW, Emily Chia YS (2013) Prediction of B-cell epitopes using evolutionary information and propensity scales. BMC Bioinform 14:S10
Sokolova M, Japkowicz N, Szpakowicz S (2006) Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. In: AI 2006: advances in artificial intelligence. Springer, Berlin, pp 1015–1021
Sun J, Wu D, Xu T, Wang X, Xu X, Tao L, Cao ZW (2009) SEPPA: a computational server for spatial epitope prediction of protein antigens. Nucleic Acids Res 37(suppl 2):W612–W616
Sweredoski MJ, Baldi P (2008) PEPITO: improved discontinuous B-cell epitope prediction using multiple distance thresholds and half sphere exposure. Bioinformatics 24:1459–1460
Sweredoski MJ, Baldi P (2009) COBEpro: a novel system for predicting continuous B-cell epitopes. Protein Eng Des Sel 22(3):113–120
Thomas JK, Barbara AO, Richard AG (2006) Kuby immunology, 6th edn. W. H. Freeman Publisher, London
Wang Y, Wu W, Negre NN, White KP, Li C, Shah PK (2011) Determinants of antigenicity and specificity in immune response for protein sequences. BMC Bioinform 12(1):251
Wee LJ, Simarmata D, Kam YW, Ng LF, Tong JC (2010) SVM-based prediction of linear B-cell epitopes using Bayes feature extraction. BMC Genom 11(Suppl 4):S21
Yao B, Zheng D, Liang S, Zhang C (2013) Conformational B-cell epitope prediction on antigen protein structures: a review of current algorithms and comparison with common binding site prediction methods. PLoS ONE 8(4):e62249
Yulong W, Wenjun W, Nicolas NN, Kevin PW, Cheng L, Parantu KS (2011) Determinants of antigenicity and specificity in immune response for protein sequences. BMC Bioinform 12:251
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Singh, C., Adlakha, N. Scoring function-based soft support vector machine model for prediction of patches containing conformational epitope. Netw Model Anal Health Inform Bioinforma 5, 2 (2016). https://doi.org/10.1007/s13721-015-0109-y
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13721-015-0109-y