Amino Acids

, Volume 40, Issue 2, pp 443–451 | Cite as

Artificial intelligence systems based on texture descriptors for vaccine development

  • Loris Nanni
  • Sheryl Brahnam
  • Alessandra Lumini
Original Article


The aim of this work is to analyze and compare several feature extraction methods for peptide classification that are based on the calculation of texture descriptors starting from a matrix representation of the peptide. This texture-based representation of the peptide is then used to train a support vector machine classifier. In our experiments, the best results are obtained using local binary patterns variants and the discrete cosine transform with selected coefficients. These results are better than those previously reported that employed texture descriptors for peptide representation. In addition, we perform experiments that combine standard approaches based on amino acid sequence. The experimental section reports several tests performed on a vaccine dataset for the prediction of peptides that bind human leukocyte antigens and on a human immunodeficiency virus (HIV-1). Experimental results confirm the usefulness of our novel descriptors. The matlab implementation of our approaches is available at


Peptide classification Vaccine development HIV-1 protease prediction Locally binary patterns Discrete cosine transform Support vector machine 


  1. Bozic I, Zhang G, Brusic V (2005) Predictive vaccinology: optimization of predictions using support vector machine classifiers. Intell Data Eng Autom Learn LNCS 3578:375–381Google Scholar
  2. Brusic V, Petrovsky N, Zhang G, Bajic VB (2002) Prediction of promiscuous peptides that bind HLA class I molecules. Immunol Cell Biol 80:280–285CrossRefPubMedGoogle Scholar
  3. Brusic V, Bajic VB, Petrovsky N (2004) Computational methods for prediction of T-cell epitopes a framework for modelling, testing, and applications. Methods 34:436–443CrossRefPubMedGoogle Scholar
  4. Cai YD, Chou KC (1998) Artificial neural network model for predicting HIV protease cleavage sites in protein. Adv Eng Softw 29:119–128CrossRefGoogle Scholar
  5. Chou KC (2000) Prediction of protein subcellular locations by incorporating quasi-sequence-order effect. Biochem Biophys Res Commun 278:477–483CrossRefPubMedGoogle Scholar
  6. Chou KC, Cai YD (2006) Predicting protein–protein interactions from sequences in a hybridization space. J Proteome Res 5:316–322CrossRefPubMedGoogle Scholar
  7. Chou KC, Shen HB (2007) MemType-2L: a web server for predicting membrane proteins and their types by incorporating evolution information through Pse-PSSM. Biochem Biophys Res Comm 360:339–345CrossRefPubMedGoogle Scholar
  8. Duda RO, Hart PE (1973) Pattern classification and scene analysis. Academic Press, LondonGoogle Scholar
  9. Feng J, Wang T-M (2008) Characterization of protein primary sequences based on partial ordering. J Theor BiolGoogle Scholar
  10. Gao Y, Shao SH, Xiao X, Ding YS, Huang YS, Huang ZD, Chou KC (2005) Using pseudo amino acid composition to predict protein subcellular location: approached with Lyapunov index, Bessel function, and Chebyshev filter. Amino Acids 28:373–376CrossRefPubMedGoogle Scholar
  11. Jaakkola T, Diekhans M, Haussler D (1999) Using the Fisher kernel method to detect remote protein homologies. In: Seventh Int Conf Intell Syst Mol Biol, AAAI Press, Menlo Park, pp 149–158Google Scholar
  12. Kawashima S, Kanehisa M (2000) AA index: amino acid index database. Nucleic Acids Research 20Google Scholar
  13. Kontijevskis A, Wikberg JES, Komorowski J (2007) Computational proteomics analysis of HIV-1 protease interactome. Proteins Struct Funct Bioinform 1:305–312CrossRefGoogle Scholar
  14. Kuncheva LI, Whitaker CJ (2003) Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy, Machine learning, 51, pp 181–207Google Scholar
  15. Lei Z, Dai Y (2005) An SVM-based system for predicting protein subnuclear localizations. BMC Bioinformatics, Dec 7, 6:291Google Scholar
  16. Leslie CS, Eskin E, Cohen A, Weston J, Noble WS (2004) Mismatch string kernels for discriminative protein classification. Bioinformatics 20:467–476CrossRefPubMedGoogle Scholar
  17. Liao S, Law MWK, Chung ACS (2009) Dominant local binary patterns for texture classification. IEEE Trans Image Process 18:1107–1118CrossRefPubMedGoogle Scholar
  18. Nanni L, Lumini A (2006a) An ensemble of K-Local hyperplane for predicting protein–protein interactions. Bioinformatics 22:1207–1210CrossRefPubMedGoogle Scholar
  19. Nanni L, Lumini A (2006b) MppS: an ensemble of support vector machines based on multiple physicochemical properties of amino-acids. Neurocomputing 69:1688–1690CrossRefGoogle Scholar
  20. Nanni L, Lumini A (2009) Using ensemble of classifiers for predicting HIV protease cleavage sites in proteins. Amino Acids 36:409–416CrossRefPubMedGoogle Scholar
  21. Nanni L, Lumini A (2010) Coding of amino acids by texture descriptors. Artif Intell Med 48:43–50CrossRefPubMedGoogle Scholar
  22. Narayanan A, Wu X, Yang Z (2002) Mining viral protease data to extract cleavage knowledge. Bioinformatics 18:S5–S13PubMedGoogle Scholar
  23. Ojala T, Pietikainen M, Maeenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Analysis Mach Intell 24:971–987CrossRefGoogle Scholar
  24. Pan Z, Rust A, Bolouri H (2000) Image redundancy reduction for neural network classification using discrete cosine transforms. In: Int Jt Conf Neural Netw, Como, Italy, pp 149–154Google Scholar
  25. Qin ZC (2006) ROC analysis for predictions made by probabilistic classifiers. In: Fourth Int Conf Mach Learning Cybern, pp 3119–3312Google Scholar
  26. Rögnvaldsson T, You L (2003) Why neural networks should not be used for HIV-1 protease cleavage site prediction. Bioinformatics, pp 1702–1709Google Scholar
  27. Rögnvaldsson T, You L, Garwicz D (2007) Bioinformatic approaches for modeling the substrate specificity of HIV-1 protease: an overview. Expert Rev Mol Diagn 4:435–451CrossRefGoogle Scholar
  28. Rögnvaldsson T, Etchells TA, You L, Garwicz D, Jarman I, Lisboa PJ (2009) How to find simple and accurate rules for viral protease cleavage specificities. BMC Bioinformatics 16Google Scholar
  29. Schilling O, Overall CM (2008) Proteome-derived, database-searchable peptide libraries for identifying protease cleavage sites. Nat Biotechnol 26:685–694CrossRefPubMedGoogle Scholar
  30. Shen HB, Chou KC (2008) HIVcleave: a web-server for predicting HIV protease cleavage sites in proteins. Anal Biochem 375:388–390CrossRefPubMedGoogle Scholar
  31. Tan X, Triggs B (2007) Enhanced local texture feature sets for face recognition under difficult lighting conditions. Analysis and Modelling of Faces and Gestures LNCS 4778:168–182CrossRefGoogle Scholar
  32. Thompson TB, Chou KC, Zheng C (1995) Neural network prediction of the HIV-1 protease cleavage sites. J Theor Biol 177:369–379CrossRefPubMedGoogle Scholar
  33. Xiao X, Chou KC (2007) Digital coding of amino acids based on hydrophobic index. Protein Pept Lett 14:871–875CrossRefPubMedGoogle Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  • Loris Nanni
    • 1
  • Sheryl Brahnam
    • 2
  • Alessandra Lumini
    • 1
  1. 1.Department of Electronic, Informatics and Systems (DEIS)Università di BolognaCesenaItaly
  2. 2.Computer Information SystemsMissouri State UniversitySpringfieldUSA

Personalised recommendations