Kernel Methods and Applications in Bioinformatics


The kernel technique is a powerful tool for constructing new pattern analysis methods. Kernel engineering provides a general approach to incorporating domain knowledge and dealing with discrete data structures. Kernel methods, especially the support vector machine (SVM), have been extensively applied in the bioinformatics field, achieving great successes. Meanwhile, the development of kernel methods has also been strongly driven by various challenging bioinformatic problems. This chapter aims to give a concise and intuitive introduction to the basic principles of the kernel technique, and demonstrate how it can be applied to solve problems with uncommon data types in bioinformatics. Section 18.1 begins with the product features to give an intuitive idea of kernel functions, then presents the definition and some properties of kernel functions, and then devotes a subsection to a brief review of kernel engineering and its applications to bioinformatics. Section 18.2 describes the standard SVM algorithm. Finally, Sect. 18.3 illustrates how kernel methods can be used to address the peptide identification and the protein homology prediction problems in bioinformatics, while Sect. 18.4 concludes.


Support Vector Machine Kernel Function Feature Space Kernel Method String Kernel 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



average overall ranking precision


deoxyribonucleic acid


hidden Markov model


knowledge discovery in databases


kernel spectral dot product


principle component analysis


radial basis function


radical basis function


rank of the last relevant item




ribonucleic acid


spectral dot product


support vector


support vector machine




  1. 18.1.
    J. Shawe-Taylor, N. Cristianini: Kernel Methods for Pattern Analysis (Cambridge University Press, Cambridge 2004)CrossRefGoogle Scholar
  2. 18.2.
    V.N. Vapnik: The Nature of Statistical Learning Theory (Springer, Berlin Heidelberg 1995)zbMATHCrossRefGoogle Scholar
  3. 18.3.
    B. Schölkopf, K. Tsuda, J.-P. Vert (Eds.): Kernel Methods in Computational Biology (MIT Press, Cambridge 2004)Google Scholar
  4. 18.4.
    A. Ben-Hur, C.S. Ong, S. Sonnenburg, B. Schölkopf, G. Rätsch: Support vector machines and kernels for computational biology, PLoS Comput. Biol. 4(10), e1000173 (2008)CrossRefGoogle Scholar
  5. 18.5.
    K.M. Borgwardt: Kernel methods in bioinformatics,. In: Handbook of Statistical Bioinformatics, ed. by H.H. Lu, B. Schölkopf, H. Zhao (Springer, Berlin Heidelberg 2011) pp. 317–334CrossRefGoogle Scholar
  6. 18.6.
    B. Schölkopf: Support Vector Learning. Dr. Thesis (Technische Universität Berlin, Berlin 1997)Google Scholar
  7. 18.7.
    J. Mercer: Functions of positive and negative type and their connection with the theory of integral equations, Philos. Trans. R. Soc. A209, 415–446 (1909)CrossRefGoogle Scholar
  8. 18.8.
    M.A. Aizerman, E.M. Braverman, L.I. Rozonofier: Theoretical foundations of the potential function method in pattern recognition learning, Autom. Remote Control 25, 821–837 (1964)Google Scholar
  9. 18.9.
    B.E. Boser, I.M. Guyon, V.N. Vapnik: A training algorithm for optimal margin classifiers, Proc. 5th Annu. ACM Workshop Comput. Learn. Theory (1992) pp. 144–152Google Scholar
  10. 18.10.
    B. Schölkopf, A.J. Smola, K.R. Müller: Nonlinear component analysis as a kernel eigenvalue problem, Neural Comput. 10, 1299–1319 (1998)CrossRefGoogle Scholar
  11. 18.11.
    P.L. Lai, C. Fyfe: Kernel and nonlinear canonical correlation analysis, Int. J. Neural Syst. 10, 365–377 (2000)CrossRefGoogle Scholar
  12. 18.12.
    S. Mika, G. Rätsch, J. Weston, B. Schölkopf, K.-R. Müller: Fisher discriminant analysis with kernels, Neural Networks for Signal Processing, Vol. 9, ed. by Y.-H. Hu, J. Larsen, E. Wilson, S. Douglas (IEEE, 1999) pp. 41–48Google Scholar
  13. 18.13.
    F.R. Bach, M.I. Jordan: Kernel independent component analysis, J. Mach. Learn. Res. 3, 1–48 (2003)zbMATHMathSciNetGoogle Scholar
  14. 18.14.
    B. Schölkopf: The kernel trick for distances. In: Advances in Neural Information Processing Systems, Vol. 13, ed. by T.K. Leen, T.G. Dietterich, V. Tresp (MIT Press, Cambridge, MA 2001) pp. 301–307Google Scholar
  15. 18.15.
    K. Yu, L. Ji, X. Zhang: Kernel nearest-neighbor algorithm, Neural Process. Lett. 15, 147–156 (2002)zbMATHCrossRefGoogle Scholar
  16. 18.16.
    J. Peng, D.R. Heisterkamp, H.K. Dai: Adaptive quasiconformal kernel nearest neighbor classification, IEEE Trans. Pattern Anal. Mach. Intell. 26, 656–661 (2004)CrossRefGoogle Scholar
  17. 18.17.
    Y. Fu: Machine Learning Based Bioinformation Retrieval, Dissertation (Chinese Academy of Sciences 2007)Google Scholar
  18. 18.18.
    J. Xu, H. Li, C. Zhong: Relevance ranking using kernels, Proc. 6th Asian Inf. Retr. Soc. Symp. (2010) pp. 1–12Google Scholar
  19. 18.19.
    W. Wu, J. Xu, H. Li, S. Oyama: Learning a robust relevance model for search using kernel methods, J. Mach. Learn. Res. 12, 1429–1458 (2011)zbMATHMathSciNetGoogle Scholar
  20. 18.20.
    H. Lodhi, C. Saunders, J. Shawe-Taylor, N. Cristianini, C. Watkins: Text classification using string kernels, J. Mach. Learn. Res. 2, 419–444 (2002)zbMATHGoogle Scholar
  21. 18.21.
    C. Watkins: Dynamic alignment kernels,. In: Advances in Large Margin Classifiers, ed. by A.J. Smola, P.L. Bartlett, B. Schölkopf, D. Schuurmans (MIT, Cambridge 1999) pp. 39–50Google Scholar
  22. 18.22.
    D. Haussler: Convolution kernels on discrete structures, Technical Report UCSC-CRL-99-10 (1999)Google Scholar
  23. 18.23.
    T.S. Jaakkola, D. Haussler: Exploiting generative models in discriminative classifiers,. In: Advances in Neural Information Processing Systems, Vol. 11, ed. by M.S. Kearns, S.A. Solla, D.A. Cohn (MIT Press, Cambridge, MA 1999) pp. 487–493Google Scholar
  24. 18.24.
    R.I. Kondor, J. Lafierty: Diffusion kernels on graphs and other discrete input spaces, Proc. 9th Int. Conf. Mach. Learn. (2002) pp. 315–322Google Scholar
  25. 18.25.
    C. Leslie, E. Eskin, W.S. Noble: The spectrum kernel: A string kernel for SVM protein classification, Proc. 7th Pac. Sympos. Biocomput. (2002) pp. 564–575Google Scholar
  26. 18.26.
    C. Leslie, E. Eskin, J. Weston, W.S. Noble: Mismatch string kernels for discriminative protein classification, Bioinformatics 20(4), 467–476 (2004)CrossRefGoogle Scholar
  27. 18.27.
    J.P. Vert: Support vector machine prediction of signal peptide cleavage site using a new class of kernels for strings, (2002) pp. 649–660Google Scholar
  28. 18.28.
    A. Zien, G. Rätsch, S. Mika, B. Schölkopf, T. Lengauer, K.-R. Muller: Engineering support vector machine kernels that recognize translation initiation sites, Bioinformatics 16, 799–807 (2000)CrossRefGoogle Scholar
  29. 18.29.
    T. Jaakkola, M. Diekhans, D. Haussler: A discriminative framework for detecting remote protein homologies, J. Comput. Biol. 7, 95–114 (2000)CrossRefGoogle Scholar
  30. 18.30.
    J.P. Vert, M. Kanehisa: Graph-driven features extraction from microarray data using diffusion kernels and kernel CCA. In: Advances in Neural Information Processing Systems, Vol. 15, ed. by S. Becker, S. Thrun, K. Obermayer (MIT Press, Cambridge, MA 2003) pp. 1425–1432Google Scholar
  31. 18.31.
    J.P. Vert: A tree kernel to analyze phylogenetic profiles, Bioinformatics 18, S276–S284 (2002)CrossRefGoogle Scholar
  32. 18.32.
    K.M. Borgwardt, C.S. Ong, S. Schönauer, S.V.N. Vishwanathan, A.J. Smola, H. Kriegel: Protein function prediction via graph kernels, Bioinformatics 1(Suppl.), 47–56 (2005)CrossRefGoogle Scholar
  33. 18.33.
    N. Cristianini, J. Shawe-Taylor: An Introduction to Support Vector Machines and Other Kernel-based Learning Methods (University Press, Cambridge 2000)CrossRefGoogle Scholar
  34. 18.34.
    G. Schweikert, A. Zien, G. Zeller, J. Behr, C. Dieterich, C.S. Ong, P. Philips, F. De Bona, L. Hartmann, A. Bohlen, N. Krüger, S. Sonnenburg, G. Rätsch: mGene: Accurate SVM-based gene finding with an application to nematode genomes, Genome Res. 19(11), 2133–2143 (2009)CrossRefGoogle Scholar
  35. 18.35.
    I. Guyon, J. Weston, S. Barnhill, V. Vapnik: Gene selection for cancer classification using support vector machines, Mach. Learn. 46, 389–422 (2002)zbMATHCrossRefGoogle Scholar
  36. 18.36.
    Y. Sun, X. Fan, Y. Li: Identifying splicing sites in eukaryotic RNA: Support vector machine approach, Comput. Biol. Med. 33(1), 17–29 (2003)CrossRefGoogle Scholar
  37. 18.37.
    J. Gubbi, A. Shilton, M. Palaniswami: Kernel methods in protein structure prediction. In: Machine Learning in Bioinformatics, ed. by Y.-Q. Zhang, J.C. Rajapakse (Wiley, Hoboken 2008)Google Scholar
  38. 18.38.
    G.R.G. Lanckriet, M. Deng, N. Cristianini, M.I. Jordan, W.S. Noble: Kernel-based data fusion and its application to protein function prediction in yeast, Proc. 9th Pac. Symp. Biocomput. (2004) pp. 300–311Google Scholar
  39. 18.39.
    H. Wang, Y. Fu, R. Sun, S. He, R. Zeng, W. Gao: An SVM scorer for more sensitive and reliable peptide identification via tandem mass spectrometry, Proc. 11th Pac. Symp. Biocomput. (2006) pp. 303–314Google Scholar
  40. 18.40.
    Y. Li, P. Hao, S. Zhang, Y. Li: Mol cell proteomics, feature-matching pattern-based support vector machines for robust peptide mass fingerprinting, Mol. Cell. Proteomic. 10(12), M110.0057852011 (2011)CrossRefGoogle Scholar
  41. 18.41.
    R. Aebersold, M. Mann: Mass spectrometry-based proteomics, Nature 422, 198–207 (2003)CrossRefGoogle Scholar
  42. 18.42.
    H. Steen, M. Mann: The ABCʼs (and XYZʼs) of peptide sequencing, Nat. Rev. Mol. Cell 5, 699–711 (2004)CrossRefGoogle Scholar
  43. 18.43.
    J.K. Eng, A.L. McCormack, J.R. Yates: An approach to correlate tandem mass spectral data of peptides with amino acid sequences in a protein database, J. Am. Soc. Mass Spectrom. 5, 976–989 (1994)CrossRefGoogle Scholar
  44. 18.44.
    K.X. Wan, I. Vidavsky, M.L. Gross: Comparing similar spectra: From similarity index to spectral contrast angle, J. Am. Soc. Mass Spectrom. 13, 85–88 (2002)CrossRefGoogle Scholar
  45. 18.45.
    B. Schölkopf, P. Simard, A. Smola, V. Vapnik: Prior knowledge in support vector kernels, Adv. Neur. Inf. Proces. Syst., Vol. 10, ed. by M. Jordan, M. Kearns, S. Solla (MIT, Cambridge 1998) pp. 640–646Google Scholar
  46. 18.46.
    Y. Fu, Q. Yang, R. Sun, D. Li, R. Zeng, C.X. Ling, W. Gao: Exploiting the kernel trick to correlate fragment ions for peptide identification via tandem mass spectrometry, Bioinformatics 20, 1948–1954 (2004)CrossRefGoogle Scholar
  47. 18.47.
    D. Li, Y. Fu, R. Sun, C. Ling, Y. Wei, H. Zhou, R. Zeng, Q. Yang, S. He, W. Gao: pFind: A novel database-searching software system for automated peptide and protein identification via tandem mass spectrometry, Bioinformatics 21, 3049–3050 (2005)CrossRefGoogle Scholar
  48. 18.48.
    A. Keller, S. Purvine, A.I. Nesvizhskii, S. Stolyar, D.R. Goodlett, E. Kolker: Experimental protein mixture for validating tandem mass spectral analysis, Omics 6, 207–212 (2002)CrossRefGoogle Scholar
  49. 18.49.
    Y. Zhang: Progress and challenges in protein structure prediction, Curr. Opin. Struct. Biol. 18, 342–348 (2008)CrossRefGoogle Scholar
  50. 18.50.
    T. Liu: Learning to Rank for Information Retrieval (Springer, New York 2011)zbMATHCrossRefGoogle Scholar
  51. 18.51.
    R. Caruana, T. Joachims, L. Backstrom: KDD Cup 2004: Results and analysis, SIGKDD Explorations 6, 95–108 (2004)CrossRefGoogle Scholar
  52. 18.52.
    Y. Fu, R. Sun, Q. Yang, S. He, C. Wang, H. Wang, S. Shan, J. Liu, W. Gao: A block-based support vector machine approach to the protein homology prediction task in KDD Cup 2004, SIGKDD Explorations 6, 120–124 (2004)CrossRefGoogle Scholar
  53. 18.53.
    C. Foussette, D. Hakenjos, M. Scholz: KDD-Cup 2004 – Protein homology task, SIGKDD Explorations 6, 128–131 (2004)CrossRefGoogle Scholar
  54. 18.54.
    B. Pfahringer: The Weka solution to the 2004 KDD cup, SIGKDD Explorations 6, 117–119 (2004)CrossRefGoogle Scholar
  55. 18.55.
    Y. Tang, B. Jin, Y. Zhang: Granular support vector machines with association rules mining for protein homology prediction, Artif. Intell. Med. 35, 121–134 (2005)zbMATHCrossRefGoogle Scholar
  56. 18.56.
    Y. Fu, R. Pan, Q. Yang, W. Gao: Query-adaptive ranking with support vector machines for protein homology prediction. In: ISBRA 2011, Lecture Notes in Bioinformatics, Vol. 6674, ed. by J. Chen, J. Wang, A. Zelikovsky (Springer, Berlin Heidelberg 2011) pp. 320–331Google Scholar
  57. 18.57.
    D. Tobi, R. Elber: Distance dependent, pair potential for protein folding: Results from linear optimization, Proteins Struct. Funct. Genet. 41, 40–46 (2000)CrossRefGoogle Scholar
  58. 18.58.
    O. Teodorescu, T. Galor, J. Pillardy, R. Elber: Enriching the sequence substitution matrix by structural information, Proteins Struct. Funct. Bioinform. 54, 41–48 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2014

Authors and Affiliations

  1. 1.Academy of Mathematics and Systems Science, Haidian DistrictChinese Academy of SciencesBeijingChina

Personalised recommendations