Multiple Kernel Support Vector Regression for siRNA Efficacy Prediction

  • Shibin Qiu
  • Terran Lane
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4983)


The cell defense mechanism of RNA interference has applications in gene function analysis and human disease therapy. To effectively silence a target gene, it is desirable to select the initiator siRNA molecules having satisfactory silencing capabilities. Computational prediction for silencing efficacy of siRNAs can assist this screening process before using them in biological experiments. String kernel functions, which operate directly on the string objects representing siRNAs and target mRNAs, have been applied to support vector regression for the prediction and improved accuracy over numerical kernels in multidimensional vector spaces constructed from descriptors of siRNA design rules. To fully utilize information provided by string and numerical kernels, we propose to unify the two in the kernel feature space by devising a multiple kernel regression framework where a linear combination of the kernels are used. We formulate the multiple kernel learning into a quadratically constrained quadratic programming (QCQP) problem, which although yields global optimal solution, is computationally inefficient and requires a commercial solver package. We further propose three heuristics based on the principle of kernel–target alignment and predictive accuracy. Empirical results on real biological data demonstrate that multiple kernel regression can improve accuracy and decrease model complexity by reducing the number of support vectors. In addition, multiple kernel regression gives insights into the kernel combination, which, for siRNA efficacy prediction, evaluates the relative significance of the design rules.


Mean Square Error Support Vector Regression Design Rule Kernel Matrix Average Mean Square Error 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hannon, G.J.: RNA interference. Nature 418, 244–251 (2002)CrossRefGoogle Scholar
  2. 2.
    Check, E.: Hopes rise for RNA therapy as mouse study hits target. Nature 432, 136 (2004)CrossRefGoogle Scholar
  3. 3.
    Brummelkamp, T.R., Bernards, R., Agami, R.: A system for stable expression of short interfering RNAs in mammalian cells. Science 296, 550–553 (2002)CrossRefGoogle Scholar
  4. 4.
    Pei, Y., Tuschl, T.: On the art of identifying effective and specific siRNA. Nature Methods 3(9), 670–676 (2006)CrossRefGoogle Scholar
  5. 5.
    Amarzguioui, M., Prydz, H.: An algorithm for selection of functional siRNA sequences. B.B.R.C. 316, 1050–1058 (2004)Google Scholar
  6. 6.
    Reynolds, A., Leake, D., Boese, Q., Scaringe, S., Marshall, W.S., Khovorova, A.: Rational siRNA design for RNA interference. Nature Biotechnology 22, 326–330 (2004)CrossRefGoogle Scholar
  7. 7.
    Ui-Tei, K., Naito, Y., Takahashi, F., Haraguchi, T., Ohki-Hamazaki, H., Juni, A., Ueda, R., Saigo, K.: Guidelines for the selection of highly effective siRNA sequences for mammalian and chick RNA interference. Nucleic Acids Research 32, 936–948 (2004)CrossRefGoogle Scholar
  8. 8.
    Jagla, B., Aulner, N., Kelly, P., Song, D., Volchuk, A., Zatorski, A., Shum, D., Mayer, T., Angelis, D.D., Ouerfelli, O., Rutishauser, U., Rothman, J.: Sequence characteristics of functional siRNAs. RNA 11, 864–872 (2005)CrossRefGoogle Scholar
  9. 9.
    Huesken, D., Lange, J., Mickanin, C., Weiler, J., Asselbergs, F., Warner, J., Meloon, B., Engel, S., Rosenberg, A., Cohen, D., Labow, M., Reinhardt, M., Natt, F., Hall, J.: Design of a genome-wide siRNA library using an artificial neural network. Nature Biotechnology 23(8), 995–1001 (2005)CrossRefGoogle Scholar
  10. 10.
    Ge, G., Wong, G., Luo, B.: Prediction of siRNA knockdown efficacy using artificial neural network models. Biochem Biophys. Res. Comm. 336, 723–728 (2005)CrossRefGoogle Scholar
  11. 11.
    Sætrom, P., Snøve Jr., O.: A comparison of siRNA efficacy predictors. Biochemical and Biophysical Research Communications 321, 247–253 (2004)CrossRefGoogle Scholar
  12. 12.
    Qiu, S., Lane, T., Buturovic, L.: A randomized string kernel and its applications to RNA interference. In: Proc. 22 AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada, pp. 627–632. AAAI Press, Menlo Park (2007)Google Scholar
  13. 13.
    Teramoto, R., Aoki, M., Kimura, T., Kanaoka, M.: Prediction of siRNA functionality using generalized string kernel and support vector machine. FEBS Lett. 579, 2878–2882 (2005)CrossRefGoogle Scholar
  14. 14.
    Jia, P., Shi, T., Cai, Y., Li, Y.: Demonstration of two novel methods for predicting functional siRNA efficiency. BMC Bioinformatics 7, 271 (2006)CrossRefGoogle Scholar
  15. 15.
    Vert, J.P., Foveau, N., Lajaunie, C., Vandenbrouck, Y.: An accurate and interpretable model for siRNA efficacy prediction. MBC Bioinformatics 7, 520 (2006)CrossRefGoogle Scholar
  16. 16.
    Vapnik, V.N.: Statistical Learning Theory. John Wiley and Sons, Chichester (1998)zbMATHGoogle Scholar
  17. 17.
    Qiu, S., Lane, T.: The RNA string kernel for siRNA efficacy prediction. In: Proc. 7th IEEE Int’l Conf. on Bioinformatics and Bioengineering (BIBE 2007), Boston, MA, pp. 307–314 (October 2007)Google Scholar
  18. 18.
    Qiu, S., Adema, C., Lane, T.: A computational study of off-target effects of RNA interference. Nucleic Acids Research 33, 1834–1847 (2005)CrossRefGoogle Scholar
  19. 19.
    Qiu, S., Lane, T.: RNA string kernels for RNAi off-target evaluation. Int. J. Bioinformatics Research and Applications (IJBRA) 2(2), 132–146 (2006)Google Scholar
  20. 20.
    Lanckriet, G.R.G., Cristianini, N., Bartlett, P., Ghaoui, L.E., Jordan, M.I.: Learning the kernel matrix with semidefinite programming. J. Machine Learning Research 5, 27–72 (2004)Google Scholar
  21. 21.
    Qiu, S., Lane, T.: Multiple kernel learning for support vector regression. Technical Report TR-CS-2005-42, Computer Science Department, The University of New Mexico, Albuquerque, NM, USA (2005)Google Scholar
  22. 22.
    Cristianini, N., Shawe-Taylor, J., Elissee, A., Kandola, J.: On kernel-target alignment. In: Dietterich, T., Becker, S., Ghahramani, Z. (eds.) Advances in Neural Information Processing Systems, vol. 14, MIT Press, Cambridge (2002)Google Scholar
  23. 23.
    Smola, A., Schölkopf, B.: A tutorial on support vector regression. Technical Report NC2-TR-1998-030, NeuroCOLT2 (1998)Google Scholar
  24. 24.
    Weston, J., Schölkopf, B., Eskin, E., Leslie, C., Noble, W.S.: A kernel approach for learning from almost orthogonal patterns. In: Elomaa, T., Mannila, H., Toivonen, H. (eds.) PKDD 2002. LNCS (LNAI), vol. 2431, Springer, Heidelberg (2002)Google Scholar
  25. 25.
    UCI: UCI machine learning data datasets,

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Shibin Qiu
    • 1
  • Terran Lane
    • 2
  1. 1.Pathwork Diagnostics Inc.SunnyvaleUSA
  2. 2.Computer Science Dept.University of New MexicoAlbuquerqueUSA

Personalised recommendations