Proceedings

Protein Function Prediction by Integrating Multiple Kernels

Download BibTeX Cite

Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence. Pages 1869-1874.

© 2013 International Joint Conferences on Artificial Intelligence

Abstract

Determining protein function constitutes an exercise in integrating information derived from several heterogeneous high-throughput experiments. To utilize the information spread across multiple sources in a combined fashion, these data sources are transformed into kernels. Several protein function prediction methods follow a two-phased approach: they first optimize the weights on individual kernels to produce a composite kernel, and then train a classifier on the composite kernel. As such, these methods result in an optimal composite kernel, but not necessarily in an optimal classifier. On the other hand, some methods optimize the loss of binary classifiers, and learn weights for the different kernels iteratively. A protein has multiple functions, and each function can be viewed as a label. These methods solve the problem of optimizing weights on the input kernels for each of the labels. This is computationally expensive and ignores inter-label correlations. In this paper, we propose a method called Protein Function Prediction by Integrating Multiple Kernels(ProMK). ProMK iteratively optimizes the phases of learning optimal weights and reducing the empirical loss of a multi-label classifier for each of the labels simultaneously, using a combined objective function. ProMK can assign larger weights to smooth kernels and downgrade the weights on noisy kernels. We evaluate the ability of ProMK to predict the function of proteins using several standard benchmarks. We show that our approach performs better than previously proposed protein function prediction approaches that integrate data from multiple networks, and multi-label multiple kernel learning methods.

  1. [Argyriou et al., 2005] A. Argyriou, M. Herbster, and M. Pontil. Combining graph laplacians for semi-supervised learning. In 18th Advances in Neural Information Process- ing Systems, pages 1-8, 2005.
  2. [Ashburner et al., 2000] M. Ashburner, C.A. Ball, J.A. Blake, D. Botstein, H. Butler, J.M. Cherry, A.P. Davis, K. Dolinski, S.S. Dwight, J.T. Eppig, et al. Gene ontology: tool for the unification of biology. Nature Genetics, 25(1):25, 2000.
  3. [Boyd and Vandenberghe, 2004] S.P. Boyd and L. Vanden- berghe. Convex optimization. Cambridge University Press, 2004.
  4. [Bucak et al., 2010] S.S. Bucak, R. Jin, and A.K. Jain. Multi- label multiple kernel learning by stochastic approximation: Application to visual object recognition. Advances in Neu- ral Information Processing Systems, 24:325-333, 2010.
  5. [Cesa-Bianchi et al., 2012] N. Cesa-Bianchi, M. Re, and G. Valentini. Synergy of multi-label hierarchical ensembles, data fusion, and cost-sensitive methods for gene functional inference. Machine Learning, 88(1-2):209-241, 2012.
  6. [Dempster et al., 1977] A.P. Dempster, N.M. Laird, and D.B. Rubin. Maximum likelihood from incomplete data via the em algorithm. Journal of the Royal Statistical Society. Series B (Methodological), pages 1-38, 1977.
  7. [Kloft et al., 2009] M. Kloft, U. Brefeld, S. Sonnenburg, P. Laskov, K.R. Müller, and A. Zien. Efficient and accu- rate lp-norm multiple kernel learning. In 22th Advances in Neural Information Processing Systems, pages 997-1005, 2009.
  8. [Kong et al., 2013] X. Kong, M. Ng, and Z. Zhou. Trans- ductive multi-label learning via label set propagation. IEEE Transactions on Knowledge and Data Engineering, 25(3):704-719, 2013.
  9. [Lanckriet et al., 2004] G.R.G. Lanckriet, T. De Bie, N. Cris- tianini, M.I. Jordan, and W.S. Noble. A statistical frame- work for genomic data fusion. Bioinformatics, 20(16):2626- 2635, 2004.
  10. [Leslie and Kuang, 2004] C. Leslie and R. Kuang. Fast string kernels using inexact matching for protein sequences. The Journal of Machine Learning Research, 5:1435-1455, 2004.
  11. [Mostafavi and Morris, 2010] S. Mostafavi and Q. Morris. Fast integration of heterogeneous data sources for predict- ing gene function with limited annotation. Bioinformatics, 26(14):1759-1765, 2010.
  12. [Mostafavi et al., 2008] S. Mostafavi, D. Ray, D. Warde- Farley, C. Grouios, and Q. Morris. Genemania: a real-time multiple association network integration algorithm for pre- dicting gene function. Genome Biology, 9(Suppl 1):S4, 2008.
  13. [Tang et al., 2009] L. Tang, J. Chen, and J. Ye. On multiple kernel learning with multiple labels. In 21st International Joint Conference on Artificial Intelligence, pages 1255- 1260, 2009. IJCAI
  14. [Tsoumakas et al., 2010] G. Tsoumakas, I. Katakis, and I. Vlahavas. Mining multi-label data. Data Mining and Knowledge Discovery Handbook, pages 667-685, 2010.
  15. [Tsuda et al., 2005] K. Tsuda, H.J. Shin, and B. Schölkopf. Fast protein classification with multiple networks. Bioin- formatics, 21(suppl 2):ii59, 2005.
  16. [Wang et al., 2009] M. Wang, X.S. Hua, R. Hong, J. Tang, G.J. Qi, and Y. Song. Unified video annotation via multi- graph learning. IEEE Transactions on Circuits and Systems for Video Technology, 19(5):733-746, 2009.
  17. [Weston et al., 2005] J. Weston, C. Leslie, E. Ie, D. Zhou, A. Elisseeff, and W.S. Noble. Semi-supervised pro- tein classification using cluster kernels. Bioinformatics, 21(15):3241-3247, 2005.
  18. [Yu et al., 2012] G. Yu, C. Domeniconi, H. Rangwala, G. Zhang, and Z. Yu. Transductive multi-label ensemble classification for protein function prediction. In 18th ACM SIGKDD International Conference on Knowledge Discov- ery and Data Mining, pages 1077-1085. ACM, 2012.
  19. [Zhou et al., 2004] D. Zhou, O. Bousquet, T.N. Lal, J. We- ston, and B. Schölkopf. Learning with local and global consistency. Advances in Neural Information Processing Systems, 16:321-328, 2004.

References were extracted automatically from the PDF and may contain errors.

Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards