Supervised Selective Kernel Fusion for Membrane Protein Prediction
详细信息 查看全文
- 作者：Alexander Tatarchuk (23)
Valentina Sulimova (24)
Ivan Torshin (23)
Vadim Mottl (23)
David Windridge (25) - 关键词：Multiple Kernel Learning ; SVM ; supervised selectivity ; support kernels ; membrane protein prediction
- 刊名：Lecture Notes in Computer Science
- 出版年：2014
- 出版时间：2014
- 年：2014
- 卷：8626
- 期：1
- 页码：98-109
- 全文大小：244 KB
- 参考文献：1. Alberts, B., Bray, D., Lewis, J., et al.: Molecular biology of the cell, 3rd edn., p. 1361. Garland Publishing, New York (1994)
2. Overington, J.P., Al-Lazikani, B., Hopkins, A.L.: How many drug targets are there? Nat. Rev. Drug. Discov.?5(12), 993-96 (2006) CrossRef
3. Krogh, A., Larsson, B., von Heijne, G., Sonnhammer, E.L.L.: Predicting Transmembrane Protein Topology with a Hidden Markov Model: Application to Complete Genomes. J. Mol. Biol.?305, 567-80 (2001) CrossRef
4. Chen, C.P., Rost, B.: State-of-the-art in Membrane Protein Prediction. Applied Bioinformatics?1, 21-5 (2002)
5. Gao, F.P., Cross, T.A.: Recent developments in membrane-protein structural genomics. Genome Biology?6, 244 (2005) CrossRef
6. Lanckriet, G., et al.: A statistical framework for genomic data fusion. Bioinformatics?20, 2626-635 (2004) CrossRef
7. Sch?lkopf, B., Tsuda, K., Vert, J.-P. (eds.): Kernel Methods in Computational Biology. MIT Press (2004)
8. Hofmann, T., Sch?lkopf, B., Smola, A.J.: Kernel methods in machine learning. Ann. Statist.?36(3), 1171-220 (2008) CrossRef
9. Vapnik, V.: Statistical Learning Theory. John-Wiley and Sons, Inc. (1998)
10. Pavlidis, P., Weston, J., Cai, J., Grundy, W.N.: Gene functional classification from heterogeneous data. In: Proceedings of the 5th Annual International Conference on Computational Molecular Biology, pp. 242-48 (2001)
11. Ong, C.S., et al.: Learning the kernel with hyperkernels. J. Mach. Learn. Res.?6, 1043-071 (2005)
12. Bie, T., et al.: Kernel-based data fusion for gene prioritization. Bioinformatics?23, 125-32 (2007) CrossRef
13. Bach, F.R., et al.: Multiple kernel learning, conic duality, and the SMO algorithm. In: Proceedings of the Twenty-First International Conference on Machine Learning (ICML 2004). Omnipress, Banff (2004)
14. Sonnenburg, S., R?tsch, G., Sch?fer, C., Sch?lkopf, B.: Large Scale Multiple Kernel Learning. Journal of Machine Learning Research?7, 1531-565 (2006)
15. Hu, M., Chen, Y., Kwok, J.T.-Y.: Building sparse multiple-kernel SVM classifiers. IEEE Transactions on Neural Networks?20(5), 827-39 (2009) CrossRef
16. G?nen, M., Alpayd, E.: Multiple Kernel Machines Using Localized Kernels. In: Proc. of PRIB (2009)
17. G?nen, M., Alpayd, E.: Localized algorithms for multiple kernel learning. Pattern Recognition?46, 795-07 (2013) CrossRef
18. Liao, L.: Data Fusion with Optimized Block Kernels in LS-SVM for Protein Classification. Engineering?5, 233-36 (2013) CrossRef
19. Cortes, C., Mohri, M., Rostamizadeh, A.: Learning non-linear combinations of kernels. In: Bengio, Y., et al. (eds.) Advances in Neural Information Processing Systems, vol.?22, pp. 396-04 (2009)
20. Mottl, V., Tatarchuk, A., Sulimova, V., Krasotkina, O., Seredin, O.: Combining pattern recognition modalities at the sensor level via kernel fusion. In: Haindl, M., Kittler, J., Roli, F. (eds.) MCS 2007. LNCS, vol.?4472, pp. 1-2. Springer, Heidelberg (2007) CrossRef
21. Kloft, M., Brefeld, U., Sonnenburg, S., et al.: Efficient and accurate lp-norm multiple kernel learning. In: Bengio, Y., et al. (eds.) Advances in Neural Information Processing Systems, vol.?22, pp. 997-005. MIT Press (2009)
22. Tatarchuk, A., Mottl, V., Eliseyev, A., Windridge, D.: Selectivity supervision in combining pattern-recognition modalities by feature- and kernel-selective Support Vector Machines. In: Proc. ICPR (2008)
23. Tatarchuk, A., Sulimova, V., Windridge, D., Mottl, V., Lange, M.: Supervised selective combining pattern recognition modalities and its application to signature verification by fusing on-line and off-line kernels. In: Benediktsson, J.A., Kittler, J., Roli, F. (eds.) MCS 2009. LNCS, vol.?5519, pp. 324-34. Springer, Heidelberg (2009) CrossRef
24. Tatarchuk, A., Urlov, E., Mottl, V., Windridge, D.: A support kernel machine for supervised selective combining of diverse pattern-recognition modalities. In: El Gayar, N., Kittler, J., Roli, F. (eds.) MCS 2010. LNCS, vol.?5997, pp. 165-74. Springer, Heidelberg (2010) CrossRef
25. Bradley, P., Mangasarian, O.: Feature selection via concave minimization and support vector machines. In: International Conference on Machine Learning (1998)
26. Wang, L., Zhu, J., Zou, H.: The doubly regularized support vector machine. Statistica Sinica?16, 589-15 (2006)
27. De Groot, M.H.: Optimal Statistical Decisions. Wiley Classics Library (2004)
28. Mewes, H.W., Frishman, D., Gruber, C., Geier, B., Haase, D., Kaps, A., Lemcke, K., Mannhaupt, G., Pfeiffer, F., Schüller, C.: MIPS: a database for genomes and protein sequences. Nucleic Acids Research?28, 37-0 (2000) CrossRef - 作者单位：Alexander Tatarchuk (23)
Valentina Sulimova (24)
Ivan Torshin (23)
Vadim Mottl (23)
David Windridge (25)
23. Computing Center of the Russian Academy of Sciences, Moscow, Russia
24. Tula State University, Tula, Russia
25. Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK - ISSN：1611-3349
文摘
Membrane protein prediction is a significant classification problem, requiring the integration of data derived from different sources such as protein sequences, gene expression, protein interactions etc. A generalized probabilistic approach for combining different data sources via supervised selective kernel fusion was proposed in our previous papers. It includes, as particular cases, SVM, Lasso SVM, Elastic Net SVM and others. In this paper we apply a further instantiation of this approach, the Supervised Selective Support Kernel SVM and demonstrate that the proposed approach achieves the top-rank position among the selective kernel fusion variants on benchmark data for membrane protein prediction. The method differs from the previous approaches in that it naturally derives a subset of “support kernels-(analogous to support objects within SVMs), thereby allowing the memory-efficient exclusion of significant numbers of irrelevant kernel matrixes from a decision rule in a manner particularly suited to membrane protein prediction.