An Imbalance SVM for MicroRNA Target Genes Prediction

Abstract:

Imbalance miRNA target sample data bring about the lower prediction accuracy of SVM(Support Vector Machine). This paper proposes an SVM algorithm to predict the target genes based on biased discriminant idea. This paper selects an optimal feature sets as input data, and constructs a kernel optimization objective function based on the biased discriminant analysis criteria in the empirical feature space. The conformal transformation of a kernel is utilized to gradually optimize the kernel matrix. Through the comparative analysis of the experimental results of human, mouse and rat, the imbalance SVM with biased discriminant has higher specificity, sensitivity and prediction accuracy, which proves that it has stronger generalization ability and better robustness.

• Periodical: Applied Mechanics and Materials (Volume 577)
• Pages: 1245-1251
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.577.1245
• Online since: July 2014
• Authors: Zhi Ru Chen*, Wen Xue Hong, Pei Pei Zhao
• Keywords: Data Imbalance, Kernel Optimization, miRNA, Prediction of Target Genes, SVM

References

[1] Lingling Zheng, Lianghu Qu . Calculate RNAomics: non-coding RAN Structure Identification and Function Prediction [J] Life Sciences, 2010, 40 (4): 294-310.

[2] Songwei Ru, Weihong Shen, Pengcheng Yang, et al. Research Situation and Development Trend of microRNA Target Gene Algorithm [J] Life Sciences, 2007, 19 (5): 562-567.

[3] Liu et al., Improving Performance of Mammalian microRNA Target Prediction [J]. BMC Bioinformatics 2010 11: 476.

[4] Xuegong Zhang. About Statistical Learning Theory and Support Vector Machine [J]. ACTA Automatica Sinica, 2000, 26 (1) : 32-42.

[5] XIAO Feifei, ZUO Zhixiang, CAI Guoshuai, et al. miRecords: an Integrated Resource for microRNA-target Interactions [J]. Nucleic Acids Research, 2009, 37(1): D105-110.

DOI: 10.1093/nar/gkn851

[6] Ding C, Peng H: Minimum redundancy feature selection from microarray gene expression data[J]. Journal of Bioinformatics and Computational Biology, 2005, 3(2): 185-205.

DOI: 10.1142/s0219720005001004

[7] Zhiming Yang. Research of SVM Classification Methods with Orientation to the Data Imbalance [D] . Harbin Institute of Technology, (2009).

[8] Amari S, Wu S. Improving Support Vector Classifiers by Modifying Kernel Functions [J]. Neural Networks, 1999, 12 (6): 783-789.

DOI: 10.1016/s0893-6080(99)00032-5

[9] Schoelkopf B, Mika S, Burges C, et al. Input Space versus Feature Space in Kernel Based Methods [J]. IEEE Transactions on Neural Networks, 1999, 10 (5): 1000-1017.

DOI: 10.1109/72.788641

[10] Xiong Huilin, Swamy M, Ahamad M Omair. Optimizing the Kernel in the Empirical Feature Space [J]. IEEE Transactions on Neural Networks, 2005, 16(2): 460-474.

DOI: 10.1109/tnn.2004.841784

[11] Abe S, Onishi K. Sparse Least Squares Support Vector Regressors Trained in the Reduced Empirical Feature Space [J]. 17th International Conference on Artificial Neural Networks. 2007, 527-536.

DOI: 10.1007/978-3-540-74695-9_54

[12] Hendrickson DG, Hogan DJ, Herschlag D, et al. Brown PO: Systematic Identification of mRNAs Recruited to Argonaute 2 by Specific microRNAs and Corresponding Changes in Transcript Abundance [J]. PLoS ONE 2008, 3(5): e2126.

DOI: 10.1371/journal.pone.0002126