基于对称不确定性和SVM递归特征消除的信息基因选择方法<sup>*</sup>

doi:10.16451/j.cnki.issn1003-6059.201705005

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (803 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要基因表达谱中存在大量与肿瘤分类无关的基因,严重降低肿瘤诊断的准确率.基因表达谱还存在高维小样本、噪声大等问题,增加肿瘤诊断的难度.为了获取基因数量较少且分类能力较强的信息基因子集,文中提出基于对称不确定性(SU)和支持向量机递归特征消除(SVM-RFE)的信息基因选择方法.首先利用SU评估基因和类标签之间的相关性,根据SU定义近似马尔科夫毯,快速消除大量无关和冗余基因.然后利用SVM-RFE进一步剔除冗余基因,获取有效的信息基因子集.实验表明,文中方法可以在选取维数较少或相等的信息基因子集情况下获取较高的肿瘤分类性能.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	叶明全
	高凌云
	伍长荣
	万春圆

关键词 ：基因选择, 对称不确定性, 支持向量机, 递归特征消除, 肿瘤分类

Abstract：A large number of genes unrelated to tumor classification exist in gene expression profiles, and thus the prediction accuracy of tumor is reduced substantially. Due to the small sample size with high dimension and noise, the tumor diagnosis is harder. To get an informative gene subset with fewer genes and a better classification accuracy, an informative gene selection method based on symmetric uncertainty(SU) and support vector machine-recursive feature elimination(SVM-RFE) is proposed. Firstly, SU is used to evaluate the correlation between genes and class labels, and approximate Markov blanket is defined grounded on SU. The elimination of irrelevant and redundant genes is achieved. Secondly, SVM-RFE algorithm is applied to obtain the effective informative gene subset by further removing redundant genes. Experimental results show that the proposed algorithm produces higher classification performance with equal or less informative gene subset.

Key words： Gene Selection Symmetric Uncertainty Support Vector Machine Recursive Feature Elimination Tumor Classification

收稿日期: 2017-01-01

ZTFLH:

TP 391

基金资助:国家自然科学基金项目(No.61672386)、教育部人文社会科学研究规划基金项目(No.16YJAZH071)、安徽省自然科学基金项目(No.1708085MF142)、安徽高校省级自然科学研究重点基金项目(No.KJ2016A275,KJ2014A266)资助

作者简介: 叶明全(通讯作者),男,1973年生,博士,教授,主要研究方向为数据挖掘、机器学习、生物医学信息学、健康医疗大数据.E-mail:ymq@wnmc.edu.cn.
高凌云,女,1991年生,硕士研究生,主要研究方向为数据挖掘、机器学习、生物医学信息学.E-mail:anningxia55@163.com.
伍长荣,女,1973年生,硕士,副教授,主要研究方向为数据挖掘、机器学习、生物医学图像处理与分析.E-mail:wcr193@126.com.
万春圆,女,1993年生,硕士研究生,主要研究方向为数据挖掘、机器学习、生物医学图像处理与分析.E-mail:1312530104@qq.com.

引用本文:

叶明全，高凌云，伍长荣，万春圆. 基于对称不确定性和SVM递归特征消除的信息基因选择方法^*[J]. 模式识别与人工智能, 2017, 30(5): 429-438. YE Mingquan, GAO Lingyun, WU Changrong, WAN Chunyuan. Informative Gene Selection Method Based on Symmetric Uncertainty and SVM Recursive Feature Elimination. , 2017, 30(5): 429-438.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.201705005 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2017/V30/I5/429

[1] BOLN-CANEDO V, SNCHEZ-MAROO N, ALONSO-BETANZOS A, et al. A Review of Microarray Datasets and Applied Feature Selection Methods. Information Sciences, 2014, 282: 111-135.
[2] APOLLONI J, LEGUIZAMN G, ALBA E. Two Hybrid Wrapper-Filter Feature Selection Algorithms Applied to High-Dimensional Microarray Experiments. Applied Soft Computing, 2016, 38: 922-932.
[3] 谢娟英,高红超.基于统计相关性与K-means 的区分基因子集选择算法.软件学报, 2014, 25(9): 2050-2075.
(XIE J Y, GAO H C. Statistical Correlation and K-means Based Distinguishable Gene Subset Selection Algorithms. Journal of Software, 2014, 25(9): 2050-2075.)
[4] 张靖,胡学钢,李培培,等.基于迭代Lasso的肿瘤分类信息基因选择方法研究.模式识别与人工智能, 2014, 27(1): 49-59.
(ZHANG J, HU X G, LI P P, et al. Informative Gene Selection for Tumor Classification Based on Iterative Lasso. Pattern Recognition and Artificial Intelligence, 2014, 27(1): 49-59.)
[5] 董红斌,滕旭阳,杨雪.一种基于关联信息熵度量的特征选择方法.计算机研究与发展, 2016, 53(8): 1684-1695.
(DONG H B, TENG X Y, YANG X. Feature Selection Based on the Measurement of Correlation Information Entropy. Journal of Computer Research and Development, 2016, 53(8): 1684-1695.)
[6] CAO J, ZHANG L, WANG B J, et al. A Fast Gene Selection Method for Multi-cancer Classification Using Multiple Support Vector Data Description. Journal of Biomedical Informatics, 2015, 53: 381-389.
[7] HUANG L K, ZHANG H H, ZENG Z B, et al. Improved Sparse Multi-class SVM and Its Application for Gene Selection in Cancer Classification. Cancer Informatics, 2013, 12: 143-153.
[8] LATKOWSKI T, OSOWSKI S. Data Mining for Feature Selection in Gene Expression Autism Data. Expert Systems with Applications, 2015, 42(2): 864-872.
[9] HSU H H, HSIEH C W, LU M D. Hybrid Feature Selection by Combining Filters and Wrappers. Expert Systems with Applications, 2011, 38(7): 8144-8150.
[10] CADENAS J M, GARRIDO M C, MARTNEZ R. Feature Subset Selection Filter-Wrapper Based on Low Quality Data. Expert Systems with Applications, 2013, 40(16): 6241-6252.
[11] VANITHA C D A, DEVARAJ D, VENKATESULU M. Gene Expression Data Classification Using Support Vector Machine and Mutual Information-Based Gene Selection. Procedia Computer Science, 2015, 47: 13-21.
[12] VERGARA J R, ESTVEZ P A. A Review of Feature Selection Methods Based on Mutual Information. Neural Computing and Applications, 2015, 24(1): 175-186.
[13] 崔自峰,徐宝文,张卫丰,等.一种近似Markov Blanket最优特征选择算法.计算机学报, 2007, 30(12): 2074-2081.
(CUI Z F, XU B W, ZHANG W F, et al. An Approximate Mar-kov Blanket Feature Selection Algorithm. Chinese Journal of Computers, 2007, 30(12): 2074-2081.)
[14] YU L, LIU H. Efficient Feature Selection via Analysis of Relevance and Redundancy. Journal of Machine Learning Research, 2004, 5: 1205-1224.
[15] ALI S I, SHAHZAD W. A Feature Subset Selection Method Based on Symmetric Uncertainty and Ant Colony Optimization // Proc of the International Conference on Emerging Technologies. Washington, USA: IEEE, 2012. DOI: 16.11.09/ICET.2012.6375420.
[16] LIU Y, ZHANG J H, MA L. A Fault Diagnosis Approach for Diesel Engines Based on Self-adaptive WVD, Improved FCBF and PECOC-RVM. Neurocomputing, 2016, 177: 600-611.
[17] PIAO Y J, PIAO M H, PARK K J, et al. An Ensemble Correlation-Based Gene Selection Algorithm for Cancer Classification with Gene Expression Data. Bioinformatics, 2012, 28(24): 3306-3315.
[18] 谢娟英,谢维信.基于特征子集区分度与支持向量机的特征选择算法.计算机学报, 2014, 37(8): 1704-1718.
(XIE J Y, XIE W X. Several Feature Selection Algorithms Based on the Discernibility of a Feature Subset and Support Vector Machines. Chinese Journal of Computers, 2014, 37(8): 1704-1718.)
[19] GUYON I, WESTON J, BARNHILL S, et al. Gene Selection for Cancer Classification Using Support Vector Machines. Machine Learning, 2002, 46(1): 389-422.
[20] DUAN K B, RAJAPAKSE J C, WANG H Y, et al. Multiple SVM-RFE for Gene Selection in Cancer Classification with Expression Data. IEEE Transactions on Nanobioscience, 2005, 4(3): 228-234.
[21] TANG Y C, ZHANG Y Q, HUANG Z. Development of Two-Stage SVM-RFE Gene Selection Strategy for Microarray Expression Data Analysis. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2007, 4(3): 365-381.
[22] ZHOU X, TUCK D P. MSVM-RFE: Extensions of SVM-RFE for Multiclass Gene Selection on DNA Microarray Data. Bioinformatics, 2007, 23(9): 1106-1114.
[23] YOON S, KIM S. Mutual Information-Based SVM-RFE for Diagnostic Classification of Digitized Mammograms. Pattern Recognition Letters, 2009, 30(16): 1489-1495.
[24] MUNDRA P A, RAJAPAKSE J C. SVM-RFE with MRMR Filter for Gene Selection. IEEE Transactions on Nanobioscience, 2010, 9(1): 31-37.
[25] 林俊,许露,刘龙.基于SVM-RFE-BPSO算法的特征选择方法.小型微型计算机系统, 2015, 36(8): 1865-1868.
(LIN J, XU L, LIU L. Feature Selection Based on SVM-RFE and Particle Swarm Optimization. Journal of Chinese Computer Systems, 2015, 36(8): 1865-1868.)
[26] TAPIA E, BULACIO P, ANGELONE L. Sparse and Stable Gene Selection with Consensus SVM-RFE. Pattern Recognition Letters, 2012, 33(2): 164-172.
[27] HIDALGO-MUOZ A R, LPEZ M, SANTOS I M, et al. Application of SVM-RFE on EEG Signals for Detecting the Most Relevant Scalp Regions Linked to Affective Valence Processing. Expert Systems with Applications, 2013, 40(6): 2102-2108.
[28] WITTEN I H, FRANK E, HALL M A. Data Mining: Practical Machine Learning Tools and Techniques. 3rd Edition. San Francisco, USA: Morgan Kaufmann, 2011.

[29] MEENAKSHI M, GEETIKA G. Survey on Classification Methods Using WEKA. International Journal of Computer Applications, 2014, 86(18): 16-19.