比较不平衡基因表达数据上的7种分类器表现

doi:10.3969/j.issn.1006-5253.2021.01.022

Abstract
Figure/Table
References (0)
Related Citation (1)

Download: PDF (1657 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract

Objective To investigate if the class imbalance poses additional challenges when dealing with class prediction of gene expression data, to evaluate the performance of seven types of classifiers on class-imbalanced data on a publicly available data set, in order to provide a theoretical basis for subsequent research. Methods We obtained different levels of class imbalance by repeatedly randomly selecting subsets of the samples from the public data set: training sets (N_n=10 vs N_p=10,15,20,30,35, and N_n=15 vs N_p=5,10,15,25,30); the test sets were balanced (N_n=20 vs N_p=20). We trained the classifiers on them and compare the classification effect of single sampling classification and 100 sampling average. Results As the number of positive samples in the data set increases, the overall sensitivity of the classification algorithm shows an upward trend, while the specificity shows a downward trend. In the colon cancer data set, AdaBoost, NB, and RF algorithms performed well, while support vector machines performed poorly and were unstable. In the leukemia data set, the overall performance of the NB algorithm is the best and stable, and the classification effect of AdaBoost, C4.5 and RF algorithms is better but fluctuates greatly.Conclusion Class imbalance, data characteristics and algorithm selection affect classification for high-dimensional data. And the results of a single analysis are contingent, with poor reproducibility. Researchers using class-imbalanced data should be careful in selecting algorithm and they should always use an appropriate method for dealing with the class imbalance problem.

Key words： font-family: 宋体 mso-spacerun: 'yes'

class imbalance')" href="#">mso-font-kerning: 1.0000pt">

class imbalance gene expression data class prediction class imbalance')" href="#"> classifier

class imbalance gene expression data class prediction classifier

Received: 24 August 2020

	Service

	E-mail this article class imbalance\| gene expression data\| class prediction\| classifier class imbalance\| gene expression data\| class prediction\| classifier ”. Please open it by linking:http://manu58.magtech.com.cn/Jwk_zgyytj/EN/abstract/abstract965.shtml" name="neirong">
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Li Jingwei
	Liu Yan
	Lu Zhen.

Cite this article:

Li Jingwei,Liu Yan,Lu Zhen..

Comparison of the performance of seven classifiers on unbalanced gene expression data

[J]. journal1, 2021, 28(1): 91-96.

URL:

http://manu58.magtech.com.cn/Jwk_zgyytj/EN/10.3969/j.issn.1006-5253.2021.01.022 OR http://manu58.magtech.com.cn/Jwk_zgyytj/EN/Y2021/V28/I1/91

［1］BLAGUS R, LUSA L. Class prediction for high-dimensional class-imbalanced data［J］. BMC Bioinform, 2010, 11:523.

［2］ALON U, BARKAI N, NOTTERMAN D A, et al. Broad patterns of gene expression revealed by clustering analysis of tumor and normal colon tissues probed by oligonucleotide arrays［J］. Proc Natl Acad USA, 1999, 96(12):6745-6750.

［3］GROBELNIK M. Feature selection for unbalanced class distribution and naive bayes［C］// Proceedings of the Sixteenth International Conference on Machine Learning, 1999.

［4］BOLONCANEDO V, SANCHEZMARONO N, ALONSOBETANZOS A, et al. A review of microarray datasets and applied feature selection methods［J］. Information Sciences, 2014, 282:111-135.

［5］GUO H X, LI Y J, SHANG J, et al. Learning from classimbalanced data: Review of methods and applications［J］. Expert Systems with Applications, 2017, 73:220-239.

［6］HOLDER L B, HAQUE M M, SKINNER M K. Machine learning for epigenetics and future medical applications［J］. Epigenetics, 2017, 12(7):505-514.

［7］袁联雄，佘玲玲，林爱华，等．常用分类算法在不同样本量和类分布的不平衡数据中的分类效果比较［J］．中国医院统计，2015，22(1)：22-26．

［8］LI L, DARDEN T A, WEINBERG C R, et al. Gene assessment and sample classification for gene expression data using a genetic algorithm/knearest neighbor method［J］. Comb Chem High Throughput Screen, 2001, 4(8):727-739.

［9］GOLUB T R, SLONIM D K, TAMAYO P, et al. Molecular classification of cancer: Class discovery and class prediction by gene expression monitoring［J］. Science, 1999, 286(5439):531-537.

［10］MOLLINEDA R, ALEJO R, SOTOCA J. The class imbalance problem in pattern classification and learning［C］// II Congreso Espanol de Informática, 2007.

［11］李军．不平衡数据学习的研究［D］．长春：吉林大学，2011． 

［12］SHI L, CAMPBELL G, JONES W D, et al. The MicroArray Quality Control (MAQC)II study of common practices for the development and validation of microarraybased predictive models［J］. Nat Biotechnol, 2010, 28(8):827-838. 

［13］GALAR M, FERNANDEZ A, BARRENECHEA E, et al. A review on ensembles for the class imbalance problem: Bagging, boosting, and hybrid-based approaches［J］. IEEE Trans Syst, Man, Cybern C, 2012, 42(4):463-484.

［14］CHERKASSKY V. The Nature Of Statistical Learning Theory［J］. IEEE Trans Neural Netw, 1997, 8(6):1564.

［15］QUINLAN J R. Induction of Decision Trees［J］. Machine Learning, 1986, 1(1):81-106.

［16］马刚．朴素贝叶斯算法的改进与应用［D］．合肥：安徽大学，2018． 

［17］BREIMAN L. Random forests［J］. Mach Learn, 2001, 45(1):5-32.

［18］PARRY R M, JONES W, STOKES T H, et al. KNearest neighbor models for microarray gene expression analysis and clinical outcome prediction［J］. Pharmacogenomics J, 2010, 10(4):292-309. 

［19］FREUND Y, SCHAPIRE R E. A decisiontheoretic generalization of online learning and an application to boosting［J］. J Comput Syst Sci, 1997, 55(1):119-139.

［20］BREIMAN L. Bagging predictors［J］. Mach Learn, 1996, 24(2):123-140.

［21］JONG V L, NOVIANTI P W, ROES K C, et al. Selecting a classification function for class prediction with gene expression data［J］. Bioinformatics, 2016, 32(12):1814-1822.