Simultaneous Gene Selection and Weighting in Nearest Neighbor Classifier for Gene Expression Data

Gene expression data, such as microarray data, plays an important role as a biomarker in order to help in the effective cancer diagnosis, tumor classification or drug design at molecular level. However, due to high-dimensionality of microarray datasets, they tend to have irrelevant or redundant features, and may lead to poor classification performance. For this reason, feature selection methods are commonly used to reduce the amount of data and to select relevant genes to improve the accuracy of machine learning methods. In this paper, a simultaneous feature ranking and weighting gene selection method with a nearest neighbor-based classifier is presented. In order to demonstrate the effectiveness of this proposal, a range of experiments over four well-known microarray datasets were carried out. Results showed that our method outperforms previous methods in terms of classification accuracy. Furthermore, evidence for significance of our results by means of non-parametric Friedman test is provided.

[1]  Trevor Hastie,et al.  An Introduction to Statistical Learning , 2013, Springer Texts in Statistics.

[2]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[3]  Lluís A. Belanche Muñoz,et al.  Feature selection algorithms: a survey and experimental evaluation , 2002, 2002 IEEE International Conference on Data Mining, 2002. Proceedings..

[4]  J. Mesirov,et al.  Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. , 1999, Science.

[5]  M. Friedman.  The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance , 1937 .

[6]  Madhubanti Maitra,et al.  Gene selection from microarray gene expression data for classification of cancer subgroups employing PSO and adaptive K-nearest neighborhood technique , 2015, Expert Syst. Appl..

[7]  Marko Robnik-Sikonja,et al.  Theoretical and Empirical Analysis of ReliefF and RReliefF , 2003, Machine Learning.

[8]  Huan Liu,et al.  Feature Selection for High-Dimensional Data: A Fast Correlation-Based Filter Solution , 2003, ICML.

[9]  J. L. Hodges,et al.  Discriminatory Analysis - Nonparametric Discrimination: Consistency Properties , 1989 .

[10]  Verónica Bolón-Canedo,et al.  An ensemble of filters and classifiers for microarray data classification , 2012, Pattern Recognit..

[11]  Hiroshi Motoda,et al.  Computational Methods of Feature Selection , 2022 .

[12]  Enrique Alba,et al.  Two hybrid wrapper-filter feature selection algorithms applied to high-dimensional microarray experiments , 2016, Appl. Soft Comput..

[13]  Estevam R. Hruschka,et al.  Feature-weighted k-Nearest Neighbor Classifier , 2007, 2007 IEEE Symposium on Foundations of Computational Intelligence.

[14]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[15]  Keinosuke Fukunaga,et al.  A Branch and Bound Algorithm for Feature Subset Selection , 1977, IEEE Transactions on Computers.

[16]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[17]  Jason Weston,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2002, Machine Learning.

[18]  Seoung Bum Kim,et al.  Sequential random k-nearest neighbor feature selection for high-dimensional data , 2015, Expert Syst. Appl..

[19]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[20]  Larry A. Rendell,et al.  The Feature Selection Problem: Traditional Methods and a New Algorithm , 1992, AAAI.

[21]  Gil Alterovitz,et al.  Accelerating wrapper-based feature selection with K-nearest-neighbor , 2015, Knowl. Based Syst..

[22]  Duncan Fyfe Gillies,et al.  A Review of Feature Selection and Feature Extraction Methods Applied on Microarray Data , 2015, Adv. Bioinformatics.