Stable feature selection and classification algorithms for multiclass microarray data

• Published in: Biology direct Vol. 7; no. 1; p. 33
• Main Authors: Student, Sebastian, Fujarewicz, Krzysztof
• Format: Journal Article
• Language: English
• Published: London BioMed Central 02.10.2012; BioMed Central Ltd; Springer Nature B.V
• Subjects: Algorithms; Analysis; Bioinformatics; Biomedical and Life Sciences; Classification; Decomposition; Discriminant Analysis; DNA microarrays; Gene expression; Gene Expression Profiling - methods; Least-Squares Analysis; Life Sciences; Linear Models; Neoplasms - genetics; Neoplasms - metabolism; Oligonucleotide Array Sequence Analysis - methods; Studies; Support Vector Machine; Transcriptome; Feature Selection; Bootstrap Sample; Feature Selection Method; Partial Little Square; Gene List
• ISSN: 1745-6150; 1745-6150
• DOI: 10.1186/1745-6150-7-33

Background Recent studies suggest that gene expression profiles are a promising alternative for clinical cancer classification. One major problem in applying DNA microarrays for classification is the dimension of obtained data sets. In this paper we propose a multiclass gene selection method based on Partial Least Squares (PLS) for selecting genes for classification. The new idea is to solve multiclass selection problem with the PLS method and decomposition to a set of two-class sub-problems: one versus rest (OvR) and one versus one (OvO). We use OvR and OvO two-class decomposition for other recently published gene selection method. Ranked gene lists are highly unstable in the sense that a small change of the data set often leads to big changes in the obtained ordered lists. In this paper, we take a look at the assessment of stability of the proposed methods. We use the linear support vector machines (SVM) technique in different variants: one versus one, one versus rest, multiclass SVM (MSVM) and the linear discriminant analysis (LDA) as a classifier. We use balanced bootstrap to estimate the prediction error and to test the variability of the obtained ordered lists. Results This paper focuses on effective identification of informative genes. As a result, a new strategy to find a small subset of significant genes is designed. Our results on real multiclass cancer data show that our method has a very high accuracy rate for different combinations of classification methods, giving concurrently very stable feature rankings. Conclusions This paper shows that the proposed strategies can improve the performance of selected gene sets substantially. OvR and OvO techniques applied to existing gene selection methods improve results as well. The presented method allows to obtain a more reliable classifier with less classifier error. In the same time the method generates more stable ordered feature lists in comparison with existing methods. Reviewers This article was reviewed by Prof Marek Kimmel, Dr Hans Binder (nominated by Dr Tomasz Lipniacki) and Dr Yuriy Gusev