ANMM4CBR: a case-based reasoning method for gene expression data classification

Abstract

Background: Accurate classification of microarray data is critical for successful clinical diagnosis and treatment. The "curse of dimensionality" problem and noise in the data, however, undermines the performance of many algorithms.

Method: In order to obtain a robust classifier, a novel Additive Nonparametric Margin Maximum for Case-Based Reasoning (ANMM4CBR) method is proposed in this article. ANMM4CBR employs a case-based reasoning (CBR) method for classification. CBR is a suitable paradigm for microarray analysis, where the rules that define the domain knowledge are difficult to obtain because usually only a small number of training samples are available. Moreover, in order to select the most informative genes, we propose to perform feature selection via additively optimizing a nonparametric margin maximum criterion, which is defined based on gene pre-selection and sample clustering. Our feature selection method is very robust to noise in the data.

Results: The effectiveness of our method is demonstrated on both simulated and real data sets. We show that the ANMM4CBR method performs better than some state-of-the-art methods such as support vector machine (SVM) and k nearest neighbor (kNN), especially when the data contains a high level of noise.

Availability: The source code is attached as an additional file of this paper.

Figure 1

Framework of ANMM4CBR for microarray classification. ANMM4CBR contains two modules, ANMM for feature selection and CBR for classification. Both ANMM and CBR are suitable for dealing with microarray data, which usually contain noisy information and only a small number of training samples are available.

Figure 2

Additive optimization of the NNM criterion. flag_m indicates whether ϕ_m has been selected. It is true if ϕ_m has been selected, otherwise false.

Figure 3

Visualization of training samples using top 3 selected features by different feature selection methods. The feature selection methods are: (a) BW, (b) ANMM without feature pre-selection and sample clustering, (c) ANMM. Results of MRMR were not listed due to space limitation. Figure 4 shows that MRMR did not perform better than BW on this data. In these figures, different marker types represent samples in different classes, and the mis-specifications are depicted with red edge. In (c) samples in different clusters are filled with different colors.

Figure 4

Boxplots of the accuracy on simulated data. "Values" indicate the accuracy. Each column indicates different algorithms: 1 - BW+kNN; 2 - MRMR +kNN; 3 - BW+SVM; 4 - MRMR+SVM; 5 - LogitBoost; 6 - ANMM4CBR without feature pre-selection and sample clustering; 7 - ANMM4CBR.