An Enhanced Dimension Reduction Approach for Microarray Gene Expression Data

Abstract

ntroduction: To achieve the high classification accuracy in microarray gene expression data set, various classification methods using dimension reductions have been extensively studied. However, these methods still require the improvement. For example, many dimension reduction methods show different results depending on data and conditions.Materials and Methods: Here, we introduce an enhancement concept that joins two dimension reduction methods of Partial Least Squares (PLS) and Minimum Average Variance Estimation (MAVE), which is called as an enhanced dimension reduction method. The PLS method generates the new transformed genes that include compressed information. Then, the MAVE method clusters samples in the same class and separate samples in other classes.Results and Discussion: By applying this enhanced dimension reduction approach into two classification methods of Adaptive Network based on Fuzzy Inference System (ANFIS) and Support Vector Machine (SVM), the classification accuracies of nine cancer data sets are improved compared to using only the PLS dimension reduction approach.Conclusion and Prospects: This study shows that the enhanced dimension reduction approach can be generally used for any classification method in order to obtain high classification quality for the data sets with the large number of features compared to the number of samples.