HykGene: An Hybrid Approach for Selecting Marker Genes for Phenotype Classification using Microarray Gene Expression Data

Motivation: Recent studies have shown that microarray gene expression data is useful for phenotype classification of many diseases. In this classification problem, the number of features (genes) greatly exceeds the number of instances (tissue samples). It has been shown that selecting a small set of informative genes can lead to improved classification accuracy. Many approaches have been proposed for this gene selection problem. Most of the previous gene ranking methods typically select 50–100 top-ranked genes, and these genes are often highly correlated. Results: We propose to select a small set of non-redundant marker genes that are most relevant for the classification. To achieve this goal, we developed a novel hybrid approach that combines gene ranking and clustering analysis. In this approach, we first apply feature filtering algorithms to select a set of top-ranked genes, and then apply hierarchical clustering on these genes to generate a dendrogram. Finally, the dendrogram is analyzed by a sweep-line algorithm, and marker genes are selected by collapsing dense clusters. Empirical study using three public data sets shows that our approach is capable of selecting relatively few marker genes while offering the same or better leave-one-out cross-validation accuracy compared to approaches that use top-ranked genes directly for classification. Availability: The software is available from the authors upon request. Contact: [email protected]