Comparison of discrimination methods for the classification of tumors using gene expression data-英文文献.pdf

Comparison of Discrimination Methods for the Classi’ cation of Tumors Using Gene Expression Data Sandrine Dudoit, Jane Fridlyand, and Terence P. Speed A reliable and precise classi cation of tumors is essential for successful diagnosis and treatment of cancer. cDNA microarrays and high- density oligonucleotide chips are novel biotechnologies increasingly used in cancer research. By allowing the monitoring of expression levels in cells for thousands of genes simultaneously, microarray experiments may lead to a more complete understanding of the molecular variations among tumors and hence to a ner and more informative classi cation. The ability to successfully distinguish between tumor classes (already known or yet to be discovered) using gene expression data is an important aspect of this novel approach to cancer classi cation. This article compares the performance of different discrimination methods for the classi cation of tumors based on gene expression data. The methods include nearest-neighbor classi ers, linear discriminant analysis, and classi cation trees. Recent machine learning approaches, such as bagging and boosting, are also considered. The discrimination methods are applied to datasets from three recently published cancer gene expression studies. KEY WORDS: Cancer; Discriminant analysis; Microarray experiment; Supervised learning; Tumor classi cation; Variable selection. 1. INTRODUCTION sequences in two DNA or RNA samples may be assessed by monitoring