Medicine and Health Sciences Commons^™

Microarray-Based Cancer Prediction Using Single Genes., Xiaosheng Wang, Richard Simon

Journal Articles: Genetics, Cell Biology & Anatomy

BACKGROUND: Although numerous methods of using microarray data analysis for cancer classification have been proposed, most utilize many genes to achieve accurate classification. This can hamper interpretability of the models and ease of translation to other assay platforms. We explored the use of single genes to construct classification models. We first identified the genes with the most powerful univariate class discrimination ability and then constructed simple classification rules for class prediction using the single genes.

RESULTS: We applied our model development algorithm to eleven cancer gene expression datasets and compared classification accuracy to that for standard methods including Diagonal Linear …