We report on the successful application of feature selection methods to a classification problem in molecular biology involving only 72 data points in a 7130 dimensional space. Our approach is a hybrid filter and wrapper approaches to feature selection. In particular, gene expression microarrays are a rapidly maturing technology that provides the opportunity to assay the expression levels of thousands or tens of thousands of genes in a single experiment. These assays provide the input to a wide variety of statistical modeling, including classification, clustering, and density estimation. For example, by measuring expression levels associated with two kinds of tissue, tumor or non-tumor, one obtains labeled data sets that can be used to build diagnostic classifiers. The number of replicates in these experiments is often severely limited. These methods are mainly based on an individual ranking scheme; therefore, it is possible that some of the selected features are mutually redundant. This scheme is most effective for statistically independent features. Because these methods ignore the interaction with the classifier, the classification performance will not be very high.