No abstract

We introduce a method of functionally classifying genes by using gene expression data from DNA microarray hybridization experiments. The method is based on the theory of support vector machines (SVMs). SVMs are considered a supervised computer learning method because they exploit prior knowledge of gene function to identify unknown genes of similar function from expression data. SVMs avoid several problems associated with unsupervised clustering methods, such as hierarchical clustering and self-organizing maps. SVMs have many mathematical features that make them attractive for gene expression analysis, including their flexibility in choosing a similarity function, sparseness of solution when dealing with large data sets, the ability to handle large feature spaces, and the ability to identify outliers. We test several SVMs that use different similarity metrics, as well as some other supervised learning methods, and find that the SVMs best identify sets of genes with a common function using expression data. Finally, we use SVMs to predict functional roles for uncharacterized yeast ORFs based on their expression data.

A variety of cytokines mediate the activation of Janus protein tyrosine kinases (Jaks). The Jaks then phosphorylate cellular substrates, including members of the signal transducers and activators of transcription (Stat) family of transcription factors. Among the Stats, the two highly related proteins, Stat5a and Stat5b, are activated by a variety of cytokines. To assess the role of the Stat5 proteins, mutant mice were derived that have the genes deleted individually or together. The phenotypes of the mice demonstrate an essential, and often redundant, role for the two Stat5 proteins in a spectrum of physiological responses associated with growth hormone and prolactin. Conversely, the responses to a variety of cytokines that activate the Stat5 proteins, including erythropoietin, are largely unaffected.

No abstract