Knowledge-based analysis of microarray gene expression data by using support vector machines

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.

Phase identity of the maize leaf is determined after leaf initiation

The vegetative development of the maize shoot can be divided into juvenile and adult phases based on the types of leaves produced at different times in shoot development. Models for the regulation of phase change make explicit predictions about when the identity of these types of leaves is determined. To test these models, we examined the timing of leaf type determination in maize. Clones induced in transition leaf primordia demonstrated that the juvenile and adult regions of these leaves do not become clonally distinct until after the primordium is 700 μm in length, implying that these cell fates were undetermined at this stage of leaf development. Adult shoot apices were cultured in vitro to induce rejuvenation. We found that leaf primordia as large as 3 mm in length can be at least partially rejuvenated by this treatment, and the location of rejuvenated tissue is correlated with the maturation pattern of the leaf. The amount and distribution of juvenile tissue in rejuvenated leaves suggests that rejuvenation occurs nearly simultaneously in all leaf primordia. In vitro culture rejuvenated existing leaf primordia and the P0 primordium, but did not change the identity of subsequent primordia or the total number of leaves produced by the shoot. This result suggests that leaf identity can be regulated independently of the identity of the shoot apical meristem, and it implies that vegetative phase change is not initiated by a change in the identity of the shoot apical meristem.