SVDMAN - singular value decomposition analysis of microarray data

We have developed two novel methods for Singular Value Decomposition analys is (SVD) of microarray data. The first is a threshold-based method for obta ining gene groups, and the second is a method for obtaining a measure of co nfidence in SVD analysis. Gene groups are obtained by identifying elements of the left singular vectors, or gene coefficient vectors, that are greater in magnitude than the threshold WN-1/2, where N is the number of genes, an d W is a weight factor whose default value is 3. The groups are non-exclusi ve and may contain genes of opposite (i.e. inversely correlated) regulatory response. The confidence measure is obtained by systematically deleting as says from the data set, interpolating the SVD of the reduced data set to re construct the missing assay, and calculating the Pearson correlation betwee n the reconstructed assay and the original data. This confidence measure is applicable when each experimental assay corresponds to a value of paramete r that can be interpolated, such as time, dose or concentration. Algorithms for the grouping method and the confidence measure are available in a soft ware application called SVD Microarray ANalysis (SVDMAN). In addition to ca lculating the SVD for generic analysis, SVDMAN provides a new means for usi ng microarray data to develop hypotheses for gene associations and provides a measure of confidence in the hypotheses, thus extending current SVD rese arch in the area of global gene expression analysis.