Abstract: Dependence between expression levels of different genes is identified through a multivariate method of statistical analysis of single color microarray gene expression data. An algorithm is applied to gene data to identify those genes that are likely to change their relationship with all other genes, and select such genes for further investigation. If genes change their relationship to other genes from phenotype to phenotype, they are treated as likely to change their relationship with one another.

Abstract: An amplification-like, unidirectional dependence between expression levels in gene pairs is identified through statistical analysis including a determination of whether there is a specified level of independence (or non-correlation) between X and Z, where X is a random variable representing the expression level of a first gene, Y is a random variable representing the expression level of a second gene, and Y=XZ where Z?1. The disclosed process provides an ability to identify genes that act as “amplifiers,” thereby facilitating appropriate priority assignment to candidate genes for further evaluation and experimentation.

Abstract: The present invention provides multivariate methods for identifying differentially expressed genes based on microarray expression data. An improved random search procedure involving certain probability distances is provided. The methods of this invention implement a successive elimination procedure to remove smaller subsets resulted from each step of the random search thereby establishing a larger set of differentially expressed genes.