In our attempts to understand cellular function at the molecular level, we must be able to synthesize information from disparate types of Genomic data. In collaboration with Columbia University, we have addressed the problem of inferring gene functional classifications from a heterogeneous data set consisting of DNA microarray expression measurements and phylogenetic profiles from whole-genome sequence comparisons. Our technologies demonstrate the application of the SVM learning algorithm to this functional inference task. The SVM kernel function was instrumental in combining heterogeneous data to obtain better results than other methods. Out of 126 functional classes, 64 are learnable with the two data sets while only 44 are learnable from microarray data only and 40 from phylogenetic profiles only.