In this article, we compare decision trees (DT) and support vector machines (SVM) in classifying gene sequences. With the explosion of genome research, tremendous amounts of data have been made available and a deep insight study becomes demanding. Among various kinds of gene analysis approaches being developed, sequence based gene feature classification is important due to its ability to identify the presence of specific gene segments. In this article, we focus on two major classification methods, namely decision trees and support vector machines. By comparing various versions of decision tree algorithms and SVMs as well as a particular SVM tuned for gene detection, it is shown that by integrating structural information of the gene squence into SVMs, a more accurate classifier is achieved.