A Feature Generation Algorithm for Sequences with Application to Splice-Site Prediction

摘要: In this paper we present a new approach to feature selection for sequence data. We identify general categories and give construction algorithms each of them. show how they can be integrated in system that tightly couples selection. This process, which refer as generation, allows us systematically search large space potential features. demonstrate the effectiveness our an important component gene finding problem, splice-site prediction. predictive models built using generation algorithm achieve significant improvement accuracy over existing, state-of-the-art approaches.