Prediction of protein secondary structure content using support vector machine

In this paper, the support vector machine was trained to grasp the relationship between the pair-coupled amino acid composition and the content of protein secondary structural elements, including α-helix, 310-helix, π-helix, β-strand, β-bridge, turn, bend and the rest random coil. Self-consistency and cross validation tests were made to assess the performance of our method. Results superior to or competitive with the popular theoretical and experimental methods have been obtained.