An approach of protein secondary structure prediction based on SVM method in compound pyramid model

Accurate secondary-structure prediction is a key element in the prediction of tertiary structure, in all but the simplest homology modeling cases. After the study on this subject for 30 years and more, there have been some breakthroughs. Based on KDTICM theory, we have proposed a model, which is composed of four layers of the intelligent interface and integrated in several ways, such as SVM, KDD^*, homology analysis and so on. Experiment shows that this model obtains Q3 accuracy of 83.06%, 80.49% on RS126 and CB513, and for the proteins which contain more alpha/beta structure, the Q3 accuracy obtained is 93.12%. This article briefly introduces this model and highlights the improved SVM method.