Improved Protein Secondary Structure Prediction using a Intelligent HSVM Method with a New Encoding Scheme

Prediction of protein secondary structures is an important problem in bioinformatics and has many applications. Successful secondary structure predictions provide a starting point for direct tertiary structure modelling, and also can significantly improve sequence analysis and sequence-structure threading for aiding in structure and function determination. Now many secondary structure prediction methods routinely achieve accuracy (Q3) of about 70%. We believe this accuracy could be further improved by using a hybrid method as essential part of the prediction process. In this article, a hybrid SVM(HSVM) has been used to predict protein secondary structure based on the method of combining physicochemical properties of amino acid residues with position-specific scoring matrices (PSSM) containing evolutionary information. Secondary structure can be predicted at significantly increased accuracy. Using a knowledge discovery theory based on inner cognitive mechanism (KDTICM) method, we have developed a gradually enhanced, multi-layered prediction system to predict protein secondary structure, compound pyramid model (CPM). The results are found to be superior to those produced by other methods with blind test dataset from the CASP9 meeting, including the popular psipred method according to Q3 and SOV99 accuracy. The results show that our method has strong generalization ability. The CPM website is accessible at http://kdd.ustb.edu.cn/protein _Web/.