Prediction of Protein Secondary Structure using Support Vector Machine with PSSM Profiles
Prediction of protein secondary structure is important to analyze the protein folding patterns.We propose a protein secondary structure prediction method based on the support vector machine (SVM) with position-specific scoring matrix (PSSM) profiles in this paper.The PSSM profiles are obtained from CB513 data set and PSI-BLAST program.We arrange the data set with the sliding window 13 and the dimension of the feature vector is 260.The grid search algorithm and genetic algorithm are used to optimize c and γ parameters of SVM.The experimental results show that the method of this paper is more effective than the traditional method which using the amino acid sequence as the data set and it increased the accuracy by 11.3%.
SVM Genetic algorithm Position specific scoring matrices Protein secondary structure
Yanchun Wang Jinyong Cheng Yihui Liu Yehong Chen
School of Information,Qilu University of Technology,Jinan,China
国际会议
重庆
英文
502-505
2016-03-20（万方平台首次上网日期，不代表论文的发表时间）