%0 Journal Article
%T PREDICTION OF PROTEIN SOLVENT ACCESSIBILITY WITH SUPPORT VECTOR MACHINE<br>基于支持向量机方法的蛋白可溶性预测
%A WANG Xian
%A LI Ao
%A WANG Ming-hui
%A FENG Huan-qing
%A <br>王娴
%A 李骜
%A 王明会
%A 冯焕清
%J 生物物理学报
%D 2005
%I 
%X Residues in protein sequences can be divided into two classes (exposed/buried) or three classes (exposed/intermediate/buried) according to their relative solvent accessibility. Several lengths and parameters of window were explored to achieve the best performance. The prediction accuracies of support vector machine (SVM) for different cut-off thresholds were analyzed and compared with other methods, which showed that the SVM was a better method than neural network and information theory when using the same dataset. The best accuracy, in two-class problem, could be as high as 79.0%, and in three-class problem, could be as high as 67.5%. These results show that the support vector machine is an effective method in the prediction of protein solvent accessibility.
%K Support vector machine
%K Amino acid residue
%K Solvent accessibility
%K Bioinformatics<br>支持向量机
%K 氨基酸残基
%K 可溶性
%K 预测
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=90BA3D13E7F3BC869AC96FB3DA594E3FE34FBF7B8BC0E591&jid=E0C9D9BBED813D6674AC13E942EAC86D&aid=E1DA181B082F0289&yid=2DD7160C83D0ACED&vid=659D3B06EBF534A7&iid=CA4FD0336C81A37A&sid=BFE7933E5EEA150D&eid=0401E2DB1F51F8DE&journal_id=1000-6737&journal_name=生物物理学报&referenced_num=1&reference_num=12