摘要
基于信息熵,融合氨基酸的物理化学性质、蛋白质的二级结构和残基的无序信息构建了Tau蛋白丝氨酸磷酸化修饰位点预测的新模型。分别探讨了每种特征对Tau蛋白丝氨酸磷酸化修饰位点的影响,特征分析结果表明,氨基酸的序列模体、卷曲结构和无序区域均有助于识别丝氨酸磷酸化修饰位点。通过10倍交叉验证,丝氨酸磷酸化修饰位点预测的准确率和马氏相关系数分别达到83.7%和65.1%,表明本文构建的模型可用于对Tau蛋白丝氨酸磷酸化修饰位点的有效预测。
A new model incorporated physicochemical properties of the amino acids,protein secondary structure and residue disorder information was proposed in the current study,which is used to predict Tau protein serine phosphorylation sites based on information entropy.We also discussed the influences of individual features on Tau protein serine phosphorylation.Epitope analysis showed that sequence motifs of amino acids,the coil structure,and residue disorder regions around the serine phosphorylation sites all could contribute to the phosphorylation sites identification.By using the 10-fold cross-validation,the predictive accuracy and Matthews correlation coefficient of the model were 83.7 % and 65.1%,respectively.These results indicate that the proposed method in this work can effectively identify phosphorylation sites.
出处
《南昌大学学报(理科版)》
CAS
北大核心
2013年第3期228-232,243,共6页
Journal of Nanchang University(Natural Science)
基金
国家自然科学基金资助项目(21175064
21265017)
江西省教育厅科技计划项目(GJJ11646)
关键词
TAU蛋白
丝氨酸磷酸化
信息熵
Tau protein
serine phosphorylation
information entropy