基于信息熵和残基电荷性的酪氨酸硝基化位点预测  

Prediction of tyrosine nitration sites based on information entropy and charge of residue

作　　者：施绍萍[1,2] 揭志勇 邱建丁[1] 

机构地区：[1]南昌大学化学系,江西南昌330031 [2]南昌大学数学系,江西南昌330031 [3]南昌陆军学院科文教研室,江西南昌330103

出　　处：《南昌大学学报（理科版）》2012年第3期245-249,共5页Journal of Nanchang University(Natural Science)

基　　金：国家自然科学基金资助项目(21175064);教育部新世纪优秀人才支持计划(NCET-11-1002);江西省教育厅科技计划项目(GJJ11646)

摘　　要：采用氨基酸残基信息熵优化窗口,结合氨基酸的电荷性构建了蛋白质酪氨酸硝基化位点的预测模型。基于10-倍交叉验证,该模型的预测准确率和马氏相关系数分别达到了84.80%和69.69%。同时,对信息熵优化窗口和传统连续窗口进行了探讨,结果表明,信息熵窗口能够有效捕获酪氨酸硝基化肽段上的重要位点,克服短肽序列易丢失信息而单纯增大肽段长度又会引入冗余信息的矛盾,并最终提高模型的预测性能。特征分析揭示酪氨酸残基的局部静电环境、邻近的进化保守位点和长程位点对酪氨酸硝基化均有重要影响。A new method based on information entropy and charge of residue was developed to predict the tyrosine nitration sites. By using the 10-fold cross-validation, the predictive accuracy and Matthews Correla- tion Coefficient of the model were 84.80% and 69.69% ,respectively. Some preliminary discussions were made to the window of information entropy and traditional continuous window. Our results showed that the window of information entropy could effectively capture the important sites in the nitro-tyrosine peptide, which overcomed the contradiction that the short peptide sequence was easy to lose information and the re- dundant information would be introduced by just increasing the length of peptide. The prediction perform- ance of the model was ultimately improved. Feature analysis revealed that the local electrostatic environ- ment of tyrosine residues,the adjacent evolutionarily conserved sites and long-range sites had some signifi- cant influences on tyrosine nitration.

关 键 词：酪氨酸硝基化 信息熵 残基电荷性 

分 类 号：Q811[生物学—生物工程] TP391[自动化与计算机技术—计算机应用技术]