文献类型： 外文期刊

作者： Tang, Hua ¹ ; Cao, Ren-Zhi ² ; Wang, Wen ² ; Liu, Tie-Shan ³ ; Wang, Li-Ming ³ ; He, Chun-Mei ³ ;

作者机构： 1.Southwest Med Univ, Dept Pathophysiol, Luzhou 646000, Peoples R China

2.Pacific Lutheran Univ, Dept Comp Sci, Tacoma, WA 98447 USA

3.Shandong Acad Agr Sci, Maize Inst, Jinan 250100, Peoples R China

关键词： Thermostability;thermophilic protein;fragment;support vector machine.

期刊名称：INTERNATIONAL JOURNAL OF BIOMATHEMATICS （ 影响因子：2.053； 五年影响因子：1.564 ）

ISSN： 1793-5245

年卷期： 2017 年 10 卷 4 期

页码：

收录情况： SCI

摘要： Improving thermostability of an enzyme can accelerate the relevant chemical reaction. Thus, the analysis and prediction of thermophilic proteins are conducive to protein engineering and enzyme design. In this study, a novel method based on two-step discrimination was proposed to distinguish between thermophilic and non-thermophilic proteins. The model was rigorously benchmarked on an objective dataset including 915 thermophilic proteins and 793 non-thermophilic proteins. Results showed that the overall accuracy of our method is 94.44% in 5-fold cross-validation, which is higher than those of other published methods. We believe that the two-step discriminated strategy will become a promising method in the relevant field of protein bioinformatics.