改进信息离散性度量方法的蛋白质二级结构预测

应用科学学报

改进信息离散性度量方法的蛋白质二级结构预测

李哲谦1,2，刘书朋1,2，严壮志1,2，辛艳飞3

1.上海大学通信与信息工程学院, 上海 200072
2.上海大学生物医学工程研究所,上海 200072
3. 浙江省医学科学院, 浙江杭州 310013

收稿日期:2007-09-01 修回日期:2007-12-21 出版日期:2008-03-31 发布日期:2008-03-31

Prediction of Protein Secondary Structure with an Improved Measure of Information Discrepancy

LI Zhe－qian1,2, LIU Shu-peng1,2, YAN Zhuang-zhi1,2, XIN Yan-fei3

1. School of Communication and Information Engineering, Shanghai University,
2. Institute of Biomedical Engineering, Shanghai University, Shanghai 200072
3. Zhejiang Academy of Medical Sciences, Hangzhou 310013, Zhejiang

Received:2007-09-01 Revised:2007-12-21 Online:2008-03-31 Published:2008-03-31

摘要/Abstract

摘要： 采用一种信息离散性度量方法对CB396数据集中的蛋白质数据进行二级结构预测，预测准确率达到72.1%，为了提高预测准确率，将FDOD算法结合PSI-BLAST进行多重序列比对，预测准确率提高到75.6%，证明了该方法的有效性。在此基础上，利用20种疏水标度改进FDOD方法，以减小计算量。最后，结合长程作用，对预测准确性的影响因素进行了讨论。

关键词: 二级结构预测, 信息离散性, 疏水特性, 长程作用

Abstract: The secondary structure prediction is important in protein structure prediction since protein secondary structure is the basis of the tertiary structure. A method of information discrepancy-FDOD (Function of Degree of Disagreement) was used to predict protein secondary structure in this work. Data were selected from the CB396 database and prediction accuracy was 72.1%. Besides, multiple alignment of PSI-BLAST was used to combine with FDOD, with the prediction accuracy increased to 75.6%. Furthermore, in order to reduce computation complexity, hydrophobic values were introduced to improve the algorithm and the impact factors of hydrophobic values. Long-range interaction is discussed in the prediction of protein secondary structure.

Key words: protein secondary structure prediction, disagreement degree, hydrophobic values, long-range interaction

李哲谦;刘书朋;严壮志;辛艳飞. 改进信息离散性度量方法的蛋白质二级结构预测 [J]. 应用科学学报.

LI Zhe－qian;LIU Shu-peng;YAN Zhuang-zhi;XIN Yan-fei. Prediction of Protein Secondary Structure with an Improved Measure of Information Discrepancy[J]. Journal of Applied Sciences.