基于修正伪氨基酸组成预测氧化还原酶辅酶类型.pdfVIP

生 物 工 程 学 报 Chin J Biotech 2008, August 25; 24(8): 1439-1445 journals.im.ac.cn Chinese Journal of Biotechnology ISSN 1000-3061 cjb@im.ac.cn © 2008 Institute of Microbiology, CAS CSM, All rights reserved 研究报告 基于修正的伪氨基酸组成预测氧化还原酶辅酶类型 张光亚, 李红春, 方柏山 华侨大学工业生物技术研究所, 泉州 362021 摘 要: 从序列出发快速确定氧化还原酶的辅酶依赖类型对于了解其结构和功能、催化机制及构建辅酶再生体系具有 重要指导作用。对Chou 提出的伪氨基酸组成方法进行了修正并用于提取氧化还原酶序列特征值, 采用k-近邻算法预测 其辅酶依赖类型。当λ=48, w=0.1 时, 10 倍交叉验证结果表明: 其ROC 曲线下面积为0.9536, 预测精度达92.0%, 比最 优条件下伪氨基酸组成预测精度提高了 3.5%; 与其他 7 种常见特征值提取方法相比, 修正的伪氨基酸组成表现最好。 结果表明从序列出发预测氧化还原酶辅酶依赖类型是可行的, 且修正的伪氨基酸组成可望成为一种新的有效提取蛋白 质序列特征值方法。 关键词: 氧化还原酶, 辅酶依赖类型, 修正的伪氨基酸组成, k -近邻, ROC 曲线下面积 Predicting the Cofactors of Oxidoreductases by the Modified Pseudo-amino Acid Composition Guangya Zhang, Hongchun Li, and Baishan Fang Institute of Industrial BiotechnologyT , Huaqiao University, Quanzhou 362021, ChinaT Abstract: Types of cofactor independency for newly found oxidoreductases sequences are usually determined by experimental analysis. These experimental methods are both time-consuming and costly. With the explosion of oxidoreductases sequences entering into the databanks, it is highly desirable to explore the feasibility of selectively classifying newly found oxidoreductases into their respective cofactor independency classes by means of an automated method. In this study, we proposed a modified Chou’s pseudo-amino acid composition method to extract features from sequences