文档介绍：
基于贝叶斯决策理论的磷酸化位点蛋白激
酶识别算法#
邹亮,李骜,韩燕,冯焕清,王明会**
5
10
15
20
25
30
35
40
(中国科学技术大学电子科学与技术系,合肥 230601)
摘要:目的通过提出一种新颖的生物信息学算法,以此准确识别已知磷酸化位点的蛋白激
酶信息。方法根据人类激酶的聚类规则,首先从最新版本的磷酸化数据库 ()
中提取出激酶特异性的磷酸化数据,构建用于激酶识别的数据集。然后基于贝叶斯决策理论,
分析阳性数据和阴性数据中磷酸化位点附近氨基酸分布规律,进而给出了相应的统计模型并
使用留一法对模型进行了评估。结果对多个激酶家族的测试表明,该算法的识别结果明显
好于 phosk 等蛋白质磷酸化位点预测方法。结论本文提出的基于贝叶斯决
策理论的磷酸化位点激酶信息识别算法将有效地提高对已知磷酸化位点的蛋白激酶识别性
能,有助于理解蛋白质磷酸化的生物机制。
关键词:模式识别;蛋白激酶;磷酸化;贝叶斯决策理论
中图分类号:TP301
A novel algorithm for identifying protein kinases associated
with phosphorylation sites based on Bayesian decision
theory
ZOU Liang, LI Ao, HAN Yan, FENG Huanqing, WANG Minghui
(Department of Electronic Science and Technology, University of Science and Technology of
China, HeFei 230601)
Abstract: Objective In this study a novel machine learning method is proposed to identify protein
kinase for known phosphorylation sites. Method According to the hierarchy structure of human
kinases, we firstly constructed datasets for each kinase or kinase cluster using the kinase-specific
phosphorylation instances extracted from the latest version of (). Based on
Bayesian decision theory, we analyzed the amino acid distribution of each residue around the
phosphorylation sites in positive and negative dataset respectively and constructed corresponding
statistical models. In addition, we evaluated the perfo