Incorporating hidden Markov models for identifying protein kinase-specific phosphorylation sites
Incorporating hidden Markov models for identifying protein kinase-specific phosphorylation sites
复制标题
DOI：
10.1002/jcc.20235
复制
发表时间：
2005-07-30
影响因子：
3
通讯作者：
Huang, KT
中科院分区：
文献类型：
--
作者：
Huang, HD;Lee, TY;Huang, KT
蛋白质磷酸化是蛋白质翻译后修饰的重要机制，它影响着细胞代谢、细胞信号转导、分化和膜转运等重要的细胞过程。蛋白质被多种蛋白激酶磷酸化。在这项研究中，我们开发了一种新的工具来计算预测催化激酶特异性磷酸化位点。来自公共领域数据源的已知磷酸化位点通过其注释的蛋白激酶进行分类。基于轮廓隐马尔可夫模型（HMM）的概念，从磷酸化位点的激酶特异性组训练计算模型。在评估训练的模型后，我们选择了在每个激酶特异性组中准确度最高的模型，并提供了一个基于Web的预测工具来识别蛋白质磷酸化位点。这里的主要贡献是，我们已经开发了一个激酶特异性磷酸化位点预测工具，具有高灵敏度和特异性。(c)2005 Wiley Periodicals，Inc.
Protein phosphorylation, which is an important mechanism in posttranslational modification, affects essential cellular processes such as metabolism, cell signaling, differentiation, and membrane transportation. Proteins are phosphorylated by a variety of protein kinases. In this investigation, we develop a novel tool to computationally predict catalytic kinase-specific phosphorylation sites. The known phosphorylation sites from public domain data sources are categorized by their annotated protein kinases. Based on the concepts of profile Hidden Markov Models (HMM), computational models are trained from the kinase-specific groups of phosphorylation sites. After evaluating the trained models, we select the model with highest accuracy in each kinase-specific group and provide a Web-based prediction tool for identifying protein phosphorylation sites. The main contribution here is that we have developed a kinase-specific phosphorylation site prediction tool with both high sensitivity and specificity. (c) 2005 Wiley Periodicals, Inc.