项目名称: 蛋白质相互作用中热区的发现与界定方法
项目编号: No.61273225
项目类型: 面上项目
立项/批准年度: 2013
项目学科: 自动化技术、计算机技术
项目作者: 张晓龙
作者单位: 武汉科技大学
项目金额: 80万元
中文摘要: 蛋白质相互作用中的热区是指蛋白质与蛋白质相互作用和对接时热点残基的活动区域。热区的发现与界定是揭示诸如细胞代谢和信号传导途径、免疫确认、DNA复制、蛋白质合成和生物制药等蛋白质功能活动的一种重要手段。本研究采用机器学习算法,结合蛋白质的生物特征、结构特征和进化特征,发现并界定蛋白质相互作用界面中热区结构模块。通过设计蛋白质的特征编码方法,对选取的蛋白质数据实施蛋白质的结构特征编码,利用分类算法预测蛋白质相互作用的界面结构域;在取得界面结构域的基础上,判定和选取热点残基的集合,同时计算得到热点残基的空间稳定构象和残基结合倾向性等特征,利用提出的优化算法有效地识别出蛋白质相互作用的热区结构模块。最后,将集成阶段性的研究成果,设计并实现一个适用于蛋白质相互作用中热区发现与界定的算法系统。本研究将为解决蛋白质相互作用中界面和热区的预测问题提供新方法,同时为探明蛋白质的功能活动提供新思路。
中文关键词: 生物信息计算;蛋白质热区预测;蛋白质相互作用;热点残基;
英文摘要: The hot regions of protein interactions refer to the activity scope where hot spots are found to be buried and tightly packing with other residues. The discovery and discrimination of the hot regions is an important way to uncover protein functional activities, such as cell metabolism and signaling pathway, immune recognition, DNA replication, protein synthesis and biological pharmacy. In this study, machine learning method is used to discover the hot regions by using biological feature, structure feature and evolutionary feature of the proteins. With the proposed protein feature coding method, the selected training data can be effectively coded and used in classification algorithm to predict protein-protein interaction interfaces. Based on these interfaces, the hot spots are easily located and selected; the space stable conformation of the hot spots can be determined, and their binding tendency with other residues can be simultaneously calculated; and then the hot regions can be discovered and efficiently discriminated by using the proposed optimization algorithm. At last, we implement the system that integrates the above algorithms and related functions to discover and discriminate the hot regions of the protein-protein interactions. This research work gives an effective method to predict the protein-protein i
英文关键词: Biological information computing;Hot region prediction;Protein-protein interaction;Hot spot residue;