基于机器学习的β-内酰胺酶注释预测和分析平台  

Beta-lactamase annotation prediction and analysis platform based on machine learning

作　　者：侯镱 蓝小斌 陈嘉豪 管军霖 HOU Yi;LAN Xiaobin;CHEN Jiahao;GUAN Junlin(School of Computer and Information Security,Guilin University of Electronic Technology,Guilin 541004,China)

机构地区：[1]桂林电子科技大学计算机与信息安全学院,广西桂林541004

出　　处：《桂林电子科技大学学报》2021年第4期320-328,共9页Journal of Guilin University of Electronic Technology

基　　金：广西研究生科研创新项目(YCSW2020152);桂林电子科技大学研究生教育创新计划项目(2020YCXS045)。

摘　　要：为了对潜在β-内酰胺酶蛋白质的功能和性质进行深入分析,构建了一个包含蛋白质信息注释、预测和特征性分析的综合平台(BLHub)。BLHub采用Java、Bootstrap3.3.6、Ajax、jQuery、MySQL和Strust2等技术实现了平台前后端的数据交互,并且该平台整合了丰富的、多源的蛋白质注释信息,包括蛋白质结构信息、蛋白质活跃位点、蛋白质分类系谱以及抗生素耐药性信息等。同时平台嵌入了机器学习的预测模型,能有效发掘潜在的β-内酰胺酶并判断其所属子类。此外,BLHub能对潜在的β-内酰胺酶进行后序的序列相似分析和亲缘性分析,便于科研人员进一步推断未知蛋白质的功能和结构,从而实现对β-内酰胺酶蛋白质的一体化分析。实验结果表明,BLHub能弥补以往的β-内酰胺酶数据库无法对潜在蛋白质进行预测和分析的不足,进一步加快潜在蛋白的发现和探索。In order to conduct an in-depth analysis of the functions and properties of potential β-lactamase proteins, a comprehensive platform(BLHub) was built with the function of protein annotation, prediction and specific analysis. The platform is implemented in Java、Bootstrap 3.3.6、Ajax、jQuery、MySQL and Strust2 technologies to realize the interaction between function and data of the front end and back end. In terms of functions, BLHub integrates rich and multi-source protein annotation information, including protein structure information, protein active sites, protein classification genealogy, and antibiotic resistance information. At the same time, the platform is embedded with a predictive tool of machine learning so as to discover potential β-lactamase proteins and identify its subtype. In addition, in order to facilitate scientific researchers to further infer the function and structure of the unknown protein, the platform provides analysis methods based on protein sequence including similarity analysis and phylogenetic analysis. Practice has shown that the BLHub makes up for the inability of the previous β-lactamase database to predict and analyze potential proteins, and further accelerates the discovery and exploration of potential proteins.

关 键 词：数据库 机器学习预测 抗生素耐药性 BLAST序列比对 亲缘性分析 重定向分析 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] Q811[自动化与计算机技术—控制科学与工程]