AP数据源融合算法构建基因调控网络  

Gene Regulatory Network Construction Based on AP Data Source Fusion Algorithm

作　　者：郑明[1,2] 刘桂霞[2] 卓慕瑰 ZHENG Ming;LIU Guixia;ZHUO Mugui(Guangxi Colleges and University Key Laboratory of Professional Software Technology, Wuzhou University,Wuzhou 543002, Guangxi Zhuang Autonomous Region, China;College of Computer Science and Technology, Jilin University, Changchun 130012, China)

机构地区：[1]梧州学院广西高校行业软件技术重点实验室,广西梧州543002 [2]吉林大学计算机科学与技术学院,长春130012

出　　处：《吉林大学学报（理学版）》2019年第5期1214-1218,共5页Journal of Jilin University:Science Edition

基　　金：国家自然科学基金(批准号:61862056);广西自然科学基金(批准号:2017GXNSFAA198148);梧州学院科研项目(批准号:2017B001)

摘　　要：针对单一数据集构建基因调控网络算法数据量不足及构建网络结果不精确的问题,提出一种基于能力与信任(AP)的数据源融合算法.该算法将基因表达数据、蛋白质相互作用数据和基序数据集,分别通过控制与被控制双向数据流传输来分析和构建基因调控网络,并与ReMoDiscovery,CLR和C3Net三种已开发模型在酵母全基因组网络构建结果的AUC值进行对比.对比结果表明,该算法在构建基因调控网络算法方面执行效率更高、收敛性更强.Aiming at the problems of insufficient data and inaccurate results of constructing gene regulatory network algorithm based on single dataset,we proposed a data source fusion algorithm based on availability and responsibility(AP).The gene expression data,protein interaction data and motif data were analyzed and constructed gene regulatory network by controlling and controlled two-way flowing information transmission respectively,and compared with AUC values of three developed models:ReMoDiscovery,CLR and C3 Net in yeast genome-wide network construction.The comparison results show that the algorithm has higher execution efficiency and stronger convergence in the construction of gene regulatory network algorithm.

关 键 词：AP算法 数据源融合 基因调控网络 全基因组关联 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]