一种用于蛋白质检索的运用混合谱特征的形状描述符  

A shape descriptor using hybrid spectral features for protein shape retrieval

作　　者：彭玉旭[1,2] 张广平 夏卓群[1,2] PENG Yu-xu;ZHANG Guang-ping;XIA Zhuo-qun(Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation, Changsha University of Science and Technology, Changsha 410114,China;School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha 410114,China)

机构地区：[1]长沙理工大学综合交通运输大数据智能处理省重点实验室,湖南长沙410114 [2]长沙理工大学计算机与通信工程学院,湖南长沙410114

出　　处：《长沙理工大学学报（自然科学版）》2019年第3期84-89,共6页Journal of Changsha University of Science and Technology:Natural Science

基　　金：湖南省自然科学基金资助项目(2019JJ40314);长沙理工大学青年教师成长计划项目(2019QJCZ014)

摘　　要：蛋白质的不同构像及结构变化使得传统的形状描述算法在蛋白质数据集上的检索效果并不理想。为了提高检索性能,提出了一种新的基于混合谱特征的蛋白质形状描述符及蛋白质检索框架,该方法结合了Wave Kernel Signature和Heat Kernel Signature产生新的Bag of Feature,即WKS_HKS算法。对WKS_HKS算法和现有的几种形状描述算法在三个不同类型的分子数据集上进行了综合比较。实验结果表明,该算法比单一的算法的检索效果更好,并优于几种对比的形状描述算法。Because of the different structure and structural changes of proteins, the traditional shape descriptor algorithm is not ideal for the retrieval of protein data sets. In order to improve the retrieval performance, a new protein shape descriptor and protein retrieval framework based on mixed spectrum features were proposed. The shape descritor was made by combining Bag of Feature of Wave Kernel Signature and Heat Kernel Signature, namely WKS_HKS algorithm.The WKS_HKS algorithm and several existing shape descriptor algorithms were compared comprehensively on three different types of molecular data sets.Experimental results show that this algorithm is better than a single algorithm, and better than several comparative shape descriptor algorithms.

关 键 词：形状描述 波核签名 热核签名 混合谱签名 蛋白质检索 BAG of FEATURE 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]