PREDICTING VIRUS PROTEIN SUBCELLULAR LOCATIONS WITH MULTI-LABEL K NEAREST NEIGHBOUR CLASSIFIER
Information of the subcellular localization of viral proteins in a host cell or virus-infected cell is very important mainly because it is closely related to their destructive tendencies and consequences. Among the existing computational methods, however, very few ones were specially developed for virus proteins. In this paper, we have developed a new predictor, called Virus-MLKNN, which can be used to deal with the systems containing both singleplex and multiplex proteins through introducing the popular multi-label k nearest neighbour classifier and combining the gene ontology information and sequential evolution information. It can be used to identify viral proteins among the following six locations: (1) viral capsid, (2) host cell membrane, (3) host endoplasmic reticulum, (4) host cytoplasm, (5) host nucleus, and (6) secreted. It is expected that Virus-MLKNN may become a very useful high throughout vehicle for both basic research and drug development.
virus protein subcellular locations multi-label KNN
R.Wang X.Wang S.Xu
College of Information Engineering, Yancheng Institute of Technology, Yancheng 224051, China Department of Control Science and Engineering, Tongji University, Shanghai 201804, China
国际会议
2012 International Conference on System Simulation(2012年国际系统仿真学术会议)
上海
英文
415-418
2012-04-06（万方平台首次上网日期，不代表论文的发表时间）