{"title":"预测蛋白质亚细胞定位的杂交系统","authors":"Shu-Bo Zhang, J. Lai","doi":"10.1109/BMEI.2009.5305500","DOIUrl":null,"url":null,"abstract":"Protein subcellular localization prediction is important to functional annotation of protein. In this study, a hybrid system based on the sorting mechanism of protein was proposed to predict protein subcellular localization. At first, an unknown protein sequence was divided into two sub-sequences at certain position, then features were extracted from them and combined into a fusion feature vector to describe the whole protein sequence. Secondly, an optimal sub-classifier was searched out to discriminate each kind of protein from the others through iterative searching strategy. Finally, all of the sub-classifiers were combined into a hybrid system to predict subcellular localization of unknown protein. Experimental results on two public datasets showed that our hybrid system is an effective way for the prediction of protein subcellular localization, and it has higher accuracy than others.","PeriodicalId":6389,"journal":{"name":"2009 2nd International Conference on Biomedical Engineering and Informatics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2009-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Hybrid System for Prediction of Protein Subcellular Localization\",\"authors\":\"Shu-Bo Zhang, J. Lai\",\"doi\":\"10.1109/BMEI.2009.5305500\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Protein subcellular localization prediction is important to functional annotation of protein. In this study, a hybrid system based on the sorting mechanism of protein was proposed to predict protein subcellular localization. At first, an unknown protein sequence was divided into two sub-sequences at certain position, then features were extracted from them and combined into a fusion feature vector to describe the whole protein sequence. Secondly, an optimal sub-classifier was searched out to discriminate each kind of protein from the others through iterative searching strategy. Finally, all of the sub-classifiers were combined into a hybrid system to predict subcellular localization of unknown protein. Experimental results on two public datasets showed that our hybrid system is an effective way for the prediction of protein subcellular localization, and it has higher accuracy than others.\",\"PeriodicalId\":6389,\"journal\":{\"name\":\"2009 2nd International Conference on Biomedical Engineering and Informatics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2009-10-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2009 2nd International Conference on Biomedical Engineering and Informatics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/BMEI.2009.5305500\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2009 2nd International Conference on Biomedical Engineering and Informatics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/BMEI.2009.5305500","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A Hybrid System for Prediction of Protein Subcellular Localization
Protein subcellular localization prediction is important to functional annotation of protein. In this study, a hybrid system based on the sorting mechanism of protein was proposed to predict protein subcellular localization. At first, an unknown protein sequence was divided into two sub-sequences at certain position, then features were extracted from them and combined into a fusion feature vector to describe the whole protein sequence. Secondly, an optimal sub-classifier was searched out to discriminate each kind of protein from the others through iterative searching strategy. Finally, all of the sub-classifiers were combined into a hybrid system to predict subcellular localization of unknown protein. Experimental results on two public datasets showed that our hybrid system is an effective way for the prediction of protein subcellular localization, and it has higher accuracy than others.