集成改进KNN算法预测蛋白质亚细胞定位  

Prediction of protein subcellular locations by ensemble of improved K-nearest neighbor

作　　者：薛卫[1] 王雄飞[1] 赵南[1] 杨荣丽[1] 洪晓宇[1] Wei Xue Xiongfei Wang Nan Zhao Rongli Yang and Xiaoyu Hong(School of Information Science and Technology, Nanjing Agricultural University, Nanjing 210095, Jiangsu, China)

机构地区：[1]南京农业大学信息科学技术学院,江苏南京210095

出　　处：《生物工程学报》2017年第4期683-691,共9页Chinese Journal of Biotechnology

基　　金：中央高校基本科研业务费专项资金(No.KYZ201668);江苏省自然科学基金(No.BK2012363);国家科技支撑计划(No.2015BAK36B05)资助~~

摘　　要：基于Adaboost算法对多个相似性比对K最近邻(K-nearest neighbor,KNN)分类器集成实现蛋白质的亚细胞定位预测。相似性比对KNN算法分别以氨基酸组成、二肽、伪氨基酸组成为蛋白序列特征,在KNN的决策阶段使用Blast比对决定蛋白质的亚细胞定位。在Jackknife检验下,Adaboost集成分类算法提取3种蛋白序列特征,3种特征在数据集CH317和Gram1253的最高预测成功率分别为92.4%和93.1%。结果表明Adaboost集成改进KNN分类预测方法是一种有效的蛋白质亚细胞定位预测方法。Adaboost algorithm with improved K-nearest neighbor classifiers is proposed to predict protein subcellular locations. Improved K-nearest neighbor classifier uses three sequence feature vectors including amino acid composition, dipeptide and pseudo amino acid composition of protein sequence. K-nearest neighbor uses Blast in classification stage. The overall success rates by the jackknife test on two data sets of CH317 and Gram1253 are 92.4% and 93.1%. Adaboost algorithm with the novel K-nearest neighbor improved by Blast is an effective method for predicting subcellular locations of proteins.

关 键 词：亚细胞区间 蛋白序列特征 K-nearest NEIGHBOR basic local ALIGNMENT search tool ADABOOST 

分 类 号：Q51[生物学—生物化学]