| 集成改进KNN算法预测蛋白质亚细胞定位 |
| |
| 引用本文： | 薛卫,王雄飞,赵南,杨荣丽,洪晓宇.集成改进KNN算法预测蛋白质亚细胞定位[J].生物工程学报,2017,33(4):683-691. |
| |
| 作者姓名： | 薛卫 王雄飞 赵南 杨荣丽 洪晓宇 |
| |
| 作者单位： | 南京农业大学 信息科学技术学院，江苏 南京 210095,南京农业大学 信息科学技术学院，江苏 南京 210095,南京农业大学 信息科学技术学院，江苏 南京 210095,南京农业大学 信息科学技术学院，江苏 南京 210095,南京农业大学 信息科学技术学院，江苏 南京 210095 |
| |
| 基金项目： | 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。
|
| 关 键 词： | 亚细胞区间，蛋白序列特征，K-nearest neighbor，basic local alignment search tool，Adaboost |
| 收稿时间： | 2016/10/18 0:00:00 |
Prediction of protein subcellular locations by ensemble of improved K-nearest neighbor |
| |
| Wei Xue,Xiongfei Wang,Nan Zhao,Rongli Yang and Xiaoyu Hong.Prediction of protein subcellular locations by ensemble of improved K-nearest neighbor[J].Chinese Journal of Biotechnology,2017,33(4):683-691. |
| |
| Authors: | Wei Xue Xiongfei Wang Nan Zhao Rongli Yang and Xiaoyu Hong |
| |
| Institution: | School of Information Science and Technology, Nanjing Agricultural University, Nanjing 210095, Jiangsu, China,School of Information Science and Technology, Nanjing Agricultural University, Nanjing 210095, Jiangsu, China,School of Information Science and Technology, Nanjing Agricultural University, Nanjing 210095, Jiangsu, China,School of Information Science and Technology, Nanjing Agricultural University, Nanjing 210095, Jiangsu, China and School of Information Science and Technology, Nanjing Agricultural University, Nanjing 210095, Jiangsu, China |
| |
| Abstract: | 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, two 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. |
| |
| Keywords: | subcellular locations protein sequence characteristics K-nearest neighbor Basic local alignment search tool (Blast) Adaboost |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《生物工程学报》浏览原始摘要信息 |
| 点击此处可从《生物工程学报》下载免费的PDF全文 |
|
