一种基于树的蛋白质功能预测算法:KDE–CSSA  

KDE–CSSA, a tree structure based algorithm for the prediction of protein function

作　　者：陈义明[1] 贺细平[1] 乔波[1] 

机构地区：[1]湖南农业大学信息科学技术学院,湖南长沙410128

出　　处：《湖南农业大学学报（自然科学版）》2015年第1期62-66,共5页Journal of Hunan Agricultural University(Natural Sciences)

基　　金：湖南省教育厅项目(11C0653)

摘　　要：针对在每个标签类上直接学习分类模型计算代价高和树层次中低层结点训练数据扭曲的问题,提出了一种基于树层次的蛋白质功能预测算法:核依赖估计–压缩排序选择算法(KDE–CSSA)。该算法先将标签向量投影到标签核的主成分上,仅仅学习少量的回归模型,然后将预测的数值向量投影回原来标签向量空间,利用压缩排序和选择算法获取满足树属性的0,1标签向量。在12个基因组数据集上使用精确率和召回率作为评测标准的实验结果表明,KDE–CSSA算法性能优于目前优秀的CLUS–HMC算法。KDE-CSSD, an tree structure algorithm was proposed for the prediction of protein fimction based on class hierarchy to solve the issues of high computational cost on label classes through direct learning classification model and of train data skew on class hierarchy among middle or lower level nodes. The algorithm firstly projected label vector onto principle components of label kernel by means of learning less regression models, then, the predicted numeric vector were back projected onto their original vector space, finally, the predicted 0 or 1 label vector meeting tree hierarchy constraint were obtained using compressed sort and selection algorithm. The experiments, adopted precise rate and recall rate as criterion on 12 genomic benchmark data sets, proved that the KDE-CSSA algorithm outperformed the outstanding CLUS-HMC algorithm.

关 键 词：蛋白质 功能预测 主成分分析 核依赖估计 压缩排序与选择算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]