基于支持向量机的拟南芥基因表达数据分析(英文)

Gene Expression Analysis with Support Vector Machines in Arabidopsis

针对拟南芥根部基因表达数据分析的问题,本文提出了一种新的基于距离度量学习的支持向机多分类算法．鉴于此问题的特殊性,本文通过最小化4分类机的LOO 误差来求得一个恰当的距离度量．并在此度量下找到若干个属于第5类(其它类)的训练点,从而构造出一个5分类机用来对所有基因分类．实验验证了此算法的可行性,并且比基因表达分析中传统使用的聚类方法更有效．

For the problem of Arabidopsis root gene expression analysis, this paper presents a new algorithm of multi-class Support Vector Machines （SVMs） , which is based on learned distance measure. Because of speciality of this problem, a distance measure is learned by minimizing Leave-one-out （LOO） error of 4-class SVMs, and some genes belong to other classes are determined, then 5-class SVMs is constructed to classify the total genes. Experiments prove the effective of our method compared with traditional clustering methods.