摘要
根据临床研究所得生理学信息和结肠癌基因表达谱数据,对生理学信息在确定基因标签中的作用进行研究。在ReCorre算法的基础上,建立基于后验概率最大准则的基因标签提取模型,利用信息融合方法,将后验概率和Bhattacharyya距离相结合,建立融入临床知识的基因标签提取模型。实验结果证明了临床研究生理学信息在基因标签提取过程中的作用,该模型确定的基因标签进行留一交叉检验正确率可达100%。
For large number of gene expression profiles of the colon tumor,how to use the physiological information obtained in the clinical investigation was researched on during the process that the informative genes were selected in this paper.First,the ReCorre feature selection algorithm was applied,and a primary selection model of informative genes was built up which was based on the maximal criterion of the posterior probability.Then,the posterior probability and the Bhattacharyya distance were fused in the new selection model with the physiological information,so that the new informative genes could be selected.In the end,2000 colon tumor gene expression samples were analyzed and the usage of physiological information turned out to be feasible and effective in the process of getting the best informative genes,which were checked out by the leave-one-out cross validation（LOOCV） method based on the sport vector machine（SVM） later in order to get the best informative genes.
出处
《兵工自动化》
2011年第7期48-51,共4页
Ordnance Industry Automation
关键词
肿瘤
基因表达谱
信息融合
tumor
gene expression profiles
information fusion
