Prediction accuracies using ten times 10-fold cross validation with different gene subsets.

SVM, support vector machine; RF, random forest; KNN, K-nearest neighbour, DLDA, diagonal linear discriminant analysis; SAM, significance analysis of microarrays; FDR, false discovery rate. Values represent mean��standard deviation corresponding to the 95% confidence interval.SVM：支持向量机（support vector machine）；RF：随机森林（random forest）；KNN：K近邻（K-nearest neighbour）；DLDA：对角线性判别分析（diagonal linear discriminant analysis）；SAM：微阵列显著性分析（significance analysis of microarrays）；FDR：错误发现率（false discovery rate）。数值代表对应95%置信区间的均值±标准差。