基于SVM-RFE的水稻抗病基因筛选

Disease Resistance Related Gene Screening in Oryza sativa Using SVM-RFE

提出一种改进的回归特征消去支持向量机特征选择方法(SVM-RFE)对水稻的抗病基因进行筛选.实验结果表明:在预测得到的20个与水稻抗病/敏感相关基因中,有3个基因与已知的水稻抗病基因紧密相关;2个基因与已知的水稻抗病基因有一定的相关性.通过该方法能找到影响水稻生长状态(正常/染病)的基因.

An improved support vector machine recursive feature extraction （SVM-RFE） algorithm was used to screen the disease resistance genes. In the 20 important genes, we found that 3 of them have strong relation to the disease resistance as reported and 2 of them have relation to the stress response. It shows that this method can find out which genes could impact the rice growth status （normal/disease）. It might provide a guide on finding other unknown rice disease resistance/sensibility genes in biology.