偏置判别SVM预测microRNA靶基因

Prediction of microRNA target genes based on biased discriminant SVM

针对靶基因样本数据不平衡导致阳性样本预测准确率较低的问题,提出基于SVM的靶基因预测算法,即偏置判别SVM。算法选取高质量的数据集和最优特征集作为输入,在经验特征空间中以偏置判别分析准则为核优化目标函数,使用核保角变换的方法逐步优化核矩阵,用最优核矩阵构造偏置判别SVM,以解决靶基因数据不平衡对预测造成的影响。对比实验分析表明,提出的偏置判别SVM算法具有更高的特异度、敏感度和预测精度。同时,偏置判别SVM具有更强的泛化能力,鲁棒性更好。

For the data imbalance problem of miRNA target, a target prediction algorithm, Biased Discriminant Support Vector Machine, is proposed to solve the lower prediction accuracy ofpositive samples. The high-quality data sets and the optimal feature set are selected as the input data. Biased discriminate analysis criteria is selected as the kernel optimize objective function in the empirical feature space, and the conformal transformation of a kernel is adopted to gradually optimize the kernel matrix. Then, the SVM classifier with the optimal kernel matrix is constructed to solve the problem for the prediction causing by imbalance data. Through comparison with the analysis of the experimental results, the biased discriminant support vector machine method shows higher specificity, sensitivity and prediction accuracy, which proves that it has stronger generalization ability and better robustness.