SVM BASED RECOGNITION OF TRANSLATION INITIATION SITES IN EUKARYOTIC DNA
基于支持向量机识别真核生物DNA中的翻译起始位点

As one of crucial steps of gene prediction, an intensive attention was paid to the recognition of translation initiation site (TIS) in recent years. On the basis of the statistical feature of sequences around TIS, some methods have been applied to identify TIS. However, their prediction accuracy remains to be improved. Considering the deficiency of traditional SVM, data optimization based SVM is presented. Its scheme is to improve the prediction accuracy of classifier by optimizing the training dataset with other statistical model. Experiment results show that data optimization based SVM is better than other methods.