sRNASVM——基于SVM方法构建大肠杆菌sRNA预测模型

在理解细菌与环境的相互作用方面，细菌sRNA的识别发挥重要作用。文章介绍了一个通过增加训练集中实验证实的sRNA来构建细菌sRNA预测模型的策略，并以大肠杆菌K-12的sRNA预测为例来说明策略的可行性。结果表明，按此策略构建的模型sRNASVM的10倍交叉检验精度达到92.45%，高于目前文献中报道的精度。因此，构建的这一模型将为实验发现sRNA提供较好的生物信息学支持。有关模型和详细结果可以从网站http://ccb.bmi.ac.cn/srnasvm/下载。

sRNASVM: a model for prediction of small non-coding RNAs in E.coli using support vector machines

Identification of bacterial small noncoding RNAs (sRNAs) plays an important role in understanding interactions between bacteria and their environments. Here we introduced a scheme for constructing models for prediction of bacterial sRNAs through incorporating the validated sRNAs into training dataset, and Escherichia coli (E.coli) K-12 was taken as an example to demonstrate the performance of the scheme. The results indicated that the 10-fold cross-validation classification accuracy of the constructed model, sRNASVM, was as high as 92.45%, which had better performance than two existing models. Therefore, the present work provides better support for experimental identification of bacterial sRNAs. The models and detailed results can be downloaded from the webpage http://ccb.bmi.ac.cn/srnasvm/.