基于集成特征选择策略的基因共表达模式识别

为有效识别内含子 miRNA 及其宿主基因共表达模式, 提出了一种基于集成特征选择的识别方法。 首先 使用基于支持度的集成特征选择算法, 获取相关性和稳定性较高的特征子集, 再使用封装式特征选择方法结合 FCBF(Fast Correlation-Based Filter)搜索策略进一步去除冗余特征和弱相关的特征, 获得最优的特征子集。 实验 结果表明, 该方法融合了多个特征选择方法的优点, 能提高学习模型的泛化能力并能有效识别内含子 miRNA 及其宿主基因的共表达模式。

Ensemble Feature Selection for Recognizing Co-Expression Patterns of Genes

A new method based on ensemble features selection technique is proposed to recognize the co-expression patterns of the intronic miRNAs with their host genes.The Support-based Ensemble Feature Selection algorithm is used to obtain a subset of features with high correlation and stability,and then through the combination of wrapper and FCBF(Fast Correlation-Based Filter) search to reduce the redundant features and weakly related features to get optimal features.The experimental results show that the proposed method can take advantage of the benefits of multiple feature selection methods and effectively recognize the co-expression patterns of the intronic miRNAs with their host genes.