CTCF介导的拓扑关联结构域边界的预测

Predictions of the CTCF-Mediated Topological Association of the Domain Boundary

转录因子的结合能够影响拓扑关联结构域(TAD)结构,进而限制了调控元件间的相互作用。以GM12878细胞系为研究对象,构建了转录因子CTCF介导的TAD边界和非边界数据集。然后,利用CTCF结合峰强度、模体打分、物种保守性、CTCF结合方向性和CTCF结合密度这五类特征,计算得到了边界和非边界集合的特征矩阵。最后,应用支持向量机(SVM)算法预测了TAD边界。结果表明,CTCF结合峰强度和模体打分具有较好的预测能力,其预测敏感性和特异性指标均高于0.9。

The binding of transcription factors can affect the structure of topological association domain,and further constrict the interaction between the regulatory elements.The dataset of TAD boundary and non-boundary regions mediated the by GM12878 cell line is constructed by the transcription factor CTCF.Then,the feature matrixes on boundary and non-boundary regions are collected with respect to five types of characteristics:peak strength of CTCF binding,motif score,species conservation score,directionality of CTCF binding and density of CTCF binding.Finally,the TAD boundary regions are identified by the support vector machine(SVM)algorithm from nonboundary regions.The results show that the peak strength of CTCF binding and motif score have good predictive power,and its sensitivity and specificity are both higher than O.9.