关键词: 基因调控网络, 直接相关, 间接相关, 皮尔逊相关系数, 斯皮尔曼等级相关系数, 互信息

Abstract:

In order to build gene regulatory network, we proposed an algorithm based on gene expression levels and network anti-delivery. The algorithm used the network anti-delivery idea to analyze indirect effect produced from the traditional correlated calculation methods, and added an norm penalty term for controlling network sparsity after considering the sparsity of regulatory networks. We use the algorithm on the E. coli experimental data. This method improves the edge predictive ability of the correlation analysis on the regulatory network, Pearson correlation coefficient increased by 6.42%, Spearman correlation coefficient increased by 5.92%, mutual information improves 9.35%. Overall, this model provides a new idea on modifying a large number of system-related data, and can be applied to network edge prediction and the control dynamics of biological network inference.

Key words: Gene regulatory networks, Direct correlation, Indirect correlation, Pearson correlation, Spearman rank correlation, Mutual information