IE_K2：一种基于贝叶斯网络的高效基因调控网络构建方法

为获得正确的节点次序,提高K2算法的执行效率和精确度,提出一种构建基因调控网络的IE-K2算法.基于两个节点互信息构建无向图,通过引入联合信息熵来获得最佳的节点次序.在Alarm网络中的实验结果表明,其预测的准确率优于爬山算法和随机节点顺序的K2算法;将IE-K2算法用于构建酿酒酵母的基因调控网络,通过现有文献证明了调控关系的正确性,结果显示了该算法的有效性.

IE_K2:An effective Bayesian method for constructing gene regulatory network

IE-K2 algorithm which constructs gene regulatory network was proposed to obtain correct execution order of nodes and to improve the execution efficiency and precision.The nondirected network was constructed based on mutual information,and the best order of nodes was obtained by introducing union information entropy.Tests on alarm network show that the proposed algorithm is superior to hill climbing algorithm and the random-ordered K2 algorithm in respect of precision accuracy.IE-K2 algorithm is also applied to construct the gene regulatory network for yeast cycle gene expression data.The effectiveness of the proposed algorithm is illustrated by verifying a part of the inferred regulations through existing literatures.