论文部分内容阅读
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.
In order to obtain the correct node order and improve the execution efficiency and accuracy of K2 algorithm, an IE-K2 algorithm for constructing gene regulation network is proposed. An undirected graph is constructed based on mutual information of two nodes, and the best information is obtained by introducing joint information entropy . The experimental results in the Alarm network show that the accuracy of the prediction is better than that of the hill-climbing algorithm and the random node sequence. The IE-K2 algorithm is used to construct the gene regulatory network of Saccharomyces cerevisiae. The correctness of the relationship between regulation and control, the results show the effectiveness of the algorithm.