Inferring gene regulatory networks by PCA-CMI using Hill climbing algorithm based on MIT score and SORDER method
Inferring gene regulatory networks by PCA-CMI using Hill climbing algorithm based on MIT score and SORDER method作者机构：Institute for Research in Fundamental Sciences (IPM) Iran Department of Mathematics and Computer ScienceAmirkabir University of Technology Tehran Iran Department of Mathematics Faculty of Mathematical SciencesCentral Tehran Branch Islamic Azad University Tehran Iran Department of Mathematics Faculty of Mathematical Science Shahid Beheshti University Tehran Iran Department of Computer Science Faculty of Mathematical Sciences Shahid Beheshti University Tehran Iran
出 版 物：《International Journal of Biomathematics》 (生物数学学报（英文版）)
年 卷 期：2016年第9卷第3期
页 面：139-156页
核心收录：
学科分类：0710[理学-生物学] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 08[工学] 071009[理学-细胞生物学] 09[农学] 0901[农学-作物学] 090102[农学-作物遗传育种] 081201[工学-计算机系统结构] 0812[工学-计算机科学与技术（可授工学、理学学位）]
基 金：Department of Research Affairs of Azad University
主 题：Inferring gene regulatory networks Bayesian network PC algorithm conditional mutual independent test MIT score.
摘 要：Inferring gene regulatory networks （GRNs） is a challenging task in Bioinformatics. In this paper, an algorithm, PCHMS, is introduced to infer GRNs. This method applies the path consistency （PC） algorithm based on conditional mutual information test （PCA-CMI）. In the PC-based algorithms the separator set is determined to detect the dependency between variables. The PCHMS algorithm attempts to select the set in the smart way. For this purpose, the edges of resulted skeleton are directed based on PC algorithm direction rule and mutual information test （MIT） score. Then the separator set is selected according to the directed network by considering a suitable sequential order of genes. The effectiveness of this method is benchmarked through several networks from the DREAM challenge and the widely used SOS DNA repair network of Escherichia coll. Results show that applying the PCHMS algorithm improves the precision of learning the structure of the GRNs in comparison with current popular approaches.
维普期刊数据库