Comparison of software packages for Bayesian network learning in gene regulatory relationship mining
Yu Kang, Xuan Yang, Menghai Sun, Junfan Hu, Zhiman Zhong, Jianxiao Liu · 2017
Gene regulatory has rapidly become a popular approach to understand the complex regulatory mechanisms in cellular systems. Mining gene regulatory relationship and thus to construct the gene regulatory network of utmost interest and has become a challenging computational problem. In order to realize this aim, a large number of tools and packages have been developed. But there is no clear consensus about which tool is the best practices for users' specific requirements, especially, when a user has no background. Aim to solve this problem, we compare 9 kinds of widely used software packages about Bayesian network learning in gene regulatory relationship mining. Our experiment results demonstrate different packages have different learning efficiency and accuracy, and it can provide general guidelines for choosing a robust selection.