文章基本信息

标题：Artificial Data Generation Scheme Based on Network Alignment for Evaluation Considering Structural Diversity
本地全文：下载
作者：Hitoshi AFUSO ; Takeo OKAZAKI ; Morikazu NAKAMURA 等
期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2012
卷号：12
期号：11
页码：59-63
出版社：International Journal of Computer Science and Network Security
摘要：Estimation of transcriptional regulatory networks (TRNs) is the one of most challenging area in post genomic era. While various methods to estimate TRNs, evaluation for such methods, based on generation of artificial TRNs and corresponding artificial gene expression profile data, has been received attentions. However, traditional artificial data generation method does not confirm the structural diversity of generated TRNs. Then, The results of evaluation for estimation methods may be biased. On the other hand, to extract the equivalent subnetwork between two different networks, network alignment methods have been proposed. In this paper, we proposed the artificial data generation scheme for evaluation of network estimation methods so that one can confirm structural diversity in generated TRNs. And also, as a example for application, we compared four score functions for edge orientation problem that one part of network estimation problem, according to proposed data generation scheme.
关键词：Artificial TRNs generation method; Confirmation of structural diversity; Network alignment