• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Iranian Conference on Biomedical Engineering >An Information Gain Approach to Infer Gene Regulatory Networks
【24h】

An Information Gain Approach to Infer Gene Regulatory Networks

机译：推断基因监管网络的信息增益方法

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The inference of a Gene Regulatory Network (GRN) using gene expression data is a major research topic in bioinformatics. Modeling GRNs is significantly important in order to understand gene dependencies, regulatory functions among genes, biological processes, way of process occurrence and avoiding some unplanned processes (disease). Due to the huge number of genes and the small number of samples, reliable inference of GRNs is still a vital challenge and providing efficient inference algorithms is a serious demand. In this paper, a rigorous framework for addressing GRNs inference is introduced. We propose a novel method for GRNs inference using feature selection approach based on information theory (information gain). In addition, by imposing a constraint on the information gain scores, the numbers of false inferred edges have been reduced, dramatically. The experimental results using biological data reveal that in spite of small number of samples and large number of genes, this method has found the gene interactions efficiently. Furthermore, the outcomes demonstrate that the proposed method achieves a comparable accuracy rate to the some state-of-the-art algorithms. Moreover, the sensitivity rate of the proposed method with respect to the other methods is increased 35% (in average).
机译：使用基因表达数据的基因调节网络（GRN）的推断是生物信息学中的主要研究课题。建模GRNS显着重要，以便了解基因依赖性，基因，生物过程，过程发生方式的监管功能，以及避免一些未约会的过程（疾病）。由于基因数量和少量样品，GRNS的可靠推动仍然是一个重要的挑战，提供有效的推理算法是一个严重的需求。本文介绍了用于寻址GRNS推理的严格框架。我们提出了一种基于信息理论（信息增益）的特征选择方法的GRNS推断的新方法。另外，通过对信息增益分数强加约束，众所周知，虚假推断边的数量已经减少。使用生物数据的实验结果表明，尽管有少量的样品和大量基因，但这种方法发现基因的相互作用有效。此外，结果表明，所提出的方法对某些最先进的算法实现了可比的准确率。此外，所提出的方法关于其他方法的灵敏度率增加了35％（平均）。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号