Inferring gene networks from gene expression data using dynamic bayesian network with different scoring metric approaches

Masarrah Abdul Mutalib, Lian En Chai, Chuii Khim Chong, Yee Wen Choon, Safaai Deris, Rosli M. Illias, Mohd Saberi Mohamad

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)


Inferring gene networks can be defined as the process of identifying gene interactions from experimental data through computational analysis. The aim is to infer gene network from gene expression data using dynamic Bayesian network (DBN) with different scoring metric approaches. The previous method, Bayesian network has successfully identified those gene networks but there are some limitations. Hence, DBN is able to infer interactions from a data set consisting time series rather than steady-state data. This research is conducted in order to construct and implement gene network and to analyze the effect by applying a different scoring metric approach for modeling gene network. In order to achieve the goals, a discrete model of DBN is used with different scoring metric approaches which are BDe and MDL. The S. cerevisiae cell cycle pathway is used for this research. To ensure the gene networks are biologically probable, this research employs previous annotation relative to the dataset. By having all of these implementations, this research is able to identify the effect of different scoring metric approaches, identify biologically meaningful gene network within the gene expression datasets and display the results in convenient representations.

Original languageEnglish
Title of host publicationAdvances in Biomedical Infrastructure 2013
Subtitle of host publicationProceedings of International Symposium on Biomedical Data Infrastructure (BDI 2013)
PublisherSpringer Verlag
Number of pages10
ISBN (Print)9783642371363
Publication statusPublished - 2013
Externally publishedYes

Publication series

NameStudies in Computational Intelligence
ISSN (Print)1860-949X


  • Dynamic bayesian network
  • Gene expression data
  • Gene regulatory networks
  • Missing values imputation
  • Network inference

ASJC Scopus subject areas

  • Artificial Intelligence


Dive into the research topics of 'Inferring gene networks from gene expression data using dynamic bayesian network with different scoring metric approaches'. Together they form a unique fingerprint.

Cite this