Detecting reliable gene interactions by a hierarchy of Bayesian network classifiers
- PMID: 18433926
- DOI: 10.1016/j.cmpb.2008.02.010
Detecting reliable gene interactions by a hierarchy of Bayesian network classifiers
Abstract
The main purpose of a gene interaction network is to map the relationships of the genes that are out of sight when a genomic study is tackled. DNA microarrays allow the measure of gene expression of thousands of genes at the same time. These data constitute the numeric seed for the induction of the gene networks. In this paper, we propose a new approach to build gene networks by means of Bayesian classifiers, variable selection and bootstrap resampling. The interactions induced by the Bayesian classifiers are based both on the expression levels and on the phenotype information of the supervised variable. Feature selection and bootstrap resampling add reliability and robustness to the overall process removing the false positive findings. The consensus among all the induced models produces a hierarchy of dependences and, thus, of variables. Biologists can define the depth level of the model hierarchy so the set of interactions and genes involved can vary from a sparse to a dense set. Experimental results show how these networks perform well on classification tasks. The biological validation matches previous biological findings and opens new hypothesis for future studies.
Similar articles
-
Bayesian modelling of shared gene function.Bioinformatics. 2007 Aug 1;23(15):1936-44. doi: 10.1093/bioinformatics/btm280. Epub 2007 May 31. Bioinformatics. 2007. PMID: 17540682
-
Advances to Bayesian network inference for generating causal networks from observational biological data.Bioinformatics. 2004 Dec 12;20(18):3594-603. doi: 10.1093/bioinformatics/bth448. Epub 2004 Jul 29. Bioinformatics. 2004. PMID: 15284094
-
A control study to evaluate a computer-based microarray experiment design recommendation system for gene-regulation pathways discovery.J Biomed Inform. 2006 Apr;39(2):126-46. doi: 10.1016/j.jbi.2005.05.011. Epub 2005 Sep 19. J Biomed Inform. 2006. PMID: 16203178
-
Bayesian methods in bioinformatics and computational systems biology.Brief Bioinform. 2007 Mar;8(2):109-16. doi: 10.1093/bib/bbm007. Epub 2007 Apr 12. Brief Bioinform. 2007. PMID: 17430978 Review.
-
Towards knowledge-based gene expression data mining.J Biomed Inform. 2007 Dec;40(6):787-802. doi: 10.1016/j.jbi.2007.06.005. Epub 2007 Jun 21. J Biomed Inform. 2007. PMID: 17683991 Review.
Cited by
-
Applications of Bayesian network models in predicting types of hematological malignancies.Sci Rep. 2018 May 3;8(1):6951. doi: 10.1038/s41598-018-24758-5. Sci Rep. 2018. PMID: 29725024 Free PMC article.
-
In Silico Gene Regulatory Network of the Maurer's Cleft Pathway in Plasmodium falciparum.Evol Bioinform Online. 2015 Oct 22;11:231-8. doi: 10.4137/EBO.S25585. eCollection 2015. Evol Bioinform Online. 2015. PMID: 26526876 Free PMC article. No abstract available.
-
Stable feature selection and classification algorithms for multiclass microarray data.Biol Direct. 2012 Oct 2;7:33. doi: 10.1186/1745-6150-7-33. Biol Direct. 2012. PMID: 23031190 Free PMC article.
-
Identification of a biomarker panel for colorectal cancer diagnosis.BMC Cancer. 2012 Jan 26;12:43. doi: 10.1186/1471-2407-12-43. BMC Cancer. 2012. PMID: 22280244 Free PMC article.
-
A Bayesian network approach for modeling local failure in lung cancer.Phys Med Biol. 2011 Mar 21;56(6):1635-51. doi: 10.1088/0031-9155/56/6/008. Epub 2011 Feb 18. Phys Med Biol. 2011. PMID: 21335651 Free PMC article.
Publication types
MeSH terms
Substances
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical
