Construction of gene regulatory network with multiple time unit lag based on combination of multiple sources of biological data

doi:10.7523/j.issn.2095-6134.2012.2.015

Abstract

Abstract:

We propose a new method (LC-DBN) of gene regulatory network (GRN) construction based on the theory of dynamic Bayesian network. In the process of GRN construction, we learn optimal regulation time unit lag for each gene and combine gene expression data with transcription factor binding location data. The construction experiments on GRN of 25 Saccharomyces Cerevisiae cell cycle data was carried out, and the results indicate that the new method enhances sensitivity by 0.72% and accuracy by 0.16% compared to Tan’s method.

Key words: gene regulation networks, multiple time unit lag, combining multiple sources of biological data, dynamic Bayesian

CLC Number:

TP391.4

YUAN Yi-Tao, SUN Ying-Fei. Construction of gene regulatory network with multiple time unit lag based on combination of multiple sources of biological data[J]. , 2012, (2): 246-250.

References

[1] Friedman N, Linial M, Nachman I, et al. Using Bayesian network to analyze expression data[J]. Journal of Computational Biology, 2000, 7: 601-620.
[2] Murphy K, Mian S. Modelling gene expression data using dynamic Bayesian networks: Technical Report. Berkeley: Computer Science Division, University of California, 1999.
[3] Zou M, Conzen S D. A new dynamic Bayesian network (DBN) approach for identifying gene regulatory networks from time Course microarray data[J]. Bioinformatics, 2005, 21(1): 71-79.
[4] Albert I, Albert R. Conserved network motifs allow protein——protein interaction prediction[J]. Bioinformatics, 2004, 20: 3346-3352.
[5] Butte A J, Kohane I S. Mutual information relevance networks: functional genomic clustering using pairwise entropy measurements[J]. Pacific Symposium on Biocomputing, 2000, 5: 415-426.
[6] Hartemink A J, Gifford D K, Jaakkola T S, et al. Combing location and expression data for principled discovery of genetic regulatory network models //Proc Pacific Symposium on Biocomputing. Kauai, World Scientific Press, 2002: 437-449.
[7] Heckerman D, Geiger D, Chichering D. Learning Bayesian networks: the combination of knowledge and statistical data[J]. Machine Learning, 1995, 20(3):197-243.
[8] Segal E, Barash Y, Simon I, et al. From promoter sequence to expression: a probabilistic framework //Proceedings of the Sixth Annual International Conference on Computational Biology. 2002: 263-272.
[9] Spellman P T, Sherlock G, Zhang M Q, et al. Comprehensive identification of cell cycle regulated genes of the yeast saccharomyces cerevisiae by microarray hybridization[J]. Molecular Biology of the Cell, 1998, 9:3273-3297.
[10] Chaitankar V, Ghosh P, Perkins E J, et al. Time lagged information theoretic approaches to the reverse engineering of gene regulatory networks[J]. Bioinformatics, 2010, 11(Suppl 6): S19.
[11] Bernard A, Hartemink A J. Informative structure priors: Joint learning of dynamic regulatory networks from multiple types of data //Pacific Symposium on Bio-computing, 2005(PSB05). 2005:459-470.
[12] Lee T, Rinaldi N J, Robert F, et al. Transcriptional regulatory networks in Saccharomyces Cerevisiae[J]. Science, 2002, 298:799-804.
[13] Arnone A, Davidson B. The hardwiring of development: organization and function of genomic regulatory systems[J]. Development, 1997, 124: 1851-1864.
[14] Cooper G F, Herskovits E. A Bayesian method for the induction of probabilistic networks from data[J]. Machine Learning, 1992, 9:309-347.
[15] Cherry J M. Saccharomyces genome database. Leland Stanford Junior University.(2007-09-15). http://www.yeastgenome.org.
[16] Tan M, AlShalalfa M, Alhajj R, et al. Combining multiple types of biological data in constraint-based learning of gene regulatory networks //Computational Intelligence in Bioinformatics and Computational Biology. Sun Valley Idaho, USA, 2008.