Putative cold acclimation pathways in Arabidopsis thaliana identified by a combined analysis of mRNA co-expression patterns, promoter motifs and transcription factors

Abstract

Background: With the advent of microarray technology, it has become feasible to identify virtually all genes in an organism that are induced by developmental or environmental changes. However, relying solely on gene expression data may be of limited value if the aim is to infer the underlying genetic networks. Development of computational methods to combine microarray data with other information sources is therefore necessary. Here we describe one such method.

Results: By means of our method, previously published Arabidopsis microarray data from cold acclimated plants at six different time points, promoter motif sequence data extracted from approximately 24,000 Arabidopsis promoters and known transcription factor binding sites were combined to construct a putative genetic regulatory interaction network. The inferred network includes both previously characterised and hitherto un-described regulatory interactions between transcription factor (TF) genes and genes that encode other TFs or other proteins. Part of the obtained transcription factor regulatory network is presented here. More detailed information is available in the additional files.

Conclusion: The rule-based method described here can be used to infer genetic networks by combining data from microarrays, promoter sequences and known promoter binding sites. This method should in principle be applicable to any biological system. We tested the method on the cold acclimation process in Arabidopsis and could identify a more complex putative genetic regulatory network than previously described. However, it should be noted that information on specific binding sites for individual TFs were in most cases not available. Thus, gene targets for the entire TF gene families were predicted. In addition, the networks were built solely by a bioinformatics approach and experimental verifications will be necessary for their final validation. On the other hand, since our method highlights putative novel interactions, more directed experiments could now be performed.

Figure 1

Part of the predicted regulatory network. Regulatory network at the gene family level. The origin of the arrow indicates the regulating TF family and the endpoint of the arrow indicates the target gene. The time scale is shown on the vertical axis.

Figure 2

Large scale regulatory network. Overview of the regulatory network. 2a. Up-regulated gene network. 2b. Down-regulated gene network. The entries in red ovals represent the TFs and the black dots represent target genes. The networks were generated using Graphviz version 1.13–16 [65].

Figure 3

Regulation pattern in up-regulated and down-regulated genes. Percentage of up-regulated and down-regulated genes that are predicted to be regulated by different TF families.