Transcription factor site dependencies in human, mouse and rat genomes

Abstract

Background: It is known that transcription factors frequently act together to regulate gene expression in eukaryotes. In this paper we describe a computational analysis of transcription factor site dependencies in human, mouse and rat genomes.

Results: Our approach for quantifying tendencies of transcription factor binding sites to co-occur is based on a binding site scoring function which incorporates dependencies between positions, the use of information about the structural class of each transcription factor (major/minor groove binder), and also considered the possible implications of varying GC content of the sequences. Significant tendencies (dependencies) have been detected by non-parametric statistical methodology (permutation tests). Evaluation of obtained results has been performed in several ways: reports from literature (many of the significant dependencies between transcription factors have previously been confirmed experimentally); dependencies between transcription factors are not biased due to similarities in their DNA-binding sites; the number of dependent transcription factors that belong to the same functional and structural class is significantly higher than would be expected by chance; supporting evidence from GO clustering of targeting genes. Based on dependencies between two transcription factor binding sites (second-order dependencies), it is possible to construct higher-order dependencies (networks). Moreover results about transcription factor binding sites dependencies can be used for prediction of groups of dependent transcription factors on a given promoter sequence. Our results, as well as a scanning tool for predicting groups of dependent transcription factors binding sites are available on the Internet.

Conclusion: We show that the computational analysis of transcription factor site dependencies is a valuable complement to experimental approaches for discovering transcription regulatory interactions and networks. Scanning promoter sequences with dependent groups of transcription factor binding sites improve the quality of transcription factor predictions.

Figure 1

Distributions according to the structural and functional classification. Expected (random) and observed distributions of dependent pairs of TFs which belong to the same structural/functional class (* p < 0.05, Chi-square test; Expected distribution gives the numbers of dependent pairs of transcription factors which belong to the same structural/functional class that one would expect to obtain if there is no difference between proportions of dependent pairs that contain transcription factors from the same and different structural/functional classes).

Figure 2

Venn diagrams of the number of dependent transcription factor binding sites pairs in human, mouse and rat genome. Venn diagrams show the number of total predicted dependent pairs, the number of predicted dependent pairs conserved in two or three species, the number of predicted dependent pairs supported by GO, and the number of predicted dependent pairs supported by overlapped supporting evidence.