Computational analysis of tissue-specific combinatorial gene regulation: predicting interaction between transcription factors in human tissues

Abstract

Tissue-specific gene expression is generally regulated by more than a single transcription factor (TF). Multiple TFs work in concert to achieve tissue specificity. In order to explore these complex TF interaction networks, we performed a large-scale analysis of TF interactions for 30 human tissues. We first identified tissue-specific genes for 30 tissues based on gene expression databases. We then evaluated the relationships between TFs using the relative position and co-occurrence of their binding sites in the promoters of tissue-specific genes. The predicted TF-TF interactions were validated by both known protein-protein interactions and co-expression of their target genes. We found that our predictions are enriched in known protein-protein interactions (>80 times that of random expectation). In addition, we found that the target genes show the highest co-expression in the tissue of interest. Our findings demonstrate that non-tissue specific TFs play a large role in regulation of tissue-specific genes. Furthermore, they show that individual TFs can contribute to tissue specificity in different tissues by interacting with distinct TF partners. Lastly, we identified several tissue-specific TF clusters that may play important roles in tissue-specific gene regulation.

Figure 1

Distance distributions between TF binding sites in promoters. (A) shows an example of two TFs without preferential distance between their binding sites in promoters. (It should be noted that here is currently no published data implicating interaction between E2F and FOXJa/b.) The line of y = 1 represents the expected distribution. (B and C) show the distance distributions for two examples with interacting TFs. (D) is an example for tissue-specific interaction. The short distance enrichment is enhanced in muscle specific genes (open squares) compared with that in entire genome (filled diamonds). The gray area in (B) was used to quantify the difference between observed and expected distributions.

Figure 2

Examples of interactions. The x-axis is the tissue types (in the same order as Table 1). Two interactions are found for muscle (A) and eye (B) based on the relationship between the TF binding motifs. The y-axis is the P-values from the prediction. (C–F) show the relative gene expression levels of single TFs in an arbitrary unit.

Figure 3

Evaluation of prediction by protein–protein interactions. (A) Two curves represent the sensitivity and enrichment in function of P-values. (B) P-value distributions for known protein–protein interaction, TF pairs without known interactions, and pairs from permutation simulation. The vertical line indicates the threhold chosen for this study.

Figure 4

Evaluation of prediction by gene expression. (A) The expression coherence (EC) distributions for tissue specific genes and non-tissue specific genes. (B) The EC of the target genes of eye-specific pair CRX and NRL in different tissues. (C) The average EC of the target genes of all eye specific TF pairs in different tissues. (D) For all tissue specific TF pairs, we calculated the co-expression of their target genes using the microarray data set obtained in eye. The eye specific TF pairs have the highest co-expression in eye.

Figure 5

One TF participating in multiple tissue specificity. (A) Both the binding site co-occurrence and target gene co-expression indicate that FOXO4 and PBX1A have eye-specific interaction. (B) FOXO4 and FOXO1A have liver-specific interaction. (C) FOXO4 can participate in regulation of eye- and liver-specific gene expression by interacting with PBX1A or FOXO1A.

Figure 6

Network of predicted TF interactions. (A) The predicted TF interaction network. (B) The most significant interactions with −log(P) > 20. The colors of nodes (TFs) and edges (interactions) indicate different tissue types. If the majority of interactions through one TF are from one tissue type, the node is colored with that tissue type. Otherwise, the node is blank. The size of nodes indicates the numbers of interactions through this TF. The thickness of edges indicates the significance of interactions.