An atlas of combinatorial transcriptional regulation in mouse and man

Abstract

Combinatorial interactions among transcription factors are critical to directing tissue-specific gene expression. To build a global atlas of these combinations, we have screened for physical interactions among the majority of human and mouse DNA-binding transcription factors (TFs). The complete networks contain 762 human and 877 mouse interactions. Analysis of the networks reveals that highly connected TFs are broadly expressed across tissues, and that roughly half of the measured interactions are conserved between mouse and human. The data highlight the importance of TF combinations for determining cell fate, and they lead to the identification of a SMAD3/FLI1 complex expressed during development of immunity. The availability of large TF combinatorial networks in both human and mouse will provide many opportunities to study gene regulation, tissue differentiation, and mammalian evolution.

Figure 1. TF expression versus connectivity

(A) Distribution of tissue specificity for all TFs. The green curves fit the bi-modal distribution as a mixture of two Gaussian. (B) Scatterplot of tissue specificity (y-axis) versus number of neighbors (x-axis). Red points are defined as specifier hubs and blue points as facilitator hubs (Supplementary Table 1). (C) TFs are binned into four groups of approximately equal size based on their number of interactions (x-axis). The tissue specificity distribution of each bin is represented by stacks of colored segments. Segment height represents the fraction of TFs in an expression group (left y-axis), and segment color represents the number of tissues in which TFs in that group are expressed. The black line displays the median TSPS of each group (right y-axis). Among TFs with six or more interactions, 70% are expressed in more than half of tissues. Among TFs with fewer than six interactions, this number falls to 45%. The results shown are for human M2H interactions supplemented with TF-TF interactions downloaded from literature (Supplementary Table 2); similar results are obtained for mouse interactions or for M2H interactions only (Supplementary Table 3. See also Supplementary Table 4 for confirmation of the M2H positives using in-vitro pull down assays as a second technology).

Figure 2. A homeobox network associated with tissue differentiation

(A) Performance of tissue separation with (green solid curve) or without (black solid curve) information about TF protein-protein interactions (Supplementary Table 2). The Bezdek cluster validity index (CVI, y-axis) is a measure of separation between the four tissue classes. CVI is plotted for increasing kernel standard deviation (x-axis), the only tuning parameter of the ncKPCA algorithm used for tissue separation. Performance was also evaluated for TF pairs predicted to cooperate based on co-occurrence of TF binding sites (yellow curve) (Yu et al., 2006) as well as for random features (dashed curves). (B) Tissue dimensionality reduction by ncKPCA into the first two Principle Components (PCs), considering features derived from the six most informative TF-TF interactions. Points represent tissues derived from ectoderm (green), mesoderm (yellow), or endoderm (red), or a monocyte cell line (blue). Gray circles denote four clusters obtained by affinity propagation in the (PC1, PC2) space, with each point connected to its cluster exemplar. This figure is related to Figure S1. (C) Informative subnetwork containing six interactions (green) used to generate features for tissue separation. Also shown are the immediate network neighbors of the interacting TFs. (D) CVI for the separation of stem cells (Supplementary Table 6) using Sammon Mapping. Four feature sets are shown: the original expression values from Muller et al, the expression of the TFs only, the entire set of TF protein-protein interactions, or the features corresponding to the six interactions in panel C (5* indicates that the interaction HOXA9-MEIS1 was not considered because HOXA9 expression was not measured in the stem cell investigation of Muller et al). (E) Stem cell dimensionality reduction obtained by Sammon Mapping using the panel C interaction set. Points represent stem cell lines derived from ectoderm (green), mesoderm (yellow), or endoderm (red). (F) Good performance of tissue separation observed with two different algorithms. ncKPCA (green curve) and Sammon Mapping (blue curve). CVI (y-axis) is plotted against the number of PC2-ranked interactions used to separate tissues (x-axis). In both cases, the maximum performance is observed using the first six PC2-ranked interactions to separate tissues.

Figure 3. TF subnetworks conserved across human and mouse

(A–F) Examples of TF subnetworks conserved in specific tissues. Human proteins are circles and mouse proteins are diamonds, colored in increasing shades of red representing increasing tissue specificity (TSPS), (Supplementary Table 1). Stars indicate hubs. Horizontal dashed links indicate protein orthology relationships across species, whereas solid links indicate protein-protein interactions within species (red links are newly-discovered, black links are literature-curated). (E–F) Conserved TF subnetworks that are specific to cerebellum, as first indicated by qRT-PCR (red nodes and Supplementary Table 5) and subsequently confirmed by in-situ hybridization to mouse brain tissue samples. All conserved subnetworks are available at http://fantom.gsc.riken.jp/4/tf-ppi.

Figure 4. Physical and functional exploration of tissue-restricted heterodimers

(A) Four heterodimers that display combinatorial logic across tissues. The heatmap shows the mRNA copy number of each heterodimeric TF across tissues measured by qRT-PCR (Supplementary Table 5). (B) In-vitro pull down experiment shows clear bi-directional physical interaction for each of the four heterodimers as detected originally by M2H assay (Supplementary Table 2). (C) mRNA levels of FLI1 and SMAD3 during THP-1 differentiation induced by PMA, as measured by qRT-PCR. (D) Graphical representation of FLI1/SMAD3 control during myeloid differentiation.