Genomic targets of Brachyury (T) in differentiating mouse embryonic stem cells

Abstract

Background: The T-box transcription factor Brachyury (T) is essential for formation of the posterior mesoderm and the notochord in vertebrate embryos. Work in the frog and the zebrafish has identified some direct genomic targets of Brachyury, but little is known about Brachyury targets in the mouse.

Methodology/principal findings: Here we use chromatin immunoprecipitation and mouse promoter microarrays to identify targets of Brachyury in embryoid bodies formed from differentiating mouse ES cells. The targets we identify are enriched for sequence-specific DNA binding proteins and include components of signal transduction pathways that direct cell fate in the primitive streak and tailbud of the early embryo. Expression of some of these targets, such as Axin2, Fgf8 and Wnt3a, is down regulated in Brachyury mutant embryos and we demonstrate that they are also Brachyury targets in the human. Surprisingly, we do not observe enrichment of the canonical T-domain DNA binding sequence 5'-TCACACCT-3' in the vicinity of most Brachyury target genes. Rather, we have identified an (AC)(n) repeat sequence, which is conserved in the rat but not in human, zebrafish or Xenopus. We do not understand the significance of this sequence, but speculate that it enhances transcription factor binding in the regulatory regions of Brachyury target genes in rodents.

Conclusions/significance: Our work identifies the genomic targets of a key regulator of mesoderm formation in the early mouse embryo, thereby providing insights into the Brachyury-driven genetic regulatory network and allowing us to compare the function of Brachyury in different species.

Figure 1. Temporal expression pattern of Brachyury during early ES cell differentiation.

The graph shows a quantitative RT-PCR profile from an embryoid body spinner culture. Brachyury expression is calculated relative to beta actin. Images show undifferentiated R1 cells on mouse embryo fibroblast feeders at day 0, early blast colonies at day 2, and embryoid bodies at days 3, 4 (when they are cross-linked) and 5.

Figure 2. Analysis of Brachyury targets.

(A) Pie chart showing the times in development at which Brachyury target gene expression begins in the mouse embryo (as a percentage of total; n = 396). Most genes (63%) start to be expressed between E7.5, when Brachyury is expressed in the primitive streak, notochord and tailbud, and E17.5, when expression is restricted to trunk mesenchyme. Of targets showing this temporal expression pattern, 30% are restricted to mesodermal derivatives, as indicated in the bar chart to the right. Others are expressed in various combinations of ectoderm, mesoderm and endoderm. (B) Temporal expression of transcription factor targets of Brachyury during ES cell differentiation in spinner culture, obtained by RT-PCR. The three panels in the top row were taken from a batch of cells in which Brachyury expression peaked at day 4 of culture; the rest were taken from a batch in which Brachyury expression peaked at day 3. All show means of triplicate measurements and are normalised to levels of beta actin. Foxa2 and Foxe1 in the top row peak with Brachyury at day 4; genes in the lower panel peak later than Brachyury.

Figure 3. Components of the Wnt pathway as Brachyury targets.

(A) The Wnt signalling pathway. Arrows indicate positive interactions and bars represent negative interactions. Targets identified in this study are outlined in bold. (B–E) Brachyury binding in genomic regions around Dkk1 (B); Ctnnb1/β-catenin (C); Dvl3 (D); and γ-Catenin/jup/plakoglobin (E). Each target shows fold enrichment against chromosomal position. Blue bars represent the T box-like site TSACANNT (N = any base, S = G/C) and green bars represent (AC)_n. Stars above bars represent sequence on the reverse strand. Plots are average of triplicate chip results, aligned to the mm8 Feb. 2006 assembly.

Figure 4. Analysis of Wnt3a, a positive regulator of the Wnt pathway.

(A) Location analysis of Wnt3a. The figure (and Figs. 5, 6) shows fold enrichment against chromosomal position. Plot is the mean of triplicate chip results, aligned to the mm8 Feb. 2006 assembly. Blue bars represent the T box-like site TSACANNT (N = any base, S = G/C); green bars represent (AC)_n; red bars the consensus TCACACCT. Stars above bars represent sequence on reverse strand. (B) Quantitative RT-PCR expression profile for Wnt3a during ES cell differentiation, expressed relative to beta actin. (C, D) Expression of Wnt3a studied by in situ hybridisation; in each, the top image shows a dorsal view, and the bottom image a lateral view. (C) Phenotypically wild type (+/+ or +/T) embryo at E8.5–8.75, and (D) a mutant (T/T) embryo from crosses of Brachyury heterozygous mutant mice. Wnt3a expression is detected with NBT/BCIP (purple) and the insets show a lateral view after double staining for Brachyury detected with INT/BCIP (orange brown). Note that in the wild type embryo Wnt3a is expressed in tailbud and paraxial mesoderm. In the mutant embryo expression of Wnt3a staining is absent or greatly reduced (n = 3). Scale bars indicate 250 µm.

Figure 5. Analysis of Axin2, a negative regulator of the Wnt pathway.

(A) Location analysis of Axin2. For details see legend to Fig. 4. (B) Quantitative RT-PCR expression profile for Axin2 during ES cell differentiation, expressed relative to beta actin. (C, D) Expression of Axin2 studied by in situ hybridisation; in each, the top image shows a dorsal view, and the bottom image a lateral view. (C) Phenotypically wild type (+/+ or +/T) embryo at E8.5–8.75 and (D) a mutant (T/T) embryo, both derived from crosses of Brachyury heterozygous mutant mice. Axin2 expression is detected with NBT/BCIP (purple) and the insets show a lateral view after double staining for Brachyury detected with INT/BCIP (orange brown). Note that in the wild type embryo Axin2 is expressed in tailbud, paraxial mesoderm and lateral margin of the neural folds. In the mutant embryo expression of Axin2 is greatly reduced (n = 9). Scale bars are 250 µm.

Figure 6. Fgf8 as a target of Brachyury.

(A) Location analysis of Fgf8. For details of methods see legend to Fig. 4. (B) Quantitative RT-PCR expression profile for Fgf8 during ES cell differentiation, expressed relative to beta actin. (C) Expression of Fgf8 studied by in situ hybridisation. The images show a phenotypically wild type (+/+ or +/T) embryo (top pair) and a mutant T/T (bottom pair) embryo derived from crosses of Brachyury heterozygous mutant mice. The wild type embryo is orientated with anterior to the left and posterior to the right; the mutant is viewed from the posterior. Fgf8 expression is detected with NBT/BCIP (purple) and Brachyury with INT/BCIP (orange brown). In the wild type embryo Fgf8 is expressed in the primitive streak and paraxial mesoderm; such expression is absent or greatly reduced in the mutant. Scale bars indicate 200 µm.

Figure 7. Conservation of BRACHYURY binding in the human genome.

(A) ChIP-qPCR performed on samples from differentiated hECSs using a specific anti-BRACHYURY IgG and a non-specific control IgG. Graph shows enrichment for regulatory regions of Brachyury targets (AXIN2, FGF8, JUP, WNT3A) and a negative control region (NCAPD2). Results are expressed relative to input chromatin divided by the enrichment for the non-specific control antibody. (B) BRACHYURY binding in the human genome. The short red lines below the chromosomal coordinates (hg19) depict the position of the PCR amplicons relative to the beginning of the human genes (blue). The three bottom tracks show the genome sequence conservation between human and mouse, zebrafish and vertebrate genomes (Genome Browser, http://genome.ucsc.edu/).