Evaluating the transcriptional regulators of arterial gene expression via a catalogue of characterized arterial enhancers

Abstract

The establishment and growth of the arterial endothelium require the coordinated expression of numerous genes. However, regulation of this process is not yet fully understood. Here, we combined in silico analysis with transgenic mice and zebrafish models to characterize arterial-specific enhancers associated with eight key arterial identity genes (Acvrl1/Alk1, Cxcr4, Cxcl12, Efnb2, Gja4/Cx37, Gja5/Cx40, Nrp1, and Unc5b). Next, to elucidate the regulatory pathways upstream of arterial gene transcription, we investigated the transcription factors binding each arterial enhancer compared to a similar assessment of non-arterial endothelial enhancers. These results found that binding of SOXF and ETS factors was a common occurrence at both arterial and pan-endothelial enhancers, suggesting neither are sufficient to direct arterial specificity. Conversely, FOX motifs independent of ETS motifs were over-represented at arterial enhancers. Further, MEF2 and RBPJ binding was enriched but not ubiquitous at arterial enhancers, potentially linked to specific patterns of behaviour within the arterial endothelium. Lastly, there was no shared or arterial-specific signature for WNT-associated TCF/LEF, TGFβ/BMP-associated SMAD1/5 and SMAD2/3, shear stress-associated KLF4, or venous-enriched NR2F2. This cohort of well-characterized and in vivo-verified enhancers can now provide a platform for future studies into the interaction of different transcriptional and signaling pathways with arterial gene expression.

Keywords: SOXF transcription factors; arterial enhancer; arterial gene transcription; arteriovenous differentiation; developmental biology; genetics; genomics; mouse; transcriptional regulation; vascular development; zebrafish.

Figure 1.. Analysis of enhancer marks around eight arterial-expressed genes identifies putative arterial enhancers.

Enhancer marks from mouse tissue include: dark red ‘ATAC adult artery EC’ denotes open chromatin assessed by ATAC-seq in primary adult aortic endothelial cells (ECs) Engelbrecht et al., 2020; bright red ‘ATAC P6 EC’ denotes open chromatin assessed by ATAC-seq in postnatal day 6 retinal ECs Yanagida et al., 2020; orange ‘EP300 E11 EC’ denotes enriched EP300 binding in Tie2Cre+ve cells in embryonic day 11.5 embryos (Zhou et al., 2017). Enhancer marks from human cells include: light blue peaks denotes enriched H3K27Ac and H3K4Me1 in human umbilical vein ECs (HUVECs) (UCSC Genome Browser; Rosenbloom et al., 2013); grey heat map denotes open chromatin regions assessed by DNAseI hypersensitivity in HUVECs (upper line) and dermal-derived neonatal and adult blood microvascular ECs (HMVEC-dBl-neo/ad, middle and bottom line) (UCSC Genome Browser). Red, pink, and orange solid boxes indicate regions fitting putative enhancers criteria and selected for analysis (red/pink/orange indicates strong/weak/silent EC activity in transgenic models, see Table 2 and Figures 2 and 3). Numbers represent approximate distance from TSS. Orange dashed boxes indicates regions below the putative enhancer threshold but included in transgenic assays as controls, grey boxes indicate regions below the putative enhancer threshold and not tested. * indicates that enhancer marks were not specific for ECs but rather found in many cell types.

Figure 1—figure supplement 1.. The mouse Dll4-12 enhancer directs arterial expression of reporter genes in the vasculature of transgenic zebrafish (A) and mice (B).

This enhancer was first reported in Sacilotto et al., 2013 but not tested in zebrafish. (A) The Dll4-12:GFP transgene directs arterial endothelial cell expression in mosaic F0 (upper) and stable F1 (middle) transgenic zebrafish at 2 days post fertilization (dpf), arterial specificity is confirmed at 3 dpf by crossing with tg(kdrl:HRAS-mCherry) (lower two panels). Grey dashed box specifies region of zoom, a indicates dorsal aorta, v indicates cardinal vein, * indicates intersegmental vessels, and n indicates neural tube expression. (B) The mouse Dll4-12:LacZ transgene directs arterial expression in a stable transgenic line. Representative whole-mount embryos from the Dll4-12:lacZ transgenic line show reporter gene expression (X-gal staining, blue) in the vasculature from embryonic day 9.5 (E9.5) to E15.5.

Figure 1—figure supplement 2.. Analysis of putative enhancers in F0 mosaic Tol2 transgenic zebrafish identifies 15 enhancers able to drive robust GFP activity in arterial endothelial cells (ECs) (other weaker/ non-arterial enhancers are detailed in Figure 1—figure supplement 3).

(A) Example of the expression of known pan-EC (kdrl1:HRAS-mCherry) (Chi et al., 2008), arterial (Dll4in3:GFP; Sacilotto et al., 2013), and vein (CoupTFII-965:GFP; Neal et al., 2019) enhancers in 2 dpf zebrafish. (B) Two representative F0 transgenic zebrafish expressing each of the 15 new strong arterial enhancers alongside a schematic of each transgene. Grey dashed box indicates region of zoom, a indicates dorsal aorta, v indicates cardinal vein, white arrow indicates intersegmental vessels, * indicates expression in neural tube, and # indicates expression in muscle fibres.

Figure 1—figure supplement 3.. Additional images of transgenic fish expressing the Unc5b-57:GFP, Cxcl12+383:GFP, Efnb2-37, Unc5b+23, Cxcl12+117, Efnb2-112 and Efnb2-159 transgenes.

(A,, B) The Unc5b-57:GFP transgene is expressed in the vasculature when investigated in either F0 Tol2 transgenic zebrafish (A) or F1/2 stable transgenic zebrafish (B). Crossing with the kdrl:HRAS-mCherry transgene demonstrates that Unc5b-57:GFP expression is restricted to venous locations towards the anterior of the fish. (C) Expression pattern driven by the three ‘weak’ enhancers identified in our F0 mosaic Tol2 transgenic zebrafish screen. Grey dashed box indicates region of zoom, a indicates dorsal aorta, v indicates cardinal vein, white arrows indicate intersegmental vessels, * indicates expression in neural tube, and # indicates expression in muscle fibres. (D) The Cxcr4-117:GFP transgene directs very limited reporter gene expression in transgenic zebrafish. The six transgenic zebrafish shown exhibited the greatest level of GFP expression seen in all injected zebrafish. Grey dashed box indicates region of zoom. (E) Expression pattern of the Efnb2-159 and Efnb2-112 enhancer:GFP transgenes in 4-week-old juvenile zebrafish fins. Grey dashed box indicates regions of zoom, a fin artery, and v fin vein.

Figure 1—figure supplement 4.. Enhancer marks in cultured human arterial endothelial cells (ECs) around the eight target arterial gene loci.

These are shown relative to the enhancer marks in human vein-origin and microvascular-origin ECs used to originally identify putative arterial enhancers in Figure 1. Red and orange boxes denote the regions identified as putative enhancers in original analysis, grey boxes denote regions below threshold, and numbers represent approximate distance from TSS in mouse sequence. * indicates that enhancer marks were not specific for ECs but rather found in many cell types. Enhancer marks in human vein-origin and microvascular-origin ECs used in original analysis: light blue peaks denote enriched H3K27Ac and H3K4Me1 in human umbilical vein ECs (HUVECs), data from the UCSC Genome Browser Hou et al., 2022; grey heat map denotes open chromatin regions assessed by DNAseI hypersensitivity in HUVECs (upper line) and dermal-derived neonatal and adult blood microvascular ECs (HMVEC-dBl-neo/ad, middle and bottom line) from the UCSC Genome Browser (Hou et al., 2022). Enhancer marks in human arterial-origin ECs are all shaded green, including very dark green ‘HAEC ATAC-seq’ denoting open chromatin assessed by ATAC-seq in human aortic ECs from Hogan et al., 2017; dark green ‘telo-HAEC ATAC-seq’ denoting open chromatin assessed by ATAC-seq in immortalized human aortic ECs from Schnitzler et al., 2024; green ‘HAEC H3K27Ac’ denoting enriched H3K27Ac enhancer marks in human aortic ECs from Hogan et al., 2017; bright green ‘HUAEC H3K27Ac’ denoting enriched H3K27Ac enhancer marks in human umbilical aortic ECs from Sissaoui et al., 2020; and lime green ‘HUAEC p300’ denoting enriched p300 binding peaks in human umbilical aortic ECs from Sissaoui et al., 2020.

Figure 2.. Analysis in 2 dpf transgenic zebrafish indicates arterial activity of fifteen novel enhancer:GFP transgenes.

Grey dashed box indicates region of zoom, da indicates dorsal aorta, cv indicates cardinal vein, dlav indicates dorsal longitudinal anastomotic vessel, white arrow indicates intersegmental vessels, and * indicates expression in neural tube. tg(Cxcr4-135:GFP) was crossed with tg(kdrl:HRAS-mCherry), which expresses mCherry in all blood vascular ECs and is shown here on the top line as a guide to vessel structure at this timepoint. F1/2 indicates generation of embryo.

Figure 3.. Analysis in 3 dpf transgenic zebrafish indicates specificity of arterial expression of each arterial enhancer.

Stable transgenic zebrafish expressing the 15 strong arterial enhancer:GFP transgenes crossed with tg(kdrl:HRAS-mCherry), which expresses mCherry in all blood vascular ECs. Grey dashed box indicates region of zoom, da indicates dorsal aorta, cv indicates cardinal vein, dlav indicates dorsal longitudinal anastomotic vessel, pale pink filled arrows indicates intersegmental arteries, pale blue open arrows indicate intersegmental veins, * indicates expression in neural tube, and F1/2 indicates generation of embryo.

Figure 3—figure supplement 1.. Analysis of enhancer activity in the 2–3 dpf ocular vasculature.

(A) Schematic diagram of the primary ocular vasculature adapted from Hashiura et al., 2017. (B) Expression pattern of 15 novel arterial enhancers in the ocular vasculature at 2 dpf and 3 dpf. At 3 dpf, kdrl:HRAS-mCherry transgene was crossed with arterial zebrafish lines to enable visualization of all ECs.

Figure 4.. Summary of enhancer:GFP expression pattern in the vasculature of stable transgenic zebrafish lines.

DA dorsal aorta, ISA intersegmental arteries, DLAV dorsal longitudinal anastomotic vessel, CV cardinal vein, ISV intersegmental veins, NT neural tube, NCA nasal ciliary artery, NCAx extends beyond NCA in direction of blood flow, HA hyaloid artery, DCV dorsal ciliary vein, OV optic vein. A fin artery, V fin vein. Letters “s” “m” and “w” equate to strong medium or weak relative expression, *restricted to distal regions, ** restricted to anterior regions, *** restricted to subset of ECs.

Figure 5.. The majority of developmentally active arterial enhancers remain active in adult zebrafish fins.

(A) Schematic drawing of the zebrafish fin vasculature adapted from Xu et al., 2014. (B) Expression pattern of the common EC marker line Fli1a:GFP in an adult fin. (C) Expression pattern of 13 novel arterial enhancer:GFP transgenes in adult fins, alongside previously identified arterial enhancers Dll4in3 and Dll4-12. Grey dashed box indicates regions of zoom, a indicates fin artery, v indicates fin vein, * arterial sprout. See also Figure 1—figure supplement 4.

Figure 6.. Five putative enhancers direct arterial expression in the vasculature of E14.5 transgenic mouse embryos.

(A–E) Two representative F0 embryos expressing each tested putative enhancer alongside a schematic of the transgene and two transverse sections through the embryo body wall and tail. Numbers in bottom left indicate embryos with arterial lacZ/total transgenic embryos. Grey dashed boxes indicate region in zoom, arrow indicates artery. (F) shows a representative E14.5 embryo from a stable transgenic line expressing the arterial Dll4in3:lacZ transgene alongside similar transverse sections through the embryo body wall and tail. Black line = 100 um.

Figure 6—figure supplement 1.. All transgenic embryos expressing the Efnb2-37:lacZ transgene at E14.5 Grey dashed boxes indicate region in zoom.

No expression is seen in vessels.

Figure 7.. Schematics summarizing the transcription factor motifs found within each arterial (A), pan-EC (B), and venous (C) enhancer.

All enhancers shown in 3’–5’ orientation relative to the arterial gene TSS. Deep black-lined rectangle boxes indicate strongly conserved motifs for transcription factors (conserved at the same depth as the surrounding enhancer sequence), shallow grey-lined boxes/text indicate weakly conserved motifs (conserved between mouse and human enhancer sequence but not at the same depth as the surrounding sequence), and rounded boxes mark motifs in enhancers conserved only human-mouse. Bold transcription factor names indicate places where ChIP-seq (or similar analysis) confirms binding. See Figure 7—figure supplements 2–6 for annotated sequences. Arterial enhancers listed with * are previously published (as detailed in Payne et al., 2024), genome locations for each enhancer are provided in Table 2—source data 2. Distances between motifs are representative but not scaled.

Figure 7—figure supplement 1.. Transcription factor motifs associated with arterial enhancers.

(A) Homer known motif enrichment results on core enhancer sequences from all 23 arterial enhancers listed in Table 1. Exact sequences include in this analysis are listed in Figure 7—figure supplement 2, and the coordinates in mm10 recorded in Table 2—source data 2. (B) Table summarizing sequence logos used to guide motif analysis, alongside the source of each logo and EC type (where relevant). (C) Exact sequences assigned as motifs for each transcription factor.

Figure 7—figure supplement 2.. Sequences of core enhancers (3’ to 5’ orientation) listed in Figure 7 alongside annotated transcription factor binding motifs.

ETS motifs highlighted in green, SOXF motifs in yellow, FOX motifs in darker blue, FOX:ETS motifs in turquoise, RBPJ motifs in red, MEF2 in bright light blue, SMAD4 motifs in light pink, SMAD1/5 GC-rich motifs in darker pink, TCF/LEF (Wnt pathway) in grey, NR2F2 motifs in purple, and KLF4 motifs in orange. The sequences assessed as transcription factor motifs are listed in Figure 8C. Bold underline strong motifs conserved to the same depth as surrounding sequence (conservation depth indicated after title of each enhancer), bold indicates weak motif conserved between human and mouse but not to the comparable depth of the surrounding sequence, and italic indicates motif just found in mouse sequence.

Figure 7—figure supplement 3.. Sequences of core enhancers (3’ to 5’ orientation) listed in Figure 7 alongside annotated transcription factor binding motifs.

Figure 7—figure supplement 4.. Sequences of core enhancers (3’ to 5’ orientation) listed in Figure 7 alongside annotated transcription factor binding motifs.

Figure 7—figure supplement 5.. Sequences of core enhancers (3’ to 5’ orientation) listed in Figure 7 alongside annotated transcription factor binding motifs.

Figure 7—figure supplement 6.. Sequences of core enhancers (3’ to 5’ orientation) listed in Figure 7 alongside annotated transcription factor binding motifs.

Figure 8.. Binding patterns of 11 vascular-associated transcription factors around each arterial enhancer.

Red dashed box indicates arterial enhancer region. Tracks show ChIP-seq/CUT&RUN signal for ERG (Sissaoui et al., 2020), ETS1 (Chen et al., 2017), SOX7, SOX17 and SOX18 (this paper), FOXO1 (Andrade et al., 2021), RBPJ (Wang et al., 2019), MEF2C (Maejima et al., 2014), SMAD1/5 (Morikawa et al., 2011), SMAD2 (Chen et al., 2019), and NR2F2 (Sissaoui et al., 2020) in HUVECs, alongside FOXO1 (Sissaoui et al., 2020), and MEF2A (Akerberg et al., 2019) in adult mouse hearts.

Figure 8—figure supplement 1.. Genomic regions around eight previously described arterial enhancers (red dashed box) alongside tracks showing ChIP-seq/CUT&RUN signal for ERG (Sissaoui et al., 2020), ETS1 (Chen et al., 2017), SOX7, SOX17, and SOX18 (this paper), FOXO1 (Andrade et al., 2021), RBPJ (Wang et al., 2019), MEF2C (Maejima et al., 2014), SMAD1/5 (Morikawa et al., 2011), SMAD2 (Chen et al., 2019), and NR2F2 (Sissaoui et al., 2020) in HUVECs, alongside FOXO1 (Sissaoui et al., 2020) and MEF2A (Akerberg et al., 2019) in adult mouse hearts.

Figure 8—figure supplement 2.. Genomic regions around 13 previously described pan-EC enhancers (grey dashed box) and 3 previously described vein enhancers (dark blue dashed box) alongside tracks showing ChIP-seq/CUT&RUN signal for ERG (Sissaoui et al., 2020), ETS1 (Chen et al., 2017), SOX7, SOX17, and SOX18 (this paper), FOXO1 (Andrade et al., 2021), RBPJ (Wang et al., 2019), MEF2C (Maejima et al., 2014), SMAD1/5 (Morikawa et al., 2011), SMAD2 (Chen et al., 2019), and NR2F2 (Sissaoui et al., 2020) in HUVECs, alongside FOXO1 (Sissaoui et al., 2020) and MEF2A (Akerberg et al., 2019) in adult mouse hearts.

Figure 8—figure supplement 3.. Assessment of SOX7, SOX17 and SOX18 CUT&RUN.

(A–B, D, F, H) Venn diagrams assessing overlap of genomic regions called as peaks of various combinations of ChIP-seq and CUT&RUN datasets. (A) Comparison of called binding peaks for ERG (Sissaoui et al., 2020) and SOX7_mCherry (Overman et al., 2017) with marks for enhancers and TSS (Sissaoui et al., 2020). (B) Comparison of called binding peaks for ERG and SOX17 (new CUT&RUN) with marks for enhancers and TSS. (D) Comparison of called binding peaks for ERG and SOX7 (new CUT&RUN) with marks for enhancers and TSS. (D, F) Comparison of called binding peaks for ERG and SOX7 (new CUT&RUN) with marks for enhancers and TSS. (H) Comparison of called binding peaks for the overlap of called peaks of our SOX7, SOX17, and SOX18 CUT&RUN data with each another and previously published ERG ChIP-seq data. (C, E, G) Top motif families called by HOMER in the SOX17 (C) and SOX7 (E) and SOX18 (G) CUT&RUN peaks.

Figure 8—figure supplement 4.. Gene expression patterns of SOX and FOX transcription factors in ECs from different scRNA-seq datasets.

(A) UMAP visualization of scRNA-seq data of CD31+EC isolated from E12 BmxCreERT2;Rosa^tdTomato lineage traced hearts with accompanying gene expression profiles. Raw data obtained from D’Amato et al., 2022. (B) Chosen gene expression profiles from scRNA-seq data of ApjCreER lineage traced EC isolated from E14.5 hearts. Plots taken from publicly available Shinyapp visualization of data from Su et al., 2018 . (C) UMAP plot and chosen gene expression profiles of CD31+EC from BmxCreERT2;Rosa^tdTomato lineage traced from E17.5 hearts. Raw data obtained from D’Amato et al., 2022 for reanalysis.

Figure 9.. Summary of transcription factor motif and binding patterns at arterial, pan-EC and venous enhancers (A), and relative to different expression patterns within the arterial vasculature (B).

(A) All known (e.g. published) endothelial enhancers with adequately described expression patterns in transgenic mouse embryos were analysed to determine occurrence of selected TF motifs and direct binding. See Figure 7—figure supplement 1 for TF motif information, Figure 7—figure supplements 2–6 for annotated enhancer sequences and Figure 8 and Figure 8—figure supplements 1 and 2 for TF binding peaks. Enhancers in bold were identified in this paper, those with * are previously published (as detailed in ¹), genome locations for each enhancer is provided in Table 2—source data 2. (B) TF binding patterns for each arterial enhancer grouped by expression patterns in the 3 dpf zebrafish trunk. DA dorsal aorta, ISA intersegmental arteries, DLAV dorsal longitudinal anastomotic vessel, CV cardinal vein, ISV intersegmental veins, NT neural tube, NCA nasal ciliary artery, NCAx extends beyond NCA in direction of blood flow, HA hyaloid artery, DCV dorsal ciliary vein, OV optic vein. A fin artery, V fin vein. Letters s m w equate to strong medium or weak relative expression, * restricted to distal regions, ** restricted to anterior regions, *** restricted to subset of ECs.