Shox2 is essential for the differentiation of cardiac pacemaker cells by repressing Nkx2-5

Abstract

The pacemaker is composed of specialized cardiomyocytes located within the sinoatrial node (SAN), and is responsible for originating and regulating the heart beat. Recent advances towards understanding the SAN development have been made on the genetic control and gene interaction within this structure. Here we report that the Shox2 homeodomain transcription factor is restrictedly expressed in the sinus venosus region including the SAN and the sinus valves during embryonic heart development. Shox2 null mutation results in embryonic lethality due to cardiovascular defects, including an abnormal low heart beat rate (bradycardia) and severely hypoplastic SAN and sinus valves attributed to a significantly decreased level of cell proliferation. Genetically, the lack of Tbx3 and Hcn4 expression, along with ectopic activation of Nppa, Cx40, and Nkx2-5 in the Shox2(-/-) SAN region, indicates a failure in SAN differentiation. Furthermore, Shox2 overexpression in Xenopus embryos results in extensive repression of Nkx2-5 in the developing heart, leading to a reduced cardiac field and aberrant heart formation. Reporter gene expression assays provide additional evidence for the repression of Nkx2-5 promoter activity by Shox2. Taken together our results demonstrate that Shox2 plays an essential role in the SAN and pacemaker development by controlling a genetic cascade through the repression of Nkx2-5.

Fig. 1

Shox2 expression in the murine developing heart. (A) Shox2 expression is initially detected in the sinus venosus region (arrowhead) at E8.5 embryo. At E10.5 (B) and E11.5 (C), Shox2 expression gradually becomes restricted to the right side of the heart to the dorsal wall of the right atrium, the SAN region (arrow, C) and sinus valves (arrowheads, B, C). At E12.5 (D), restricted Shox2 expression in the SAN and sinus valves (arrowheads) is clearly observed. (E) Shox2 expression at E16.5 follows the same pattern as previous stages. (F) Whole mount in situ hybridization showing the expression of Shox2a isoform in the sinus venosus region (yellow arrowhead). A, atrium; V, ventricle; D, dorsal side.

Fig. 2

Shox2 deficiency causes embryonic lethality and cardiac morphological and functional abnormalities. (A, B) Panoramic comparison between a wild type (A) and a Shox2^−/− (B) embryos at E11.5. The mutant embryo exhibits cardiac edema (arrow) and vascular defects (arrowheads). Brain defects are observed in some specimens. (C, D) Histological comparison shows hypoplastic SAN and sinus valves in the Shox2^−/− mutant heart (red arrowheads in panel D), as compared to the wild type controls (C), evidenced by the length of the sinus valves (red arrows in panels C and D) and the difference in size of the SAN region (black arrows in panel D). Additionally, a thinner atrial wall and an enlarged atrial chamber were observed in the Shox2^−/− heart (D). (E, F) BrdU labeling shows a significantly decreased level of cell proliferation in the Shox2^−/− SAN and sinus valves (F), as compared to the wild type (E). (G) Comparison of the percentage of BrdU-positive cells present in the SAN and sinus valves demonstrate a significant difference between wild type and Shox2^−/− hearts (*: P<0.05); the interventricular septum region was chosen as a control region shows no significant difference. (H) Measurement of the contraction rate in isolated hearts at E10.5 after 24 h of culture shows a significantly slower beating rate in the Shox2^−/− samples, as compared to the wild type (wt) and Shox2 heterozygote (het) samples (*: P<0.001). A, atrium; bpm=beats per minute. Scale bars represent 1 mm (A, B) or 50 μm (C–F).

Fig. 3

Altered gene expression in the Shox2^−/− heart. Expression patterns of Hcn4 (A–D), Tbx3 (EH), Nkx2-5 (I–L), Nppa (M–P), Cx40 (Q–T) and cTnt (U–X) at E10.5 and at E11.5 in the wild type and Shox2^−/− hearts are shown. Hcn4 is expressed in the dorsal right wall of the right atrium in the wild type (A, C) and is reduced or absent in the Shox2 mutant (B, D). Tbx3 is expressed in the dorsal right wall of the right atrium and in the sinus valves (E, G), however is absent in the Shox2 mutant (F, H) at both stages. Nppa, Cx40, and Nkx2-5 are ectopically expressed in the dorsal right wall of the Shox2^−/− right atrium at both stages (J, N, R, L, P, T), as compared to the wild type controls (I, M, Q, K, O, S). cTnt shows comparable expression level in the Shox2^−/− heart (V, X) and the wild type controls (U, W). In all panels, the arrows point to the SAN region, while the arrowheads point to the sinus valves. A, atrium. Scale bars represent 50 μm.

Fig. 4

Shox2 overexpression downregulates Nkx2-5 expression. XNkx2-5 and XcTnI expression was analyzed by in situ hybridization in control embryos at stage 26 (A, E) and at stage 41 (C, G) and in GR-Shox2 mRNA injected induced embryos at same stages (B, F, D, H). XNkx2-5 expression is clearly reduced at the midline of injected induced embryos at stage 26 (B), as compared to control embryos (A). XcTnI expression is maintained in injected induced embryos laterally, but is absent at the midline at stage 26 (F), as compared to the controls (E). At stage 41, XNkx2-5 expression is absent in injected induced embryos (D) compared to control embryos (C). XcTnI expression in injected induced embryos (D) is comparable to that of control embryos (H). Altered gene expression is accompanied by the abnormal heart morphology when comparing control and injected induced embryos (C, D, G, H). Histological transverse sections of Xenopus embryos showing loss of mesodermal cardiac progenitor cells in the ventral midline in injected induced embryos (B′, D′, arrowheads), as evidenced by the loss of XNkx2-5 expression in the corresponding region when compared to control embryos (A′, C′, arrowheads). Scale bars represent 50 μm.

Fig. 5

Shox2 represses the activity of the Nkx2-5 promoter in cell cultures. (A) Neonatal rat cardiomyocytes and H9c2 cells were utilized. Co-transfection of with 100 ng of pGL3 basic vector as controls or Nkx2-5-Luc construct, with Myc-Shox2 expression vector at 50 ng, and 200 ng was performed. Reporter gene expression shows a progressive significant reduction in the activity of the Nkx2-5 promoter on both cell culture systems (* =P<0.001 at 200 ng). The Y axis represents activity of the Nkx2-5 promoter relative to the background after normalization. B) Reporter gene expression assay shows that the activity of the truncated Nkx2-5 promoters when co-transfected with myc-Shox2 (0, 200 and 400 ng/μl) follows a similar trend to the 3.3-kb promoter (*, significant difference, P<0.05).

Fig. 6

Shox2 regulates the SAN genetic program through repression of Nkx2-5. A genetic hierarchy model places Shox2 downstream of Pitx2 but upstream of Nkx2-5 in the regulation of SAN formation. Black arrows represent the up- or downregulation of expression depending on the expression or lack thereof of the upstream gene.