Remember me
Research ArticleCardiologyGeneticsVascular biology
Open Access | 
10.1172/jci.insight.187315
1Department of Genetic Medicine and
2Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
3Wilmer Eye Institute, Johns Hopkins Hospital, Baltimore, Maryland, USA.
4Department of Bioengineering, Northeastern University, Boston, Massachusetts, USA.
5Howard Hughes Medical Institute, Chevy Chase, Maryland, USA.
Address correspondence to: Caitlin J. Bowen or Harry C. Dietz, 733 N. Broadway, MRB 539, Baltimore, Maryland 21205, USA. Phone: 410.614.0701; Email: caitlin.bowen@childrens.harvard.edu (CJB); Email: hdietz@jhmi.edu (HCD).
Find articles by Bowen, C. in: JCI | PubMed | Google Scholar
1Department of Genetic Medicine and
2Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
3Wilmer Eye Institute, Johns Hopkins Hospital, Baltimore, Maryland, USA.
4Department of Bioengineering, Northeastern University, Boston, Massachusetts, USA.
5Howard Hughes Medical Institute, Chevy Chase, Maryland, USA.
Address correspondence to: Caitlin J. Bowen or Harry C. Dietz, 733 N. Broadway, MRB 539, Baltimore, Maryland 21205, USA. Phone: 410.614.0701; Email: caitlin.bowen@childrens.harvard.edu (CJB); Email: hdietz@jhmi.edu (HCD).
Find articles by Sorber, R. in: JCI | PubMed | Google Scholar
1Department of Genetic Medicine and
2Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
3Wilmer Eye Institute, Johns Hopkins Hospital, Baltimore, Maryland, USA.
4Department of Bioengineering, Northeastern University, Boston, Massachusetts, USA.
5Howard Hughes Medical Institute, Chevy Chase, Maryland, USA.
Address correspondence to: Caitlin J. Bowen or Harry C. Dietz, 733 N. Broadway, MRB 539, Baltimore, Maryland 21205, USA. Phone: 410.614.0701; Email: caitlin.bowen@childrens.harvard.edu (CJB); Email: hdietz@jhmi.edu (HCD).
Find articles by Calderón Giadrosic, J. in: JCI | PubMed | Google Scholar
1Department of Genetic Medicine and
2Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
3Wilmer Eye Institute, Johns Hopkins Hospital, Baltimore, Maryland, USA.
4Department of Bioengineering, Northeastern University, Boston, Massachusetts, USA.
5Howard Hughes Medical Institute, Chevy Chase, Maryland, USA.
Address correspondence to: Caitlin J. Bowen or Harry C. Dietz, 733 N. Broadway, MRB 539, Baltimore, Maryland 21205, USA. Phone: 410.614.0701; Email: caitlin.bowen@childrens.harvard.edu (CJB); Email: hdietz@jhmi.edu (HCD).
Find articles by
Doyle, J.
in:
JCI
|
PubMed
|
Google Scholar
|
1Department of Genetic Medicine and
2Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
3Wilmer Eye Institute, Johns Hopkins Hospital, Baltimore, Maryland, USA.
4Department of Bioengineering, Northeastern University, Boston, Massachusetts, USA.
5Howard Hughes Medical Institute, Chevy Chase, Maryland, USA.
Address correspondence to: Caitlin J. Bowen or Harry C. Dietz, 733 N. Broadway, MRB 539, Baltimore, Maryland 21205, USA. Phone: 410.614.0701; Email: caitlin.bowen@childrens.harvard.edu (CJB); Email: hdietz@jhmi.edu (HCD).
Find articles by
Rykiel, G.
in:
JCI
|
PubMed
|
Google Scholar
|
1Department of Genetic Medicine and
2Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
3Wilmer Eye Institute, Johns Hopkins Hospital, Baltimore, Maryland, USA.
4Department of Bioengineering, Northeastern University, Boston, Massachusetts, USA.
5Howard Hughes Medical Institute, Chevy Chase, Maryland, USA.
Address correspondence to: Caitlin J. Bowen or Harry C. Dietz, 733 N. Broadway, MRB 539, Baltimore, Maryland 21205, USA. Phone: 410.614.0701; Email: caitlin.bowen@childrens.harvard.edu (CJB); Email: hdietz@jhmi.edu (HCD).
Find articles by Burger, Z. in: JCI | PubMed | Google Scholar
1Department of Genetic Medicine and
2Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
3Wilmer Eye Institute, Johns Hopkins Hospital, Baltimore, Maryland, USA.
4Department of Bioengineering, Northeastern University, Boston, Massachusetts, USA.
5Howard Hughes Medical Institute, Chevy Chase, Maryland, USA.
Address correspondence to: Caitlin J. Bowen or Harry C. Dietz, 733 N. Broadway, MRB 539, Baltimore, Maryland 21205, USA. Phone: 410.614.0701; Email: caitlin.bowen@childrens.harvard.edu (CJB); Email: hdietz@jhmi.edu (HCD).
Find articles by Zhang, X. in: JCI | PubMed | Google Scholar
1Department of Genetic Medicine and
2Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
3Wilmer Eye Institute, Johns Hopkins Hospital, Baltimore, Maryland, USA.
4Department of Bioengineering, Northeastern University, Boston, Massachusetts, USA.
5Howard Hughes Medical Institute, Chevy Chase, Maryland, USA.
Address correspondence to: Caitlin J. Bowen or Harry C. Dietz, 733 N. Broadway, MRB 539, Baltimore, Maryland 21205, USA. Phone: 410.614.0701; Email: caitlin.bowen@childrens.harvard.edu (CJB); Email: hdietz@jhmi.edu (HCD).
Find articles by Espinoza Camejo, W. in: JCI | PubMed | Google Scholar
1Department of Genetic Medicine and
2Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
3Wilmer Eye Institute, Johns Hopkins Hospital, Baltimore, Maryland, USA.
4Department of Bioengineering, Northeastern University, Boston, Massachusetts, USA.
5Howard Hughes Medical Institute, Chevy Chase, Maryland, USA.
Address correspondence to: Caitlin J. Bowen or Harry C. Dietz, 733 N. Broadway, MRB 539, Baltimore, Maryland 21205, USA. Phone: 410.614.0701; Email: caitlin.bowen@childrens.harvard.edu (CJB); Email: hdietz@jhmi.edu (HCD).
Find articles by Anderson, N. in: JCI | PubMed | Google Scholar
1Department of Genetic Medicine and
2Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
3Wilmer Eye Institute, Johns Hopkins Hospital, Baltimore, Maryland, USA.
4Department of Bioengineering, Northeastern University, Boston, Massachusetts, USA.
5Howard Hughes Medical Institute, Chevy Chase, Maryland, USA.
Address correspondence to: Caitlin J. Bowen or Harry C. Dietz, 733 N. Broadway, MRB 539, Baltimore, Maryland 21205, USA. Phone: 410.614.0701; Email: caitlin.bowen@childrens.harvard.edu (CJB); Email: hdietz@jhmi.edu (HCD).
Find articles by Sabnis, S. in: JCI | PubMed | Google Scholar
1Department of Genetic Medicine and
2Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
3Wilmer Eye Institute, Johns Hopkins Hospital, Baltimore, Maryland, USA.
4Department of Bioengineering, Northeastern University, Boston, Massachusetts, USA.
5Howard Hughes Medical Institute, Chevy Chase, Maryland, USA.
Address correspondence to: Caitlin J. Bowen or Harry C. Dietz, 733 N. Broadway, MRB 539, Baltimore, Maryland 21205, USA. Phone: 410.614.0701; Email: caitlin.bowen@childrens.harvard.edu (CJB); Email: hdietz@jhmi.edu (HCD).
Find articles by Bellini, C. in: JCI | PubMed | Google Scholar
1Department of Genetic Medicine and
2Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
3Wilmer Eye Institute, Johns Hopkins Hospital, Baltimore, Maryland, USA.
4Department of Bioengineering, Northeastern University, Boston, Massachusetts, USA.
5Howard Hughes Medical Institute, Chevy Chase, Maryland, USA.
Address correspondence to: Caitlin J. Bowen or Harry C. Dietz, 733 N. Broadway, MRB 539, Baltimore, Maryland 21205, USA. Phone: 410.614.0701; Email: caitlin.bowen@childrens.harvard.edu (CJB); Email: hdietz@jhmi.edu (HCD).
Find articles by MacFarlane, E. in: JCI | PubMed | Google Scholar
1Department of Genetic Medicine and
2Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
3Wilmer Eye Institute, Johns Hopkins Hospital, Baltimore, Maryland, USA.
4Department of Bioengineering, Northeastern University, Boston, Massachusetts, USA.
5Howard Hughes Medical Institute, Chevy Chase, Maryland, USA.
Address correspondence to: Caitlin J. Bowen or Harry C. Dietz, 733 N. Broadway, MRB 539, Baltimore, Maryland 21205, USA. Phone: 410.614.0701; Email: caitlin.bowen@childrens.harvard.edu (CJB); Email: hdietz@jhmi.edu (HCD).
Find articles by Dietz, H. in: JCI | PubMed | Google Scholar
Published January 21, 2025 - More info
Published in Volume 10, Issue 5 on March 10, 2025
AbstractAortic dissection or rupture is a major cause of mortality in vascular Ehlers-Danlos syndrome (vEDS), a connective tissue disorder caused by heterozygous mutations in the collagen type III alpha 1 chain (COL3A1) gene. C57BL6/J (BL6) mice carrying the Col3a1G938D/+ mutation recapitulate the vEDS vascular phenotype and die suddenly of aortic rupture/dissection. However, 129S6/SvEvTac (referred to here as 129) mice expressing the same Col3a1G938D/+ mutation show near-complete lifelong protection from vascular rupture. To identify genetic modifiers of vascular risk in vEDS, we performed genome-wide genotyping of intercrossed BL6/129 vEDS mice stratified by survival and identified a significant protective locus encompassing a variant in Map2k6, encoding mitogen-activated protein kinase kinase 6 (M2K6), a p38-activating kinase. Genetic ablation of Map2k6 rendered previously protected 129 vEDS mice susceptible to aortic rupture, in association with reduced protein phosphatase 1 activity and increased PKC and ERK phosphorylation. Accelerated vascular rupture in vEDS mice treated with a pharmacological inhibitor of p38 was rescued by concomitant ERK antagonism, supporting an opposing role for ERK and p38 in the modification of aortic rupture risk in vEDS. These results suggest that pharmacologic strategies aimed at mimicking the effect of this natural protective pathway may attenuate aortic rupture risk in vEDS.
IntroductionVascular Ehlers-Danlos syndrome (vEDS) is an inherited connective tissue disorder caused by heterozygous mutations in the collagen type III alpha 1 chain (COL3A1) gene (1–6). The clinical manifestations of vEDS include characteristic facial features, thin skin, frequent bruising, and spontaneous life-threatening arterial or hollow organ ruptures (1, 2). Disease severity and risk of vascular events can be influenced by the nature and location of COL3A1 mutations (1–3, 7, 8). Overall, substitutions of glycine residues in the triple helical domain and splice-site mutations that lead to in-frame exon skipping are associated with a more severe phenotype than any mutational mechanism leading to functional haploinsufficiency (3). Intuitively, since type III collagen monomers interact to form a triple helical structure, seven-eighths of the total type III collagen triple helices will be abnormal if the mutant allele produces an abnormal monomer capable of homomeric interaction. In contrast, while haploinsufficiency is expected to lead to half the normal levels of type III collagen, all the resultant collagen III homotrimers will be qualitatively normal. Although these distinctions provide some insight regarding phenotypic variation in vEDS, significant clinical variability and severity of disease is observed among patients carrying mutations within a given mutational class and even between family members who harbor the identical disease alleles (6, 8–10). These observations suggest the existence of sources of genetic or environmental modification that remain to be defined (11–15).
We have previously described the generation and characterization of a mouse model of vEDS harboring a glycine substitution in the triple helical domain of type III collagen, Col3a1G938D/+, which is representative of the most common class of pathogenic variant seen in patients with vEDS (16). These mice recapitulate the vEDS phenotype, including a very high risk of spontaneous aortic rupture (16). In this study, we sought to identify genetic modifiers of vEDS by analysis of 2 mouse strains or backgrounds that have a strong influence on the rate of aortic rupture/dissection. We map the protection afforded by the 129S6/SvEvTac (referred to here as 129) background relative to the C57BL/6 (BL6) background to a single significant protective locus and identified a single gene (Map2k6, encoding mitogen-activated protein kinase kinase 6) as a modifier of vascular risk in vEDS, via modulation of PKC/ERK signaling.
ResultsThe 129 background protects Col3a1G938D/+ mice from aortic rupture. Mice of BL6 genetic background expressing the disease-causing Col3a1 allele (Col3a1G938D/+), henceforth referred to as BL6 vEDS mice, recapitulate a severe vEDS phenotype, with spontaneous death due to aortic rupture or dissection, leading to a median survival of approximately 60 days (Figure 1A) (16). To examine if the risk of aortic rupture caused by this mutation was modified by the mouse genetic background, we backcrossed the Col3a1G938D/+ mutation onto a pure 129 background. One backcross of BL6 vEDS mice to the 129 background (F1 generation) was sufficient to improve survival, though the effect was more modest in male compared with female mice (Supplemental Figure 1, A and B; supplemental material available online with this article; https://doi.org/10.1172/jci.insight.187315DS1). More pronounced protection from aortic rupture and premature death became apparent in both male and female vEDS mice in the F2 generation relative to sex-matched BL6 vEDS mice (Supplemental Figure 1, A and B), and mice with 3 backcrosses to the 129 background and above (henceforth referred to as 129 vEDS mice) showed essentially complete long-term survival in both sexes (Figure 1, A and B). This protection from vascular events on a 129 background was also recapitulated in another, less severe, vEDS mouse model (Col3a1G209S/+) (Supplemental Figure 2 and ref. 16). There were no background-specific differences in blood pressure or body mass, though both BL6 and 129 vEDS mice were slightly smaller than their wild-type littermates (Supplemental Figure 3). Alterations in aortic wall architecture in BL6 vEDS mice were relatively modest but include elastin fiber breaks, decreased aortic wall thickness, and reduced collagen content at 2 months of age (16). Each of these aortic wall abnormalities was also observed in 129 vEDS aortas, despite their improved survival (Figure 1, C–F). Analysis of passive biaxial mechanical behavior of the descending thoracic aorta of control and vEDS mice showed that increased circumferential stretch and stress in vEDS mice relative to controls was observed in the BL6 but not 129 background when evaluated at the same luminal pressure (120 mmHg), though the differences were modest and of unclear clinical significance. There were no differences observed in axial mechanical properties between vEDS mice on either background and their corresponding control group in the physiological range of loads (Supplemental Figure 4).
Figure 1The 129Sve background protects vEDS mice from premature death. (A) Kaplan-Meier survival curve comparing control (Col3a1+/+) (n = 199) and vEDS (Col3a1G938D/+) mice (n = 191) on a BL6 background with control (n = 18) and vEDS mice (n = 31) on a 129 background. Significant differences were calculated using log-rank (Mantel-Cox) analysis (*** P < 0.001). (B) Kaplan-Meier survival curve comparing male BL6 vEDS male (n = 82) and female (n = 109) mice with 129 vEDS male (n = 15) and female (n = 16) mice. Significant differences were calculated using log-rank (Mantel-Cox) analysis (*** P < 0.001). (C) Verhoeff–Van Gieson (VVG), Masson’s trichrome, and Picrosirius red (PSR) staining of control and vEDS aortic cross sections at 2 months of age. White arrows indicate elastin fiber breaks. Scale bar is 50 microns. (D) Quantification of aortic wall thickness in aortic cross sections. P value refers to 2-way ANOVA with Holm-Šídák post hoc test (*** P < 0.001). (E) Quantification of elastin fiber breaks in VVG-stained aortic cross sections. Asterisks identify discovery (q < Q) by Kruskal-Wallis test with post hoc false discovery rate correction. (F) Quantification of collagen content in aortic cross sections, as measured by normalized PSR intensity. P value refers to 2-way ANOVA with Holm-Šídák post hoc test (*** P < 0.001). (G) Immunoblot of aortic lysates obtained from the proximal descending aortas of control and vEDS mice in the BL6 and 129 backgrounds at 2 months of age, probed with antibodies directed against phosphorylated PKCβ at residue Ser660 (pPKC) and phosphorylated ERK (pERK1/2). (H) Quantification for immunoblot shown in G. P value refers to 2-way ANOVA with Holm-Šídák post hoc test for p-PKC and Kruskal-Wallis test for p-ERK (* P < 0.05, *** P < 0.001). For D–F and H, each symbol represents an independent biological replicate, with unfilled symbols representing male samples. Error bars show mean ± SEM. Black circles represent control mice and red squares represent vEDS mice.
We have previously shown that increased activation of PKC and ERK contributes to risk of aortic rupture in vEDS mouse models (16); we thus obtained tissue from the descending thoracic aorta of 2-month-old BL6 and 129 vEDS mice, prior to any physical evidence of vascular enlargement or tear, and examined the status of these 2 signaling proteins. As previously observed, activation of ERK1/2 and PKC was accentuated in the proximal thoracic descending aorta of BL6 vEDS mice, while activation of these signaling pathways in 129 vEDS aortas was not different from that observed in wild-type littermates (Figure 1, G and H, and Supplemental Figure 5). Taken together, these data suggested the existence of protective genetic modifiers of vEDS phenotypic severity within the 129 background, possibly acting through modulation of signaling pathways previously implicated in the risk of aortic rupture/dissection in this mouse model.
Identification of a genetic modifier using mixed background mice. To identify genetic variants underlying the difference in vascular rupture risk between the BL6 and 129 backgrounds, we intercrossed wild-type BL6 and 129 animals and their progeny for 4 generations (F4), with expansion of numbers of mice in each generation, to introduce extensive recombination between the strain-specific chromosomes (Figure 2A). Mixed-background control females were then bred to Col3a1G938D/+ male mice on a pure BL6 background to generate a large cohort of vEDS mice with a different complement of 129 alleles in heterozygosity. Introduction of the vEDS mutation was delayed until after complete intermixing and recombination to avoid any potential selection bias that could result in skewed allele distributions due to early death from aortic rupture.
Figure 2A single locus on distal chromosome 11 associates with protection from death by rupture in vEDS mice. (A) Breeding scheme for the generation of vEDS mice of mixed background used for GWAS. (B) Survival and stratification strategy of vEDS mice of mixed background. Mice that died from vascular rupture before 12 weeks of age were coded as cases (BL6-like, shown in black), while those surviving more than 24 weeks are coded as controls (129-like, shown in red). Mice that did not die from vascular rupture (i.e., malocclusion) or died between 12 and 24 weeks of age were not included in the analysis, as defined prospectively. (C) Manhattan plot of mixed-background vEDS mice (n = 91 controls, n = 96 cases). The red line indicates the genome-wide significance threshold. (D) Filtering strategy used to identify candidate modifier genes within the locus of interest. (E) Graphical representation of the region of interest on chromosome 11 showing annotated transcripts color-coded based on the type of variant existing in the BL6 compared with the 129 genetic background. Black and gray shapes represent BL6-like mice, and red shapes represent 129-like mice. Bptf, bromodomain PHD finger transcription factor; Helz, helicase with zinc finger.
This mixed-background cohort was monitored twice daily, with immediate autopsy on deceased animals to document cause of death to stratify intercrossed vEDS animals based on vascular event–related survival (Figure 2B). To maximize both signal intensity and power of downstream analyses, we focused our analysis on the extremes of survival distribution. More than 74% of all vEDS mice on the BL6 background died by 12 weeks of age, while more than 95% of vEDS mice on the 129 background lived longer than 24 weeks. Thus, death from aortic rupture between 1 and 12 weeks of age was defined as a “severe phenotype,” while survival past 24 weeks of age was defined as a “mild phenotype.” Mice that died within 1 week of birth were excluded from analysis because of ambiguity regarding the cause of death and the associated difficulty in reliable sample collection. As expected, the mixed-background population stratified into “mild” and “severe” phenotypic groups (Figure 2B). Male vEDS mice were more likely than female vEDS mice to be categorized as “severe” (P < 0.0001), reflective of the observed sex difference in F1 vEDS survival.
We genotyped 91 mixed-background vEDS mice with a mild phenotype (coded as controls, 62 females and 29 males) and 96 mixed-background vEDS mice with a severe phenotype (coded as cases, 29 females, 67 males). A linkage disequilibrium (LD) block-pruned set of 615 SNPs was used to perform a logistic regression GWAS using sex as a covariate. We identified 1 locus that was linked with protection from aortic rupture on chromosome 11 that attained genome-wide significance, with a peak P value of 7.08 × 10–5 (Figure 2C). The odds ratio of 0.2293 (95% CI: 0.1109–0.4741) indicated that the presence of a single 129 allele at this locus substantially decreased the odds of early death due to aortic rupture. We did not observe an association signal on chromosome X, suggesting that the increased severity in F1 and mixed males is not attributable to an X-linked trait but rather an autosomal trait that is sex limited or sex influenced. The study was underpowered to identify sex-specific autosomal modifiers of disease (Supplemental Figure 6).
We next leveraged genomic information and RNA transcriptomic analysis to filter genes that were present in the region of interest (Figure 2, D and E, and Supplemental Table 1). We specifically examined the 3.5 Mb region on mouse chromosome 11 that was flanked by the closest neighboring upstream and downstream SNP markers below the genome-wide significant peak on chromosome 11 (107,079,000–110,573,573 bp) (Figure 2E). We assessed this region for the presence of genes that were expressed in the aorta, and that contained putatively functional sequence variation between the 2 strains, including splice-site, nonsense and frameshift, or missense and insertion/deletion variants with a predicted impact on protein structure or function (Figure 2, D and E, and Supplemental Table 1). Of the 5 genes satisfying these criteria, Bptf, Helz, and Map2k6 also showed differential expression in the descending aorta of mice from the 2 backgrounds based on bulk RNA-sequencing analysis (Table 1 and Supplemental Tables 1 and 2).
To narrow the scope of downstream functional analysis, we used evidence from the literature to identify, among these 3 genes, the one most likely to play a role in modulation of the vEDS phenotype. Haploinsufficiency for Bptf is associated with severe neurodevelopmental disability and congenital anomalies, arguing against a role in isolated modification of a vascular phenotype (17, 18). Similarly, Helz encodes a widely expressed RNA helicase, not suggestive of a strong relevance to vascular homeostasis (19). Based on these considerations, we thus focused downstream analyses on the missense variant in Map2k6 (rs51129320; n.11:110490856-110490856G>A; c.G227A; p.G76E), a gene expressed in multiple aortic cell types, including smooth muscle cells and endothelial cells, and coding for mitogen-activated protein kinase kinase 6 (M2K6) (Supplemental Figure 7) (20). This glycine to glutamic acid substitution is predicted to have an effect on the function of the gene by in silico analysis (PROVEAN score –3.66).
M2K6 is 1 of the 2 upstream activators of the p38 family of kinases (p38α, p38β, p38γ, and p38δ) (21, 22). To examine if M2K6 activity was indeed altered between the protective 129 background relative to BL6, we used phospho-specific antibodies to assess phosphorylation of p38α at residues targeted by M2K6 (p-p38, Thr180/Tyr182) in the proximal descending thoracic aorta of 60-day-old mice. Immunoblot of aortas derived from 129 background mice showed increased levels of p-p38α relative to BL6 samples, independently of the genotype at the Col3a1 locus (Supplemental Figure 8), consistent with the notion that this variant leads to intrinsically higher levels of M2K6 activity in 129 mice, which could contribute to reduced risk of aortic rupture in vEDS.
Map2k6-dependent protection of vEDS from aortic rupture associates with increased protein phosphatase 1 activity and reduced PKC/ERK phosphorylation. To directly examine the role of Map2k6/M2K6 in modulating the aortic rupture risk in vEDS, we next crossed protected 129 vEDS mice to Map2k6–/– mice, also on a 129 background, to generate 129 vEDS mice haploinsufficient or fully deficient for Map2k6. While Map2k6–/– mice have no known vascular phenotype, they have been reported to develop cardiac hypertrophy after 6 months of age in the BL6 background (23). While biallelic loss of Map2k6 alone did not affect survival of control 129 mice (Supplemental Figure 9), it rendered previously protected 129 vEDS mice of either sex vulnerable to vascular rupture (Figure 3, A and B).
Figure 3Map2k6 exerts a protective effect against death by aortic rupture in vEDS mice. Kaplan-Meier survival curve comparing (A) male 129 vEDS Map2k6+/+ (n = 17), vEDS Map2k6+/– (n = 20), and vEDS Map2k6–/– mice (n = 10) and (B) female 129 vEDS Map2k6+/+ (n = 19), vEDS Map2k6+/– (n = 15), and vEDS Map2k6–/– mice (n = 12). Significant differences were calculated using log-rank (Mantel-Cox) analysis (* P < 0.05; ** P < 0.01). (C) Immunoblot analysis of phosphorylated PKC at residue Ser660 (pPKC) and phosphorylated ERK (pERK1/2) comparing aortic lysates obtained from the proximal descending aortas of mice at 2 months of age. (D) Quantification of p-PKC and p-ERK normalized to β-actin of control Map2k6+/+ (n = 3), vEDS Map2k6+/+ (n = 4), control Map2k6–/– (n = 7), and vEDS Map2k6–/– (n = 5) mice. P value refers to 2-way ANOVA with Holm-Šídák post hoc test (* P < 0.05, *** P < 0.001). (E) Immunofluorescence of sections from the proximal descending thoracic aorta of vEDS Map2k6+/+ and vEDS Map2k6–/– mice. The dashed line marks the approximate boundaries of the aortic wall. Scale bar is 50 microns. (F) Mean and total protein phosphatase 1 (PP1) dephosphorylation activity in aortic protein lysates from 129 vEDS Map2k6+/+ mice (n = 6) and 129 vEDS Map2k6–/– (n = 7). P value refers to unpaired t test with Welch’s correction (* P < 0.05, ** P < 0.01).DiFMU, 6,8-difluoro-7-hydroxy-4-methylcoumarin. In D and F, each symbol represents an independent biological replicate, with unfilled symbols representing male samples. Error bars show mean ± SEM. (G) Kaplan-Meier survival curve comparing control 129 vEDS Map2k6–/– mice (n = 33, 17 females and 16 males) with 129 vEDS Map2k6–/– (n = 11, 8 females and 3 males) mice receiving ruboxistaurin (PKC inhibitor) starting at postnatal day 21. Significant differences were calculated using log-rank (Mantel-Cox) analysis (* P < 0.05).
However, the effect of Map2k6 haploinsufficiency (Col3a1G938D/+Map2k6+/–) was sexually dimorphic, with loss of only 1 Map2k6 allele sufficient to cause increased death in male but not female mice, paralleling the dimorphism seen in F1 vEDS mice (Supplemental Figure 1, A and B). Histological defects observable in the aorta of vEDS mice of either background (Figure 1) were also seen in the aorta of Map2k6-deficient vEDS mice, with no significant differences driven by Map2k6 deficiency (Supplemental Figure 10). No BL6 vEDS mice with only 1 copy of Map2k6 on a BL6 background (BL6 Col3a1G938D/+Map2k6+/–) were observed past postnatal day 1, suggesting that the loss of 1 Map2k6 allele in vEDS mice on a BL6 background results in complete prenatal or perinatal lethality (Supplemental Table 3).
Analogous to what was observed in vEDS mice on the BL6 background (Figure 1G and Supplemental Figure 5), increased risk of aortic rupture in 129 Map2k6-deficient vEDS mice associated with increased levels of PKC and ERK phosphorylation, as assessed both by immunoblot and immunofluorescence analyses (Figure 3, C–E), as well as the expected decreased p38 phosphorylation (Figure 3) (23). M2K6-activated p38 can increase activation of PP1 and PP2A (21, 22, 24), which dephosphorylate PKC and ERK, among many other substrates (24–26). We therefore hypothesized that the protective role of M2K6 may depend, at least in part, on the activation of phosphatases that dephosphorylate PKC and ERK. Consistent with this hypothesis, the descending thoracic aorta of vulnerable 129 Map2k6-deficient vEDS mice showed reduced levels of PP1 activity relative to protected 129 Map2k6+/+ vEDS mice (Figure 3F). Levels of protein phosphatase activity were also increased in protein lysates from the descending thoracic aorta of 129 background mice compared with BL6 background mice at 2 months of age, with PP1 contributing to approximately 70% of the overall activity regardless of genotype (Supplemental Figure 11). To demonstrate direct relevance of increased PKC and ERK activation to the increased risk of death from aortic rupture in 129 Map2k6-deficient vEDS mice, we treated 129 Map2k6-deficient vEDS mice with a PKC inhibitor, ruboxistaurin, which fully rescued the phenotype with 4 months of treatment leading to 100% survival, compared to only 50% survival in placebo-treated mice (Figure 3G).
Inhibition of p38 activation increases vascular rupture risk in vEDS mice. The data presented above suggested that the M2K6/p38/PP1 pathway may play a protective role in vEDS aortic rupture risk. To directly examine the role of p38 activity on vascular rupture, we first treated BL6 vEDS mice with SB203580, a selective p38 inhibitor. Treatment significantly decreased survival in BL6 vEDS mice without affecting BL6 control mice (Figure 4A), suggesting that p38 activity has a significant protective effect on the risk of vascular rupture in vEDS mice. Surprisingly, treatment with an equivalent or doubled dose of SB203580 did not affect the risk of vascular rupture in 129 vEDS mice, though the increased dose was associated with gradual wasting, irrespective of genotype (Supplemental Figure 12). Analyses of protein lysates of the descending thoracic aorta of vEDS mice treated with the p38 inhibitor showed that the elevated risk of rupture correlated with increased levels of both PKC and ERK phosphorylation in BL6 vEDS mice (Figure 4B), while PKC and ERK phosphorylation were not affected in the 129 vEDS mice that did not demonstrate an increased risk of aortic rupture (Supplemental Figure 13). Consistent with a protective role for p38 in suppression of excessive ERK activation in vEDS aorta, elevated risk of rupture driven by inhibition of p38 in BL6 vEDS mice could be rescued by concomitant treatment with a MEK inhibitor (cobimetinib) (Figure 4A and Supplemental Figure 14). Taken together, these data suggested that the M2K6/p38/PP1 and PKC/ERK pathways play antagonistic roles in the modulation of vascular risk in vEDS mouse models (Figure 4C).
Figure 4Inhibition of p38 activation increases the risk of vascular rupture in BL6 vEDS mice. (A) Kaplan-Meier survival curve comparing saline-injected BL6 vEDS mice (n = 19, 7 female and 12 male) with BL6 vEDS mice (n = 14, 6 females and 8 males) receiving SB203580 (p38 inhibitor) via intraperitoneal injection and SB203580-treated also receiving cobimetinib, a MEK inhibitor (n = 14, 6 females and 8 males), starting at postnatal day 21 and continuing for 40 days thereafter. Significant differences were calculated using log-rank (Mantel-Cox) analysis (** P < 0.01, *** P < 0.001). (B) Immunoblot of aortic lysates from the proximal descending thoracic aortas of BL6 vEDS mice treated with placebo or p38 inhibitor at 45 days of age, probed with antibodies directed for p-PKCβ and p-ERK and quantification of immunoblot. Each symbol represents an independent biological replicate, with unfilled symbols representing male samples. Error bars show mean ± SEM. P value refers to unpaired t test with Welch’s correction (** P < 0.01). Red circles represent placebo-treated mice, and blue squares represent p38 inhibitor–treated mice. (C) Summary figure outlining contributors to risk of vascular rupture in the aorta of vEDS mouse models.
DiscussionIn this study, we show that the risk of vascular rupture is attenuated in 129 vEDS mice and that this protection associates with a protective variant in the Map2k6 locus (rs51129320), coding for M2K6, a p38-activating kinase. Deficiency in Map2k6 decreased the survival of otherwise-protected 129 vEDS mice, in association with reduced p38 activation, reduced PP1 activity, and increased levels of PKC and ERK phosphorylation. Similarly, pharmacological inhibition of p38 in BL6 vEDS mice resulted in increased aortic rupture risk, also in association with increased PKC and ERK phosphorylation. These observations, and the fact that increased risk of rupture due to p38 inhibition was rescued by concomitant MEK/ERK inhibition, suggest that maladaptive integration between ERK and M2K6/p38 signaling contributes to the pathogenesis of aortic rupture in vEDS animal models. The mechanisms regulating activation of these 2 pathways, and the cell types responsible for their maladaptive and adaptive functions, remain unclear.
Biallelic deletion of Map2k6 in 129 vEDS mice did not fully recapitulate the extent of vulnerability observed in BL6 vEDS animals, suggesting the existence of additional modifying variation between the 2 strains. Furthermore, isolated pharmacologic p38 inhibition was insufficient to break the protection observed in 129 vEDS animals — even to the extent observed in 129 Map2k6–/– vEDS mice. Although this may be the result of ineffective p38 inhibition, it is also possible that the protective effect of M2K6 activity may occur independently of p38 activation, for example by direct phosphorylation of members of the p21-activated kinase family (27), or that protection is imposed, and irreversible, during early development. In addition to the 129 strain, the FVB mouse strain has been shown to be resistant to β-aminopropionitrile–induced vascular rupture, and informatively this background also carries the same protective c.G227A allele at the Map2k6 locus, suggesting a role for Map2k6 activity in the pathogenesis of other models of aortic dissection/rupture (Ensembl database) (28).
Sexual dimorphism in survival was observed in both vEDS mice haploinsufficient for Map2k6 and in those carrying only 1 copy of the hypomorphic BL6 variant of Map2k6. It remains unclear if this simply reflects the generalized enhanced vulnerability in the M2K6-deficient state, effectively unmasking added susceptibility imposed by male sex, or direct crosstalk between M2K6 and androgen signaling cascades. It is notable that activation of p38 has previously been implicated in the negative regulation of androgen receptor activity (29). Integration of androgen signaling and M2K6/p38 and PKC/ERK activation may also differ among different aortic cell types, resulting in complex crossregulation that is not explored in this work and will require analysis of mice with cell type–specific pathway inhibition. Further work should also focus on whether people with vEDS are more or less susceptible to aortic rupture based on their MAP2K6 genetic profiles. Previous work that has identified genes that affect aortic dimensions may not be as directly relevant to this disease or model, which largely presents with spontaneous dissection without aneurysm (30, 31). Despite these limitations, the findings presented in this work suggest that pharmacologic strategies that can mimic the natural mechanism of protection observed in the 129 background through modulation of M2K6/p38/PP1 or PKC/ERK signaling pathways have a strong potential of reducing aortic rupture risk in vEDS. Perhaps more generally, this work challenges the view that clinical outcomes in vEDS are uniquely determined by an obligate structural deficiency of the tissues and highlight the therapeutic potential of addressing modifiable cellular signaling events to achieve and sustain vascular homeostasis.
MethodsSex as a biological variable. Our study examined male and female mice, and sex-dimorphic effects are reported.
Study design. The aim of this study was to find genes that modify the risk of vascular rupture in mouse models of vEDS. Utilizing mouse models carrying knockin heterozygous mutations in Col3a1, we conducted a GWAS of mixed-background vEDS mice. Sample size was calculated using power analysis (32) and relative risk assumptions based on survival data of F1 and F2 vEDS mice. Exclusion criteria were defined a priori: mice that died between 12 and 24 weeks of age were excluded, and mice that did not have clear hemothorax or hemoperitoneum on necropsy were excluded. The effects of the variant on intracellular signaling pathways were studied ex vivo. For all survival analyses, mice were censored only if unrelated to the outcome, such as for planned biochemical or histologic analy
Comments (0)