Requirement for sphingosine kinase 1 in mediating phase 1 of the hypotensive response to anandamide in the anaesthetised mouse

Abstract

In the isolated rat carotid artery, the endocannabinoid anandamide induces endothelium-dependent relaxation via activation of the enzyme sphingosine kinase (SK). This generates sphingosine-1-phosphate (S1P) which can be released from the cell and activates S1P receptors on the endothelium. In anaesthetised mice, anandamide has a well-characterised triphasic effect on blood pressure but the contribution of SK and S1P receptors in mediating changes in blood pressure has never been studied. Therefore, we assessed this in the current study. The peak hypotensive response to 1 and 10 mg/kg anandamide was measured in control C57BL/6 mice and in mice pretreated with selective inhibitors of SK1 (BML-258, also known as SK1-I) or SK2 ((R)-FTY720 methylether (ROMe), a dual SK1/2 inhibitor (SKi) or an S1P₁ receptor antagonist (W146). Vasodilator responses to S1P were also studied in isolated mouse aortic rings. The hypotensive response to anandamide was significantly attenuated by BML-258 but not by ROMe. Antagonising S1P₁ receptors with W146 completely blocked the fall in systolic but not diastolic blood pressure in response to anandamide. S1P induced vasodilation in denuded aortic rings was blocked by W146 but caused no vasodilation in endothelium-intact rings. This study provides evidence that the SK1/S1P regulatory-axis is necessary for the rapid hypotension induced by anandamide. Generation of S1P in response to anandamide likely activates S1P₁ to reduce total peripheral resistance and lower mean arterial pressure. These findings have important implications in our understanding of the hypotensive and cardiovascular actions of cannabinoids.

Keywords: Anandamide; Hypotension; Mouse; Sphingosine kinase; Sphingosine-1-phosphate.

Fig. 1

Representative experimental recording showing the changes in BP induced by i.v. injection of two doses of anandamide (1 and 10 mg/kg) in mice. Arrows indicate the injections of anandamide which were administered at 5 min intervals.

Fig. 2

Effect of pretreatment with SK inhibitors on the peak hypotensive response to i.v. anandamide administration. (A) Mice were pre-treated with either vehicle or dual SK1/2 inhibitor, SKi (75 mg/kg) for 24 h prior to baseline MAP measurement. n = 12. (B) Baseline values were compared to the peak hypotensive response following tocrisolve or anandamide injection. **P < 0.01, n = 4–8, two-way ANOVA. (C) Mice were pre-treated with either vehicle or the selective SK1 or SK2 inhibitors (75 mg/kg), BML-258 or ROMe respectively, for 24 h prior to baseline MAP measurement. *P < 0.05 and ***P < 0.001, n = 5–12, one-way ANOVA. (D) Baseline values were compared to the peak hypotensive response following increasing doses of anandamide. *P < 0.05, n = 5–9, two-way ANOVA.

Fig. 3

Effect of the S1P₁ antagonist W146 on the peak hypotensive response to i.v. administration of anandamide. (A) Mice were pre-treated with either vehicle or W146 (10 mg/kg) for 30 min prior to baseline MAP measurements. n = 6–12. (B and C) Baseline MAP and systolic BP values were compared to the peak hypotensive response following increasing doses of anandamide. *P < 0.05 and ***P < 0.001, n = 5–6, two-way ANOVA.

Fig. 4

Responses to sphingosine and S1P in the presence and absence of a SK inhibitor and S1P receptor antagonists in denuded mouse aortic rings. (A) Vessels were pre-treated with the dual SK1/2 inhibitor SKi prior to U46619-induced contraction. n = 3–9. (B) Dose-response to sphingosine and in the presence of SKi (10 μM) were produced. *P < 0.05 versus sphingosine alone, n = 3–9, two-way ANOVA. (C) Vessels were pre-treated with selective S1P₁ antagonist W146 or the S1P_1/3 antagonist, VPC 23019 (both 10 μM) prior to U46619-induced contraction. n = 5–9. (D) Dose-response to S1P in the presence and absence of W146 and VPC 23019 were produced. (E) The BK_Ca channel opener NS1619 produced a vasodilation in endothelium-intact aortic rings which was not affected by either W146 or VPC 23019. ***P < 0.001 versus S1P alone, n = 5–9, two-way ANOVA.

Fig. 5

S1P₁ immunostaining in the endothelium and medial vascular smooth muscle cells of aortae from vehicle- and W146-treated mice. Representative photomicrographs (n = 6) of sections stained with S1P₁ and counterstained with haematoxylin. Specific staining is seen as a brown colour and was visualised via a peroxidase-DAB method (magnification × 400 for all panels).

Fig. S1

Recovery time of MAP following injection of AEA. Mice were pre-treated with either DMSO (control; n = 9), BML-258 (n = 5) or ROMe (n = 4) 24 h prior to the i.v. injection of AEA or Tocrisolve (solvent; n = 6). AEA was injected at increasing doses of 1 and 10 mg/kg at 5 min intervals. To assess the duration of the phase 3 response induced by AEA and the time taken to return to baseline, MAP was analysed 5 min after the injection of the relevant dose and expressed as percentage of baseline MAP. In all groups, MAP had recovered to baseline levels 5 min after injection of the lower dose of AEA. Data are expressed as mean ± S.E.M. *P < 0.05 vs. control.

Fig. S2

Variable bradycardic response during phase 1 hypotension. Mice were pre-treated with either DMSO, (control) BML-258 or ROMe (both 75 mg/kg) and anaesthetised with isoflurane. The %-decrease from pre-injection values for HR during the initial hypotension in response to 1 and 10 mg/ml AEA or the equivalent amount of tocrisolve solvent was quantified for the different treatment groups. Data are expressed as mean ± S.E.M. Numbers in the bars denote n-numbers. P = ns for comparisons made with the control group.