Human and mouse cortical astrocytes differ in aquaporin-4 polarization toward microvessels

Abstract

Aquaporin-4 (AQP4), the predominant water channel in the brain, is expressed in astrocytes and ependymal cells. In rodents AQP4 is highly polarized to perivascular astrocytic endfeet and loss of AQP4 polarization is associated with disease. The present study was undertaken to compare the expression pattern of AQP4 in human and mouse cortical astrocytes. Cortical tissue specimens were sampled from 11 individuals undergoing neurosurgery wherein brain tissue was removed as part of the procedure, and compared with cortical tissue from 5 adult wild-type mice processed similarly. The tissue samples were immersion-fixed and prepared for AQP4 immunogold electron microscopy, allowing quantitative assessment of AQP4's subcellular distribution. In mouse we found that AQP4 water channels were prominently clustered around vessels, being 5 to 10-fold more abundant in astrocytic endfoot membranes facing the capillary endothelium than in parenchymal astrocytic membranes. In contrast, AQP4 was markedly less polarized in human astrocytes, being only two to three-fold enriched in astrocytic endfoot membranes adjacent to capillaries. The lower degree of AQP4 polarization in human subjects (1/3 of that in mice) was mainly due to higher AQP4 expression in parenchymal astrocytic membranes. We conclude that there are hitherto unrecognized species differences in AQP4 polarization toward microvessels in the cerebral cortex.

Keywords: AQP4; brain; electron microscopy; endfeet; perivascular.

Figure 1

AQP4 distribution in the mouse and human cerebral cortex revealed by immunogold cytochemistry. The human tissue was removed from the ID 7 subject (see Table 1) as part of neurosurgical treatment of epilepsy. Representative micrographs from (a) mouse and (b) human showing AQP4 labeling over astrocytic membranes in the vicinity of a capillary. The astrocytic endfoot membranes facing the neuropil (abluminal or “parenchymal astrocytic membrane”, cf. Materials and Methods) and endothelium (adluminal membrane) are indicated by white and black arrowheads, respectively. The AQP4 immunogold particles are concentrated in the adluminal endfoot membranes in both species, but AQP4 polarization is clearly less in human than in mouse. The mouse micrograph shows that segments of the parenchymal astrocytic membrane ensheathe nerve terminals (T). End, capillary endothelium; Lu, capillary lumen; RBC, red blood cell. Scale bars, 0.5 μm

Figure 2

AQP4 immunogold labeling in the mouse (a–c) and human (d–f) cerebral cortex. (d) and (f) are from subject ID 4, whereas (e) is from ID 5 (see Table 1). Both adluminal endfoot membranes and perisynaptic astrocytic membranes are indicated with open arrowheads. Double filled arrowheads denote astrocytic endfoot membrane segments adjacent to pericytes (P). Other labels are as in Figure 1. Boxed region in A is shown at higher magnification in (b). Scale bars, (a, d): 1 μm; (b, c, e, f): 0.25 μm

Figure 3

AQP4 immunogold labeling of human cortical specimens. The tissue sections were obtained from subjects referred for neurosurgical treatment of (a) epilepsy (ID 6, see Table 1), (b) aneurysm (ID 3), and (c) tumor (ID 4). Labels as in Figure 1. Boxed areas are shown in insets. Scale bars, 1 μm and 0.5 μm (inset)

Figure 4

Quantitative analysis of AQP4 immunogold labeling in humans and mice. Comparison of linear densities of AQP4 signaling gold particles along (a) the astrocytic endfoot membrane towards the capillary endothelium, (b) the astrocytic endfoot membrane towards pericytes, and (c) the parenchymal astrocytic membrane (facing neuropil) in humans and mice. (d) AQP4 polarization towards endothelial cells, that is, the ratio of AQP4 immunogold labeling density over membranes facing the endothelium and neuropil, in humans versus mice. (e) AQP4 polarization towards pericytes. Values are mean with 95% confidence interval, and differences between the species were determined by independent samples t test. The degree of polarization towards both endothelial cells and pericytes was significantly higher in mouse (d–e)

Figure 5

Correlation between age of the human individual and AQP4 immunogold labeling. Plots of age versus AQP4 labeling along (a) endfoot membranes next to capillary endothelial cells, or (b) parenchymal astrocytic membranes in the vicinity of capillaries. (c) Plot of age versus AQP4 polarization towards capillaries, that is, the ratio of AQP4 immunogold labeling density along the two membrane domains in (a) and (b). The Pearson correlation coefficient (r) and significance level is given for each plot

Figure 6

AQP4 immunogold labeling in the vicinity of a human arteriole. The specimen is from subject ID 1. The density of AQP4 signaling gold particles is higher in the endfoot membrane facing the arteriole (filled arrowheads) than in the membrane facing neuropil (open arrowheads). Note collagen (Co) fibers in the para‐arteriolar space. Sm, vascular smooth muscle cell. Other legends as in Figure 1. Scale bars, 1 μm and 0.5 μm (inset)

Figure 7

AQP4 immunogold labeling around human capillaries versus arterioles. Comparison of the two vessel segments with regard to (a) linear density of gold particles over the perivascular astrocytic endfoot membrane (endfoot membranes facing capillary endothelial cells and pericytes were pooled), (b) linear density of gold particles over the parenchymal astrocytic endfoot membrane (facing neuropil), and (c) AQP4 polarization index (ratio of labeling over perivascular versus parenchymal astrocytic membranes). Values are mean with 95% confidence interval, and differences between the species were determined by independent samples t test. There were no significant differences between peri‐capillary and peri‐arteriolar AQP4 labeling patterns.