Rod-Shaped monocytes patrol the brain vasculature and give rise to perivascular macrophages under the influence of proinflammatory cytokines and angiopoietin-2

Abstract

The nervous system is constantly infiltrated by blood-derived sentinels known as perivascular macrophages. Their immediate precursors have not yet been identified in situ and the mechanism that governs their recruitment is mostly unknown. Here, we provide evidence that CD68(+)GR1(-) monocytes can give rise to perivascular macrophages in mice suffering from endotoxemia. After adhesion to the endothelium, these monocytes start to crawl, adopt a rod-shaped morphology when passing through capillaries, and can manifest the ability to proliferate and form a long cytoplasmic protuberance. They are attracted in greater numbers during endotoxemia by a combination of vasoregulatory molecules, including TNF (tumor necrosis factor), interleukin-1beta, and angiopoietin-2. After a period of several hours, some of them cross the endothelium to expand the population of perivascular macrophages. Depletion of adherent monocytes and perivascular macrophages can be achieved by injection of anti-angiopoietin-2 peptide-Fc fusion protein. This study extends our understanding of the behavior of monocytes at the blood-brain interface and provides a way to block their infiltration into the nervous tissue under inflammatory conditions.

Figure 1.

Phenotype of rod-shaped leukocytes attached to the luminal surface of cerebral capillaries. a–c, Confocal images showing GFP⁺ leukocytes (green; arrows) immunostained for CD11b, CD68, or GR1 (red) in the brain of a chimeric mouse. These cells exhibited a polarized shape typical of migrating cells. Arrowhead, Microglia. Scale bar: a–c, 5 μm. d, Monocyte with a DAPI-stained monolobed nucleus (red, false color) that was positive for CD68 (data not shown). See supplemental Movie 1, left panel (available at www.jneurosci.org as supplemental material), for a three-dimensional reconstruction of this cell. Scale bar: d, e, 1 μm. e, Granulocyte with a multilobed nucleus that was positive for GR1 (data not shown). See supplemental Movie 1, right panel (available at www.jneurosci.org as supplemental material), for a three-dimensional reconstruction. f–h, Light micrographs of leukocytes stained for F4/80, CD163, or stabilin-1 by immunohistochemistry. Scale bar: f–h, 10 μm.

Figure 2.

LPS increases the number of adherent leukocytes in the brain vasculature. a, b, Rod-shaped or round leukocyte immunostained for CD45 in the brain of a normal mouse. Scale bar: a, b, 5 μm. c, Stereological analysis revealed an increased number of CD45⁺ adherent leukocytes in the cerebral cortex of mice killed 6 or 12 h after intraperitoneal injection of LPS (1 mg/kg). *Significantly different from LPS 1 h (ANOVA, p ≤ 0.0035). Error bars indicate SEM. d, A positive correlation was found between the number of rod-shaped leukocytes and that of round leukocytes (Pearson's correlation, p < 0.0001, r = 0.87). Each data point represents a mouse treated with LPS or saline.

Figure 3.

LPS increases the proliferation of rod-shaped leukocytes. a, Confocal images showing a GFP⁺ rod-shaped leukocyte (green; arrow) that was dividing inside the cerebral vasculature (red) in a chimeric mouse. Scale bar, 10 μm. b, c, Dividing leukocytes exhibiting nuclei (red, false color) in telophase. Scale bars, 5 μm. d, e, Leukocytes that were labeled with BrdU (red) during the S-phase of the cell cycle. Scale bars, 5 μm. f, Light micrograph of a dividing leukocyte stained for CD45 by immunohistochemistry. Scale bar, 5 μm. g, Stereological analysis revealed an increase in the number of dividing rod-shaped leukocytes in the cerebral cortex 6 h after intraperitoneal LPS injection. *Student's t test, p < 0.0001. Error bars indicate SEM.

Figure 4.

Rod-shaped monocytes can cross the cerebral endothelium and extend cytoplasmic processes. a, b, Confocal images of GFP⁺ monocytes (green; arrows) that seemed to be in the process of migrating through the endothelium (red). Scale bars: a, 5 μm; b–g, 10 μm. c, Two monocytes, one (arrow) that was located in a capillary and the other (arrowhead) in the parenchyma. Note that the latter had a polarized shape typical of migrating cells, with a leading edge (bottom) and uropod (top). d–f, Monocyte-derived perivascular macrophages exhibiting an elongated cell body with cytoplasmic processes. Note the typical shape of the nucleus in f. g, Monocyte that extended a long cytoplasmic process in a capillary.

Figure 5.

LPS induces a delayed increase in the recruitment of perivascular macrophages. a–d, Different types of bone marrow-derived cells stained for GFP by immunohistochemistry in brain sections from chimeric mice. Scale bar: a–d, 10 μm. e, Stereological analysis revealed increased numbers of adherent leukocytes and perivascular macrophages expressing GFP in the cerebral cortex of mice killed 1 or 3 d after intraperitoneal LPS injection (n = 9 per group). *Two-way ANOVA: treatment effect, p < 0.0001; time effect, p > 0.05; interaction, p > 0.05. **Two-way ANOVA: treatment effect, p = 0.014; time effect, p < 0.0001; interaction, p = 0.0037. Error bars indicate SEM.

Figure 6.

TNF and IL-1β partially mediate the effect of LPS on the adhesion of leukocytes to the cerebral vasculature. a, b, Dark-field micrographs showing in situ hybridization signals for TNF or IL-1β mRNA in the cerebral cortex of a mouse killed 6 h after intraperitoneal LPS injection (1 mg/kg). Scale bar: a, b, 50 μm. The asterisk (*) indicates blood vessel lumen. c, Stereological analysis revealed reduced numbers of CD45⁺ adherent leukocytes in the cerebral cortex of mice deficient in TNF and/or IL-1β 6 h after LPS injection. *Significantly different from LPS-treated wild types (WT) (ANOVA, p ≤ 0.0030). Error bars indicate SEM. d, A positive correlation was found between the number of rod-shaped leukocytes and that of round leukocytes (Pearson's correlation, p < 0.0001, r = 0.65). Each data point represents a wild-type or knock-out mouse treated with LPS or saline.

Figure 7.

Angpt2 is expressed throughout the brain during endotoxemia, mainly by endothelial cells and rarely by astrocytes. a–d, Dark-field micrographs showing in situ hybridization signals for Angpt2 mRNA in brain sections of mice killed at different times after intraperitoneal LPS injection. Abbreviations: CC, Corpus callosum; Cor, cerebral cortex; CP, caudoputamen; LV, lateral ventricle. Scale bar: a–d, 250 μm. e, Bright-field image showing hybridization signals (black grains) for Angpt2 mRNA at higher magnification. Blue, Thionin counterstaining. Scale bar, 20 μm. f, Increased levels of Angpt2 mRNA were detected by real-time PCR in the brains of mice killed 6 h after LPS injection. Data are expressed as a ratio to 18S rRNA *Significantly different from the other groups (two-way ANOVA: treatment effect, p < 0.0001; time effect, p < 0.0001; interaction, p < 0.0001). Error bars indicate SEM. g–i, Double labelings for Angpt2 mRNA (black grains; in situ hybridization) and different cell-specific markers (red-brown; immunoperoxidase staining). The arrows indicate double-labeled cells. Scale bar: g–i, 20 μm.

Figure 8.

TNF regulates Angpt2 expression in vivo. a, b, Dark-field micrographs showing in situ hybridization signals for Angpt2 mRNA in the brain of a wild-type or TNF-deficient mouse killed 6 h after intraperitoneal LPS administration. Scale bar: a, b, d, e, 250 μm. c, Stereological analysis revealed reduced numbers of Angpt2 mRNA⁺ cells in the cerebral cortex of mice deficient in TNF killed 6 h after LPS injection. *Significantly different from wild type (WT) and IL-1β knock-out (KO) mice (ANOVA, p = 0.0012). Error bars indicate SEM. d, e, Hybridization signals for Angpt2 mRNA in brain sections of mice killed 6 h after injection of TNF (100 ng) or saline into the right caudoputamen. Abbreviations: CC, Corpus callosum; Cor, cerebral cortex; CP, caudoputamen; LV, lateral ventricle. f, As estimated by the Cavalieri method, the volume occupied by Angpt2 mRNA⁺ cells in TNF-injected mice was 6.5 times that in control mice at 6 h after injection. *Significantly different from the other groups (two-way ANOVA: treatment effect, p = 0.0008; time effect, p = 0.0018; interaction, p = 0.010). Error bars indicate SEM.

Figure 9.

TNF regulates Angpt2 expression in vitro. a, b, Quantification of Angpt2 mRNA by real-time PCR in bEnd.3 cerebral endothelial cells or primary astrocytes cultured for 6 h in the presence of LPS (1 μg/ml), TNF (10 or 100 ng/ml), and/or anti-TNF antibody (10 μg/ml). *Significantly different from control [ANOVA, p < 0.0001 (a) or = 0.0072 (b)]. Error bars indicate SEM. c, Confirmation of the presence of Angpt2 mRNA in bEnd.3 cells and astrocytes, cultured in normal conditions, by standard PCR and agarose gel electrophoresis. Right column, DNA ladder. d, Quantification of TNF mRNA by real-time PCR in bEnd.3 cells and astrocytes cultured for 6 h with or without LPS. *Significantly different from PBS (Student's t test, p < 0.0001). Error bars indicate SEM. e, Confocal image of astrocytes in primary culture immunostained for GFAP (red). Blue, DAPI-stained nuclei. Scale bar, 20 μm.

Figure 10.

Angpt2 mediates the effect of LPS on the adhesion of leukocytes to the cerebral vasculature and the recruitment of perivascular macrophages. a, Stereological analysis revealed a reduced number of adherent leukocytes, but not of perivascular macrophages (Student's t test, p = 0.64), in the cerebral cortex of nonchimeric mice infused intracerebroventricularly with L1-10 and killed 6 h after LPS injection. *Student's t test, p ≤ 0.002. b, c, The number of adherent leukocytes and perivascular macrophages was reduced in the cerebral cortex of chimeric mice injected intravenously with L1-10 and killed 3 d after LPS administration. *Student's t test, p ≤ 0.02. **Student's t test, p ≤ 0.0006. Error bars indicate SEM.

Figure 11.

Monocyte activity at the blood–brain interface. 1, Activated by inflammatory stimuli (e.g., LPS), monocytic cells release proinflammatory cytokines such as TNF. This can occur in the brain or in peripheral tissues. 2, TNF acts on the cerebral microvasculature by inducing the expression of Angpt2, which permits vascular changes that promote the adhesion of CD68⁺GR1⁻ monocytes. 3, 4, When firmly attached, these cells adopt a rod-shaped morphology and crawl on the endothelium. 5, Most frequently at capillary branch points, they can divide into two daughter cells that continue to crawl in opposite directions. 6, While monitoring the environment, they can extend a long cytoplasmic process whose function is unknown. 7, Where needed, some of them cross the blood–brain barrier by a process of diapedesis. 8, 9, After infiltration, they search for a vacant niche in which they ultimately differentiate into perivascular macrophages. Although CD68⁺GR1⁻ monocytes do not give rise to microglia in response to endotoxemia, it remains to be investigated whether they can do so in other inflammatory conditions.