Identification of polarized macrophage subsets in zebrafish

Abstract

While the mammalian macrophage phenotypes have been intensively studied in vitro, the dynamic of their phenotypic polarization has never been investigated in live vertebrates. We used the zebrafish as a live model to identify and trail macrophage subtypes. We generated a transgenic line whose macrophages expressing tumour necrosis factor alpha (tnfa), a key feature of classically activated (M1) macrophages, express fluorescent proteins Tg(mpeg1:mCherryF/tnfa:eGFP-F). Using 4D-confocal microscopy, we showed that both aseptic wounding and Escherichia coli inoculation triggered macrophage recruitment, some of which started to express tnfa. RT-qPCR on Fluorescence Activated Cell Sorting (FACS)-sorted tnfa(+) and tnfa(-) macrophages showed that they, respectively, expressed M1 and alternatively activated (M2) mammalian markers. Fate tracing of tnfa(+) macrophages during the time-course of inflammation demonstrated that pro-inflammatory macrophages converted into M2-like phenotype during the resolution step. Our results reveal the diversity and plasticity of zebrafish macrophage subsets and underline the similarities with mammalian macrophages proposing a new system to study macrophage functional dynamic.

Keywords: developmental biology; immunology; live imaging; macrophages; stem cells; zebrafish.

Figure 1.. The (tnfa:eGFP-F) reporter line recapitulates transcriptional activation of tnfa upon wound-induced inflammation and Escherichia coli infection.

(A–E) Tumour necrosis factor alpha (tnfa) mRNA expression (blue, arrowhead) was detected by in situ hybridization using tnfa anti-sense probe: at 6 hpA in (A) intact (control) and (B) amputated fins from 3 dpf WT larvae, (C) in uninfected larvae (54 hpf, hours post-fertilization) and (D, E) E. coli infected larvae (24 hpi, 54 hpf). Arrows show melanocytes (black). (E) Imaging of tnfa mRNA expression in the muscle at higher magnification, asterisks show muscle fibres, scale bar in (B) = 100 μm and in (E) = 50 μm. (F, G) eGFP fluorescence (green) was analyzed by fluorescent microscopy in (F) intact (control) and (G) amputated Tg(tnfa:eGFP-F) fins at 6 hpA, dotted lines outline the caudal fin, scale bar = 100 μm and at 16 hpi in Tg(tnfa:eGFP-F) larvae injected with (H) PBS or (I, J) E. coli (red) in the muscle. Arrows show auto-fluorescent xanthophores. (J) Multi-scan confocal analysis of GFP expression in E. coli-infected Tg(tnfa:eGFP-F) larvae, scale bar = 20 μm. (K) tnfa mRNA and eGFP-F expressions were analyzed using microscopy at 6 hpA in amputated fins from 3 dpf Tg(tnfa:eGFP-F) larvae. Dotted lines delimit the caudal fin, arrowheads show overlapping signals, and arrows show the pigments. Scale bar = 100 μm. (L) Graphed data of representative fluorescence-activated flow cytometry analysis of eGFP⁺ cells in upon amputation. Tg(tnfa:eGFP-F) larvae were either kept intact (control) or amputated at 3 dpf, and cells were collected at 6 hr post-treatment. Green gates represent eGFP⁺ population and mean percentage of eGFP⁺ population ±s.e.m is indicated. (M) Relative expression of tnfa in eGFP- and GFP⁺ cells in amputated larvae. Real-time RT-PCR on separated cells using EF1a as a reference gene. Graph represents the mean value of three independent experiments ±s.e.m. *p < 0.05. DOI: http://dx.doi.org/10.7554/eLife.07288.003

Figure 2.. Activation, morphology, and behaviour of TNF-α⁺ macrophages in (tnfa:eGFP-F/mpeg1:mCherry-F) transgenic larvae upon wound-induced inflammation.

(A) eGFP-F (green) and mCherryF (red) fluorescence was analyzed by fluorescent microscopy in intact (control) and amputated Tg(mpeg1:mCherryF/tnfa:eGFP-F) fins at 6 hpA of 3 dpf larvae. Arrowheads show recruited macrophages that express tnfa, arrows show tnfa⁺ cells that are not macrophages, and asterisks show auto-fluorescent pigments. Dotted lines outline the caudal fin, scale bar = 100 μm. (B) Bright-field image of the wounded fin of a 3 dpf Tg(mpeg1:mCherryF/tnfa:eGFP-F) larva. Dotted red box shows the region imaged in C. (C) Representative time-lapse maximum projections show the activation of macrophages arriving at the wound in 3 dpf amputated Tg(mpeg1:mCherryF/tnfa:eGFP-F). The time pA is shown on top right corner and indicated in hours and minutes, white lines outline the caudal fin. The transcriptional activation of tnfa (green) in recruited macrophage (red, arrowhead) was first observed from 3 hpA. Scale bar = 30 μm. White lines outline the caudal fin. (D, E) Maximum projections of confocal analysis of eGFP-F (green) and mCherryF (red) expressions in recruited macrophages at (D) 18 hpA and (E) 24 hpA in Tg(mpeg1:mCherryF/tnfa:eGFP-F). tnfa⁺mpeg1⁺ macrophages exhibit a round and protrusive morphology, while tnfa⁻mpeg1⁺ macrophages exhibit a dendritic morphology. (F) Velocity of tnfa⁺mpeg1⁺ and tnfa⁻mpeg1⁺ macrophages (N = 18). (G) Frequency of macrophage–macrophage contacts and (H) time length of the contacts of tnfa⁻mpeg1⁺ and tnfa⁺mpeg1⁺ cells. Measurements were extracted from three independent videos of amputated Tg(mpeg1:mCherryF/tnfa:eGFP-F), for contact frequency, N = 15 and for duration of the interaction, N = 11 macrophages. ****p < 0.0001. (I) Representative time-lapse maximum projections show the behaviour of tnfa⁺mpeg1⁺ macrophages, starting 19h20 pA during 42 min. Two macrophages (green + red) interact by cell–cell contact. These macrophages (eGFP in grey) remain attached up to 40 min. Scale bar 20 = μm. (J) Representative time-lapse maximum projections show the behaviour of tnfa⁻mpeg1⁺ macrophages, starting 25h12 pA during 52 min. Macrophages (red) barely establish cell–cell contact. Scale bar = 30 μm. DOI: http://dx.doi.org/10.7554/eLife.07288.004

Figure 2—figure supplement 1.. Activation of tnfa⁺ macrophages in (tnfa:eGFP-F/mpeg1:mCherry-F) transgenic larvae upon E. coli infection.

(A) Diagram showing the site where Crimson E. coli or non-fluorescent E. coli (blue) were injected in the muscle of 3 dpf Tg(mpeg1:mCherryF/tnfa:eGFP-F) larvae. The red dotted box represents the region imaged by confocal microscopy. (B) Tg(mpeg1:mCherryF/tnfa:eGFP-F) larvae were infected with crimson-expressing E. coli (blue) at 3 dpf in the muscle and imaged from 30 min pi to 10 hr 30 min pi every 3 min 30 s. Representative time-lapse maximum projections show the expression of tnfa (green) induced in myeloid-like cells at the infection site from 3 hpA. The time pA is shown on top right corner, scale bar = 25 μm. (C) Maximum projections of confocal analysis of GFP-F (green) and mCherryF (red) expressions in Tg(mpeg1:mCherryF/tnfa:eGFP-F). Larvae were previously infected with E. coli at 3 dpf in the muscle and imaged at 6 hpi. Arrowheads show macrophages expressing tnfa. Scale bar on left panels = 20 μm and on right panels = 10 μm. DOI: http://dx.doi.org/10.7554/eLife.07288.005

Figure 3.. Isolation and molecular characterization of macrophage phenotypes.

(A) Graphed data of representative fluorescence-activated flow cytometry analysis of tnfa⁺ and tnfa⁻ macrophages upon inflammatory stimulations. Tg(mpeg1:mCherryF/tnfa:eGFP-F) larvae were either kept intact (control), or amputated, or injected with PBS or with E. coli at 3 dpf, and cells were collected at 6 hr post-treatment. Red, green, and yellow gates represent mCherry⁺, eGFP⁺, and mCherry⁺eGFP⁺ populations, respectively. (B) Graph represents the kinetic of the frequency of mpeg1⁺tnfa⁺ macrophages in macrophage population (mpeg1⁺) in three independent experiments following stimulation: amputation and E. coli infection (E. coli) at indicated time points. *p < 0.05 vs 3 hpA, mean value of three experiments ±s.e.m. (C) Gating strategy to isolate control cells (mCherry⁻ eGFP⁻, neg), tnfa⁻ macrophages (mCherry⁺ eGFP⁻, mCh⁺), tnfa⁺ macrophages (mCherry⁺eGFP⁺, dbl⁺). (D–H) Relative expression of (D) mpeg1, (E) tnfa, (F) tnfb, il1b, (G) il6, (H) tgfb1, ccr2, and cxcr4b in cells neg, mCh⁺, and dbl⁺. Tg(mpeg1:mCherryF/tnfa:eGFP-F) were amputated at 3 dpf and cells were collected and separated at 6 hpA and 26 hpA. Real-time RT-PCR on separated cells using EF1a as a reference gene. Graph represents the mean value of five independent experiments ±s.e.m. Statistical significance between bars are indicated *p < 0.05, **p < 0.01. DOI: http://dx.doi.org/10.7554/eLife.07288.010

Figure 4.. M1-like macrophages convert their phenotype toward M2-like phenotype in the wounded fin.

(A) Diagram showing the site where caudal fin was transected (dotted red line) in 3 dpf Tg(mpeg1:mCherryF/tnfa:eGFP-F) larvae. The black dotted box represents the region imaged by confocal microscopy. (B) Representative time-lapse maximum projections of 3 dpf Tg(mpeg1:mCherryF/tnfa:eGFP-F) amputated fins showing the fate of tnfa⁺ macrophages (magenta + green) at the indicated times pA (hours:minutes) from 6 hpA to 26 hpA. White lines delimit the caudal fin. Scale bar = 30 μm. (C) Tracking of tnfa⁺ macrophages from 6 to 26 hpA. The distinct colours of the lines correspond to the distinct macrophages that were indicated with an arrowhead in B. (D) Diagram representing macrophage activation and polarization in zebrafish. Unpolarized macrophages (mpeg1⁺) are mobilized and recruited to the wound following fin amputation. They are activated and polarized toward a M1-like phenotype (pro-inflammatory) few hours following fin amputation. After 24 hpA, in response to changes in environmental cues, the same macrophages progressively change their phenotype toward intermediate phenotypes and maybe fully polarized M2-like phenotype (non-inflammatory). Main markers of macrophage subtypes are indicated and resemble those found in human (tnfa/b indicates tumour necrosis factor alpha; il1b, interleukin 1-beta; il6, interleukin 6; tgfb1, tumour growth factor beta 1; ccr2, c–c chemokine receptor type 2; cxcr4b, chemokine (C-X-C motif) receptor 4b). DOI: http://dx.doi.org/10.7554/eLife.07288.011

Figure 4—figure supplement 1.. Recruited macrophages remain in the region of tissue injury at 26 hpA.

(A) Diagram showing the site where caudal fin was transected (dotted red line) in 3 dpf Tg(mpeg1:GAL4/UAS:Kaede) larvae. The black dotted box represents the region imaged by confocal microscopy. (B) Representative maximum projections of confocal analysis of Kaede (green and red) expression in recruited macrophages at 6 hpA in Tg(mpeg1:GAL4/UAS:Kaede) fins. Images were acquired before photoconversion at 6 hpA (left panel), immediately after photoconversion at 6 hpA (middle panel), and at 26 hpA (right panel). The blue dashed boxes represent the region that was scanned using UV laser allowing photoconversion of few macrophages at the wound leaving them with red fluorescence rather than green. Arrowheads show the traced and photoconverted macrophages at 26 hpA and white dotted line outline the amputated fin. (n_cells = 13, n_larvae = 5) Scale bar = 20 μm. DOI: http://dx.doi.org/10.7554/eLife.07288.012

Author response image 1.. GFP-F is expressed in macrophages in Tg(tnfa:eGFP-F).

(A) eGFP-F (Green) and mCherry-F (red) fluorescences were analyzed by confocal microscopy amputated Tg(mpeg1:mCherryF/tnfa:eGFP-F) fins at 18 hpA. Both farnesylated fluorescent proteins are localised to the membrane of macrophages and mainly colocalise with the exception of mCherry-F accumulation in a structure inside the macrophage. Separated and merged channels are shown. (B) High magnification of the region boxed in A. (C) eGFP-F (Green) and nitroreductase fused with mCherry (NTR-mCherry, red) expressions were analyzed by confocalmicroscopy in amputated Tg(mpeg1:GAL4 / UAS:NTR-Cherry/ tnfa:eGFP-F) fins at 6 hpA. The farnesylated form of the eGFP localises to the membrane of macrophages and outlines cytoplasmic NTR-mCherry. Separated and merged channels are shown. (D) High magnification of the region boxed in A. DOI: http://dx.doi.org/10.7554/eLife.07288.017