Neutrophils have been reported to secrete chemokines in response to microbial stimuli [20]. First we determined whether L. major induced the transcription and secretion of DC-attracting chemokines in inflammatory neutrophils. L. major-recruited inflammatory neutrophils were purified by MACS and incubated with L. major and/or with IFNγ, an activator of neutrophils. Sixteen hours later, cells were collected for mRNA analysis, or twenty-four hours later, cell-free supernatant was analyzed for chemokines reported to attract immature DCs. Incubation of C57BL/6 neutrophils with L. major increased both CCL3 transcript levels and protein secretion, while only a very mild effect was seen in response to IFNγ alone (Figure 1A,B). In contrast, incubation of C57BL/6 neutrophils with L. major alone did not induce a significant increase of either CCL4 mRNA or protein, but incubation of neutrophils with IFNγ induced an increase in its mRNA and release (Figure 1A,B). IFNγ and to a lower extent L. major, independently induced CCL5 mRNA, with IFNγ alone inducing the highest release of CCL5. Interestingly, the presence of L. major significantly impaired the IFNγ-induced release of both CCL4 and CCL5 (Figure 1B).

To determine if L. major would induce similar transcription and secretion of DC-attracting chemokines from neutrophils in the L. major-susceptible BALB/c mice, L. major recruited inflammatory BALB/c neutrophils were treated and analyzed as described above. L. major did not induce significant level of chemokine transcription nor elevated release from BALB/c neutrophils (Figure 1A,B). Neither C57BL/6 nor BALB/c neutrophils secreted or transcribed CCL20 in response to L. major, IFNγ or both (data not shown).

The selective secretion of CCL3 by L. major peritoneally-induced inflammatory C57BL/6 but not BALB/c neutrophils (Figure 1) was also measured in inflammatory dermal neutrophils recruited in the ear dermis 24 hours after L. major inoculation (Figure S1).

Altogether, these results show that, once exposed to L. major promastigotes, C57BL/6 neutrophils secrete CCL3 a chemokine known to attract immature DCs, and that the production of chemokines by BALB/c neutrophils is significantly lower in response to the parasite.

We next tested the potential effect of neutrophil supernatant on chemoattraction of immature DCs using Transwell cell migration assays. Bone marrow-derived partially immature C57BL/6 and BALB/c DCs (MHCII^low, CD40⁻, B7.1⁻, B7.2^low) were deposited on the filter of a Transwell migration assay plate, the lower compartment containing the supernatants recovered from C57BL/6 or BALB/c neutrophils exposed or not to L. major. While robust chemo-attractive activity for BM-iDCs was detected in the supernatants of C57BL/6 neutrophils exposed to L. major, no similar strong chemo-attractive activity was detectable in the supernatants of BALB/c neutrophils exposed to L. major (Figure 1C).

To assess if this chemo-attractive activity was due to CCL3 two approaches were selected. First, CCL3 was depleted from supernatant of C57BL/6 mouse neutrophils exposed to L. major, and the CCL3-depleted supernatant monitored for its iDCs chemo-attractive activity, using the Transwell migration assay. Remarkably, a significant decrease of the BM-iDC migration towards the latter supernatant was measured (Figure 1D). Second, supernatants from CCL3^−/− C57BL/6 mouse neutrophils exposed to L. major were similarly tested and shown to display reduced chemo-attractive activity for +/+ BM-iDCs (data not shown).

In contrast, CCL3 depletion of BALB/c supernatants showed only a mild and not statistically significant effect on DC chemoattraction, in line with the low chemokine secretion and chemoattraction of L. major-stimulated BALB/c neutrophil supernatants (Figure 1D).

These results demonstrate that the CCL3 present in the supernatant of C57BL/6 neutrophils exposed to L. major promastigotes is the main chemokine attracting BM-iDCs in vitro.

A significant difference in chemokine secretion was measured in our ex vivo/in vitro analysis between L. major-stimulated C57BL/6 and BALB/c neutrophils, with consequence on the recruitment of iDCs. This prompted us to investigate whether similar differences were observed in vivo. To evaluate how neutrophil and chemokine release influence dendritic cell recruitment in vivo, the model of ear skin explants was used. L. major was delivered intradermally in the ear and at different time points post inoculation, ears were recovered, and further processed as ear explants. This ex vivo approach allows the evaluation of DC recruitment in the skin dermis [21],[22].

C57BL/6 and BALB/c mice were infected i.d. in the ear with L. major, and the number of cells that migrated out of infected ear skin explants was analyzed by FACS and quantified during the first 48 hours following parasite inoculation.

A large number of neutrophils emigrated from the ear explant within hours of parasite inoculation and their number started to decrease 48 hours later (Figure 2A). As previously reported for L. major infected footpads [4],[5], at this early stage post parasite inoculation the neutrophil number did not differ between C57BL/6 and BALB/c mice. We then estimated the number of Langerhans cells (LC) and dermal DC (dDC), defined by FACS analysis by their high surface expression of CD11c, DEC205, and MHC Class II (Figure 2B). Already six hours after infection, the number of LC and dDC migrating out of the ear dermis was significantly higher in C57BL/6 than in BALB/c mice, with the highest difference occurring twenty-four hours post infection (Figure 2A). As monocyte-derived DC (MoDC) play an important role in L. major infection [23], this cell population, characterized as being Ly6G⁻, Ly6C⁺, CD11b⁺ and CD11c^dim (Figure 2B), was also analyzed by FACS. Twenty-four hours post L. major inoculation, a significantly higher number of MoDCs emigrated from C57BL/6 ear explants as compared to BALB/c ear explants (Figure 2A). Most of the DCs emigrating from the ears resulted from the L. major presence, while only a small percentage of DCs emigrated from the ears was due to needle-dependent injury, as illustrated by the low DC recruitment measured when medium alone was injected (Figure S2).

These results reveal a significant difference in DC migration during the first day post infection with L. major between C57BL/6 and BALB/c mice.

In order to further investigate whether the difference in the number of DCs recruited during the first day post L. major inoculation in C57BL/6 and BALB/c mice correlated with their distinct neutrophil functional phenotype, mice of both strains were given i.p. a single injection of the neutrophil-depleting mAb NIMP-R14, and six hours later, L. major promastigotes were i.d. delivered in one of their ears. Twenty-four hours post L. major inoculation, the DC subsets sedimenting out of the ear explants were analyzed by FACS, quantified and compared to the ones sedimenting from ear explants prepared from mice that were given a control mAb. Depletion of neutrophil significantly decreased the number of LC and dDC and abolished the recruitment of MoDC in the ear skin dermis (Figure 3A,B). These results demonstrate an essential role for neutrophils in the early recruitment of DC following inoculation of L. major.

Since neutrophils appeared to be essential for the recruitment of dendritic cells in the first days following infection with L. major and as we have shown in vitro that the CCL3 secreted by neutrophils was critical for the recruitment of DCs, we next sought to document whether this chemokine could play an essential role in vivo.

To this end, the level of chemokine mRNA was measured in L. major infected ears during the first 48 hours post infection. In C57BL/6 infected mice, CCL3 mRNA was strongly induced within 24 hours of L. major inoculation (Figure 4A), while significantly less CCL3 mRNA was induced in L. major infected BALB/c mice. L. major induced only a small increase in CCL4 and CCL5 mRNA at the site of infection (Figure 4A), while infection did not induce CCL20 mRNA (data not shown).

To investigate if neutrophils were responsible for CCL3 transcription at the site of infection in C57BL/6 mice, neutrophils were depleted with an injection of the NIMP-R14 mAb 6 hours prior to infection, and chemokine transcript abundance was measured in infected ears 24 hours post parasite inoculation. In L. major infected mice injected with a control mAb, CCL3 mRNA levels were increased significantly 24 hours after L. major inoculation while in neutrophil-depleted mice, CCL3 mRNA levels were much lower (Figure 4B). Among the three other chemokine transcripts - CCL4, CCL5, and CCL20 – monitored, only the CCL4 followed a transcript profile similar to the CCL3 one though with lower amplitude (Figure 4A). These data demonstrate that twenty-four hours post parasite inoculation in the ear, neutrophils contribute to most of the CCL3 and part of the CCL4 present during the first day of infection.

In order to directly establish that CCL3 acts as a key chemokine accounting for the recruitment of DCs in the L. major-loaded dermis, CCL3 was depleted in mice by treatment with Evasin-1 [24], a highly selective neutralizing chemokine binding protein with high affinity for CCL3 and to weaker affinity for CCL4 [25]. Mice were given Evasin-1 two hours prior to i.d. L. major inoculation in the ear, and DC mobilization in the infected ear explants was quantified as described above. Injection of Evasin-1 had no significant effect on the number of neutrophils that migrated out of ear skin dermis 24 hours after infection (Figure 5A). This allowed the investigation of the role of neutrophils on DC recruitment at the site of infection, under conditions when CCL3 secretion was neutralized. While injection of Evasin-1 into C57BL/6 mice resulted in significant decrease of emigration of both LC/dDC and MoDC from the ear explants, injection of Evasin-1 into BALB/c mice did not result in any similar phenotypic changes (Figure 5A).

To confirm the role of CCL3 in DC recruitment in vivo, C57BL/6 mice or mice genetically deficient in CCL3 (CCL3^−/−) on the C57BL/6 genetic background, were infected with L. major i.d., and emigration from the ear explants assessed as described above. As measured in mice treated with Evasin-1, neutrophil recruitment was not significantly decreased one day post infection. However, recruitment of both LC/dDC, and MoDC was significantly reduced in CCL3^−/− mice (Figure 5B), confirming that CCL3 is a major chemokine involved in LC/dDC migratory properties as well as MoDC recruitment. These results strongly suggest that the CCL3 secreted by neutrophils contributes for a major part to early DC trafficking and/or recruitment in the dermis of L. major inoculated mice.

So far, our data suggest that neutrophils and CCL3 contribute significantly to the early DC trafficking/recruitment to the site of L. major inoculation in C57BL/6 mice. In order to monitor whether neutrophils were indeed the major source of CCL3 that mediates DC recruitment, we transferred either C57BL/6 wild type (WT), or CCL3^−/− neutrophils into CCL3^−/− mice that were given i.d. L. major, and twenty-four hours later, leucocytes emigrating from the ear explants were analyzed by FACS. The number of neutrophils did not differ significantly after injection of WT or CCL3^−/− neutrophils into C57BL/6 and CCL3^−/− mice (Figure 6A). However, injection of WT neutrophils into ears of CCL3^−/− mice strongly increased the number of LC/dDC and MoDC migrating out of the the ear explants, to levels that were comparable to those measured in WT mice injected with WT or CCL3^−/− neutrophils (Figure 6B,C right panels). Even though injection of CCL3^−/− neutrophils into CCL3^−/− mice also increased the number of LC/dDC and MoDCs, the levels attained were significantly lower than those obtained when CCL3^−/− mice were injected with WT neutrophils. These results demonstrate that the CCL3 secreted by neutrophils plays an important role in the early trafficking/recruitment of DCs cells to the site of infection during the first days of L. major infection.

To investigate the role of CCL3 in the onset of the immune response in C57BL/6 mice, CCL3 was inhibited during the first five days post L. major inoculation by daily administration of Evasin-1. Fifteen and forty days post infection, the development of T helper immune response was assessed. L. major-specific IFNγ and IL-4 cytokine production was measured in draining lymph node CD4⁺ T cells, and immunoglobulin isotype switching was measured in the serum. Fifteen days post infection the transient depletion of CCL3 resulted in almost total abolition of IFNγ secretion, but no significant difference in IL-4 levels (Figure 7A). The low IFNγ levels correlated with a significant decrease of L. major-specific IgG2a and a milder but not statistically significant increase in IgG1 serum levels in Evasin-1 treated mice (Figure 7C). Low IFNγ secretion was also measured fifteen days post L. major inoculation in CCL3^−/− mice (Figure 7A and 7C), in line with results from a previously published study [26], but IgG2a levels did not differ significantly from C57BL/6 controls, while IgG1 levels were slightly increased (Figure 7C). Of note, very low levels (<100pg/ml) of IL-13 and IL-17 were measured in supernatant of L. major-restimulated CD4⁺ T cells, with no difference between the groups (data not shown).

Six weeks post L. major inoculation, high levels of IFNγ with correspondingly high levels of L. major-specific IgG2a, and low levels of IL-4 and IgG1 characteristic of a Th1 immune response were measured, with no statistically significant difference being noted between the groups (Figure 7B, 7D). Mice treated with Evasin-1 developed slightly larger lesion than control mice but smaller lesions than CCL3^−/− mice, with no statistically significant difference (Figure 7E). In contrast, development of lesion was markedly increased in CCL3^−/− mice compared to C57BL/6 controls, and CCL3^−/− mice harboured higher parasite load within their lesions, with a significant difference compared to Evasin-1 treated or control mice (Figure 7G).

Female BALB/c and C57BL/6 mice were purchased from Harlan Olac Ltd. (Bicester, UK). CCL3^−/− mice were purchased from Jackson laboratory (Bar Harbor,USA). All mice were bred in the pathogen-free facility at the BIL Epalinges Center and used at 6 week of age. L. major (LV 39 MRHO/Sv/59/P strain) were maintained and grown as previously described [2]. All animal experimental protocols were approved by the veterinary office regulations of the State of Vaud, Switzerland, authorization 1266.3 to FTC, and experiments were performed adhering to protocols created by this office.

Mouse inflammatory neutrophils collected by peritoneal lavage 4 hours post infection i.p. of 5.10⁷ stationary phase L. major, were isolated and purified using MACS-positive selection as previously described [9]. Purity of neutrophils was >98% as assessed by FACS and Diff-Quick (Dade Behring) staining of cytospins. Each experiment was validated using FACS sorted neutrophils positively gated through 1A8 labeling and negatively gated with a cocktail of mAbs (against CD3, CD49b, B220, F4/80, and CD11c, see below).

Neutrophils were cultured in RPMI-1640 media supplemented with 10% FCS and antibiotics (2.5×10⁶ cells/ml) in the presence or absence of L. major metacyclic promastigotes (at a 5∶1 parasite∶cell ratio). The protease inhibitor aprotinin (0.4 µg/ml, Sigma Chemical Co., St. Louis, MO, USA) was added to the culture to facilitate cytokine detection. Chemokine concentration in the culture supernatant was quantified by ELISA using kits from R&D systems.

Inflammatory neutrophils cultured in vitro under different conditions were harvested, mRNA extracted, cDNA synthesized and quantitative RT-PCR performed as previously described with a LightCycler system (Roche) [9]. Each cytokine transcript was normalized to the value of the hypoxanthine phosphoribosyltransferase endogenous control, represented as arbitrary values. The primers for the real time PCR were the following: CCL3: F 5′ CCA AGT CTT CTC AGC GCC AT 3′, R 5′ TCC GGC TGT AGG AGA AGC AG 3′, CCL4: F 5′ TCT TGC TCG TGG CTG CCT 3′, R 5′ GGG AGG GTC AGA GCC CA 3′, CCL5 [39], CCL20 F5′ CTT GCT TTG GCA TGG GTA CT 3′, R 5′ GTC TGT ATG TAC GAG AGG CA 3′.

CCL3 depletion in neutrophil supernatants. Neutrophil supernatant were placed on a plate coated with antibody from the CCL3 ELISA kit (R&D systems). Depletion in supernatant was checked by ELISA. For in vivo depletion, mice were treated with Evasin-1, a CCL3 blocking protein, engineered by Merck-Serono [24]. 10 µg of Evasin-1 were injected intraperitoneally 2h before injection of the parasite. As controls, mice were injected with a similar regimen of PBS.

Bone-marrow cells were cultured in RPMI-1640 media supplemented with 10% FCS, antibiotics and 30% GM-CSF for 6 days, as previously described [40]. At day 6, the maturation of DCs was checked by FACS, measuring the levels of MHC ClassII, CD40, B7-1 and B7-2 surface molecules.

Supernatant from neutrophils cultured under different conditions were placed in the lower compartment of a transwell plate (96 well plate, 3.2mm diameter 5um pore size, ChemoTx System, NeuroProbe, UK). 10⁵ DCs were put on top of the filter. After 2h of incubation at 37°C, the number of DCs that migrate towards the supernatant were counted on Neubauer chambers using trypan blue.

Mice were given i.p. -6h before L. major inoculation 250 µg of the NIMP-R14 mAb, a rat IgG2b mAb that selectively binds to mouse neutrophils [41]. This treatment was previously reported to deplete selectively neutrophils for three days [8]. As controls, mice were given i.p. the RR3-16 mAb against the Vα3.2 chain of the T-cell receptor (RR3-16, gift of R. MacDonald, Ludwig Institute for Cancer Research, Epalinges, Switzerland).

Mice were given intradermally into ear PBS or 10⁶ stationary phase L. major promastigotes. Six, 24, 48h post L. major inoculation mice were sacrificed, the ventral and dorsal sheets of the ear were separated with forceps, the two leaflets being transferred dermal side down in a plate containing RPMI-1640 media supplemented with 10% FCS and antibiotics at 37°C. The leukocyte populations emigrating spontaneously over 14 hours from the ear explants were then counted and stained for a FACS analysis [22]. In selected experiments, dorsal and ventral sheets of the ears were separated and the dermal side was digested with 0.1 mg/ml of Liberase TL (Roche) for 2h at 37°C. Ears from 7 mice were pooled, cut into pieces and filtered through a 40 µm filter, washed and processed for FACS sorting. Sorted neutrophils were further incubated in RPMI medium for 24 hours. Chemokine presence in neutrophil-free supernatant was then analyzed by ELISA.

Leukocytes emigrating from the ear explants were processed for cell surface staining. The mAb 24G2 was used to block FcRs. For analysis of cell populations several mAbs were used: PE conjugated anti-LY6G (clone 1A8), anti-CD3 (clone G4.18), anti-CD49b (clone DX5), anti-MHCII (clone M5/114.15.2), Cyc conjugated-strepatvidin, PE conjugated, APC and Cyc conjugated anti-CD11c (clone N418), FITC conjugated anti-LY6-C (clone AL-21), Cyc conjugated anti-CD11b (clone M1/70), all mAbs from e-bioscience, SanDiego, CA, US; anti-DEC205 (clone NLDC-145, AbB Serotec,UK, Ldt). Biotinilated anti-F4/80 (clone C1∶A3-1,CEDRALANE, Canada). Cells were analyzed with a FACScan (3 colors) or FACSCalibur (4 colors) (BD Biosciences, Mountain View, CA, USA) and analyzed with the program FlowJo (Tree Star. Inc., Ashland, OR, USA).

Four hours post i.p. inoculation of L. major peritoneal lavage neutrophils were purified by MACS. 10⁶ C57BL/6 or CCL3^−/− neutrophils were co-injected in the ear dermis with 10⁶ stationary phase L. major promastigotes. Twenty-four hours later, mice were sacrified, ears were processed as above and emigrating cell populations analyzed by FACS.

3×10⁶ L. major were inoculated in the footpad of either CCL3^−/− mice or +/+ mice in which CCL3 was blocked during the first five days of infection by daily injection of Evasin-1. Mice were sacrificed 15 and 40 days post- L. major inoculation in the footpad. Draining lymph node CD4⁺ T cells were isolated by MACS (Miltenyi Biotec), and cultured in the presence of irradiated C57BL/6 splenocytes ± UV-irradiated L. major promastigotes. Cytokine levels were measured by ELISA. Sera obtained at different time points post L. major inoculation were tested for L. major-binding IgG1 and IgG2a, and parasite burden was determined by limiting dilution assay as previously described [42].

Data were analysed using the Student's t-test for unpaired data.