C57BL/6J mice were obtained from Charles River. TLR3 knockout mice were a kind gift from Dr. Monique Lafon (Institut Pasteur, France) and have been described in [1]. PD-L1 knockout mice were obtained from Dr. Heinz Wiendl (University of Münster). OT-1 RAG-KO and Ubi-GFP OT1 mice were bred in the Institut Curie animal facility. Ubi-GFP OT1 cells were derived by crossing OT-1 RAG1-KO transgenic mice to Ubi-GFP mice expressing the GFP protein under the control of the ubiquitin C promoter. Bone marrow-derived DCs (BMDCs) were obtained by differentiating bone marrows with granulocyte/macrophage colony-stimulating factor (40 ng/mL)–containing medium (IMDM with 10% heat-inactivated serum, penicillin/streptomycin, 2mM L-glutamine, 50μM ß-mercaptoethanol) during 10 days. Supernatant from J558 plasmacytoma cells was used as GM-CSF source. B3Z cells specific for the SIINFEKL (OVA257–264/Kb) peptide of OVA that express β-galactosidase under the control of the IL-2 promoter were used for the cross-presentation assay. The present experiments, which used mouse strains exhibiting non-harmful phenotypes, did not require a project authorization and benefited from guidance of the Animal Welfare Body, Research Centre, Institut Curie. No specific approval was obtained from the animal welfare body for this research. Mice were sacrificed by cervical dislocation. All animal procedures and breeding were in accordance with the guidelines and regulations of the French Veterinary Department. The mice were bred and housed in an accredited animal facility (C75-05-18).

Low molecular weight polyI:C (referred to as polyI:C, 0.2-1kb in size) was obtained from Invivogen. LPS (from Salmonella enterica enterica, serovar Typhimurium) and celastrol were from Sigma-Aldrich. Anti-PD-L1 antibody (clone 10F.9G2) and the rat isotype control antibody were from BioXcell and used for blocking experiments at 20 μg/mL. Fluorochrome-labelled antibodies to PD-L1 (clone MIH5), PD-1 (clone J43), CD86 (clone GL1), CD40 (clone HM40-3), H2K^b (clone AF6-88.5), CD80 (clone 16-10A1), CD40L (clone MR1) and the isotype controls were from BD bioscience. Mouse recombinant CD40L-Fc chimera was from R&D systems.

Amine-modified polystyrene beads (Polysciences) were pre-activated with 8% (vol/vol) glutaraldehyde for 3 h at room temperature. Beads were incubated with 20 mg/mL OVA or BSA to different percentages of OVA (Worthington Biochemicals) (100%, 50%, 25% or 0% OVA) on a rotating wheel overnight at 4°C. The next day, the beads were quenched in PBS containing 0.5 M glycine for 30 min before assays with cells. DCs were incubated with bead-bound OVA for 3 h and washed twice with PBS 2% BSA. B3Z cells were added at a 1:1 ratio to the DCs and incubated for 16 h. Beta-galactosidase activity was measured using a chemiluminescent 1,2-dioxetane substrate (Applied Biosystems).

Cytometric analysis of OVA-degradation in the phagosome has been described in detail elsewhere [24]. Briefly, beads were prepared as above with 100% OVA coating. DCs were pulsed with the bead-bound OVA for 30 min at 18°C, washed in ice cold PBS. Fetal calf serum (FCS) flotation was performed 3 times by overlaying the cells on 3 mL of fetal calf serum and centrifuging at 900rpm to remove non-internalised beads. Cells were chased at 37°C in CO2-independent medium for the 30, 60, 90 or 120 min, resuspended in homogenization buffer (8% sucrose in PBS, 3 mM imidazole, 1 mM dithiothreitol) and disrupted mechanically with 2 mL syringes and 22-gauge needles (Terumo Medical). After centrifugation, the post-nuclear supernatant was transferred to 96-well conical microplates followed by labelling on ice with a rabbit polyclonal antibody against OVA (Sigma) and an Alexa647-labelled secondary antibody and analysed using a FACSCalibur flow cytometer.

DCs (10⁵) were activated with polyI:C (25 μg/mL unless indicated otherwise) or LPS (10 ng/mL unless indicated otherwise) for 20 hours and then washed 3 times with PBS 0.2% BSA. They were incubated with different concentrations of soluble OVA peptide (SIINFEKL) diluted in PBS 0.2% BSA for 3 h at 37°C followed by 3 washes with PBS 0.2% BSA. When antibody blocking was performed, the isotype control or anti-PD-L1 antibodies were added at 20 μg/mL for 1 hour on ice. The cells were washed 3 times with PBS 0.2% BSA before adding 10⁵ CFSE-labelled OT-1 splenocytes prepared by staining with 10μM CFSE (Invitrogen) for 10 min. Three days after co-culture, the number of total CFSE high and low-positive cells were counted with the help of 10μm counting beads (Biovalley) using an Accuri flow cytometer.

Soluble cytokines were measured in the supernatant of DCs activated with polyI:C (25 μg/mL) or LPS (10 ng/mL) for 20 h using a bead-based immunoassay (Flowcytomix technology, eBioscience). Fluorescence was read using an LSRII flow cytometer (BD Bioscience). IFNα and IFNβ were dosed using the ELISA kits from PBL interferon source.

DCs were plated on glass coverslips in a 24 well plate and activated with nothing, polyI:C (25 μg/mL) or LPS (10 ng/mL). After 16 hrs, recombinant CD40L-Fc chimera (500 ng/mL) was added to the cells for different periods of time. The cells were then fixed with 4% paraformaldehyde for 20 min and stained for PD-L1 in PBS containing 0.5% saponin and 2% BSA. Coverslips were mounted in mounting medium containing DAPI and samples were imaged on a Nikon Ti Inverted Microscope fitted with a confocal A1R system, using a 60x oil immersion objective with a numerical aperture of 1.4.

On day 10 of culture, DCs from C57BL/6 and PDL-1 KO mice were seeded at 2.10⁵ cells/mL and activated with nothing, polyI:C (25 μg/mL) or LPS (10 ng/mL. On day 11, DCs were loaded with 4 pg/mL of SIINFEKL peptide for 3 h. Splenic Ubi-GFP OT-I CD8⁺ T cells, pre-activated for 48 h with coated anti-CD3 antibody (10 μg/mL) and soluble anti-CD28 antibody (1 μg/mL), were added to a DC:T cell ratio of 1:5 or 1:10. Imaging was started immediately, and images were acquired every minute for 12 h, 4 fields per condition. Imaging was performed on an epifluorescence video-microscope Nikon TiE, equipped with a cooled CCD camera (HQ2, Photometrics), a 10X objective, and an environmental chamber controlled for temperature, humidity and CO₂. Contact times were manually measured using ImageJ software. All T cells present in the fields at 30 min after the beginning of the recording were considered and tracked for the measurement of the contact times with DCs. Since a lot of contacts were longer than the duration of the recording we first analysed the percentage of long contacts (>600 min) as compared to shorter ones (<600 mins). Z-test was used to compute the significance of the differences between all conditions.

All statistical analysis was performed using a two-way ANOVA test followed by Bonferroni or Tukey posttests to determine significance between treatments in Graphpad (Prism).

Conventional high molecular weight polyI:C not only triggers TLR3 but also MDA-5 signalling, a cytosolic RNA sensor [25], in bone marrow-derived DCs. To selectively analyse the effect of TLR3 signalling in the ability of DCs to cross-present antigen, we checked that low molecular weight polyI:C induced signalling only through TLR3 in our setting (S1 Fig), and used it throughout the study.

In order to cross-present antigen, DCs uptake proteins into the endocytic pathway where they sample the antigen upon degradation to present MHC class I-loaded peptides to T cells. In order to address the effect of polyI:C on the cross-presentation pathway, we first exposed DCs for 20 h to polyI:C and analysed the capacity of DCs to degrade beads-associated OVA. We found that polyI:C treatment did not affect the ability of DCs to degrade bead-associated OVA (Fig 1A) suggesting that the antigen processing machinery was not affected. However, the ability of polyI:C-matured DCs to cross-present bead-bound OVA to B3Z, an OVA-specific CD8⁺ T cell clone, was significantly reduced upon pre-treatment with polyI:C in a dose-dependent manner (Fig 1B). Surprisingly, we found that the presentation of the soluble OVA peptide was also diminished (Fig 1C) although MHC class I, and the co-stimulation markers CD86, CD80 and CD40 levels increased on the DC surface (S2 Fig). The lower T cell proliferation in response to the soluble OVA peptide, that does not need internalisation or processing to be presented, suggested a second mechanism independent of antigen processing that lowered the ability of DCs to present antigen to B3Z CD8⁺ T cells.

To extend our findings to primary T cells, we performed similar experiments with primary naive OT1 CD8⁺ T cells. Pre-treatment of DCs with polyI:C marginally increased the ability of DCs (loaded with increasing doses of peptide) to induce OT1 T cell proliferation as compared to non-treated DCs (Fig 2A). Moreover, increasing doses of polyI:C did not significantly increase T cell proliferation though the expression of co-stimulatory molecules and MHC I showed a polyI:C dose-dependent increase on the cell surface (S2 Fig). In contrast, LPS pre-treated DCs induced an important LPS dose-dependent increase in OT1 T cell proliferation (Fig 2B). Phenotypic analysis of the OT1 response indicated that polyI:C-matured DCs induced lower frequencies of IFNγ and granzyme B-secreting CD8⁺ T cells than LPS-matured DCs (Fig 2C). The observation that increasing doses of polyI:C was unable to induce higher OT1 T cell proliferation suggested that an active mechanism was in play to restrict T cell responses.

During activation, DCs up-regulate inhibitory molecules such as PD-L1 that can bind PD-1 on activated T cells and inhibit T cell activation through its ITIM motif [26]. PolyI:C and LPS treatments induced an increase in both intracellular and extracellular levels of PD-L1 with polyI:C inducing slight but consistently higher levels than LPS (Fig 3A). OT1 T cells co-cultured with polyI:C and LPS-matured DCs loaded with peptide also increased the expression of surface PD-1 in a peptide dose-dependent manner with a peak at 2 days after co-culture (Fig 3B). Importantly, there was no significant difference in the levels of PD-1 on T cells co-cultured with polyI:C and LPS pre-treated DCs (Fig 3B). Blockade of PD-L1 using anti-PD-L1 blocking antibodies increased T cell proliferation when DCs were not matured or matured with polyI:C (Fig 3C). Interestingly, no effect of PD-L1 blockade on T cell proliferation was observed when T cells were co-cultured with LPS-matured DCs even at low peptide concentrations (Fig 3C). This selective effect of PD-L1 on T cell proliferation restricted to DCs matured with polyI:C and not LPS was even more pronounced when we used DCs from PD-L1-deficient mice (Fig 3D). These results suggest that the low T cell proliferation observed upon polyI:C-induced maturation of DCs is, in part, due to the expression of PD-L1 on DCs.

The unexpected observation that T cell proliferation induced by polyI:C-, but not LPS-treated DCs, was susceptible to PD-L1 blockade led us to question whether PD-L1 itself was regulated differently between the two DC populations. Indeed, in the absence of T cells, PD-L1 expression on the DCs were comparable between both treatments. We questioned whether the presence of a T cell-dependent signal would modulate this PD-L1 surface expression. The interaction of CD40L on T cells with CD40 on DCs is required to induce complete DC maturation and T cell proliferation [27]. We found that CD40L on OT1 T cells increased progressively upon co-culture with peptide-loaded DCs pre-treated or not with polyI:C or LPS (S3A Fig). Expression of CD40L on T cells followed a similar kinetic to PD-1 expression on T cells with a peak at 2 days after T-DC co-culture (compare S3A Fig and Fig 3B).

In order to monitor PD-L1 trafficking alone and simplify the system, we replaced the CD40L-derived signals received from the T cell upon T-DC interactions with recombinant CD40L (rCD40L). Confocal analysis on fixed and permabilised cells showed that most of the PD-L1 is present intracellulary in control DCs with no TLR stimuli and rCD40L treatment did not significantly alter this distribution (Fig 4A). In contrast, DCs pre-treated with polyI:C but not LPS significantly increased cell surface PD-L1 after 90 min treatment with rCD40L (Fig 4A). Quantification by FACS revealed that PD-L1 surface levels of polyI:C pre-treated (but not LPS) DCs increased as early as 15 min after addition of rCD40L and peaked at 60 min suggesting together with the confocal images that this rapid cell surface increase may result from trafficking from intracellular stores rather than from a transcriptional up-regulation (Fig 4B, left panel). Of note, CD86 expression remained unchanged in control and LPS-treated DCs upon rCD40L treatment whereas it was only slightly modulated in polyI:C-treated DCs as compared to PD-L1 (Fig 4B, right panel). No prominent difference in PD-L1 location was observed upon CD40L treatment in LPS-matured DCs (Fig 4A) although CD40 expression was consistently and homogenously higher in LPS-treated DCs as compared to polyI:C treatment (S3B Fig) indicating that the CD40L-induced increase of surface PD-L1 was specific to polyI:C-treated DCs. This increase in cell surface PD-L1 was dependent on CD40 signalling since celastrol, an inhibitor for the NF-kB signalling cascade downstream of CD40, inhibited the rCD40L-induced PD-L1 trafficking in polyI:C-treated DCs while basal PD-L1 surface levels were unaffected (Fig 4C, left panel). Of note, celastrol treatment reduced basal CD86 expression but there was no effect on CD86 expression upon CD40L treatment (Fig 4C, right panel). These results indicate that PD-L1 trafficking to the cell surface upon CD40 signalling is selectively modulated in polyI:C pre-treated DCs in an NF-kB dependent manner.

Previous studies have suggested that cell surface expression of PD-1 limits the time of contact of T cells with DCs [28, 29]. Indeed, blocking of the PD-1-PD-L1 interaction between activated or tolerized T cells and PD-L1 expressing APCs leads to longer arrest of T cells on APCs and a better effector response. We thus investigated whether the low T cell response observed with polyI:C-treated DCs was due to the lack of stable DC-T cell contacts. PD-1 and CD40L surface expression were concomitantly increased on OT1 T cells when activated with anti-CD3 and CD28 Abs with a peak at day 2 after activation (Fig 5A). To measure the DC-T contact times in the various conditions, we performed 12 h imaging of co-cultures between Ubi-GFP OT1 T cells activated for 2 days (thus PD-1⁺CD40L⁺) and untreated, polyI:C- or LPS-treated DCs that were peptide-loaded. Analysis of the movies revealed that more than 60% of the observed contacts were longer than the duration of the recording as expected in such strong stimulation conditions. However, the proportion of contacts measured that were shorter than 600 min significantly changed between the different conditions (Fig 5B). The cumulative distributions of the measured contact times indicate that the changes in contact time can be attributed to the duration of contacts of the whole population (Fig 5C). The proportion of shorter contacts significantly increased from 23% in non-treated DCs to 38% in polyI:C-treated DCs, while it was reduced to 9% in LPS-treated DCs. This suggests that TLR3 signalling in DCs leads to the reduction of contact times with specific T cells, while TLR4 signalling extends the duration of the contacts allowing for better T cell activation (see Fig 2B). Conversely, the absence of PD-L1 on the DCs lowered the percentage of cells forming shorter contacts between T cells and DCs in all conditions. In polyI:C-treated DCs the proportion strongly decreased from 38% to 12% whereas the reduction was moderate in LPS-treated DCs although not statistically significant. Thus, presence of PD-L1 on polyI:C-treated DCs strongly impacts on DC-T cell contact duration and correlates with T cell activation. These observations are in line with the absence of a PD-L1-dependent regulation of T cell proliferation in LPS-treated DCs suggesting again that the regulation of PD-L1 expression and function in LPS- and polyI:C-treated DCs are distinct. We conclude that expression of PD-L1 at the surface of polyI:C-treated DCs is responsible for shortening the contact time with specific activated T cells.