CD8+ T Cell Fate and Function Influenced by Antigen-Specific Virus-Like Nanoparticles Co-Expressing Membrane Tethered IL-2

Abstract

A variety of adjuvants fostering humoral immunity are known as of today. However, there is a lack of adjuvants or adjuvant strategies, which directly target T cellular effector functions and memory. We here determined whether systemically toxic cytokines such as IL-2 can be restricted to the site of antigen presentation and used as 'natural adjuvants'. Therefore, we devised antigen-presenting virus-like nanoparticles (VNP) co-expressing IL-2 attached to different membrane-anchors and assessed their potency to modulate CD8+ T cell responses in vitro and in vivo. Efficient targeting of IL-2 to lipid rafts and ultimately VNP was achieved by fusing IL-2 at its C-terminus to a minimal glycosylphosphatidylinositol (GPI)-anchor acceptor sequence. To identify optimal membrane-anchor dimensions we inserted one (1Ig), two (2Ig) or four (4Ig) immunoglobulin(Ig)-like domains of CD16b between IL-2 and the minimal GPI-anchor acceptor sequence of CD16b (GPI). We found that the 2IgGPI version was superior to all other evaluated IL-2 variants (IL-2v) in terms of its i) degree of targeting to lipid rafts and to the VNP surface, ii) biological activity, iii) co-stimulation of cognate T cells in the absence of bystander activation and iv) potency to induce differentiation and acquisition of CD8+ T cell effector functions in vitro and in vivo. In contrast, the GPI version rather favored memory precursor cell formation. These results exemplify novel beneficial features of membrane-bound IL-2, which in addition to its mere T cell stimulatory capacity include the induction of differential effector and memory functions in CD8+ T lymphocytes.

Fig 1. Expression and targeting of IL-2 fused to different membrane anchors of CD16b.

(A) Surface expression levels of IL-2 fused to different membrane anchors on HEK-293 cells. HEK-293 producer cells were transfected with indicated plasmids and stained with IL-2-specific (black line) or non-binding control mAb (grey histograms), followed by flow cytometric analysis. Numbers indicate percent positive cells. (B) Percentage of IL-2 positive HEK-293 cells upon transfection with the indicated constructs. (C and D) Expression of IL-2v in HEK-293 producer cells and corresponding VNP preparations as detected with IL-2-specific antiserum. Anti-Gag was used as loading control. Bottom panels show quantification of band intensities (Image J 1.48 software) normalized to values obtained from whole cell lysates of IL-2::GPI transfectants and corresponding VNP. (E) Relative amounts of IL-2 targeted to VNP compared to IL-2::GPI VNP. (F) GPI-anchor attachment targets IL-2 into lipid rafts of HEK-293 cells. Triton X-100 lysates of HEK-293 cells were resolved by 5 to 40% sucrose gradients into nine fractions (top to bottom), subjected to SDS-PAGE, blotted and probed (IB) with IL-2-specific antiserum, CD59 (lipid raft targeting control) and CD147 (non-lipid raft targeting control) mAb. (G) Dot-blot analyses of relative amounts of particles secreted by HEK-293 producer cells transfected with indicated constructs using p30Gag immunoblotting (IB). Data are representative (A, C, D, F) or show the summary (B, E, G) of three (except six for IL-2::GPI and IL-2::1IgGPI) (A to D), four (E, G) and two (F) independent experiments. * p < 0.05, ***, p < 0.001; Kruskal-Wallis test and Mann-Whitney-U-test followed by post hoc Bonferroni correction (B), ANOVA and Tukey’s multiple comparison test (G).

Fig 2. Scheme and functional evaluation of IL-2v.

(A) Scheme of mutations introduced into IL-2v. IL-2 loss-of-function mutation (black asterisk), IgG-binding mutant (white asterisk). (B) Biological activity of IL-2v. IL-2 dependent HT-2 cells were incubated with titrated amounts of VNP decorated with either IL-2::GPI, IL-2::2IgGPI or their p.C72A mutated relatives IL-2(A)::GPI, IL-2::2Ig(F)GPI and IL-2(A)::2Ig(F)GPI, or alternatively recombinant IL-2 and analyzed for proliferation. ED₅₀ values for IL-2::GPI (dashed black line), IL-2::2IgGPI (dashed red line), IL-2::2Ig(F)GPI (dashed blue line) decorated VNP are indicated. (C) Amounts of particles required to induce half maximal proliferation rates in HT-2 cells. (D) Flow cytometry analysis of IgG binding to HEK-293 cells transfected with indicated constructs. Figure shows percent reduction of Ig binding compared to unmodified molecules. Data are representative (B) or show the summary (C, D) of eleven (IL-2::GPI), seven (IL-2::2IgGPI) and six (IL-2::2Ig(F)GPI, IL-2(A)::GPI, IL-2(A)::2Ig(F)GPI and recombinant IL-2) (B), eleven (IL-2::GPI), seven (IL-2::2IgGPI) and six (IL-2::2Ig(F)GPI) (C) and five (except four IL-2(A)::2Ig(F)GPI) (D) independent experiments. * p < 0.05, **, p < 0.01, ***, p < 0.001; ANOVA and Tukey’s multiple comparison test (C) and Kruskal-Wallis test and Mann-Whitney U-test followed by post hoc Bonferroni correction (D).

Fig 3. Differential activation of CD8⁺ T cells by IL-2v decorated VNP.

(A) Flow cytometry analysis of CD69 and TCR expression on P14 TCR transgenic splenocytes. Cells were either left untreated (grey shaded histograms), or stimulated (black line) with IL-2v asVNP or alternatively with αCD3/αCD28 coated microbeads supplemented with 10 or 100 U/ml IL-2 for 18 hours. Percentages of CD69^high and TCR^low cells are shown. (B and C) Flow cytometry analysis of CD25 expression on CD8⁺ T cells. Purified P14 CD8⁺ T cells were stimulated for the indicated number of days with IL-2v asVNP, or αCD3/αCD28 coated microbeads supplemented with 10 or 100 U/ml IL-2, as indicated or were left untreated. (B) CD25 expression on CD8⁺ T cells co-cultured with IL-2v asVNP for three days. Numbers indicate MFI of CD25⁺ cells. (C) Kinetics of CD25 expression on CD8⁺ T cells stimulated with indicated asVNP, ansVNP, or αCD3/αCD28 coated microbeads supplemented with 10 or 100 U/ml IL-2. (D) Proliferation of CD8⁺ T cells upon incubation with IL-2v asVNP, ansVNP, medium or PMA/ionomycin. (E) Absolute numbers of viable P14 CD8⁺ T cells after 5 days of co-culture with IL-2v asVNP or αCD3/αCD28 coated microbeads supplemented with IL-2. Data are representative (A, B) or show the summary (C-E) of four (except two for αCD3/αCD28) (A), five (except three for ansVNP) (B), at least three (C), nine (except five for ansVNP and two αCD3/αCD28 microbeads) (D) and seven (except four for αCD3/αCD28 microbeads) (E) independent experiments. * p < 0.05, **, p < 0.01, ***, p < 0.001; t-test comparing IL-2::GPI with IL-2::2Ig(F)GPI asVNP (C), Kruskal-Wallis test and Mann-Whitney U-test followed by post hoc Bonferroni correction (D) ANOVA and Tukey’s multiple comparison test (E).

Fig 4. Strong CD8⁺ T cell effector functions induced by IL-2::2Ig(F)GPI asVNP.

(A) Flow cytometry analysis showing proliferation and intracellular IFN-γ-expression of CFSE-labeled CD8⁺ TCR Vα2⁺ T-cells. Markers set according to negative stainings and no-stimulation control. Numbers indicate percentage of cells in respective quadrants. (B) Flow cytometry analysis, (C) percentage and (D) fold-induction of IFN-γ producing CD8⁺ T cells in the absence or presence of indicated stimuli. (E) Amounts of IFN-γ (pg/ml) secreted upon co-culture of CD8⁺ T cells with indicated IL-2v asVNP or αCD3/αCD28 coated microbeads plus IL-2 (10 or 100 U/ml). (F-H) IL-2::2Ig(F)GPI asVNP increase the cytotoxic potential of antigen-specific T cells. P14 splenocytes were stimulated with IL-2v asVNP for 48 hours or left untreated and were subsequently co-cultured with 1x10⁴ wt (CPD^bright) or LCMV-GP expressing (CPD^dim) EL-4 target cells. Specific target cell lysis was analyzed after 20 hours by flow cytometry. (F) Flow cytometry analysis showing specific lysis of LCMV-GP⁺ but not wt target cells at an effector/target ratio of 10. (G) Quantification by flow cytometric analysis of specific target cell lysis relative to maximum lysis (LCMV-GP_33-41 stimulated effector cells, E:T ratio 20:1). (H) Determination of cytotoxic potential in ⁵¹Cr-release assays of P14 splenocytes, which were stimulated with IL-2v asVNP or left untreated for 48 hours. Effector cells were co-cultured with ⁵¹Cr-labelled wildtype or LCMV-GP-expressing EL-4 target cells (1x10⁴) and specific lysis was analyzed. Data are representative (A, B, F, H) or show the summary (C, D, E, G) of three (A, B, F, G), five (except three for αCD3/αCD28 microbeads) (C, D), four (except two for 48 and 72 hrs) (E) and triplicates of one (H) independent experiments. * p < 0.05, **, p < 0.01, ***, p < 0.001; ANOVA and Tukey’s multiple comparison test (C, D), Kruskal-Wallis test and Mann-Whitney U-test and Bonferroni correction (E), t-test comparing IL-2::GPI with IL-2::2Ig(F)GPI asVNP (G, H).

Fig 5. Acquisition of memory-like functions by CD8⁺ T cells is supported by IL-2 decorated asVNP.

(A) Re-expression kinetics of CD127 on IL-2v asVNP stimulated purified P14 CD8⁺ TCR Vα2⁺ T cells. Mean fluorescence intensity of CD127 expression on CD8⁺ T cells at indicated time points after stimulation with IL-2::GPI, IL-2::2Ig(F)GPI asVNP or αCD3/αCD28 microbeads plus 100 U/ml IL-2. Bottom panel indicates absolute CD127⁺ cell numbers obtained at day 7. (B) Percentage and (C) absolute numbers of viable (propidium iodide negative) CD8⁺ T cells upon VNP-mediated primary stimulation for 7 days followed by removal of particles and a 4-day culture ±IL-7 (125 U/ml). n.d, not determinable (T cells did not survive day 7 of primary culture). (D) Flow cytometry analysis showing memory and activation phenotype of naïve (shaded grey histograms) and IL-2v asVNP or αCD3/αCD28 microbeads plus 100 U/ml IL-2 activated cells (black line). (E) Absolute numbers of viable CD8⁺CD25⁺CD62L^low and CD8⁺CD25⁺CD62L^high cells after 11 days of culture (co-culture and resting phase). n.d, not determinable (T cells did not survive day 7 of primary culture). (F—H) Secondary responses of CD8⁺ T cells upon pre-stimulation with IL-2v. Viable cells (1x10⁴) pre-stimulated as indicated were re-stimulated with LCMV-GP_33-41 peptide pulsed or non-pulsed irradiated splenocytes. Freshly isolated CD8⁺ T cells served as control. (F) Proliferation was determined by [³H]-thymidine incorporation after 48 hours of stimulation. Freshly purified CD8⁺ T cells served as control. Secreted (G) IL-2 and (H) IFN-γ levels in supernatants of CD8⁺ T cells during secondary responses. Data are representative (D) or show the summary (A, B, C, E-H) of three (except two for αCD3/αCD28 microbeads plus IL-2) (A), five (except three for αCD3/αCD28 microbeads plus IL-2) (B, C), three (D-H) independent experiments. * p < 0.05, **, p < 0.01, ***, p < 0.001; t-test (A, E), ANOVA and Tukey’s multiple comparison test (B, F-H), Kruskal-Wallis test and Mann-Whitney U-test and Bonferroni correction (C).

Fig 6. Induction of effector functions and memory phenotypes by IL-2v asVNP.

Enhanced in vivo cytotoxicity of CD8⁺ effector T cells in mice immunized with IL-2::2Ig(F)GPI asVNP. (A) Flow cytometry analysis showing recovery of adoptively transferred and differentially CPD labeled LCMV-GP_33-41 peptide (CPD^dim) or mock peptide (CPD^bright) pulsed congenic CD45.1⁺ splenocytes from CD45.2⁺ wild-type recipient mice. Two days before target cell transfer, wt mice received 2x10⁵ purified P14 CD45.1⁺CD8⁺ effector T cells and were immunized with IL-2::GPI or IL-2::2Ig(F)GPI asVNP (black histograms) or with IL-2(A)::GPI or IL-2(A)::2Ig(F)GPI asVNP (open histograms) or were left untreated. (B) Quantification of specific target cell lysis in vivo. Horizontal lines indicate the mean. (C-E) Pre-stimulation of CD8⁺ T cells with IL-2::GPI asVNP generates higher absolute numbers of memory cells in vivo. P14 CD8⁺ T cells (CD45.2⁺) were in vitro pre-stimulated with IL-2v asVNP or αCD3/αCD28 microbeads (+100 U/ml IL-2) for six days. Equal amounts of viable naïve and activated cells (1x10⁶) were adoptively transferred into CD45.1⁺ congenic recipient mice. After 7 days engraftment of P14 CD8⁺CD45.2⁺ T cells in the inguinal lymphnodes and the spleens were determined by flow cytometry. (C) Flow cytometry analysis showing expression of the indicated markers on naïve (shaded grey histograms) and in vitro pre-activated (black line) CD8⁺CD45.2⁺ donor cells isolated from the lymph nodes of recipient mice. Absolute numbers of CD62L^low and CD62L^high donor cells recovered from (D) inguinal lymphnodes and (E) spleens of recipient mice. Data are representative (A, C) or show the summary (B, D, E) of 28 mice (seven per group) that were analyzed in four independent experiments (A, B), or of 18 mice (eight per group, except for naïve (two), IL-2::GPI (three), αCD3/αCD28 microbeads plus IL-2 (five)) (C-E) that were analyzed in two independent experiments. * p < 0.05, **, p < 0.01 ANOVA, t-test and post hoc Bonferroni correction (B); Mann-Whitney U-test (D, E).