Immunodominant, protective response to the parasite Toxoplasma gondii requires antigen processing in the endoplasmic reticulum

Abstract

The parasite Toxoplasma gondii replicates in a specialized intracellular vacuole and causes disease in many species. Protection from toxoplasmosis is mediated by CD8(+) T cells, but the T. gondii antigens and host genes required for eliciting protective immunity are poorly defined. Here we identified GRA6, a polymorphic protein secreted in the parasitophorous vacuole, as the source of the immunodominant and protective decapeptide HF10 presented by the H-2L(d) major histocompatibility complex class I molecule. Presentation of the HF10-H-2L(d) ligand required proteolysis by ERAAP, the endoplasmic reticulum aminopeptidase associated with antigen processing. Consequently, expansion of protective CD8(+) T cell populations was impaired in T. gondii-infected ERAAP-deficient mice, which were more susceptible to toxoplasmosis. Thus, endoplasmic reticulum proteolysis is critical for eliciting protective immunity to a vacuolar parasite.

Figure 1

Uncontrolled parasite replication in ERAAP-deficient H-2^d mice and greater susceptibility to T. gondii infection. (a) Kaplan-Meier survival curves of B10.D2 (H-2^d) mice challenged intraperitoneally with 500 T. gondii Pru tachyzoites. *, P = 0.047 (Mantel-Cox log-rank test). Data are representative of two independent experiments with at least six mice per group. (b,c) Flow cytometry (b) of GFP⁺ infected splenocytes (*, P = 0.0043) or peritoneal macrophages (*, P = 0.038) and semiquantitative PCR (c) of parasite burden in the brain (*, P > 0.05), spleen (*, P = 0.012) and liver (*, P = 0.013) in mice infected intraperitoneally with 3 × 10³ GFP-expressing Pru tachyzoites and analyzed 12 d later. +/+, +/−, pooled wild-type and ERAAP-heterozygous; −/−, ERAAP-deficient. Each symbol represents an individual mouse; small horizontal bars indicate the mean. Data represent two to four independent experiments with at least three mice per group.

Figure 2

All T. gondii–specific CD8⁺ T cell hybridomas are stimulated by H-2L^d MHC class I. (a) Flow cytometry of IFN-γ production by CD8⁺ T cells from the spleens of T. gondii–immunized BALB/c mice, analyzed ex vivo 1 week after challenge (left) or after one restimulation (middle) or two restimulations (right) in vitro with infected J774 macrophages. Numbers under outlined areas indicate percent cells in each. Data are representative of two experiments. (b) The lacZ responses of T cell hybridomas (CTgEZ hybrids from batch E and CTgHZ hybrids from batch H; numbers along axis indicate hybridoma number) after overnight culture together with T. gondii–infected L cells expressing H-2L^d (filled bars) or H-2K^d (open bars), measured with a chromogenic substrate. The hybridomas were generated by fusion of IFN-γ-producing CD8⁺ T cells from two independent groups of mice to a lacZ-inducible fusion partner. A₅₉₅, absorbance at 595 nm. Data are from two experiments.

Figure 3

T. gondii–specific CD8⁺ T cell hybrids recognize the HF10 decapeptide presented by H-2L^d MHC class I. (a) Response of the T. gondii–specific CTgEZ.4 hybridoma to H-2L^d L cells transfected with full-length GRA6 cDNA or cDNA encoding a GRA6 construct lacking the carboxy-terminal residues 170–224 (GRA6Δ170 – 224), assessed as induction of β-galactosidase. (b) Response of CTgEZ.4 to synthetic GRA6 peptides (right) presented exogenously by H-2L^d L cells. (c,d) The CTgEZ.4-stimulatory capacity of synthetic peptides (c) or extracts of GRA6-transfected H-2L^d L cells or infected BMDMs or BMDCs (d), analyzed after fractionation by HPLC. Each fraction was pulsed onto H-2L^d L cells, which served as APCs. B (right margin, c), organic solvent (acetonitrile and 0.1% (vol/vol) trifluoroacetic acid). Red arrowheads indicate the HPLC fraction in which HF10 coelutes. Data in a–d are representative of at least two experiments.

Figure 4

The HF10–H-2L^d complex is the only detectable ligand recognized by CD8⁺ T cells in T. gondii–infected H-2^d mice. (a) Frequency of HF10-specific CD8⁺ cells after oral infection of BALB/c mice with T. gondii cysts. Numbers adjacent to outlined areas indicate percent CD8⁺ cells stained by an H-2L^d multimer (DimerX) loaded with HF10 or QL9 (irrelevant H-2L^d peptide). Data are representative of two experiments with two mice (brain) or three mice (spleen). (b) Expansion of HF10–H-2L^d–specific splenic CD8⁺ T cell populations over time in mice infected orally (n = 6 mice total, with only one mouse analyzed at the 5-week time point). Data are presented as mean ± s.e.m., corrected for background with QL9, and are representative of two experiments. (c) Frequency of HF10–H-2L^d–specific CD8⁺ cells in BALB/c mice infected intraperitoneally with 3 × 10³ T. gondii tachyzoites and analyzed 7 weeks after infection. Data (mean and s.e.m.) are representative of two experiments with brains from four mice and spleen cells pooled from four mice. (d,e) Flow cytometry of IFN-γ production by CD8⁺ splenic T cells activated by T. gondii–infected J774 APCs (d) or HF10-loaded J774 APCs (e) 4 weeks after B10.D2 mice were infected intraperitoneally with 5 × 10³ tachyzoites. Splenocyte/J774 cell ratio in e is 2.7. Dashed lines indicate the response elicited by 100 pM HF10 peptide. Data (mean and s.e.m.) are representative of two experiments with three mice each.

Figure 5

Immunization with HF10 protects mice from toxoplasmosis. (a,b) Survival of B10.D2 mice (a) or C57BL/6 mice (b) immunized with BMDCs pulsed with HF10 or YL9 (irrelevant H-2L^d peptide) and challenged with either of two doses of T. gondii tachyzoites (TZ). Data are representative of two independent experiments with three mice per group. (c,d) Infected (GFP⁺) splenocytes (c) and peritoneal cells (d) 10 d after infection of B10.D2 mice previously immunized with BMDCs pulsed with HF10 or YL9; mice were left undepleted (−) or were depleted of CD8⁺ cells 36 h before immunization by one intraperitoneal injection of depleting antibody (+). Data (mean and s.e.m.) are representative of two experiments with two to three mice per condition.

Figure 6

Presentation of the HF10–H-2L^d complex requires proteasomal activity and TAP transport. (a,b) Induction of β-galactosidase by the CTgEZ.4 hybridoma in response to BMDMs pretreated for 2 h with the proteasome inhibitors epoxomicin (a) or lactacystin (b) and infected for 8 h with T. gondii. Data are representative of two independent experiments. (c) Induction of β-galactosidase by CTgEZ.4 in response to H-2^b BMDMs from C57BL/6J mice (WT) or TAP-deficient mice (TAP-KO) transduced with H-2L^d before T. gondii infection. Measurement of GFP expression at a multiplicity of infection (MOI) of 8 showed that 77% of C57BL/6J cells and 73% of TAP-deficient cells were infected. Data are representative of two independent experiments.

Figure 7

Presentation of HF10–H-2L^d complexes requires proteolysis in the endoplasmic reticulum. (a,b) Induction of β-galactosidase by the CTgEZ.4 hybridoma in response to ERAAP-heterozygous or ERAAP-deficient BMDMs (a) or BMDCs (b) infected for 8 h with T. gondii at a multiplicity of infection of 8. Approximately 90% of ERAAP-heterozygous BMDMs, 93% of ERAAP-deficient BMDMs, 69% of ERAAP-heterozygous BMDCs and 70% of ERAAP-deficient BMDCs were infected, as determined by GFP expression. (c,d) Presentation of synthetic HF10 peptide at various concentrations (horizontal axis) by ERAAP-heterozygous or ERAAP-deficient BMDMs (c) or BMDCs (d) to CTgEZ.4. Data (mean ± s.e.m.) are representative of three (b,d) or six (a,c) experiments. (e) Induction of β-galactosidase by CTgEZ.4 in response to peptide extracts fractionated by HPLC from ERAAP-deficient or ERAAP-heterozygous BMDMs infected as described in a. Data are representative of four experiments. (f) Frequency of HF10-Ld–multimer–binding CD8⁺ cells in mouse spleens at 12 d after infection with 3 × 10³ Pru tachyzoites. Each symbol represents one mouse; small horizontal lines indicate the mean. *, P = 0.0173. Data are representative of three independent experiments.