Discovery of a protective Rickettsia prowazekii antigen recognized by CD8+ T cells, RP884, using an in vivo screening platform

Abstract

Rickettsia prowazekii has been tested for biological warfare due to the high mortality that it produces after aerosol transmission of very low numbers of rickettsiae. Epidemic typhus, the infection caused by these obligately intracellular bacteria, continues to be a threat because it is difficult to diagnose due to initial non-specific symptoms and the lack of commercial diagnostic tests that are sensitive and specific during the initial clinical presentation. A vaccine to prevent epidemic typhus would constitute an effective deterrent to the weaponization of R. prowazekii; however, an effective and safe vaccine is not currently available. Due to the cytoplasmic niche of Rickettsia, CD8(+) T-cells are critical effectors of immunity; however, the identification of antigens recognized by these cells has not been systematically addressed. To help close this gap, we designed an antigen discovery strategy that uses cell-based vaccination with antigen presenting cells expressing microbe's proteins targeted to the MHC class I presentation pathway. We report the use of this method to discover a protective T-cell rickettsial antigen, RP884, among a test subset of rickettsial proteins.

Figure 1. Diagram of the methodology to discover antigens recognized by T-cells.

The steps involved are numbered as follows: 1) selection of appropriate antigen presenting cells (APCs) based on MHC class I expression, 2) transfer of R. prowazekii gene clones to an eukaryotic expression vector, 3) expression vector transfer to APCs, 4) visual screening to verify expression of rickettsial gene, 5) APC-based immunization of naive mice using pools of 4–6 different APCs expressing rickettsial genes, 6) challenge with R. typhi and determination of bacterial load as indicator of protection, and 7) identification of protective rickettsial genes by deconvolution of protective pools.

Figure 2. Characteristics of new eukaryotic expression vector.

A) Diagram of plasmid components. B) Comparison of the same rickettsial proteins expressed as fusion proteins with GFP (pDEST47) or with our new vector, pDEST-M1. Note the visual difference between signal and background.

Figure 3. Verification of expression of rickettsial proteins in APCs.

Examples of R. prowazekii proteins expressed by SVEC4-10 cells as detected by fluorescence microscopy (with and without Shield, a blocker of the destabilization domain) and western blot. Note that RP042 is expressed when codons are optimized for eukaryotic expression (GeneArt) but not when using native rickettsial codons (JCVI).

Figure 4. In vivo identification of rickettsial antigens.

A) Thirty-six APC lines expressing high levels of individual R. prowazekii proteins were randomly combined into 8 pools. Eight groups of mice (4 mice per group) were immunized with pools of APCs expressing 4 or 5 different R. prowazekii proteins (see table S1) by inoculating 2×10⁵ APCs i.v. As a control, one group of mice was immunized with APCs expressing a gene from A. thaliana. We also included a group without any manipulation (blank control). Fifteen days after immunization, all mice were challenged with 3×LD₅₀ R. typhi. At day 7 post-infection, all animals were terminated, and rickettsial load in liver and lungs (not shown) was determined using quantitative real-time PCR targeting the rickettsial gene gltA and the mouse gene ldhal6b. We identified one group of mice with a significantly lower load of Rickettsia. B) This group was deconvoluted by immunizing mice with the individual constructs following a similar strategy as the one above. We found one protective rickettsial protein in this group, RP884.

Figure 5. Efficacy of RP884 as a protective antigen and mechanism of protection.

A) Naive mice immunized with 2×10⁵ APCs expressing either RP884 or an A. thaliana gene (control) were challenged with 3×LD₅₀ of R. typhi and followed in time to determine survival; 60% of RP884-immune animals survived while none of the control animals did (p<0.0001). B and C) RP884-immune animals and mice immunized with the A. thaliana control gene were challenged with 6× LD₅₀ of R. typhi and sacrificed 7 days later (4 hours after i.p. injection of brefeldin A and monensin) to obtain splenocytes for flow cytometric analysis; cells were stained with antibodies against CD3, CD8, CD44, IFN-γ, and granzyme B to determine the proportion of antigen-experienced CD8⁺ T-cells (B) stimulated to produce IFN-γ (C) ex vivo after rickettsial challenge. Differences were statistically significant (p = 0.0003 for panel B and p = 0.001 for panel C). We show individual data points, mean, and standard error of the mean (SEM).