CD4+ T-cell memory: generation and multi-faceted roles for CD4+ T cells in protective immunity to influenza

Abstract

We have outlined the carefully orchestrated process of CD4+ T-cell differentiation from naïve to effector and from effector to memory cells with a focus on how these processes can be studied in vivo in responses to pathogen infection. We emphasize that the regulatory factors that determine the quality and quantity of the effector and memory cells generated include (i) the antigen dose during the initial T-cell interaction with antigen-presenting cells; (ii) the dose and duration of repeated interactions; and (iii) the milieu of inflammatory and growth cytokines that responding CD4+ T cells encounter. We suggest that heterogeneity in these regulatory factors leads to the generation of a spectrum of effectors with different functional attributes. Furthermore, we suggest that it is the presence of effectors at different stages along a pathway of progressive linear differentiation that leads to a related spectrum of memory cells. Our studies particularly highlight the multifaceted roles of CD4+ effector and memory T cells in protective responses to influenza infection and support the concept that efficient priming of CD4+ T cells that react to shared influenza proteins could contribute greatly to vaccine strategies for influenza.

Fig. 1. Stages of CD4⁺ T-cell differentiation

This figure depicts the stages of CD4⁺ T-cell differentiation from naïve to memory, as we have found in our studies. Noted are the factors driving naïve expansion and differentiation, including Ag (antigen) and PI (proinflammatory) cytokines. Also shown under functional characteristics are benchmark features that distinguish the different stages.

Fig. 2. Changes in gene expression: from naïve to effector to rested effector to memory CD4⁺ T cells

AND T-cell receptor transgenic mice that recognize a fragment of pigeon cytochrome c (PCCF; amino acids 88–104) presented by I-E^k were used for isolation and generation of naïve, effector, rested effector, and memory CD4⁺ T cells (1). Th1 and Th2 effector cells were generated in vitro through incubation of naïve CD4⁺ T cells for 4 days with antigen-presenting cells (APCs) and PCCF in the presence of interleukin (IL)-2, IL-12, and anti-IL-4 antibody for Th1 and IL-2, IL-4, and anti-interferon-γ for Th2. Rested effector cells were derived from the effector cells, after removal of antigen and cytokines, cultured for additional 3 days in vitro. Memory cells were isolated from host mice after 4–12 weeks of adoptive transfer of rested effector cells. RNA were isolated from CD4⁺ subsets of both Th1 and Th2 lineages and were used for cDNA synthesis as probes. A custom-made cDNA microarray filter consists of 4000 genes that were selected from screening over 15 000 unique cDNA clones for their expression in mouse lymphocytes. The data were derived from three independent microarray experiments. The differentially expressed genes met the two criteria: (i) they are statistically significant determined by the false discovery rate (FDR) analysis (FDR ≤ 0.05) and (ii) the intensity difference is greater than two.

Fig. 3. Maintenance of phenotypic heterogeneity: effector to memory

Naïve carboxyfluoresein succinimidyl ester (CFSE)-labeled CD4⁺ T cells from HNT.TCR Tg.Thy1.1 mice (5 × 10⁶) were transferred into intact BALB/c hosts. Recipient mice were infected intranasally with 0.5 LD₅₀ of influenza A virus (A/PR8/34) a day later (19). After day 7 and 6 weeks postinfluenza infection, cell suspensions from lymphoid organs of individual mice (spleen, peripheral LN, draining LN) and nonlymphoid tissues (lung and bronchoalveolar lavage) were stained with anti-Thy1.1-biotin followed by streptavidin- allophycocyanin and anti-CD4-cychrome to identify donor T cells. The dot plots (one representative from lymphoid and nonlymphoid tissues) show the expression of CD44 and CD62L against residual CFSE on gated donor cells at effector and memory stages. The dot plots representing lymphoid tissues show that heterogeneity, in terms of subpopulations at different stages of cell division and expression of CD44 and CD62L, were maintained into memory cells. Donor cells from nonlymphoid tissues remained CFSE^loCD44^hiCD62L^lo. The maintenance of phenotypic heterogeneity was similar for the expression of many other markers analyzed (CD49d, CD11a, CCR7). These data are a representation of three individual experiments using three mice per group.

Fig. 4. Generating effector and memory heterogeneity

A model depicting the postulated progressive differentiation of CD4⁺ T cells as they become fully differentiated effector cells. The model indicates phenotypic and functional changes that occur. The expression of helper function in the distinct subsets has not yet been tested, as indicated by the question mark. Arrows indicate the direction of progression. It is suggested that most effector subsets can become small resting memory cells, except for the naïve precursors and terminally differentiated effectors, which undergo activation-induced or programmed cell death.

Fig. 5. Effect of antigen dose and duration and inflammation on effector differentiation and memory

This figure depicts a summary of the results and conclusions in Jelley-Gibbs et al. (47). When naïve CD4⁺ influenza-specific indicator cells are introduced at day 0, they encounter high levels of virus (pink lines) and inflammation (orange line). They expand (blue lines), becoming effectors capable of high levels of interferon-γ (IFN-γ) production and nonlymphoid migration to the lung. They also lose ability to produce interleukin (IL)-2. Naïve cells introduced at successively later times (1 and 2 weeks are shown) expand less and have a less pronounced effector phenotype and function, as indicated by the triangles. Memory generation, in terms of recovery of memory cells at 4 or more weeks, is equivalent.

Fig. 6. Mechanism of protection by Th1 effectors: a 1–2 punch

This illustration depicts the major mechanisms of protection revealed by the responses seen in wildtype and B-cell-deficient JhD mice. In both strains, transferred donor CD4⁺ Th1 cells appear in the lung soon after transfer and then decay after a few days (red line). Antibody develops early (relative to a primary encounter) in the wildtype mouse (magenta solid line), but of course not in the JhD (magenta dotted line). Weight loss plateaus in both groups, but the wildtype mice go on to gain weight (solid blue line) and recover, while the JhD mice again lose weight and die (dotted blue line). Antibody from convalescent wildtype mice, added in small amounts (10 μL), rescues the JhD hosts (not shown, see Table 1). Thus, we suggest the CD4⁺ effector T cells work in two stages. First, they help in the clearance of infected cells (days 3–8) using cytotoxic and perhaps other mechanisms. Second, they help host B cells to make antibody responses, which mediate viral clearance after 8 days (Brown, Dilzer, Meents, and Swain, manuscript submitted).

Fig. 7. Protection due to CD4⁺ effector T-cell transfer

Influenza-specific CD4⁺ Th1-polarized effectors were generated in vitro. Effectors were transferred to adoptive hosts (dotted lines). Controls received no cells (solid lines). All mice were infected intranasally with 5 LD₅₀ PR8 influenza virus. Depicted are levels of virus (log₁₀ live viral titers) in blue, donor CD4⁺ T cells (log number in lung) in red, IgG antibody to influenza in serum in green, and percentage weight loss.

Fig. 8. Patterns of expression of stage-specific genes: the transition from effector to rested effector to memory

Th2 effector cells were generated in vitro as described in Fig. 2. Naïve CD4⁺ T cells, from an AND T-cell receptor (TCR) receptor mouse that was transgenic for green fluorescence protein (GFP), were incubated with antigen-presenting cells (APCs) and PCCF in the presence of interleukin (IL)-2, IL-4, and anti-interferon-γ (IFN-γ) for 4 days. In vitro-rested effector cells (RE1) were derived from these effector cells, by washing and reculturing in the absence of antigen and cytokines for an additional 3 days. In vivo-rested effectors (RE2) were obtained by transferring Th2 effectors to class II knockout hosts. Donor cells were recovered 3 days later (RE2) from the hosts using fluorescence-assisted cell sorting for GFP⁺ cells. Memory cells were isolated from the host mice receiving effectors 4–12 weeks after adoptive transfer. Gene expression experiments and selection of differentially expressed genes were the same as shown in Fig. 2. Shown are the levels at each stage of the genes that were most highly expressed in effectors cells (left), or memory cells (right), grouped into clusters with similar patterns (Weng NP et al., unpublished data). E = effector; M = memory.

Fig. 9. Stages of CD4⁺ T-cell responses: receptors and functions

Depicted are changes in known functions and related receptors and markers as naïve cells become effector and then memory cells. We have suggested a bipartite separation that occurs during the effector to memory transition. Many functions and surface receptors associated with activation state of the T cells go either up or down with effector development (blue, up; green, down), and these return to naïve levels when the cells become resting memory. Others, which are associated with differentiation and the improved response potential of memory cells, stay at effector levels (orange, up; magenta, down).

Fig. 10. Which effectors become memory cells?

This figure represents the model we have developed based on our studies. As naïve CD4⁺ T cells respond to infection, they progressively differentiate with successive rounds of division and exposure to growth and inflammatory cytokines, eventually becoming terminally differentiated effectors (as depicted also in Fig. 4). We suggest that all activated cells can become memory cells, except for those naïve cells that have not responded to antigen, and the end-stage effectors that either are destined to die or have progressed to a nonresponsive state (79).

Fig. 11. Heterosubtypic CD4⁺ and CD8⁺ T-cell responses

B6 mice were uninfected (black) or infected with either PR8 (blue), cold-adapted Alaska (red), or cold-adapted Hong Kong (yellow) influenza virus to test whether heterosubtypic responses to internal proteins (NP, PA) would be generated. Spleen cells from sublethally infected mice were tested for interferon-γ (IFN-γ)- and interleukin (IL)-2-producing enzyme-linked immunospots (ELISPOTs) following stimulation with influenza peptide-pulsed antigen-presenting cells (Strutt, Hollenbough, Dutton, Roberts, Woodland, and Swain, unpublished data). Peptides were identified using screening overlapping 15-mers, as described in our earlier report (71).