Peripheral T Follicular Helper Cells Are the Major HIV Reservoir within Central Memory CD4 T Cells in Peripheral Blood from Chronically HIV-Infected Individuals on Combination Antiretroviral Therapy

Abstract

In this study, we examined the peripheral blood (PB) central memory (TCM) CD4(+) T cell subsets designated peripheral T follicular helper cells (pTfh cells) and non-pTfh cells to assess HIV permissiveness and persistence. Purified pTfh and non-pTfh cells from healthy HIV-negative donors were tested for HIV permissiveness using green fluorescent protein (GFP)-expressing HIV-1NL4-3/Ba-L, followed by viral reactivation using beads coated with anti-CD3/anti-CD28 monoclonal antibodies. The role of pTfh cells in HIV persistence was analyzed in 12 chronically HIV-1 infected patients before and 48 weeks after initiation of raltegravir-containing combination antiretroviral therapy (cART). Total cellular HIV-1 DNA and episomes containing two copies of the viral long terminal repeat (2LTR circles) were analyzed in using droplet digital PCR in the purified pTfh and non-pTfh cells. Activation-inducible HIV p24 expression was determined by flow cytometry. Results indicate that pTfh cells, in particular PD1(+) pTfh cells, showed greater permissiveness for HIV infection than non-pTfh cells. At week 48 on cART, HIV DNA levels were unchanged from pre-cART levels, although a significant decrease in 2LTR circles was observed in both cell subsets. Inducible HIV p24 expression was higher in pTfh cells than in non-pTfh cells, with the highest frequencies in the PD1(+) CXCR3(-) pTfh cell subset. Frequencies of HLADR(+) CD38(+) activated CD4 T cells correlated with 2LTR circles in pTfh and non-pTfh cells at both time points and with p24(+) cells at entry. In conclusion, among CD4 TCM cells in PB of aviremic patients on cART, pTfh cells, in particular the PD1(+) CXCR3(-) subset, constitute a major HIV reservoir that is sustained by ongoing residual immune activation. The inducible HIV p24 assay is useful for monitoring HIV reservoirs in defined CD4 T cell subsets.

Importance: Identification of the type and nature of the cellular compartments of circulating HIV reservoirs is important for targeting of HIV cure strategies. In lymph nodes (LN), a subset of CD4 T cells called T follicular helper (Tfh) cells are preferentially infected by HIV. Central memory (TCM) CD4 T cells are the major cellular reservoir for HIV in peripheral blood and contain a subset of CD4 TCM cells expressing chemokine receptor CXCR5 similar in function to LN Tfh cells termed peripheral Tfh (pTfh) cells. We found that the circulating pTfh cells are highly susceptible to HIV infection and that in HIV-infected patients, HIV persists in these cells following plasma virus suppression with potent cART. These pTfh cells, which constitute a subset of TCM CD4 T cells, can be readily monitored in peripheral blood to assess HIV persistence.

FIG 1

pTfh cells are more permissive to HIV infection than non-pTfh cells. Memory CD4 T cells were negatively isolated from buffy coat PBMC (n = 5) and sorted for pTfh (CXCR5⁺ CCR7⁺) and non-pTfh (CXCR5^neg CCR7⁺) cells. Sort-purified cells were infected with GFP-expressing macrophage-tropic HIV-1 NL4-3/Ba-L and analyzed by flow cytometry. Shown are representative flow cytometry dot plots depicting HIV infection in pTfh and non-pTfh cells, when cells were infected, without activation (A) and after 3 days of PHA activation (B). Bar graphs present the mean frequencies of GFP⁺ cells when cells were infected without preactivation (C) and after PHA activation (D) and mean frequencies of PD1⁺ cells within infected (GFP⁺) cells when cells were infected without preactivation (E) and after PHA activation (F).

FIG 2

pTfh cells infected in vitro with HIV-1 NL4-3/Ba-L-EGFP in the absence of activation show higher levels of GFP expression after restimulation with anti-CD3/anti-CD28 beads. Memory CD4 T cells were negatively isolated from buffy coat PBMC (n = 5) and sorted for pTfh (CXCR5⁺ CCR7⁺) and non-pTfh (CXCR5^neg CCR7⁺) cells. Sort-purified cells were infected with GFP-expressing macrophage-tropic HIV-1 NL4-3/Ba-L without preactivation for 3 days. On day 3, cells were activated for induction of HIV with anti-CD3/anti-CD28 stimulation. (A) Representative flow cytometry dot plots showing GFP expression within pTfh and non-pTfh cells after reactivation. (B) Bar graphs represent the mean frequencies of GFP⁺ cells within pTfh and non-pTfh cells with and without reactivation.

FIG 3

pTfh cells show higher expression of PD1 before and after in vitro activation. Memory CD4 T cells were negatively isolated from buffy coat PBMC and sorted for pTfh (CXCR5⁺ CCR7⁺) and non-pTfh (CXCR5^neg CCR7⁺) cells and analyzed for phenotypic markers either without stimulation or after 3 days of PHA stimulation. (A) pTfh and non-pTfh cells expressing HIV-1 coreceptor CCR5, HLA-DR, PD1, and Ki67 before activation. (B) pTfh and non-pTfh cells expressing HIV-1 coreceptor CCR5, HLA-DR, PD1, and Ki67 after 3 days of PHA activation.

FIG 4

Frequencies of pTfh cells are increased following 48 weeks of cART in treatment-naive patients. Cryopreserved PBMC from study participants and healthy controls (HC) were thawed, rested overnight, and stained for markers specific for pTfh cell phenotyping along with LIVE/DEAD stain. (A) Gating strategy for pTfh cells and for pTfh cell subset identification based on PD1 and CXCR3 expression; (B to G) scatter plots showing frequencies of pTfh (B) and non-pTfh (C) cells at entry and week 48 on cART and frequencies of PD1⁺ CXCR3^neg (D), PD1⁺ CXCR3⁺ (E), PD1^neg CXCR3⁺ (F), and PD1^neg CXCR3^neg (G) pTfh cell subsets at entry and week 48 on cART.

FIG 5

cART reduces activation state of pTfh and non-pTfh cells after 48 weeks of treatment. Cryopreserved PBMC from study participants were thawed, rested overnight, and stained for markers specific for pTfh cell phenotyping along with LIVE/DEAD staining and markers of immune activation (HLA-DR and CD38). Scatter plots show total CD4 (A) and pTfh and non-pTfh cells (B) depicting dual expression of HLA-DR and CD38 at entry and week 48 on cART in comparison to HC. In addition, scatter plots show dual expression of HLA-DR and CD38 at entry and week 48 on cART in pTfh cell subsets (C to F) and non-pTfh cell subsets (G to J) based on PD1 and CXCR3 expression.

FIG 6

Frequencies of HIV p24 inducible cells are higher in pTfh than in non-pTfh cells. CD8-depleted PBMC were activated for induction of HIV with anti-CD3/anti-CD28 stimulation and surface stained for markers for pTfh phenotyping, followed by intracellular staining for HIV-p24. (A) Flow cytometric dots plots showing p24 expression in CD4 T cells and pTfh and non-pTfh cells; (B to D) scatter plots showing mean frequencies of p24 expression in total CD4, pTfh and non-pTfh cells (B and C) and p24 expression in PD1⁺ CXCR3⁻ and PD1⁺ CXCR3⁺ pTfh subsets (D).

FIG 7

2LTR circles decrease in pTfh and non-pTfh cells at week 48 and correlate with CD4 T cell activation. Sort-purified populations of pTfh and non-pTfh cells were subjected to analysis of total HIV-DNA and 2LTR circles by real-time PCR and droplet digital PCR, respectively. Scatter plots show total HIV DNA in CD8-depleted PBMC (A), total HIV DNA and 2LTR circles in pTfh cells (B and C), and total HIV DNA and 2LTR circles in non-pTfh cells (D and E) at entry and at week 48 on cART. Correlations between CD4 T cell immune activation with 2LTR DNA levels in pTfh cells at entry and week 48 on cART (F and G) and frequencies of p24 expression in pTfh cells at entry and week 48 on cART (H and I) are also shown.

FIG 8

CD8 T cell immune activation at entry correlates with 2LTR DNA in pTfh and non-pTfh cells at entry. Sort-purified populations of pTfh and non-pTfh cells were subjected to 2LTR circles analysis by droplet digital PCR. Correlations between CD4 IA at entry and week 48 with 2LTR DNA in non-pTfh cells at entry and week 48 (A) and CD8 T cell immune activation at entry with entry pTfh and non-pTfh 2LTR circles (B) are shown.