Effect of the use of Galectin-9 and blockade of TIM-3 receptor in the latent cellular reservoir of HIV-1

Abstract

Reactivation of latent HIV-1 is a necessary step for the purging of the viral reservoir, although it does not seem to be enough. The stimulation of HIV-1 specific cytotoxic T lymphocytes (CTL) may be just as essential for this purpose. In this study, we aimed to show the effect of galectin-9 (Gal-9), known to revert HIV-1 latency, in combination with the blockade of TIM-3, a natural receptor for Gal-9 and an exhaustion marker. We confirmed the ability of Gal-9 to reactivate latent HIV-1 in Jurkat-LAT-GFP cells, as well as in an IL-7-based cellular model. This reactivation was not mediated via the TIM-3 receptor, but rather by the recognition of the Gal-9 of a specific oligosaccharide pattern of resting memory CD4⁺ T cells' surfaces. The potency of Gal-9 in inducing transcription of latent HIV-1 was equal to or greater than that of other latency-reversing agents (LRA). Furthermore, the combination of Gal-9 with other LRA did not show synergistic effects in the reactivation of the latent virus. To evaluate the impact of TIM-3 inhibition on the CTL-response, different co-culture experiments with CD4⁺T, CD8⁺ T, and NK cells were performed. Our data showed that blocking TIM-3 was associated with control of viral replication in both in vitro and ex vivo models in cells from PLWH on antiretroviral therapy. A joint strategy of the use of Gal-9 to reactivate latent HIV-1 and the inhibition of TIM-3 to enhance the HIV-1 CTL specific-response was associated with control of the replication of the virus that was being reactivated, thus potentially contributing to the elimination of the viral reservoir. Our results place this strategy as a promising approach to be tested in future studies. Reactivation of latent-HIV-1 by Gal-9 and reinvigoration of CD8⁺ T cells by TIM-3 blockade could be used separately or in combination.ImportanceHIV-1 infection is a health problem of enormous importance that still causes significant mortality. Antiretroviral treatment (ART) has demonstrated efficacy in the control of HIV-1 replication, decreasing the morbidity and mortality of the infection, but it cannot eradicate the virus. In our work, we tested a protein, galectin-9 (Gal-9), an HIV-1 latency-reversing agent, using an in vitro cellular model of latency and in cells from people living with HIV-1 (PLWH) on antiretroviral therapy. Our results confirmed the potential role of Gal-9 as a molecule with a potent HIV-1 reactivation capacity. More importantly, using a monoclonal antibody against T cell immunoglobulin and the mucin domain-containing molecule 3 (TIM-3) receptor we were able to enhance the HIV-1 cytotoxic T lymphocytes (CTL) specific response to eliminate the CD4⁺ T cells in which the virus had been reactivated. When used together, i.e., Gal-9 and TIM-3 blockade, control of the replication of HIV-1 was observed, suggesting a decrease in the cellular reservoir.

FIG 1

Galectin-9 (Gal-9) reactivates latent HIV-1 in Jurkat-LAT-GFP cells. Bars show HIV-1 reactivation, calculated as percent GFP expression. After Gal-9 (2 nM) treatment (18 h) in a model of Jurkat-LAT-GFP cells (n = 4), we did not observe significant differences compared with the PMA (positive control). Similar results were obtained with the combination of Gal-9 (2 nM) with an antibody against TIM-3 (anti-TIM-3) (5 μg/ml). Significant differences were observed when we compared the Gal-9 reactivation alone or with anti-TIM-3 to the negative control (uninfected primary Jurkat cell line). Uninfected Jurkat cells that expressed GFP constitutively (Control GFP⁺) showed significantly higher GFP values than reactivation mediated by Gal-9. An increase (not significant) in GFP expression was observed after Gal-9 treatment compared to expression without Gal-9 addition (Jurkat cells). The same comparison achieved a significant difference when anti-TIM-3 was added (Gal-9 2 nM+ αTIM3 5 μg/ml). Statistical significance was calculated using the Mann-Whitney U test. P values of <0.05 were considered statistically significant. *, P < 0.05; NS, not significant.

FIG 2

Scheme of the HIV-1 primary CD4⁺ T cell latency model. Resting memory CD4⁺ T cells (CD4⁺ HL-DR⁻ CD25⁻) were treated with IL-7 for 5 days and then infected with an X4-tropic NL4.3 strain and cultured for 5 additional days. Galectin-9 (Gal-9) was used for HIV-1 reactivation measured by quantification of the HIV-1 p24 antigen in culture supernatants. After 24 h of Gal-9 treatment, supernatants were collected for p24 antigen determination.

FIG 3

qPCR analysis of HIV-1 proviral integration. Data are copy numbers of integrated provirus per 10⁶ cells. IL-7 allowed viral integration in the CD4⁺ T model using an X4-tropic NL4.3 strain compared with the control (without Il-7). *, P < 0.05.

FIG 4

Galectin-9 (Gal-9) reverse HIV-1 latency in a cellular model based on IL-7. Bars show HIV-1 reactivation, expressed as p24 antigen production (n = 8). No significant differences were observed between p24 antigen concentrations with the positive control (PMA) and the different Gal-9 concentrations with or without an antibody against TIM-3 (anti-TIM-3). The comparison with the cellular model alone (Control) showed in all cases a significant difference in the p24 antigen values. Statistical significance was calculated using the Mann-Whitney U test. P values of <0.05 were considered statistically significant. *, P < 0.05; NS, not significant.

FIG 5

Deglycosylation assay with tunicamycin (TNC). Bars show HIV-1 reactivation, expressed as p24 antigen production (n = 4) in a cellular model based on IL-7. Comparison of p24 antigen values between Gal-9 alone and Gal-9 with TNC showed a reduction, although it was not significant. Similar results were observed with the presence of an antibody against TIM-3 (anti-TIM-3). Comparison with the cellular model alone (Control) showed a significant difference in the p24 antigen values in the cases of Gal-9 alone, Gal-9 with TNC, and Gal-9 with TNC and anti-TIM-3 (αTIM3). Statistical significance was calculated using the Mann-Whitney U test. P values of <0.05 were considered statistically significant. *, P < 0.05; NS, not significant.

FIG 6

HIV-1 latency reactivation by Galectin-9 (Gal-9) and other latency reversal agents (LRA) in a cellular model based on IL-7. The bars show HIV-1 reactivation, expressed as p24 antigen production (n = 4) in a cellular model based on IL-7. No synergism between Gal-9 and other LRA was observed. (A) Reactivation mediated by Gal-9 alone or Gal-9 with an antibody against TIM-3 (αTIM-3) compared with the cellular model alone (control [Ct]) showed a significant increase in p24 antigen values. p24 antigen values for Gal-9 with or without anti-TIM-3 were significantly different from those for MVC, JQ1, and Ds and not significantly different from those for Vor, Bryo, and Rmd. (B) Several combinations of at least two LRA with Gal-9 did not reach the p24 antigen values obtained with Gal-9 alone. A significant difference was observed for the combinations Gal-9+MVC+Vor+Bryo; Gal-9+JQ1+Vor+Bryo; Gal-9+MVC+Vor+Bryo, and Gal-9+MVC+JQ1+Bryo. Statistical significance was calculated using Mann-Whitney U test. P values of <0.05 were considered statistically significant. *, P < 0.05; NS, not significant. MVC, maraviroc; Vor, vorinostat; DS, disulfiram; Rmd, romidepsin; Bryo, bryostatin-1.

FIG 7

TIM-3 blockade improves CTL response in CD8⁺ T cells. Bars show HIV-1 reactivation, expressed as p24 antigen production (n = 10) in different coculture conditions. (A) In the CD4:CD8 cocultures, no significant differences were observed between the p24 antigen values in infected CD4 cells alone and CD4 cells with CD8 cells. However, a significant reduction in the p24 antigen values in the cocultures with an antibody against TIM-3 receptor (anti-TIM-3) at different concentrations (5 μg/ml and 7.5 μg/ml) was observed. No significant differences (NS) were detected with or without the addition of Gal-9 at 2 nM concentration in the coculture. (B) In the CD4:NK cocultures, no significant differences were observed between the p24 antigen values for infected CD4 cells alone and CD4 cells with NK cells. Although not significant, a reduction in the p24 antigen values in the cocultures with anti-TIM-3 at different concentrations (5 μg/ml and 7.5 μg/ml) was observed. No significant differences were detected with and without the addition of Gal-9 at 2 nM in the coculture. (C) In the CD4:CD8:NK cocultures, no significant differences were observed between the p24 antigen values in the infected CD4 cells alone and those in CD4 cells with CD8:NK cells. However, a significant reduction in the p24 antigen values in the cocultures with anti-TIM-3 was observed. No significant differences were detected with and without the addition of Gal-9 at 2 nM in the coculture. Statistical significance was calculated using the Mann-Whitney U test. P values of <0.05 were considered statistically significant. *, P < 0.05; NS, not significant.

FIG 8

Galectin-9 (Gal-9) and TIM-3 inhibition as a joint strategy in HIV-1 latency. Bars show HIV-1 reactivation, expressed as p24 antigen production (n = 3) in a cellular model based on IL-7. Significant differences were observed after Gal-9 (2 nM) addition compared with CD4r:CD8 alone. The TIM-3 inhibition with and without Gal-9 resulted in a significant reduction in p24 antigen values. Statistical significance was calculated using the Mann-Whitney U test. P values of <0.05 were considered statistically significant. *, P < 0.05; NS, not significant. CD4r, resting CD4⁺ T cells of the cellular model.

FIG 9

TIM-3 blockade improves CTL response in CD8⁺ T cells from PLWH. Bars show mean p24 antigen reduction (log) (n = 10). (A) Without Gal-9 addition, significant increases (*, P < 0.05) in p24 of ≥2 log with TIM-3 inhibition (α-TIM-3) (dark green bars) in the CD4:CD8 and CD4:CD8:NK cocultures were observed; no significant difference was seen in the case of CD4:NK alone. No differences were detected between results on day 7 and day 10. (B) With Gal-9 addition, significant increases in p24 of ≥2 log with TIM-3 inhibition (dark green bars) in the CD4:CD8 and CD4:CD8:NK cocultures were observed; no significant difference was seen in the case of CD4:NK alone. No differences were detected between results on day 7 and day 10. Statistical significance was calculated using the Mann-Whitney U test. P values of <0.05 were considered statistically significant. *, P < 0.05; NS, not significant.

FIG 10

Cytokine levels at day 7 from supernatants of CD4:CD8:NK coculture (in vitro model). Each graph presents expression levels for one cytokine. The control infection (purple) had only cells without Gal-9 or an antibody against TIM-3 (αTIM3). The addition of Gal-9 (2 nM) alone (green) or with an antibody against TIM-3 at 5 μg/ml and 7.5 μg/ml (orange and blue) was evaluated. Anti-TIM-3 alone at 5 μg/ml and 7.5 μg/ml (red and pink) was also tested. No differences were observed in the levels of all cytokines analyzed before and after the addition of anti-TIM-3.

FIG 11

Cytokine levels at day 7 in supernatants of CD4:CD8:NK coculture (ex vivo model). Each graph represents the expression levels for one cytokine. CD4:CD8:NK cocultures (green) had only cells without Gal-9 or an antibody against TIM-3 (anti-TIM-3). The addition of Gal-9 (2 nM) alone (orange) to the CD4:CD8:NK coculture was evaluated. No differences were observed in the levels of all cytokines analyzed after the addition of anti-TIM-3 without Gal-9 (blue) or with Gal-9 (pink) to the CD4:CD8:NK coculture.