PD-1 blockade restores helper activity of tumor-infiltrating, exhausted PD-1hiCD39+ CD4 T cells

Abstract

Tumor antigen-specific CD4 T cells accumulate at tumor sites, evoking their involvement in antitumor effector functions in situ. Contrary to CD8 cytotoxic T lymphocyte exhaustion, that of CD4 T cells remains poorly appreciated. Here, using phenotypic, transcriptomic, and functional approaches, we characterized CD4 T cell exhaustion in patients with head and neck, cervical, and ovarian cancer. We identified a CD4 tumor-infiltrating lymphocyte (TIL) population, defined by high PD-1 and CD39 expression, which contained high proportions of cytokine-producing cells, although the quantity of cytokines produced by these cells was low, evoking an exhausted state. Terminal exhaustion of CD4 TILs was instated regardless of TIM-3 expression, suggesting divergence with CD8 T cell exhaustion. scRNA-Seq and further phenotypic analyses uncovered similarities with the CD8 T cell exhaustion program. In particular, PD-1hiCD39+ CD4 TILs expressed the exhaustion transcription factor TOX and the chemokine CXCL13 and were tumor antigen specific. In vitro, PD-1 blockade enhanced CD4 TIL activation, as evidenced by increased CD154 expression and cytokine secretion, leading to improved dendritic cell maturation and consequently higher tumor-specific CD8 T cell proliferation. Our data identify exhausted CD4 TILs as players in responsiveness to immune checkpoint blockade.

Keywords: Cancer immunotherapy; Immunology; T cells.

Figure 1. CD39 expression in CD4⁺ Tconv TILs.

Isolated CD4⁺ and CD8⁺ TILs were stained ex vivo and analyzed by flow cytometry. (A) Dot plot shows PD-1 versus CD39 expression in cells gated on memory CD4 Tconvs as shown in Supplemental Figure 1A. Proportions of CD39⁺ cells (center, n = 21) and correlation between the proportion of PD-1⁺ and CD39⁺ (right, n = 19) in CD4 Tconvs. (B) Dot plot shows PD-1 expression and gates defining PD-1^neg, PD-1^int, and PD-1^hi cells within CD4 Tconvs. Proportions of PD-1^neg, PD-1^int, and PD-1^hi cells in CD4 Tconvs (n = 21). (C and D) Histogram plots in C show TIGIT, CD39, CTLA-4, and TIM-3 expression in PD-1^neg, PD-1^int, and PD-1^hi CD4 Tconvs and proportions are summarized in D (n = 21). (E) Dot plot shows TIM-3 versus CD39 expression in PD-1^hi CD4 Tconvs. Proportions of TIM-3^–CD39^–, TIM-3⁺CD39^–, TIM-3^–CD39⁺, and TIM-3⁺CD39⁺ cells among PD-1^hi CD4 Tconvs (n = 21) and PD-1^hi CD8⁺ TILs (n = 10). Data are presented as mean ± SD. **P < 0.01; ***P < 0.001; ****P < 0.0001. Pearson’s correlation (A), 2-tailed paired t test or Wilcoxon (D), and 2-tailed unpaired t test (E) were used to compare variables. Tconvs, conventional FOXP3^- CD4 T cells; TILs, tumor-infiltrating lymphocytes.

Figure 2. PD-1^hiCD39⁺ tumor-infiltrating CD4 Tconvs are functionally exhausted.

(A and B) Isolated CD4⁺ TILs were stimulated in vitro with PMA/ionomycin and stained and analyzed by flow cytometry. (A) Top left dot plot shows PD-1 versus CD39 expression in CD4 Tconvs. IFN-γ versus TNF-α expression is shown in the indicated CD4 Tconv populations. Proportions of cytokine⁺ (IFN-γ and/or TNF-α; bottom left) and TNF-α⁺IFN-γ^–, TNF-α^–IFN-γ⁺, and TNF-α⁺IFN-γ⁺ cells in PD-1^–CD39^–, PD-1^loCD39^–, PD-1^hiCD39^–, and PD-1^hiCD39⁺ subsets and according to TIM-3 expression (n = 8). (B) Dot plots show CD39 versus IFN-γ or TNF-α in CD4 Tconvs. Numbers in dot plots correspond to MFI of cytokine staining. MFI of IFN-γ and TNF-α staining in IFN-γ⁺ and TNF-α⁺ cells, respectively, are summarized for Tconv subpopulations defined as in A (n = 8). Samples in A and B are shown according to the proportion of TIM-3⁺ cells among PD-1^hiCD39⁺ CD4 Tconv (<50% TIM-3⁺, square; ≥50% TIM-3⁺, triangle; unknown, round) (C) CD4 Tconv TIL subsets PD-1^–CD39^– (gray), PD-1^loCD39^– (green), PD-1^hiCD39^– (blue), and PD-1^hiCD39⁺ (red) were sorted, expanded in vitro for 10 days, and restimulated or not with PMA/ionomycin overnight. TNF-α and IFN-γ secretion was quantified by CBA in the supernatant (n = 5). (D) Isolated CD4⁺ TILs were stained ex vivo and analyzed by flow cytometry. Proportions of TOX⁺ cells in each Tconv subset are summarized (n = 10). Data are presented as mean ± SD. **P < 0.01; ***P < 0.001; ****P < 0.0001. P values were determined using the Wilcoxon (A and B) and 2-tailed paired t tests (D). Bonferroni’s correction was applied to account for multiple testing in D and significance level was adjusted accordingly (*P < 0.0083; **P < 0.00166; ***P < 0.000166). Tconvs, conventional FOXP3^- CD4 T cells; CBA, cytometric bead array; TILs, tumor-infiltrating lymphocytes.

Figure 3. scRNA-Seq of tumor-infiltrating CD4 Tconvs.

CD45⁺ cells isolated ex vivo from 4 head and neck cancer specimens were subjected to scRNA-Seq. (A) t-SNE plot of 2060 CD4 Tconvs color-coded by their associated cluster. (B) Results of differential expression analysis of scRNA-Seq data from ENTPD1⁺ versus ENTPD1^– CD4 Tconvs are shown in a volcano plot. Genes significantly upregulated in ENTPD1⁺ cells are shown in red and those significantly downregulated are shown in orange. (C) Violin plots showing the expression of CTLA4, HAVCR2, and LAG3 in ENTPD1^– and ENTPD1⁺ cells (left) and t-SNE plots color-coded by levels of expression (gray to red) of ENTPD1, CTLA4, HAVCR2, and LAG3 (right). (D) t-SNE plots showing analysis of TOX exhaustion gene sets (left,ref. , and right, ref. 12) using Single-Cell Signature Explorer Viewer. Tconvs, conventional FOXP3^- CD4 T cells; TILs, tumor-infiltrating lymphocytes.

Figure 4. PD-1^hiCD39⁺ CD4 Tconv TILs encompass tumor Ag–specific cells and respond to PD-1 blockade by enhancing DC-mediated CD8 T cell proliferation.

(A–C) Ex vivo isolated CD4⁺ TILs from one OC NY-ESO-1–seropositive patient were FACS-sorted into PD-1^–CD39^–, PD-1^hiCD39^–, and PD-1^hiCD39⁺ CD4 Tconv (CD3⁺CD4⁺CD25^-CD127⁺) subsets and cloned. (A and B) Clonal populations were stained and analyzed by flow cytometry. (A) PD-1 versus CD39 expression in clones representative of the 3 sorted Tconv populations. (B) Proportions of PD-1⁺ and CD39⁺ cells are summarized for all clones derived from PD-1^–CD39^– (n = 54), PD-1^hiCD39^– (n = 17), and PD-1^hiCD39⁺ (n = 22) subsets. (C) IFN-γ concentration in the supernatant was quantified by ELISA for each clone stimulated with NY-ESO-1 peptide pool (fold increase over unstimulated condition) (n as in B). (D–F) Ex vivo CD4⁺ TILs (± anti–PD-1 mAbs pretreatment) were cocultured with iDCs in the presence or absence of PHA. (D) TNF-α, IFN-γ, IL-2, and IL-12 concentrations were quantified by CBA in the 24-hour supernatants (n = 3). (E) Histogram plots show CD154 expression in CD4 Tconvs after 6-hours stimulation. Proportions of CD154⁺ cells are summarized (n = 5). (F) Histogram plots show CD86 expression in DCs in day 2 cultures. MFI of CD86 staining are summarized (n = 4). (G) CD4⁺ TILs from OC NY-ESO-1–seropositive patients (± anti–PD-1 mAbs pretreatment); autologous iDCs and circulating CD8 T cells were cocultured in the presence of NY-ESO-1 peptides, stained with MHC-I/NY-ESO-1 peptide multimers on day 10, and analyzed by flow cytometry. Examples of dot plots show multimer staining and CD8 expression and proportions of multimer⁺CD8⁺ cells are summarized (n = 5). A 2-tailed paired t test was used to compare variables (E and F). Bonferroni’s correction was applied to account for multiple testing (E and F) and significance level was adjusted accordingly (*P < 0.016; **P < 0.0032). (E and F). Tconvs, conventional FOXP3^- CD4 T cells; TILs, tumor-infiltrating lymphocytes; OC, ovarian cancer; iDCs, immature DCs; CBA, cytometric bead array.