Differential effects of anti-CD20 therapy on CD4 and CD8 T cells and implication of CD20-expressing CD8 T cells in MS disease activity

Abstract

A small proportion of multiple sclerosis (MS) patients develop new disease activity soon after starting anti-CD20 therapy. This activity does not recur with further dosing, possibly reflecting deeper depletion of CD20-expressing cells with repeat infusions. We assessed cellular immune profiles and their association with transient disease activity following anti-CD20 initiation as a window into relapsing disease biology. Peripheral blood mononuclear cells from independent discovery and validation cohorts of MS patients initiating ocrelizumab were assessed for phenotypic and functional profiles using multiparametric flow cytometry. Pretreatment CD20-expressing T cells, especially CD20^dimCD8⁺ T cells with a highly inflammatory and central nervous system (CNS)-homing phenotype, were significantly inversely correlated with pretreatment MRI gadolinium-lesion counts, and also predictive of early disease activity observed after anti-CD20 initiation. Direct removal of pretreatment proinflammatory CD20^dimCD8⁺ T cells had a greater contribution to treatment-associated changes in the CD8⁺ T cell pool than was the case for CD4⁺ T cells. Early disease activity following anti-CD20 initiation was not associated with reconstituting CD20^dimCD8⁺ T cells, which were less proinflammatory compared with pretreatment. Similarly, this disease activity did not correlate with early reconstituting B cells, which were predominantly transitional CD19⁺CD24^highCD38^high with a more anti-inflammatory profile. We provide insights into the mode-of-action of anti-CD20 and highlight a potential role for CD20^dimCD8⁺ T cells in MS relapse biology; their strong inverse correlation with both pretreatment and early posttreatment disease activity suggests that CD20-expressing CD8⁺ T cells leaving the circulation (possibly to the CNS) play a particularly early role in the immune cascades involved in relapse development.

Keywords: CD20-expressing T cells; CD20dim T cells; CD20dimCD8+ T cells; anti-CD20 therapy; ocrelizumab.

Fig. 1.

aCD20 treatment alters CD4⁺ and CD8⁺ T cell phenotype—discovery cohort. Changes in immune-cell subsets of 10 MS patients between pretreatment (Pre) and 2 to 4 mo (M2–4) after aCD20 (ocrelizumab) initiation (see SI Appendix, Fig. S1 for flow cytometry gating strategy). (A) Absolute counts and frequencies of major immune-cell subsets including CD19⁺ B cells, CD4⁺ T cells, CD8⁺ T cells, γδ T cells, NKT, and NK cells. (B) Effect of ocrelizumab on the CD4⁺/CD8⁺ T cell ratio. (C and D) Absolute counts and frequencies of major T cell subsets, including naive (Tn, CCR7⁺CD45RA⁺), central memory (Tcm, CCR7⁺CD45RA⁻), effector memory (Tem, CCR7⁻CD45RA⁻) and terminally differentiated effector memory (Temra, CCR7⁻CD45RA⁺) among CD4⁺ T cells (C), and among CD8⁺ T cells (D). (E and F) Absolute counts and frequencies of cytokine-producing CD4⁺ (E) and CD8⁺ T cells (F) after ex vivo stimulation with phorbol 12-myristate 13-acetate and ionomycin for 4 h. (G and H) Absolute counts and frequencies of CCR2⁺CCR5⁺CD4⁺ (G), and CCR2⁺ CCR5⁺ CD8⁺ T cells (H). Absolute counts and frequencies of adhesion molecule-expressing CD4⁺ T cells (I) and CD8⁺ T cells (J). Statistical analysis was performed using the Wilcoxon matched-pairs signed-rank test followed by multiple comparison correction using the false discovery rate by Benjamini, Krieger, and Yekutieli's two-stage step-up method. P value, *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001.

Fig. 2.

Efficient depletion by aCD20 treatment of CD20^dim T cells that are highly enriched for proinflammatory effector cells. (A) Absolute cell counts and frequencies of CD20^dim T cells of 10 MS patients at baseline (Pre) and months 2 to 4 (M2–4) after the initiation of ocrelizumab. (B) Cell counts and frequencies of CD20^dim cells within CD4⁺ T cells, CD8⁺ T cells, γδ T cells, and NKT cells. (C) Comparison of surface or intracellular markers between CD20^dimCD4⁺ and CD20⁻CD4⁺ cells at baseline (n = 14). (D) Comparison of surface or intracellular markers between CD20^dimCD8⁺ and CD20⁻CD8⁺ cells at baseline (n = 14). Abbreviations: ns, not significant; Tcm, central memory T cells; Tem, effector memory T cells; Temra, terminally differentiated effector memory T cells; Tn, naive T cells. Statistical analysis was performed using the Wilcoxon matched-pairs signed-rank test (A and B) and Wilcoxon matched-pairs signed-rank test followed by multiple comparison correction using the false discovery rate by Benjamini, Krieger, and Yekutieli's two-stage step-up method (C and D). P value, *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001.

Fig. 3.

Correlations between treatment-induced changes in CD4⁺ and CD8⁺ T cell counts, and pretreatment (baseline) counts of CD20^dimCD4⁺ and CD8⁺ T cell subsets. Correlations between: (A) treatment-induced changes (Δ) in CD4⁺ Tem counts and pretreatment (baseline) counts of CD20^dimCD4⁺ Tem cells; (B) treatment-induced changes in IFN-γ⁺CD4⁺ T cell counts and pretreatment counts of CD20^dimIFN-γ⁺CD4⁺ T cells; (C) treatment-induced changes in TNF-α⁺CD4⁺ T cell counts and pretreatment counts of CD20^dimTNF-α⁺CD4⁺ T cells; (D) treatment-induced changes in CD8⁺ Tem counts and pretreatment counts of CD20^dimCD8⁺ Tem; (E) treatment-induced changes in IFN-γ⁺CD8⁺ T cell counts and pretreatment counts of CD20^dimIFN-γ⁺CD8⁺ T cells; (F) treatment-induced changes in TNF-α⁺CD8⁺ T cell counts and pretreatment counts of CD20^dimTNF-α⁺CD8⁺ T cells. Statistical analysis was performed using Spearman correlation coefficient.

Fig. 4.

MS disease activity is associated with decreases in CD20-expressing T cells. (A–C) Comparison of the percentages of (A) CD20^dim and CD20^– T cells; (B) CD20^dim and CD20⁻CD4⁺ T cells; and (C) CD20^dim and CD20⁻CD8⁺ T cells (C) at baseline between MS patients with and without Gadolinium (Gd)-enhancing T1 lesion at baseline (n = 14, n = 10, respectively). (D–F) Correlation between the number of Gd-enhancing T1 lesion at baseline and the frequency of CD20^dim T cells (D); CD20^dimCD4⁺ T cells (E); and CD20^dimCD8⁺ T cells (F). Frequencies of CD20-expressing T cells assessed at baseline (G); and at week 12 (H); and week 24 (I) after ocrelizumab treatment initiation, were compared between patients who did (red symbols) or did not (blue symbols) experience new disease activity beyond 12 wk of ocrelizumab treatment (see also SI Appendix, Table S3). Statistical analysis was performed using the unpaired t test, Mann–Whitney test, or Spearman correlation coefficient. P value, *P < 0.05, **P < 0.01, ***P < 0.001.

Fig. 5.

Reappearing CD20^dimCD8⁺ T cells exhibit a less proinflammatory phenotype compared with pretreatment. Frequencies of naive and memory CD20^dimCD8⁺ T cells (A), cytokine-producing cells CD20^dimCD8⁺ T cells (B), and cytokine-producing memory CD45RA⁻CD20^dimCD8⁺ T cells (C) prior to treatment (Pre) and at time of partial reconstitution at week 24 (W24, n = 18). Statistical analyses were performed by the Wilcoxon matched-pairs signed-rank test followed by multiple comparison correction using the false discovery rate by Benjamini, Krieger, and Yekutieli's two-stage step-up method. P value, *P < 0.05, **P < 0.01.

Fig. 6.

Reappearing B cells early after aCD20 initiation exhibit a predominantly transitional anti-inflammatory phenotype. (A) Kinetics of cell counts and frequencies of total B cells at baseline (Pre, n = 21), 2 to 4 mo (M2–4, n = 11) and 6 to 7 mo (M6–7, n = 12) after the first infusion of ocrelizumab. (B) Kinetics of cell counts and frequency of B cell subsets in PBMCs. (C–E) Comparisons of proliferation markers (C), costimulatory/coinhibitory molecules (D) and adhesion molecules (E) expressed on B cells between at Pre and M6–7. (F) Comparison of cytokine-producing B cells after ex vivo stimulation with phorbol 12-myristate 13-acetate and ionomycin for 4 h between Pre and M6–7. (G) The ratios of proinflammatory cytokines (IL-6 and TNF-α) to anti-inflammatory cytokine (IL-10) in 11 MS patients at Pre and M6–7. Statistical analysis was performed by fitting mixed-effects model with the Geisser–Greenhouse correction, followed by Sidak's multiple comparison to compare the differences among all pairs, or by the Wilcoxon matched-pairs signed-rank test. P value, *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001.