NR4A transcription factors limit CAR T cell function in solid tumours

Abstract

T cells expressing chimeric antigen receptors (CAR T cells) targeting human CD19 (hCD19) have shown clinical efficacy against B cell malignancies^1,2. CAR T cells have been less effective against solid tumours^3-5, in part because they enter a hyporesponsive ('exhausted' or 'dysfunctional') state^6-9 triggered by chronic antigen stimulation and characterized by upregulation of inhibitory receptors and loss of effector function. To investigate the function of CAR T cells in solid tumours, we transferred hCD19-reactive CAR T cells into hCD19⁺ tumour-bearing mice. CD8⁺CAR⁺ tumour-infiltrating lymphocytes and CD8⁺ endogenous tumour-infiltrating lymphocytes expressing the inhibitory receptors PD-1 and TIM3 exhibited similar profiles of gene expression and chromatin accessibility, associated with secondary activation of nuclear receptor transcription factors NR4A1 (also known as NUR77), NR4A2 (NURR1) and NR4A3 (NOR1) by the initiating transcription factor NFAT (nuclear factor of activated T cells)^10-12. CD8⁺ T cells from humans with cancer or chronic viral infections^13-15 expressed high levels of NR4A transcription factors and displayed enrichment of NR4A-binding motifs in accessible chromatin regions. CAR T cells lacking all three NR4A transcription factors (Nr4a triple knockout) promoted tumour regression and prolonged the survival of tumour-bearing mice. Nr4a triple knockout CAR tumour-infiltrating lymphocytes displayed phenotypes and gene expression profiles characteristic of CD8⁺ effector T cells, and chromatin regions uniquely accessible in Nr4a triple knockout CAR tumour-infiltrating lymphocytes compared to wild type were enriched for binding motifs for NF-κB and AP-1, transcription factors involved in activation of T cells. We identify NR4A transcription factors as having an important role in the cell-intrinsic program of T cell hyporesponsiveness and point to NR4A inhibition as a promising strategy for cancer immunotherapy.

Extended Data Figure 1 |. Functional assessment of a human CD19 (huCD19)-reactive chimeric antigen receptor (CAR).

(a) Left three panels, EL4, MC38 and B16-OVA cell lines expressing huCD19. Gray, parental; black, huCD19-expressing cells. Right; B16-OVA-huCD19 cells recovered after growth in a C57BL/6J mouse followed by culture for 7 days. Gray, isotype control; black, anti-huCD19. Data from one biological replicate in each case. (b) Left, growth curves (mean ± s.e.m., 15 mice per group) of 250,000 B16-OVA parental or B16-OVA-huCD19 tumor cells in vivo after inoculation into C57BL/6J mice. There is no significant difference at any timepoint (ordinary two-way ANOVA, p >0.9999). Right, growth curves (mean ± s.e.m.) of 250,000 (n=5 mice) or 500,000 (n=6 mice) B16-OVA-huCD19 tumor cells in vivo after inoculation (significant difference between the two groups at day 21; ordinary two-way ANOVA; *p=0.0146). (c) Diagram of the CAR construct. LS, leader sequence; SS, signal sequence; myc, myc epitope-tag; scFv, single chain variable fragment against human CD19; followed by the mouse (m) CD28 and CD3ζ signaling domains, the 2A self-cleaving peptide and the mouse Thy1.1 reporter. (d) CAR surface expression monitored by myc epitope-tag and Thy1.1 expression. Mock-transduced CD8⁺ T cells were used as controls. (e) Cytokine (TNF, IFNγ) production by CAR CD8⁺ T cells after restimulation with EL4-huCD19 cells or with PMA/ionomycin. (f) Quantification of the data shown in (e); p-values (TNF: ****p<0.0001, IFNγ: ***p=0.0009) were calculated using a two-tailed unpaired t-test. (g) In vitro killing assay (mean ± s.e.m.) of CD8⁺ CAR and mock-transduced T cells; data from two biologically independent experiments, each with three technical replicates. (h) Inhibitory surface receptor expression on CAR- and mock-transduced CD8⁺ T cells cultured in vitro for 5 days; data representative of three biological replicates. Gray shading, isotype control, black line, mock or CAR. Data in (d, e, h) are representative of 3 independent experiments. For all p-value calculations, *p ≤0.05, **p ≤0.01, ***p ≤0.001, ****p ≤0.0001.

Extended Data Figure 2 |. Adoptively transferred CD8⁺ CAR-T cells infiltrating B16-OVA-huCD19 tumors exhibit phenotypes and gene expression profiles similar to those of OT-I and endogenous CD8⁺ TILs.

(a, b) Experimental design to assess CD45.1⁺ OT-I and CD45.2⁺ endogenous TILs; 1.5×10⁶ OT-I T cells were adoptively transferred into C57BL/6J mice 13 days after tumor inoculation. (c) Tumor growth curves (mean ± s.e.m.) of mice adoptively transferred with CAR or OT-I CD8⁺ T cells; graph is a compilation of 3 independent experiments. At days 7 and 21, mouse numbers were: CAR, n=24, 17; for OT-I, n=21, 20. (d) Tumor growth curves (mean ± s.e.m.) of mice adoptively transferred with CAR or PBS; graph is a compilation of 3 independent experiments. At days 7 and 21, mouse numbers were: CAR n=35, 35; PBS n=8, 6. (c, d) For tumor sizes on day 21 after tumor inoculation, p=0.3527 for CAR compared to OT-I (c) and p=0.6240 for PBS compared to CAR (d); p-values were calculated using a two-tailed unpaired t-test with Welch’s correction, *p ≤0.05, **p ≤0.01, ***p ≤0.001, ****p ≤0.0001. (e, f) Flow cytometry gating scheme for CAR (e) and OT-I (f) CD8⁺ TILs. (g) Mean average (MA) plots of genes differentially expressed in the indicated comparisons. Wald test was performed to calculate p-values, as implemented in DESeq2; p-values were adjusted using the Benjamini-Hochberg method. Genes differentially expressed (adjusted p-value <0.1 and log₂FoldChange ≥1 or ≤−1) are highlighted. Selected genes are labeled. Top row, comparisons of the CAR-TIL populations amongst themselves and to endogenous PD-1^loTIM3^lo TILs; middle row, comparisons within the endogenous TIL populations; bottom row, comparisons of CAR and endogenous PD-1^hiTIM3^hi TILs (left), and CAR and endogenous PD-1^hiTIM3^lo TILs (right).

Extended Data Figure 3 |. Adoptively transferred CAR-expressing mouse CD8⁺ T cells infiltrating B16-OVA-huCD19 tumors exhibit chromatin accessibility profiles similar to those of endogenous CD8⁺ TILs.

(a) Pairwise euclidean distance comparisons of log₂ transformed ATAC-seq density (Tn5 insertions per kilobase) between all replicates at all peaks accessible in at least one replicate. (b) Scatterplot of pairwise comparison of ATAC-seq density (Tn5 insertions per kb) between samples indicated. (c) Genome browser views of sample loci, Pdcd1 (left), Itgav (right); scale range is from 0–600 for all tracks and data are the mean of all replicates. CD8⁺ TIL populations are as indicated and defined in Fig. 1b, 1d: (A) PD-1^hiTIM3^hi CAR, (B) PD-1^hiTIM3^lo CAR, (C) PD-1^hiTIM3^hi endogenous, (D) PD-1^hiTIM3^lo endogenous, (E) PD-1^loTIM3^lo endogenous.

Extended Data Figure 4 |. Mouse and human CD8⁺ TILs exhibit increased expression of Nr4a1, Nr4a2, Nr4a3.

(a, b) Flow cytometry gating scheme for CAR (a) and endogenous (b) CD8⁺ TILs. (c) Representative flow cytometry histograms of Nr4a proteins in PD-1^hiTIM3^hi TILs, PD-1^hiTIM3^lo TILs, and PD-1^loTIM3^lo TILs and their corresponding fluorescence minus one controls (in off-white). Data are representative of 3 independent experiments in which the sample from each independent experiment is comprised of TILs pooled together from 9–14 mice. (d) Representative flow cytometry histograms for Nr4a protein expression, comparing CAR and endogenous TIL populations (A-E) defined in Fig. 1. (e, f, g) Plotting in single cells the expression of PDCD1 and HAVCR2 (x- and y-axis respectively), and (displayed by the color scale) the expression of the following: (e) Genes differentially upregulated in PD-1^hiTIM3^hi TILs relative to PD-1^loTIM3^lo TILs. (f) Genes coding for selected TFs showing differential expression in the comparison of PD-1^hiTIM3^hi TILs relative to PD-1^loTIM3^lo TILs. (g) Genes differentially downregulated in PD-1^hiTIM3^hi TILs relative to PD-1^loTIM3^lo TILs. Each dot represents a single cell. Human CD8⁺ TILs data are from [ref.14].

Extended Data Figure 5 |. Prolonged survival of immunocompetent tumor-bearing mice adoptively transferred with CD8⁺ Nr4aTKO compared to WT CAR-T cells.

(a) CD8a only staining control (previously tested to be the same as fluorescence minus one controls for CAR⁺ expression and NGFR⁺ expression) of CAR-T cells prior to adoptive transfer. (b) CAR and NGFR expression of CD8⁺ WT CAR-T cells prior to adoptive transfer. (c) CAR and NGFR expression of CD8⁺ Nr4aTKO CAR-T cells prior to adoptive transfer. Data in (a-c) are representative of 4 independent experiments. (d) 6×10⁶ CAR-T cells were adoptively transferred into C57BL/6J mice 7 days after tumor inoculation. (e) Growth of B16-OVA-huCD19 (left;13–15 mice per condition) and MC38-huCD19 (right; 10 mice per condition) tumors in individual mice. (f) B16-OVA-huCD19 (left) and MC38-huCD19 (right) tumor sizes (mean ± s.d.) at day 21 and 19 post inoculation respectively. p-values were calculated using an ordinary one-way ANOVA with Tukey’s multiple comparisons test: B16-OVA-huCD19, no significant difference; MC38-huCD19, PBS vs Nr4aTKO ***p=0.0001; PBS vs WT, p=0.3252; WT vs Nr4aTKO, *p=0.0120. (g) Survival curves for mice bearing B16-OVA-huCD19 tumors (left) and MC38-huCD19 tumors (right). p-values calculated using log-rank (Mantel-Cox) test. For B16-OVA-huCD19, surviving mouse numbers at d7, d21, d90 were: PBS, n=13, 11, 0; WT, n=15, 11, 0; Nr4aTKO, n=14, 13, 2; * p=0.0026. For MC38-huCD19, surviving mouse numbers at d7 and d19 were: PBS, n=10, 9; WT, n =10, 7; Nr4aTKO, n=10, 10; all mice died by d23; *p=0.0138. For all p-value calculations in (f, g), *p ≤0.05, **p ≤0.01, ***p ≤0.001, ****p ≤0.0001.

Extended Data Figure 6 |. Tumor-bearing mice adoptively transferred with CAR CD8⁺ T cells lacking all three Nr4a family members exhibit prolonged survival compared to mice transferred with wildtype CAR CD8⁺ T cells or CAR CD8⁺ T cells lacking only one of the three Nr4a family members.

(a) Experimental design; 3×10⁶ WT, Nr4aTKO, Nr4a1KO, Nr4a2KO, or Nr4a3KO CAR-T cells were adoptively transferred into Rag1−/− mice 7 days after tumor inoculation. (b) Growth of B16-OVA-huCD19 tumors in individual mice, comprised of 17 or more mice per condition (these data include the WT and Nr4aTKO data from Figure 3). (c) Graph shows mean ± s.d. and the individual values of B16-OVA-huCD19 tumor sizes at day 21 after inoculation. p-values were calculated using an ordinary one-way ANOVA with Tukey’s multiple comparisons test; PBS vs WT, *p=0.0395; WT vs Nr4a1KO, p=n.s.=0.0511; WT vs Nr4a2KO, **p=0.002, WT vs Nr4a3KO, *p=0.0161; and WT vs Nr4aTKO, ****p<0.0001. (d) Survival curves. **** p< 0.0001, calculated using log-rank (Mantel-Cox) test. Surviving mouse numbers at d7, d21, and d90 were n=31, 14, 0 for PBS; n=35, 25, 1 for WT; n=17, 12, 0 for Nr4a1KO; n=17, 15, 1 for Nr4a2KO; n=32, 22, 11 for Nr4a3KO; and n=39, 36, 27 for Nr4aTKO. For all p-value calculations, *p ≤0.05, **p ≤0.01, ***p ≤0.001, ****p ≤0.0001.

Extended Data Figure 7 |. Phenotypic and genomic features of mouse CD8⁺ T cells expressing Nr4a1, Nr4a2 or Nr4a3.

Mouse CD8⁺ T cells were isolated, activated, transduced with empty retrovirus or retroviruses encoding HA-tagged Nr4a1, Nr4a2, or Nr4a3 with human NGFR reporter, and assayed on day 5 post activation. (a) Flow cytometry gating of CD8⁺ NGFR⁺ empty vector control, Nr4a1, Nr4a2, and Nr4a3-expressing cells at a constant expression level of NGFR reporter. (b) Quantification of surface receptor expression (data from 3 independent replicates). (c) Representative flow cytometry plots of cytokine production upon restimulation with PMA/ionomycin. (d) Quantification of the data in (c). All p-values were calculated using an ordinary one-way ANOVA with Dunnett’s multiple comparisons test; *p ≤0.05, **p ≤0.01, ***p ≤0.001, ****p ≤0.0001. (e) PCA plot of RNA-seq data from in vitro resting mouse CD8⁺ T cells ectopically expressing Nr4a1, Nr4a2, Nr4a3, and empty vector control. (f) MA plots of genes differentially expressed in the comparisons of ectopic expression of Nr4a1, Nr4a2, or Nr4a3 against empty vector (top row), and pairwise comparisons between the ectopic expression of various Nr4a family members (bottom row). Wald test was performed to calculate p-values, as implemented in DESeq2. p-values were adjusted using the Benjamini-Hochberg method. Genes differentially expressed (adjusted p-value <0.1 and log₂FoldChange ≥1 or ≤−1) are highlighted using different colors as indicated in the PCA plot as in (e). Selected genes are labeled. (g) Scatterplot of pairwise comparison of ATAC-seq density (Tn5 insertions per kb) between the indicated samples. Data in (a-d) are from three independent experiments, data in (e-g) from two independent experiments, each with two technical replicates.

Extended Data Figure 8 |. CD8⁺ Nr4aTKO CAR-TILs show increased effector function compared to WT CAR-TILs.

(a) Tumor growth curves (mean ± s.e.m.) after adoptive transfer of 1.5×10⁶ CAR-T cells into Rag1−/− mice on day 13 after tumor inoculation. Mouse numbers at d7 and d21 were: WT, n=47, 35; Nr4aTKO, n=41, 32. p-values were calculated using an ordinary 2-way ANOVA with Tukey’s multiple comparisons test; for WT vs Nr4aTKO, p=0.6908. (b) Flow cytometry gating scheme for surface markers, cytokines, and TFs expressed by WT (top) and Nr4aTKO (bottom) TILs. All samples are gated on cells with a set level of CAR expression (10³ – 10⁴) within the CAR⁺ NGFR⁺ population. (c) Bar plots (mean ± s.d.) showing (left) number of WT and Nr4aTKO CAR-TILs per gram of tumor (5 independent experiments; p-value was calculated using a two-tailed ratio paired t-test) and (right) MFI of Ki67 of WT and Nr4aTKO CAR-TILs (2 independent experiments). (d) Top, representative flow cytometry for TIM3 and TCF1 expression in WT and Nr4aTKO CAR-TILs (2 independent experiments). Bottom, bar plots (mean ± s.d.) of TF expression by WT and Nr4aTKO CAR-TILs (6 independent experiments). p-values were calculated using two-tailed paired t-tests. For all p-value calculations, *p ≤0.05, **p ≤0.01, ***p ≤0.001, ****p ≤0.0001. (e) PCA plot of RNA-seq data from Nr4aTKO or WT CAR-TILs. (f) Normalized enrichment scores (NES) of gene sets defined from pairwise comparisons of effector, memory and exhausted CD8⁺ T cells from LCMV-infected mice. Enrichment score calculated using a Kolmogorov-Smirnov test, as implemented in gene set enrichment analysis (GSEA). (g) GSEA of RNA-seq data from Nr4aTKO and WT CAR-TILs displayed as enrichment plots, ranking genes by log₂ fold change in expression between those conditions. The false discovery rate (FDR) for both (f, g) is controlled at a level of 5% by the Benjamini–Hochberg correction. For (e-g), data are from two independent experiments each consisting of 1–2 technical replicates.

Extended Data Figure 9 |. Nr4a family members bind to predicted Nr4a binding motifs that are more accessible in the WT CAR-TILs compared to the Nr4aTKO CAR-TILs, and regions more accessible in WT compared to Nr4aTKO CAR-TILs are more accessible in CA-RIT-NFAT1- and Nr4a1/2/3-transduced cells.

(a) Right top, histogram view showing expression of Nr4a in cells ectopically expressing HA-tagged versions of Nr4a1, Nr4a2, Nr4a3; data are representative of 2 independent experiments. Middle, genome browser views of the Ccr7, Ccr6, Ifng loci for WT CAR-TILs compared to Nr4aTKO CAR-TILs, including binding motifs for NFAT, Nr4a (Nur77), bZIP, NFkB, and the location of the qPCR primers used. Scale range is 0–1000 for all tracks and data are mean of two independent experiments. Right, bar plots showing enrichment of Nr4a at regions probed; data representative of 2 independent experiments consisting of three technical replicates each. (b) Genome browser views of the Il21 (top), Tnf (bottom) loci incorporating WT CAR-TILs compared to Nr4aTKO CAR-TILs, including binding motifs for NFAT, Nr4a (Nur77), bZIP, NFkB. Scale range is 0–600 for all tracks except Tnf for which the scale is 0–1000; data are mean of two independent experiments. (c) Top four panels, ATAC-seq data from Nr4aTKO and WT CAR-TILs compared with data from cells ectopically expressing CA-RIT-NFAT1, Nr4a1, Nr4a2, or Nr4a3. Bottom panel, ATAC-seq data from Nr4aTKO and WT CAR-TILs compared with data from cultured cells stimulated with PMA/ionomycin.

Extended Data Figure 10 |. Nr4a family members show a moderate decrease in mRNA expression in antigen-specific cells from LCMV-infected mice treated with anti-PDL1 or IgG control.

(a) MA plots of genes differentially expressed in cells treated with anti-PDL1 compared to cells treated with IgG control, highlighting two different categories of differentially expressed genes: those with adjusted p-value <0.1 and log₂FoldChange ≥0.5 or ≤−0.5 (lighter colors); and those with adjusted p-value < 0.1 and log₂FoldChange ≥1 or ≤−1 (darker colors). Selected genes are labeled. Displayed are the number of genes in each category. The sequencing data in this analysis was obtained from [ref.19]. Wald test was performed to calculate p-values, as implemented in DESeq2; p-values were adjusted using the Benjamini-Hochberg method.

Figure 1 |. CAR, OT-I, and endogenous CD8⁺ TILs isolated from B16-OVA-huCD19 tumors exhibit similar phenotypes.

(a) Experimental design to assess CAR and endogenous TILs; 1.5×10⁶ CAR-T cells were adoptively transferred into C57BL/6J mice 13 days after tumor inoculation. (b) Left, representative flow cytometry plot identifying CD45.2⁺ endogenous TILs and CD45.1⁺Thy1.1⁺ CAR-TILs (Thy1.1 encoded in the CAR retroviral vector). Right, flow cytometry plots showing PD-1 and TIM3 surface expression on CD8⁺ CAR and endogenous TILs. (c) Bar graph showing the percentage of CAR and OT-I TILs in total CD8⁺ TILs. Bars show mean values with data points for 6, 5 and 11 independent experiments for CAR, OT-I and endogenous TILs respectively. (d) Quantification of cytokine production after restimulation of CAR, OT-I and endogenous CD8⁺ TILs, compared to cultured CD8⁺ CAR-T cells stimulated with PMA/ionomycin or left unstimulated. Bars show mean values with data points for 3 independent experiments. All p-values were calculated using two-tailed unpaired t-tests with Welch’s correction, *p≤0.05, **p≤0.01, ***p≤0.001, ****p≤0.0001. (e) Representative flow cytometry plots of cytokine production after restimulation.

Figure 2 |. CAR and endogenous CD8⁺ TILs exhibit similar gene expression and chromatin accessibility profiles.

(a) Principal component analysis of RNA-seq data from PD-1^hiTIM3^hi (A) and PD-1^hiTIM3^lo (B) CAR-TILs, and endogenous PD-1^hiTIM3^hi (C), PD-1^hiTIM3^lo (D), PD-1^loTIM3^lo (E) TILs. Data represent 3 independent experiments, each using TILs pooled from 9–14 mice. (b) Top, heatmap of mouse CD8⁺ T cell ATAC-seq data showing log₂ fold change from row mean for 9 k-means clusters. Bottom, heatmap of motif enrichment analysis. Data shown for one representative member of TF families enriched in at least one cluster compared to all accessible regions. (c) Quantification of Nr4a expression (MFI); p-values for CAR comparisons (top) were calculated using two-tailed paired t-tests; p-values for endogenous comparisons (bottom) were calculated using row-matching one-way ANOVA with Greenhouse-Geisser correction and Tukey’s multiple comparisons tests; for both calculations, *p≤0.05, **p≤0.01, ***p≤0.001, ****p≤0.0001. Data show mean and individual values from three independent experiments, each using TILs pooled from 9–14 mice. (d) Scatterplots of RNA-seq data showing expression of PDCD1 (x-axis) and HAVCR2 (y-axis) in single cells of human CD8⁺ TILs, with expression of the indicated NR4A genes shown in the color scale. Each dot represents a single cell. (e) Top, human CD8⁺ T cell ATAC-seq data from PD-1^hi TILs (two samples from melanoma, one sample from non-small cell lung tumor [ref. 13]) and antigen-specific CD8⁺ T cells from HIV-infected individuals showing log₂ fold change from row mean for 9 k-means clusters. Bottom, heatmap of motif enrichment analysis.

Figure 3 |. Nr4a-deficient CAR-TILs promote tumor regression and prolong survival.

(a) Experimental design; 3×10⁶ WT or Nr4aTKO CAR-T cells were adoptively transferred into Rag1−/− mice 7 days after tumor inoculation. PBS was injected as a control. (b) Top, tumor growth in individual mice. Bottom, tumor sizes of individual mice at day 21 (mean ± s.d.); p-values calculated using an ordinary one-way ANOVA with Tukey’s multiple comparisons test. (c) Survival curves; ****p<0.0001 calculated using log-rank (Mantel-Cox) test. Surviving mouse numbers at d7, d21 and d90 were n=21, 14, 0 (PBS); n=35, 25, 1 (WT); n=39, 36, 27 (Nr4aTKO). (d) Experimental design; 1.5×10⁶ WT or Nr4aTKO CAR-T cells were adoptively transferred into Rag1−/− mice 13 days after tumor inoculation, and analyzed 8 days later. (e) Surface PD-1 and TIM3 expression on CAR⁺ NGFR⁺ cells with a set level of CAR expression (10³ – 10⁴). Representative flow cytometry plots (top), histograms (middle and bottom, left) and means and individual values (right) of 6 independent experiments, each using TILs pooled from 3–8 mice. p-values were calculated using two-tailed paired t-tests with Welch’s correction. (f) Top, representative flow cytometry plots for TNF and IFNγ production. Bottom, quantification of 5 independent experiments, each using TILs pooled from 3–8 mice. IL-2 was not detectable above background (not shown). p-values were calculated using two-tailed paired t-tests between unstimulated and stimulated WT and Nr4aTKO CAR-TILs. For all p-value calculations, *p≤0.05, **p≤0.01, ***p≤0.001, ****p≤0.0001.

Figure 4 |. Gene expression and chromatin accessibility profiles indicate increased effector function of Nr4aTKO compared to WT CAR-TILs.

(a) Mean average plots of genes differentially expressed in Nr4aTKO versus WT CAR-TILs; p-values calculated using Wald test (as implemented in DESeq2), and adjusted using the Benjamini-Hochberg method. Differentially expressed genes (adjusted p-value <0.1, log₂FoldChange ≥1 or ≤−1) are highlighted; selected genes are labeled. (b) Heatmap of genes with opposing expression changes between Nr4a deletion and Nr4a overexpression. Fold change values (log₂scale) of genes differentially expressed in Nr4aTKO relative to WT CAR-TILs were compared to corresponding values in cells ectopically expressing Nr4a1, Nr4a2, or Nr4a3, and 7 k-means clusters were identified. Genes downregulated after Nr4a deletion/ upregulated after Nr4a overexpression (e.g. Pdcd1, Havcr2, Tox), or upregulated after Nr4a deletion/ downregulated after Nr4a overexpression (e.g. Tnf, Il21) are indicated. (c) Scatterplot of pairwise comparison of ATAC-seq density (Tn5 insertions per kb) between Nr4aTKO and WT CAR-TILs, showing differentially accessible regions and associated de novo identified motifs. (d) Left, genome browser view of the Pdcd1 locus in all previously-mentioned ATAC-seq samples and CA-RIT-NFAT1-transduced cells. Gray bar, exhaustion-specific enhancer ~23 kb 5’ of the Pdcd1 TSS. Top right, histogram of Nr4a expression in cells expressing HA-tagged Nr4a1, Nr4a2, or Nr4a3 (representative of two biological replicates). Bottom right, ChIP-qPCR showing enrichment of HA-tagged Nr4a over background at the Pdcd1 enhancer (technical replicates from one of two independent experiments). (e) Proposed role of Nr4a in T cells chronically stimulated with antigen.