LXR-inverse agonism stimulates immune-mediated tumor destruction by enhancing CD8 T-cell activity in triple negative breast cancer

Abstract

Triple-negative breast cancer (TNBC) is a highly aggressive subtype that is untreatable with hormonal or HER2-targeted therapies and is also typically unresponsive to checkpoint-blockade immunotherapy. Within the tumor microenvironment dysregulated immune cell metabolism has emerged as a key mechanism of tumor immune-evasion. We have discovered that the Liver-X-Receptors (LXRα and LXRβ), nuclear receptors known to regulate lipid metabolism and tumor-immune interaction, are highly activated in TNBC tumor associated myeloid cells. We therefore theorized that inhibiting LXR would induce immune-mediated TNBC-tumor clearance. Here we show that pharmacological inhibition of LXR activity induces tumor destruction primarily through stimulation of CD8+ T-cell cytotoxic activity and mitochondrial metabolism. Our results imply that LXR inverse agonists may be a promising new class of TNBC immunotherapies.

Figure 1

TNBC tumors produce LXR-agonists that inhibit myeloid cell activity (A) Table showing patient tumor pathology data. Samples BC3 and BC5 are triple-negative breast tumors. Tumor infiltrating immune cells were isolated and subjected to single cell RNA-sequencing (scRNA-seq) as described by Azizi et al.. (B) scRNA-seq data showing NR1H3 (LXRα) expression among tumor infiltrating immune cells from the tumors listed in A. Red boxes highlight the TNBC tumors (BC3 and BC5). (C) Dot-plot of sc-RNA-seq data showing the average expression and the percentage of cells expressing LXRα (NR1H3) and ABCA1 among tumor infiltrating immune-cells. Red boxes highlight the TNBC tumors (BC3 and BC5). (D) sc-RNA-seq data dot-plot showing clusters of TNBC tumor-infiltrating immune cells that express LXRα and (E) ABCA1. Cell type clusters were generated using Seurat (see Materials and Methods section for details). (F) LXRE-driven Luciferase reporter assay (LXRE-Luc) showing induction of LXR transactivation in response to tumor-conditioned media (TCM). BT549: human TNBC cell line. E0771: mouse TNBC cell line. HEK-293 cells were transfected with LXRE-Luc plasmid reporter and exposed to increasing percentages of TCM for 24 h. (G) LXRE-Luc reporter assay showing fold induction of LXR activity in response to E0771 TCM alone or in combination with 100 nM of the LXR inverse agonist SR9243 or 100 nM GW3965. (H) RT-QPCR analysis showing induction of Lxrα, Lxrβ, and the Lxr target genes Abca1, Fasn and Srebp1c in bone marrow derived macrophages (BMDMs) treated with TCM or control E0771 culture media (RPMI1640 + 10%FBS). (I) Expression of the proinflammatory (M1) macrophage marker; Tnfα, or the anti-inflammatory (M2) marker; Cd36 in LPS-activated mature BMDMs in response to 10 μM SR9243 or 5 μM GW3965 treatment for 24 h. Letters above bars identify means that are significantly different based on p < 0.05 as determined by 2-Way ANOVA.

Figure 2

LXR inhibition using SR9243 promotes CD4+ T-cells Th1 polarization and inhibits Treg viability (A) FACs histogram showing Tbet expression in differentiated Th1 CD4+ T-cells (CD3+ CD4+ Tbet+) exposed to vehicle (DMSO), SR9243 or GW3965. (B) Mean count as determined by FACs of Th1 (Tbet+ CD3+ CD4+) T-cells generated from Th0 cells cultured in Th1 differentiation conditions (αCD3, αCD28, IL2, IL12 and αIL4) and treated with DMSO, SR9243 or GW3965 for 7 days (C) FACs showing the mean percentage of Th1 polarized cells generated from Th0 splenocytes cultured under Th1 polarizing conditions and exposed to DMSO vehicle, SR9243 or GW3965 treatment for 7 days. (D) FACs showing the average percentage of Th2 cells (CD3+ CD4+ Gata3+) produced from Th0 splenocytes cultured under Th2 polarizing conditions (αCD3, αCD28, αIFNγ, IL2 and IL4) and exposed to vehicle, SR9243 or GW2965 treatment for 7 days. (E) FACs histogram showing the viability of polarized Th1 cells in response to vehicle, SR9243 or GW3965 with TCM (-upper panel) or RPMI1640 control media (-lower panel) for 24 h. (F) FACs data showing the mean percentage of Th1-polarized cells produced in response to DMSO, SR9243 or GW3965 treatment for 24 h with or without TCM cotreatment. (G) FACs data showing the number of viable Treg cells (CD4+ Foxp3+) produced from Th0 cells cultured under Treg differentiation conditions (αCD3, αCD28, αIFNγ, αIL12/αIL23, αIL4, IL6 and TGFβ) and treated with TCM or control media in tandem with DMSO, SR9243 or GW3965 for 7 days (H) FACs quantified viability of fully differentiated Tregs exposed to DMSO, SR9243 and GW3965 with or without TCM for 24 h. (I) FACs analysis showing the percentage of fully differentiated Tregs produced in response to DMSO, SR9243 or GW3965 with TCM or control media treatment for 24 h. For all experiments naïve CD4+ (Th0) splenocytes and lymphocytes were isolated from C57BL6J mice using a pan CD4+ negative selection affinity column (Miltenyi) and differentiated under Th1/Th2/Treg polarizing conditions as described. Cells were treated with 10 μM SR9243, 5 μM GW3965 or DMSO for 7 days or with LXR ligands and either 50% E0771 TCM or RPMI1640 control media for 24 h starting on day 6 of differentiation where stated. FACs histograms are representative results. All bar graphs are average percentages from three repeat experiments. *p < 0.05 1-Way ANOVA.

Figure 3

LXR inhibition activates CD8+ T-cells. (A) The number of CD8+ effector T-cells. (CD3+ CD8+ Tbet+) produced in response to 10 μM SR9243 or 5 μM GW3965 or DMSO vehicle treatment for 24 h as determined by FACs. (B) Percentage of CD8 + effector T-cells (CD3+ CD8+ Tbet+) produced from differentiated CD8+ T-cells treated with SR9243, GW3965 or vehicle for 24 h. Naïve CD8+ T-cells were isolated from C57BL6J mouse splenocytes using negative selection column purification (Militenyi) and cultured under CD8+ differentiation conditions (αCD3, αCD28, IL2 and IL7) for 4 days and exposed to LXR ligands for 24 h starting on day 3. (C–E) Cytometric bead assay showing CD8+ T-cell production of (C) IFNγ (D) IL6 and (E) IL2 in response to 10 μM SR9243 or 5 μM GW3965 for 24 h. Differentiated CD8+ T-cells were re-stimulated using 50 ng/mL/1 µg/mL PMA/Ionomycin for 4 h prior to cytokine quantification. (F) Average percentage of IFNγ expressing CD8+ effector T-cells (CD3+ CD8+ Tbet+) produced from differentiated CD8+ T-cells exposed to vehicle, 10 μM SR9243 or 5 μM GW3965 in the presence or absence of TCM. Cells were treated with LXR ligands for 24 h prior to FACs analysis (G) FACs histogram showing PD-1 expression in CD8+ effector T-cells treated with vehicle, SR9243 or GW3965 in the presence of 50% E0771 TCM or relevant control media (RPMI1640) for 24 h (H) Average PD-1 expression in CD8+ effector T-cells treated with vehicle, SR9243 or GW3965 for 24 h as determined by FACs analysis. (I) Carboxyfluorescein succimidyl (CFSE) proliferation assay of differentiating CD8+ T-cells treated with SR9243 or DMSO. Column isolated CD8 T cells were labeled with 1 µM CellTrace^TM CFSE (ThermoFisher) for 20 minutes at room temperature, then subjected to CD8+ T-cell differentiation conditions for 96 h, as described, in the presence of vehicle or 10 µM SR9243. Expansion, proliferation and replication indices were then determined via FACs analysis of CFSE dilution profiles using Flow-Jo. (J) Cell killing/CD8+ T-cell cytotoxicity assay showing CD8+ T-cell destruction of cultured E0771 cells in response to SR9243, with or without TCM co-treatment. CD8+ T-cells were differentiated for 4 days then exposed to 10 μM SR9243 along with 50% E0771 TCM or RPMI1640 for 24 h. CD8+ cells were exposed to CD3/CD28 activation in the presence of target cells; E0771 cells were pre-stained with 1 µM CFSE and 4 µg/mL 7-Aminoactinomycin-D (7-AAD). The percentage of E0771 cells (CFSE + 7-AAD+) were then quantified via FACs. (K) Mean percentage of IFNγ + GZMB+ human CD8+ T-cells (CD3+ CD8+ Tbet+) produced in response to SR9243, with or without PD-L1 immune-checkpoint suppression. CD8+ T-cells were isolated from PMBCs from healthy female volunteers via negative selection using the RosetteSep™ Human CD8+ T Cell Enrichment Cocktail. Cells were then exposed to 5 μg/mL purified human PD-L1 protein or vehicle (PBS) in the presence of 100 nM SR9243 for 24 h. *p < 0.05 as determined by 1-Way ANOVA.

Figure 4

LXR inhibition enhances CD8+ T-cell mitochondrial metabolism. (A) Extracellular flux analysis (Seahorse) showing the oxygen consumption rate (OCR) of mouse CD8+ T-cells exposed to 50% RPMI1640 control culture media (−TCM) and either DMSO (vehicle), SR9243 or GW3965 for 4 h. (B) OCR of mouse CD8+ T-cells cultured in 50% E0771-TCM (+TCM) and treated with vehicle, SR9243 or GW3965 for 24 h. (C,D), Mitochondrial profiling (OCR) of mature CD8+ T-cells isolated from wildtype C57BL6J (Nr1h3^+/+) or LXRα knockout mice (Nr1h3^−/−) mice cultured in 50% TCM (TCM) or relevant control media (Control) for 24 h prior to analysis. (E,F), Glycolytic metabolism profiling showing the extracellular acidification rate (ECAR) of mature Nr1h3^+/+ or Nr1h3^−/− CD8+ T-cells cultured in TCM (TCM) or control media (Control) for 24 h. OCR and ECAR were quantified simultaneously using the XF96 Seahorse bioanalyzer (Agilent). CD8+ T-cells were column isolated from mouse splenocytes and differentiated for 3 days as described and treated with DMSO 100 nM SR9243 or 100 nM GW3965 for 4 h then plated in Seahorse base-media prior to analysis. Glycolytic and mitochondrial profiles were determined using the XF-Mitochondrial stress-test or the Glycolysis stress-test assay (Agilent) as per manufacturer’s instructions. Olig.: Olygomycin, FCCP: carbonylcyanide-4 (trifluoromethoxy) phenylhydrazone Rot + Ant: Rotenone and Antimycin A, Gluc: glucose, 2-DG: 2-deoxyglucose. (G) Oil-Red-O neutral lipid staining showing lipid content of wildtype CD8+ T-cells exposed to 100 nM SR9243 or 100 nM GW3965 for 24 h. Micrographs shown are representative images from 2 repeat experiments. (H) Mean lipid content quantified from images of Oil-Red-O stained CD8+ T-cells. Oil-Red-O and DAPI nuclear staining quantified using ImageJ. (I) Total cholesterol content of CD8+ T-cells treated with 100 nM SR9243 and 100 nM GW3965 for 24 h. (J) Ratio of membrane-versus-intracellular cholesterol in mature CD8+ T-cells treated with vehicle or 100 nM SR9243 or 100 nM GW3965 for 24 h. Cholesterol content measured using Amplex-Red Assay (Sigma) using manufacturer’s instructions. (K) RT-QPCR-quantified expression Abcg1 in CD8+ T-cells in response to LXR ligands and TCM. For staining and RT-QPCR CD8+ T-cells were column isolated and differentiated as described, 3 days then exposed to the LXR ligands for 24 h. *p < 0.05 determined by 2-Way ANOVA or 1-Way ANOVA where relevant.

Figure 5

SR9243 induces immune-mediated TNBC tumor destruction in vivo. (A,B) E0771-tumor volumes in C57BL6J mice treated with vehicle (DMSO:Tween80:PBS/10:10:80) or 60 mg/kg SR9243 for 16 days. A: Line graph showing growth of individual tumors. B: Line graph showing the mean tumor volume for each group. (C,D) EMT6-tumor volumes in C57BL6J mice treated with vehicle or 60 mg/kg SR9243. C: Line graph showing growth of individual tumors. (D) Line graph showing the mean tumor volume for each group. (E,F) E0771-tumor volumes in Foxn1^nu nude mice treated with vehicle or 60 mg/kg SR9243. C: Line graph showing growth of individual tumors. (D) Line graph showing the mean tumor volume for each group. Mice were implanted with 1 × 10⁶ E0771 or 2 × 10⁵ EMT6 cells in the lower left mammary fat pad. Tumors were allowed to establish to 50 mm³ then mice were treated with 60 mg/kg SR9243 or vehicle (10:10:80-DMSO:Tween80:PBS) once daily for 16 days (n = 6). Tumor volume was calculated using perpendicular caliper measurements (1/2LW²). *p < 0.05 as determined by 2-Way-ANOVA (G) Histogram displaying the number of tumor resident dendritic cells (CD11C + MHCII+) in SR9243 versus vehicle treated E0771 tumor-bearing C57BL6J mice quantified by FACs. (H) Average percentage of tumor resident DCs (CD11c + MHCII+) in tumors (I) FACs dot-plot showing the percentages of tumor resident myeloid derived suppressor cells (MDSCs: PMN-MDSCs: CD11B + Ly6G + Ly6C−) and monocytic MDSCs (M-MDSCs: CD11b + Ly6G-Ly6C+) resident in E0771-tumors implanted in C57BL6J mice. (J) Average percentage of tumor resident PMN-MDSCs and M-MDSCs (right panel) in control versus SR9243 groups determined by FACs (n = 6). (K) FACs-dot plot showing the percentage of tumor-resident CD8+ T-cells in response to SR9243 treatment. (L) Average percentage of CD8+ T-cells among tumor infiltrating lymphocytes in vehicle and SR9243 treated tumors.

Figure 6

SR9243 immunotherapeutic activity is CD8+ T-cell dependent. (A) Immunohistochemical staining showing CD8+ infiltration into E0771 tumors from SR9243 or vehicle control treated mice. (B) Average number of CD8+ T-cells quantified in vehicle versus SR9243 treated tumors (n = 6). The number of CD8+ cells were quantified using ImageJ. *p < 0.05 determined by student’s t-test. (C) FACs dot-plot showing the percentage of tumor resident CD8+ effector T-cells expressing PD-1 in vehicle and SR9243 treated mice (D) Average percentage of tumor-resident CD8+ effector T-cells expressing PD-1+ in vehicle versus SR9243 treated groups (n = 6). (E) FACs dot-plot showing the percentage of lymph-node resident CD8+ effector T-cells that are positive for PD-1 expression in vehicle and SR9243 treated mice (F) Average percentage of lymph-node resident CD8+ effector T-cells expressing PD-1+ in vehicle versus SR9243 treated groups (n = 6). (G) FACs dot-plot showing the percentage of lymph node resident CD8+ effector memory T-cells expressing GZMB in control or SR9243 treated mice. (H) Average percentage of GZMB expressing effector T-cells in the draining lymph-nodes of vehicle and SR9243 treated mice. (I) FACs dot-plot showing the percentage of lymph node resident CD8+ T-cells expressing GZMB in vehicle and SR9243 mice. (J) Mean percentage of lymph-node resident CD8+ T-cells expressing GZMB in vehicle and SR9243 treated mice (K) Individual E0771 tumor allograft volumes for individual mice receiving Rat IgG2A and dosed with vehicle or 60 mg/kg SR9243. (L) Mean tumor allograft volume for vehicle and SR9243 treated groups in J. (M) Individual E0771-allograft volumes for SR9243 and vehicle treated mice (N) Mean E0771-tumor allograft volumes for mice depleted of CD8 T-cells and treated with vehicle or SR9243 in K. For CD8+ T-cell depletion tumor bearing mice were dosed with αCD8 antibody (Bio-X-Cell) (or Rat IgG control) every three days for 9 days. Mice were then treated with 60 mg/kg SR9243 or vehicle once daily for 14 days (n = 10). *p < 0.05 ***p < 0.001 as determined by student’s t-test of 2-Way ANOVA.