Down-regulation of AR splice variants through XPO1 suppression contributes to the inhibition of prostate cancer progression

Abstract

Emerging studies have shown that the expression of AR splice variants (ARv) lacking ligand-binding domain is associated with castrate-resistant prostate cancer (CRPC) and higher risk of tumor metastasis and recurrence. Nuclear export protein XPO1 regulates the nuclear localization of many proteins including tumor suppressor proteins. Increased XPO1 in prostate cancer is associated with a high Gleason score and bone metastasis. In this study, we found that high expression of AR splice variant 7 (AR-v7) was correlated with increased XPO1 expression. Silencing of XPO1 by RNAi or treatment with Selective Inhibitor of Nuclear Export (SINE) compounds selinexor and eltanexor (KPT-8602) down-regulated the expression of AR, AR-v7 and ARv567es at mRNA and protein levels. XPO1 silencing also inhibited the expression of AR and ARv regulators including FOXA1, Src, Vav3, MED1 and Sam68, leading to the suppression of ARv and AR target genes, UBE2C and PSA. By targeting XPO1/ARv signaling, SINE suppressed prostate cancer (PCa) growth in vitro and in vivo and potentiated the anti-cancer activity of anti-AR agents, enzalutamide and abiraterone. Therefore, XPO1 inhibition could be a novel promising agent used in combination with conventional chemotherapeutics and AR-targeted therapy for the better treatment of PCa, especially CRPC.

Keywords: AR SPLICE variant; CRM1; SINE; metastatic prostate cancer; nuclear export.

Figure 1. High expression of AR splice variants is correlated with over expression of XPO1 in PCa cells

(A) The expression levels of AR, AR-v7, ARv567es and XPO1 mRNA in 22Rv1, VCaP, LNCaP and C4-2B PCa cells were measured by using real-time RT-qPCR. (B) The expression levels of AR-v7 and XPO1 mRNA in paraffin-embedded tissues from 32 cases of PCa patients were assessed by real-time RT-qPCR.

Figure 2. Silencing of XPO1 inhibits AR splice variants and their regulators

(A) 22Rv1 cells were transfected with XPO1 siRNA. The expressions of XPO1, AR-v7, ARv567es, FOXA1, MED1 and UBE2C mRNA were tested by using real-time RT-qPCR. (B) The diagram showing possible regulatory mechanism underlying XPO1 regulated AR splice variant signaling.

Figure 3. SINE significantly inhibits AR and AR splice variants

22Rv1 and VCaP cells were treated with 70–100 nM selinexor (A) or 200 nM KPT-8602 for 48 hours (B). The expressions of AR, AR-v7 and ARv567es mRNA were accessed by real-time RT-qPCR (^*p < 0.05; ^**p < 0.01). (C) 22Rv1 and VCaP cells were treated with 100–200 nM selinexor or 250 nM KPT-8602 for 72 hours and total proteins were extracted from these cells. 22Rv1 and VCaP cells were also treated with 1 μM selinexor for 24 hours and cytoplasmic and nuclear proteins were separately extracted from these cells. The expression levels of AR and ARv proteins were measured by using Western Blot analysis. The signal was quantified by using AlphaEaseFC and the expression level of AR and ARv was calculated and normalized by Lamin B for nuclear protein and GAPDH for total and cytoplasmic proteins.

Figure 4. SINE inhibits regulators and targets of ARv and AR

22Rv1 cells were treated with 100 nM selinexor (A) or 200 nM KPT-8602 for 48 hours (B). The expressions of FOXA1, Src, MED1, Vav3, Sam68, UBE2C and PSA mRNAs were accessed by real-time RT-qPCR (^*p < 0.05; ^**p < 0.01). (C) 22Rv1 were treated with 100–200 nM selinexor for 72 hours and total proteins were extracted from these cells. The expression levels of p-Src, Src, MED1 and FOXA1 proteins were measured by using Western Blot analysis. The signal was quantified by using AlphaEaseFC and the expression level was calculated and normalized by actin. (D) The cell lysate from control and 300 nM selinexor treated 22Rv1 cells were immunoprecipitated with IgG or AR antibody which recognizes AR and ARv. Western Blot analysis was then conducted for testing FOXA1 binding to AR and ARv. (E) The diagram showing the regulatory mechanisms by which selinexor inhibits ARv, AR and their down-stream targets. (F) HEK293 XPO1 wild-type and mutant (C528S) cells were treated with 500 nM selinexor for 48 hours. The expressions of FOXA1 and UBE2C mRNAs were accessed by real-time RT-qPCR (^*p < 0.05; ns: p > 0.05).

Figure 5. SINE regulates eIF4E to retain AR-v7 RNA in nuclear compartment

22Rv1 and VCaP cells were treated with 500 nM selinexor (A) or 1 μM KPT-8602 (B) for 24 hrs. Cytoplasmic and nuclear proteins were extracted and the expression of eIF4E was assessed by Western Blot analysis. The signal was quantified by using AlphaEaseFC and the expression level of eIF4E was calculated and normalized by Lamin for nuclear protein and actin or GAPDH for cytoplasmic protein. (C and D) RNA was isolated as nuclear (Nuc) and cytoplasmic (Cyt) fractions using the RNA Subcellular Isolation Kit. Real-time RT-qPCR was conducted for measurement of AR-v7 (C) and PSA (D) mRNAs.

Figure 6. SINE potentiates the anti-cancer proliferation activity of enzalutamide and abiraterone

(A) 22Rv1 and VCaP cells were treated with 12.5–400 nM selinexor for 72 hours. MTT assay was conducted to assess cell proliferation index. (B) 22Rv1 cells were treated with 50–200 nM selinexor, 5–20 μM enzalutamide, 5–20 μM abiraterone, or combination of selinexor with enzalutamide or abiraterone for 72 hours. MTT assay and isobologram analysis were conducted to assess the combination index (CI). (C) 22Rv1 cells were treated with 200 nM selinexor, 10 μM enzalutamide, or combination for 48 hours. The expression levels of AR, AR-v7, FOXA1, PSA and UBE2C mRNA were assessed by real-time RT-qPCR (^*p < 0.05; ^**p < 0.01).

Figure 7. SINE inhibits tumor growth and prolongs survival of a 22Rv1 xenograft through retention of TSPs

(A) %TGI on Day 16 was 84% and 87% by selinexor and KPT-8602, respectively, when compared to the vehicle. (B) Kaplan–Meier plot shows that vehicle treated mice have a median OS of 20 days while both SINE treatment groups have an undefined median OS at end of the study (Day 37). (C and D) KPT-8602 and abiraterone combination treatment significantly inhibited the growth of tumors in mice, showing decreased tumor size (C) and weight (D). The mouse tumor tissues with KPT-8602 and/or abiraterone were immunochemistry stained with anti-AR (E) or anti-ARv (F) antibodies. (G) 22Rv1 cells were treated with 250 nM selinexor for 48 hour. The apoptotic cell death was tested by Annexin V FITC assay.