Increased AR expression in castration-resistant prostate cancer rapidly induces AR signaling reprogramming with the collaboration of EZH2

Abstract

Elevated androgen receptor (AR) expression is a hallmark of castration-resistant prostate cancer (CRPC) and contributes to the restoration of AR signaling under the conditions of androgen deprivation. However, whether overexpressed AR alone with the stimulation of castrate levels of androgens can be sufficient to induce the reprogramming of AR signaling for the adaptation of prostate cancer (PCa) cells remains unclear. In this study, we used a PCa model with inducible overexpression of AR to examine the acute effects of AR overexpression on its cistrome and transcriptome. Our results show that overexpression of AR alone in conjunction with lower androgen levels can rapidly redistribute AR chromatin binding and activates a distinct transcription program that is enriched for DNA damage repair pathways. Moreover, using a recently developed bioinformatic tool, we predicted the involvement of EZH2 in this AR reprogramming and subsequently identified a subset of AR/EZH2 co-targeting genes, which are overexpressed in CRPC and associated with worse patient outcomes. Mechanistically, we found that AR-EZH2 interaction is impaired by the pre-castration level of androgens but can be recovered by the post-castration level of androgens. Overall, our study provides new molecular insights into AR signaling reprogramming with the engagement of specific epigenetic factors.

Keywords: AR; CRPC; DNA damage repair; EZH2; androgen; androgen receptor; androgen-deprivation therapy; prostate cancer.

Figure 1

AR chromatin binding is altered in AR ^high/DHT^low cells. (A) Immunoblotting for AR in LNCaP cells stably expressing tetracycline-regulated AR (LNCaP-tet-AR). (B) mRNA expression of AR in these cells (measured by qRT-PCR). (C) Proliferation of LNCaP-tet-AR cells treated with 10 nM DHT alone or with 0.25 µg/ml doxycycline plus 0.1 nM DHT for 0-6d. (D) Venn diagram for ChIP-AR peaks in LNCaP-tet-AR cells treated with vehicle, doxycycline alone, or doxycycline plus DHT (0.1nM for 4h). (E) Heatmap view for ChIP-seq signal intensity at these sites. (F) Venn diagram for ChIP-AR peaks in parental LNCaP cells treated with 10 nM DHT (AR ^low/DHT^high) and in LNCaP-tet-AR cells treated with 0.25 µg/ml doxycycline and 0.1 nM DHT (AR ^high/DHT^low). (G) Heatmap view for ChIP-seq signal intensity at clustered sites. (H) Genomic distribution for AR binding peaks. (I) Motif enrichment analysis for clustered AR binding sites (motifs were ranked based on z-score). (J) Unique motif enrichment by comparing motif enrichment for unique sites over common sites.

Figure 2

AR activates a unique transcription program in AR ^high/DHT^low cells. (A, B) RNA-seq analyses were performed in LNCaP-tet-AR cells pretreated with or without doxycycline and then stimulated with 0, 0.1, or 10 nM DHT (for 24h). Volcano blots for DHT-regulated genes in cells treated with 10 nM DHT alone (A) or with 0.1 nM DHT plus doxycycline (B) were shown. (C) Gene Set Enrichment Analysis (GSEA) for enriched hallmark gene sets. (D) Gene Ontology analysis with the biological process (GO-BP) for differentially expressed genes (fold-change > 1.5; adjusted P-value < 0.05).

Figure 3

Identification of AR direct targets in AR ^high/DHT^low cells. (A, B) Binding and Expression Target analysis (BETA) for the association of AR binding sites (ChIP-AR) and DHT-regulated genes in AR ^low/DHT^high or AR ^high/DHT^low cells (A) and the AR ^high/DHT^low-unique AR binding sites and DHT-regulated genes in AR ^high/DHT^low cells (B). (C) Boxplot for AR ^low/DHT^high unique AR signature (58-gene), AR ^high/DHT^low unique AR signature (27-gene), and previously published classic AR targets (10-gene) in LNCaP-tet-AR cells under indicated conditions. (D) The expression levels of AR ^high/DHT^low-unique AR signature in TCGA (normal and primary PCa), UW (mCRPC), and SU2C (mCRPC) datasets. (E) Kaplan-Meier survival analysis for the overall survival from the initiation of the first-line ARSi in mCRPC patients (SU2C cohort) with higher scores (purple, top 25%) of the signature versus the lower scores (yellow, bottom 75%).

Figure 4

AR directly activates genes mediating DNA damage response. (A, B) LNCaP-tet-AR cells were pre-treated with or without 0.25 µg/ml doxycycline for 2d and then stimulated by DHT (0.1 or 10 nM for 24h). mRNA expression of a panel of AR ^high/DHT^low uniquely regulated genes (A) and classic AR-targeted genes (B) were measured. A genome view of AR binding peaks at the target gene loci was also shown for each gene. (C, D) Cell growth inhibition for LNCaP-tet-AR cells under the indicated conditions and treated with or without 10 µM olaparib for 0-6d (C), or 50 µM cisplatin for 2d (D).

Figure 5

Prediction of transcription or epigenetic factors involved in the reprogramming of AR. (A) Prediction of the involvement of transcription factor/chromatin regulator in mediating AR activity in AR ^low/DHT^high cells or AR ^high/DHT^low cells using Causal Inference Enrichment (CIE) platform for significant gene expression (fold-change > 2, FDR < 0.05). ChIP-Atlas prostate cell line dataset was selected as the database, and Fisher’s exact test was used as the enrichment method. Enriched factors with adjusted P-value < 0.05 are shown. (B–F) Correlation of predicted factors, E2F1 (B), MYBL2 (C), FOXM1 (D), EZH2 (E), and MAF (F), with the expression of AR ^low/DHT^high signature or AR ^high/DHT^low signature in mCRPC patient dataset.

Figure 6

EZH2 is engaged in the reprogramming of AR in CRPC. (A) Venn diagram for DHT-regulated genes in AR ^low/DHT^high and AR ^high/DHT^low LNCaP-tet-AR cells and EZH2-regulated genes in LNCaP-ABL cells (fold-change > 1.5, adjusted P-value < 0.05). (B) Boxplot for AR/EZH2 co-target gene expression (68-genes) in LNCaP-tet-AR cells under indicated conditions. (C) qRT-PCR for AR ^high/DHT^low-unique AR regulated genes treated with 0.1 nM DHT and an EZH2 inhibitor, GSK126 (50μM for 24h). (D) Gene ontology of AR/EZH2 co-regulated 68 genes (FDR< 0.05). (E, F) AR/EZH2 co-target gene expression (68-gene) in TCGA, UW, and SU2C datasets (E) and Balk PCa dataset (F). (G) Kaplan-Meier survival analysis for the overall survival from the initiation of the first-line ARSi in mCRPC patients (SU2C cohort) with higher scores (purple, top 25%) of AR/EZH2 target signatures versus the lower scores (yellow, bottom 75%). (H) Immunoblotting for indicated proteins in LNCaP versus LNCaP-C4-2 cells. (I) Immunoblotting for indicated proteins in LNCaP-tet-AR cells immunoprecipitated with AR. (J) ChIP-qPCR of EZH2 at indicated AR binding sites. (K) Cell growth inhibition for LNCaP-tet-AR cells under the indicated conditions and treated with 30µM olaparib for 2d, or olaparib plus GSK126 (50 µM for 2d).