Androgen receptor non-nuclear regulation of prostate cancer cell invasion mediated by Src and matriptase

Abstract

Castration-resistant prostate cancers still depend on nuclear androgen receptor (AR) function despite their lack of dependence on exogenous androgen. Second generation anti-androgen therapies are more efficient at blocking nuclear AR; however resistant tumors still develop. Recent studies indicate Src is highly active in these resistant tumors. By manipulating AR activity in several different prostate cancer cell lines through RNAi, drug treatment, and the use of a nuclear-deficient AR mutant, we demonstrate that androgen acting on cytoplasmic AR rapidly stimulates Src tyrosine kinase via a non-genomic mechanism. Cytoplasmic AR, acting through Src enhances laminin integrin-dependent invasion. Active Matriptase, which cleaves laminin, is elevated within minutes after androgen stimulation, and is subsequently shed into the medium. Matriptase activation and shedding induced by cytoplasmic AR is dependent on Src. Concomitantly, CDCP1/gp140, a Matriptase and Src substrate that controls integrin-based migration, is activated. However, only inhibition of Matriptase, but not CDCP1, suppresses the AR/Src-dependent increase in invasion. Matriptase, present in conditioned medium from AR-stimulated cells, is sufficient to enhance invasion in the absence of androgen. Thus, invasion is stimulated by a rapid but sustained increase in Src activity, mediated non-genomically by cytoplasmic AR, leading to rapid activation and shedding of the laminin protease Matriptase.

Keywords: Src; castration-resistant; metastasis; nongenomic AR signaling; prostate cancer.

Figure 1. AR stimulation alters cell shape, migration, and invasion via laminin integrins

(A, B) Parental PC3 (Puro) and 2 PC3-AR clones (AR1 and AR2) were plated on laminin for 1 hour then (A) immunostained for vinculin (green), stained for F-actin with phalloidin (red), and counterstained with Hoecsht (blue). (B) Percentage of cells with filopodia was quantified. (C) Migration on laminin-coated Boyden chamber inserts was quantified in PC3-Puro (PP) versus PC3-AR clones. (D) Extent of invasion through Matrigel-coated Boyden chambers was quantified following treatment of PC3 (Puro) or PC3-AR clones with ethanol (Veh), 10 nM Casodex (Caso), or 10 nM RU486. (E, F) Matrigel invasion was measured in LNCaP or C4–2 cells treated with ethanol (Veh) or 10 nM R1881 for 24 hours (E) without or (F) with scrambled siRNA (Scrm) or AR-specific siRNA (siAR). (G) Matrigel invasion by PC3-Puro (PP) or PC3-AR clones treated with scrambled (Scr) or combined integrin α3 and α6 siRNA (a3/a6) was measured.

Figure 2. AR stimulates Src activation

(A, B) Src activation and expression in PC3-Puro (PP) or PC3-AR clones (AR1/AR2) was measured by immunoblotting of Src immunoprecipitates with anti-Y416 phospho-specific antibody or total anti-Src antibody respectively in (A) untreated cells or (B) cells treated with scrambled siRNA (scr) or AR-specific siRNA (siAR). *All samples were run on the same gel, but image was cut to remove extraneous lanes. Total levels of AR and tubulin (Tub) expression served as loading controls and were monitored by immunoblotting. (C, D) Src activation and expression was measured in LNCaP or C4–2 cells stimulated with ethanol (−) or 10 nM R1881 for 20 minutes in (C) untreated cells or (D) cells treated with scrambled siRNA (scr) or AR-specific siRNA (siAR). (E) Src activation and expression was measured in PC3-AR1 cells treated with ethanol (Veh), 10 nM RU486 or 10 nM Casodex (Caso) for 24 hours. (F) Src and AR expression were measured by immunoblotting in PC3-Puro (PP) or PC3-AR clones (AR1/AR2) treated with scrambled siRNA (scr) or Src-specific siRNA (siSrc). (G) PC3-Puro (PP) or PC3-AR clones (AR1/AR2) were treated with scrambled siRNA (scr) or integrin α6-specific siRNA (siα6). Src activation and expression in immunoprecipitates and integrin α6 expression cell lysates were measured by immunoblotting. (H) Percentage of cell death was measured by trypan blue dye exclusion following adhesion to laminin.

Figure 3. AR and Src are required for invasion

(A) Matrigel invasion was measured in PC3-Puro (PP) or PC3-AR clones (AR1/AR2) treated with scrambled siRNA (scr), AR-, or Src-specific siRNA (siAR, siSrc). (B, C) Matrigel invasion was measured in R1881-stimulated LNCaP, VCaP, or C4–2 cells following treatment with (B) scrambled siRNA (scr) or Src-specific siRNA (siSrc) or upon expression of (C) control shRNA (shCtrl) or two different shSrc constructs. Src levels before and after shSrc expression were measured by immunoblotting of Src immunoprecipitates. (D) Src activation and expression was measured in PC3 cell lines expressing wild type (AR1/AR2), nuclear localization deficient (NLS), or ligand binding deficient (LBD) AR mutants by immunoblotting of Src immunoprecipitates with anti-Y416 phospho-specific antibody or total anti-Src antibody respectively. (E, F) Matrigel invasion was measured in PC3 (Vec), PC3-AR1, AR-NLS, or AR-LBD clones treated with scrambled siRNA (scr) or Src-specific siRNA (siSrc).

Figure 4. AR stimulates Matriptase activation and extracellular shedding in a non-nuclear fashion

(A) PC3-Puro or PC3-AR clones were stimulated with 10 nM R1881 for 0, 20, 60, 120 minutes (0, 20′, 1 hr, 2 hr). Levels of active Matriptase in cell lysates and secreted into the conditioned medium were measured by immunoblotting. (B) PC3-AR cells stabling expressing a Tet-inducible AR shRNA (shARTet) were stimulated with 100–400 μg/ml doxycycline for 24 hours and the levels of AR and active Matriptase in the cell lysate measured by immunoblotting. (C) PC3 cells expressing ARΔNLS or ARΔLBD were stimulated with 10 nM R1881 for 0, 20, 60, 120 minutes (0, 20′, 1 hr, 2 hr). Levels of active Matriptase in cell lysates and secreted into the conditioned medium were measured by immunoblotting. (D, E) LNCaP or C4–2 cells were stimulated with 10 nM R1881 for (D) 24 hours or (E) 0, 20, 60, 120 minutes (0, 20′, 1 hr, 2 hr). (D) Active Matriptase secreted into the conditioned medium or (E) in cell lysates was measured by immunoblotting. (F) Active Matriptase in the lysates (Ly) or conditioned medium (CM) from LNCaP or C4–2 cells stimulated with 10 nM R1881 for 20 minutes (20′) or 24 hours (24 h) was measured by immunoblotting. (G) C4–2 cells were stimulated with ethanol (0) or 10 nM R1881 for 20 minutes (20′) after 2 hours of pretreatment with vehicle (−) or 10 μg/ml Actinomycin D (+). Active Matriptase in the cell lysate was measured by immunoblotting. *All samples were run on the same gel, but image was cut to rearrange lanes. (H) C4–2 cells treated with vehicle (Veh) or 10 nM dasatinib for 24 hours were then stimulated with 10 nM R1881 for 20 minutes (20′) or 24 hours (24 h). Active Matriptase in the conditioned medium was measured by immunoblotting. (I) C4–2 cells expressing control shRNA (shCtrl) or two different Src shRNAs (shSrc) were stimulated with 10 nM R1881 for 30 minutes (30′) or 24 hours (24 h) and the levels of Matriptase in conditioned medium and cell lysates measured by immunoblotting.

Figure 5. CDCP1 activity is regulated by AR and Src

(A) PC3-Puro (PP) or PC3-AR cells were treated with scrambled siRNA (Sc), AR- or Src-specific siRNA (sAR, sSr), or 10 nM dasatinib for 24 hours. Tyrosine phosphorylation and expression of full length (140kDa) and cleaved (70kDa) CDCP1 from immunoprecipitates were measured by immunoblotting with anti-phosphotyrosine antibody or CDCP1 antibody respectively. (B, C) PC3-AR cells were treated with scrambled siRNA (Scr) or CDCP1-specific siRNA (siCP1). (B) CDCP1 expression was measured by immunoblotting and (C) Matrigel invasion was quantified.

Figure 6. Matriptase, but not CDCP1, promotes AR-dependent invasion

(A, B) PC3-AR cells were treated with scrambled siRNA (Scr) or Matriptase-specific siRNA (siMpt). (A) Matriptase expression was measured by immunoblotting and (B) Matrigel invasion was quantified. (C, D) Conditioned medium (+CM) containing Matriptase from unstimulated PC3-AR cells or BSA (−CM) (C) was added to unstimulated C4–2 cells or (D) CM was first depleted of Matriptase with specific antibody (Mtpase Ab) or IgG and the supernatant added to unstimulated C4–2 cells. The ability of untreated or treated C4–2 cells to invade Matrigel was quantified.