Noncoding RNA gas5 is a growth arrest- and starvation-associated repressor of the glucocorticoid receptor

Abstract

The availability of nutrients influences cellular growth and survival by affecting gene transcription. Glucocorticoids also influence gene transcription and have diverse activities on cell growth, energy expenditure, and survival. We found that the growth arrest-specific 5 (Gas5) noncoding RNA, which is abundant in cells whose growth has been arrested because of lack of nutrients or growth factors, sensitized cells to apoptosis by suppressing glucocorticoid-mediated induction of several responsive genes, including the one encoding cellular inhibitor of apoptosis 2. Gas5 bound to the DNA-binding domain of the glucocorticoid receptor (GR) by acting as a decoy glucocorticoid response element (GRE), thus competing with DNA GREs for binding to the GR. We conclude that Gas5 is a "riborepressor" of the GR, influencing cell survival and metabolic activities during starvation by modulating the transcriptional activity of the GR.

Fig. 1. The organization of the Gas5 gene and its ncRNA products

The human Gas5 gene contains 12 exons (white boxes) and 10 snoRNAs (black boxes), and produces two mature, spliced isoforms Gas5a and Gas5b with alternative use of exon 7a and b, in addition to at least 5 other variants reported as ESTs, which contain one or more snoRNA sequences (Genbank accession number NR_002578 and AF141346) (17,54). Gray box located 5′ terminally to exon 1 indicates 5′TOP sequence. In our study, we called Gas5a as Gas5 and studied its expression and effects, as this isoform is the main form expressed in HeLa cells. The Gas5 siRNA we employed corresponds to a sequence located in exon 6 and its location in Gas5 isoforms is shown with “*”. Gas5 GRE-mimic is located in exon 12, which is found in all splicing isoforms. bs: bases, EST: expression sequence tag, GRE: glucocorticoid response element, ncRNA: noncoding RNA, snoRNA: small nucleolar RNA.

Fig. 2. Gas5 RNA interacts with GR at its DBD and suppresses its transcriptional activity

(A) Endogenous Gas5 interacts with GR in a dexamethasone-dependent fashion. GR-expressing HeLa cells were treated with 10⁻⁶ M of dexamethasone. The GR/RNA complex was precipitated with a specific antibody against GR LBD (anti-GR Ab), and rabbit IgG was used as a negative control. GR-associated Gas5 was detected with regular PCR (left panel) employing an adjusted PCR cycle and a primer pair that amplifies the entire Gas5 sequence or with SYBR Green real-time PCR (middle panel) using a specific primer pair. Results of Western blots show the abundance of the GR protein (bottom gel of the left panel). The right panel shows titration curves of dexamethasone for the association of Gas5 to GR examined with anti-GR (closed circles) or control (open circles) antibody. Bars and circles represent the mean +/− SEM values of the fold Gas5 precipitation over the baseline (“Control” in the absence of dexamethasone) (n=3). IP Ab: antibody used for immunoprecipitation. (B, C) GR is associated with Gas5 and tRNA(Arg) in a ligand-dependent fashion, whereas control RNAs miR191, SC35 mRNA, and U75 snoRNA are not. HeLa cells were treated with 10⁻⁶ M of dexamethasone. GR-associated Gas5, miR191, and SC35 mRNA (B), or U75 snoRNA and tRNA(Arg) mRNA (C) were detected with regular PCR employing an adjusted PCR cycle and specific primer pairs that amplify the entire sequences. Results of Western blots demonstrating GR protein abundance are shown in the bottom gels. (D) Gas5 is associated with the GR DBD. GR-deficient HCT116 cells were transfected with the control plasmid (Vector), pRShGRα (GR WT), or G-gal-G, and treated with 10⁻⁶ M of dexamethasone. Gas5 coprecipitated with GR or G-gal-G with a GR LBD-specific antibody (anti-GR Ab) was detected with regular PCR (left panel) employing an adjusted PCR cycle and a primer pair that amplifies the entire Gas5 sequence or with SYBR Green real-time PCR (right panel) using a specific primer pair. Western blots showing the abundance of GR WT and G-gal-G are provided at the bottom of the left panel. Bars represent the mean +/− SEM values of fold Gas5 precipitation over the baseline (“Vector” in the absence of dexamethasone) (n=3). IP: immunoprecipitation. (E) Gas5 suppresses the transcriptional activity of wild type (WT) GR but not of the GR chimera containing the GAL4 DBD. HCT116 cells were transfected with the Gas5-expressing plasmid together with pRShGRα and pMMTV-Luc, or G-gal-G and p17mer-tk-Luc, in the presence of pSV40-β-Gal. Western blots showing GR WT and G-gal-G abundance are provided at the bottom. Bars represent the mean +/− SEM values of luciferase activity normalized to β-galactosidase activity. *; p<0.01; n.s., not significant, compared to the baseline (in the presence of control siRNA and dexamethasone) (n=3).

Fig. 3. Gas5 is located both in the cytoplasm and the nucleus and translocates from the cytoplasm into the nucleus with GR in response to dexamethasone

(A) Gas5 is localized both in the cytoplasm and the nucleus. Top left shows RNA fluorescence in situ hybridization performed with the Alexa488-labeled Gas5 probe in HeLa cells. Bottom left shows the negative control obtained with samples treated with RNase. Middle panels demonstrate staining with DAPI, and the right panels show merged images of left and middle panels. (B) Gas5 translocates into the nucleus with GR in response to dexamethasone. HeLa cells were transfected with Gas5 wild type (WT)- or GRE-1 Mut-expressing plasmid and were treated with 10⁻⁶ M of dexamethasone. Transfected Gas5s and endogenous GR, α-tubulin, and Oct1 in these subcellular fractions were detected with SYBR Green real-time PCR and Western blots, respectively (top panels). The bottom panel shows Western blots for the presence of α-tubulin and Oct1 in the subcellular fractions. To detect exogenously expressed Gas5, we employed the forward primer, which recognized the plasmid sequence adjacent to 5′ end of the Gas5 sequence that was expressed with Gas5 RNA. Bars represent the mean +/− SEM values of fold accumulation of Gas5 RNA compared to the baseline (transfected with wild type Gas5 RNA in the absence of dexamethasone). *: p<0.01, compared to the conditions indicated (n=3). (C) The GR mutant defective in nuclear translocation reduces cytoplasmic to nuclear translocation of Gas5. GR-deficient HCT116 cells were transfected with GR WT- or NL1⁻ mutant-expressing plasmid and were treated with 10⁻⁶ M of dexamethasone. Endogenous Gas5 and transfected GRs, α-tubulin, and Oct1 in these subcellular fractions were detected with SYBR Green real-time PCR and Western blots, respectively. Bars represent the mean +/− SEM values of fold accumulation of Gas5 RNA compared to the baseline (transfected with wild type GR in the absence of dexamethasone) (n=3).

Fig. 4. Overexpression of Gas5 suppresses both the association of GR with cIAP2 GREs and GR-induced cIAP2 mRNA expression

HeLa cells were transfected with increasing amounts of Gas5-expressing plasmid and treated with 10⁻⁶ M of dexamethasone. The ChIP assay and total RNA purification were performed using fractions of these cells. (A) Gas5 suppresses the association of GR with cIAP2 GREs. ChIP assays were performed with the GR antibody against GR LBD (anti-GR Ab) and the cIAP2 promoter fragment that contains tandem GREs was amplified by PCR with an adjusted PCR cycle using a specific primer pair. The bottom blots are Western blots showing GR protein abundance. (B and C) Gas5 suppresses dexamethasone-induced cIAP2 mRNA expression. Total RNA was purified, and the abundance of the cIAP2 and control RPLP0 mRNAs and of the Gas5 RNA were measured with SYBR Green real-time PCR. Bars represent the mean +/− SEM values of fold induction of the cIAP2 mRNA (B) and the Gas5 RNA (C) expression normalized for the RPLP0 mRNA abundance compared to the baseline (in the absence of Gas5 transfection and dexamethasone). *, p < 0.01, compared to the condition in the absence of Gas5 transfection and in the presence of dexamethasone (n=3).

Fig. 5. Gas5 suppresses GR-induced mRNA expression of glucocorticoid-responsive genes, as well as the association of GR to their GREs, but does not influence PPARδ-induced mRNA expression of the ADRP gene or the association of PPARδ to its PPREs

HeLa and HepG2 cells were transfected with the Gas5-expressing plasmid and treated with 10⁻⁶M of dexamethasone or GW501516. Total RNA purification, ChIP assays, and Western blots were performed from the appropriate samples. mRNA abundance of the glucocorticoid-responsive genes encoding GILZ, SGK1, PEPCK, and G6Pase, and the PPARδ-responsive gene ADRP (A), as well as the association of GR and PPARδ to their GREs or PPREs in ChIP assays (B) were examined with SYBR Green real-time PCR with their specific primer pairs. Bars represent the mean +/− SEM values of fold mRNA expression (A) and fold association of GR and PPARδ to their GREs or PPREs (B) compared to the baseline (in the absence of Gas5 transfection and dexamethasone or GW501516 treatment). *: p<0.01, n.s.: not significant, compared to the conditions indicated (n=3). (C) The abundance of GR and PPARδ was analyzed by Western blotting.

Fig. 6. Endogenous Gas5 functions as a negative regulator of GR-induced cIAP2 and SGK1 mRNA expression

HeLa cells were transfected with Gas5 or control siRNA and were cultured in serum-free medium for the indicated time periods. The abundance of the cIAP2, SGK1, and RPLP0 mRNAs and of the Gas5 RNA were determined with SYBR Green real-time PCR. (A) Thymidine incorporation was also examined in cells from the same experiment and is shown as % of the baseline. Bars represent the mean +/− SEM values of fold induction of the Gas5 RNA (B) and the cIAP2 (C) and SGK1 (D) mRNAs normalized for RPLP0 mRNA abundance compared to the baseline (in the absence of Gas5 siRNA and dexamethasone at time “0”). (n=3).

Fig. 7. Depletion of endogenous Gas5 with siRNA potentiated dexamethasone-induced inhibition of apoptosis and caspase activities caused by treatment with Fas antibody and IFN-γ

HeLa cells were transfected with Gas5 or control siRNA and cultured in serum-free medium for 72 hours. 10⁻⁶ M of dexamethasone, 100 ng/ml of Fas antibody (anti-Fas Ab), and 250 U/ml of IFN-γ were added to the medium. (A) The percent of apoptotic cells. Bars represent the mean +/− SEM values of % of TUNEL-positive apoptotic cells in over 200 counted cells. The activities of caspase 3/7 (B) and 9 (C) are shown. Bars represent the mean +/− SEM values. *, p<0.01; n.s., not significant, compared to the condition indicated (n=3).

Fig. 8. Gas5 forms hairpin structures and interacts through its 3′ portion with the GR

(A) Gas5 is associated with GR through its nucleotides 400 to 598. HeLa cells were transfected with plasmids expressing the indicated fragments of Gas5 and treated with 10⁻⁶ M of dexamethasone and RNA/protein coprecipitation assays were performed. GR-associated Gas5 fragments were detected with SYBR Green real-time PCR. The forward primer recognizing the plasmid sequence adjacent to 5′ end of the Gas5 sequence and the reverse primers in the Gas5 sequence were used to amplify exogenously expressed Gas5 fragments. (B) Gas5 suppresses GR-induced transcriptional activity though nucleotides 400 to 598. HeLa cells were transfected with plasmids expressing the indicated fragments of Gas5 together with the GR-expressing plasmid, pMMTV-Luc, and pSV40-β-Gal. Bars represent the mean +/− SEM values of luciferase activity normalized for β-galactosidase activity (n=3). (C) Summary of functional and physical interactions between Gas5 and the GR. Results from the coimmunoprecipitation and reporter assays both indicate that Gas5 interacts with GR through the region enclosed by its nucleotides 400 to 598. IP, immunoprecipitation. (D) 2-dimensional structure of Gas5 nucleotides 400–598. Gas5 (400-598) consists of 6 hairpin structures and the hairpin #5 contains two “GRE” sequences at nucleotides 539–544 (“GRE-1”) and 553–559 (“GRE-2”) (shown in boxes), which form a double-stranded hairpin structure that we call the Gas5 GRE-mimic. Gas5 hairpin #3 harbors, at nucleotides 473–478, a MRE-resembling sequence, which does not have a perfectly complementing sequence. G540 and C554 of the Gas5 GRE-mimic, located at the 5′ and 3′ strands, respectively, are shown in black boxes. These residues are conserved among the consensus DNA GREs and are critical for them to interact with K442 and R447 residues of the GR DBD to specify their affinity to this protein module (36). Wobble base-pairing is indicated in green, and Watson-Crick base-pairing is shown with blue and red. (E) Double-stranded GRE is required for Gas5 to repress GR-induced transcriptional activity. HCT116 cells were transfected with the indicated Gas5-expressing plasmid together with pRShGRα and pMMTV-Luc in the presence of pSV40-β-Gal. Luciferase activity is shown in the left panel, and RNA expression of Gas5 wild type (WT) and mutants measured with SYBR Green real-time PCR are shown in the right panel. Bars represent the mean +/− SEM values of luciferase activity normalized for β-galactosidase activity or fold Gas5 expression compared to the baseline (Gas5 WT transfection in the absence of dexamethasone). *, p<0.01; n.s., not significant, compared to the condition tranefected with control plasmid and in the presence of dexamethasone (n=3). (F) Disruption of the Gas5 GRE-mimic prevents Gas5 from inhibiting the association of GR with cIAP2 GREs and suppressing GR-mediated cIAP2 transcription. HeLa cells were transfected with Gas5 WT- or GRE-1 Mut-expressing plasmid, treated with 10⁻⁶ M of dexamethasone. The abundance of cIAP2 mRNA and exogenously expressed Gas5s, as well as the association of GR to cIAP2 GREs in ChIP assays were evaluated with SYBR Green real-time PCR (right 3 panels) or regular PCR with adjusted PCR cycles (left panel). Similar abundance of GR was demonstrated by Western blotting. Bars represent the mean +/− SEM values of fold change in mRNA expression of cIAP2 and exogenously expressed Gas5 molecules and fold change in the association of GR to cIAP2 GREs. *, p < 0.01; n.s., not significant, compared to the baseline (in the absence of Gas5 transfection and dexamethasone treatment) (n=3).

Fig. 9. Gas5 binds GR DBD through its double-stranded RNA GRE-mimic located at hairpin #5 and competes with DNA GREs for binding to GR DBD in vitro

(A, B) Gas5 directly binds GR DBD through its double-stranded RNA GRE-mimic in an in vitro binding assay. 10⁻⁴ M of indicated Gas5 RNAs was incubated with 1 μg of GST or GST-fused GR DBD bound to GST beads in the presence or absence of increasing concentrations (0, 10⁻⁵, 10⁻⁴, 10⁻³, and 10⁻²) of the double-stranded DNA GREs. Associated RNA was measured with the SYBR Green real-time PCR. Bars and circles represent the mean +/− SEM values of fold change in Gas5 association compared to the baseline (GST) and of the Gas5 molecules associated with GR DBD, respectively. (B) is a Scatchard plot (n=3). (C) Gas5 competes with FAM-labeled DNA GREs for binding to the GR DBD through its RNA GRE-mimic in vitro. Oneμg of GST-fused GR DBD bound to the GST beads was incubated with 10⁻⁷ M of FAM-labeled double-stranded GREs in the presence of the double-stranded GREs, wild type (WT) Gas5 or Gas5 GRE-1 Mut RNAs. Symbols represent the mean +/− SEM values of % binding obtained by dividing the FAM-oriented fluorescence intensity of each point with those of the baseline (in the absence of competitors) (n=3). (D) Three-dimenstional structure of Gas5 GRE-mimic and its interaction model with GR DBD (left structure). Three-dimentional model of (left structure) GR DBD/DNA GRE association, (middle 2 structures) Gas5 GRE-mimic without and with GR DBD, and (right structure) Gas5 MRE-resembling region. K442 and R447 of GR DBD contact the G7 of the 5′ strand and the G4 of the 3′ strand (shown in red), which lie across from each other in the major groove of the DNA GRE (left structure) (36). The analogous base pairs in the Gas5 GRE-mimic (G540 and C554, respectively, shown in red) are calculated to be oriented similarly to those in the native DNA, possibly enabling them to form the hydrogen bonds with K442 and R447 of the GR DBD, respectively. The analogous base pairs in the Gas5 RNA MRE-resembling region (U453 and G474, shown in red) are calculated to be poorly oriented for potential binding to GR DBD. (F: Replacement of K442, R447, or both of GR DBD attenuates interaction of GST-GR DBD to Gas5 in vitro. 10⁻⁴ M of wild type (WT) Gas5 RNA was incubated with 1 μg of GST or the indicated GST-fused GR DBDs bound to GST beads. Associated Gas5 RNA was measured with SYBR Green real-time PCR. Bars represent the mean +/− SEM values of fold change in the association of Gas5 RNA normalized to baseline (with GST). *, p<0.01, compared to GR DBD WT (n=3). (F) Mutant GRs defective in either K442, R447, or both fail to bind Gas5. GR-deficient HCT116 cells were transfected with the control plasmid (Vector), pRShGRα (GR WT), pRShGRαK442A, R447A, or KR442/447AA and treated with 10⁻⁶ M of dexamethasone. Gas5 was coprecipitated with GRs with a GR LBD-specific antibody and GR-associated Gas5 was detected with SYBR Green real-time PCR. GR protein abundance was shown by Western blotting. Bars represent the mean +/− SEM values of fold Gas5 precipitation over the baseline (“Vector” in the absence of dexamethasone). *: p<0.01, compared to cells expressing GR WT and treated with dexamethasone (n=3).

Fig. 10. Gas5 suppresses the transcriptional activity of several steroid receptors

(A) Gas5 suppresses mineralocorticoid (MR), progesterone-A (PR-A) and androgen (AR) receptor-induced transcriptional activity. (B) Gas5 does not influence ERα-, PPARδ-, p53- or GAL4-VP16-mediated transcription. For A and B, HCT116 cells were transfected with GR-, MR-, PR-A-, AR-, ERα-, PPARδ/RXRα-, p53-, or the VP16 activation domain (AD) fused to GAL4 DBD-expressing plasmid (GAL4-VP16AD), together with their responsive luciferase-expressing reporter plasmid and pSV40-β-Gal. Bars represent the mean +/− SEM values of luciferase activity normalized for β-galactosidase activity in the absence or presence of 10⁻⁶ M of dexamethasone (Dex) or progesterone (Prog), 10⁻⁸ M of aldosterone (Aldo), dehydrotestosterone (DHT) or estradiol (E2), 10⁻⁶ M of GW501516 (PPARδ agonist), or the indicated trans-acting factors. *: p<0.01, n.s.: not significant, compared to the baseline (in the absence of Gas5 transfection treated or transfected with indicated ligand or a trans-acting factor) (n=3). (C) Gas5 physically interacts with the DBD of the AR and PR-A, in addition to that of the GR, whereas it does not bind the ERα DBD. 10⁻⁴ M of wild type (WT) Gas5 RNA was incubated with 1 μg of GST or GST-fused DBDs of GR, MR, AR, PR-A or ERα bound to GST beads. Associated Gas5 RNA was measured with SYBR Green real-time PCR. Bars represent the mean +/− SEM values of fold association of Gas5 RNA normalized for the baseline (with GST) (n=3).