E2F mediates cell cycle-dependent transcriptional repression in vivo by recruitment of an HDAC1/mSin3B corepressor complex

Abstract

Despite biochemical and genetic data suggesting that E2F and pRB (pocket protein) families regulate transcription via chromatin-modifying factors, the precise mechanisms underlying gene regulation by these protein families have not yet been defined in a physiological setting. In this study, we have investigated promoter occupancy in wild-type and pocket protein-deficient primary cells. We show that corepressor complexes consisting of histone deacetylase (HDAC1) and mSin3B were specifically recruited to endogenous E2F-regulated promoters in quiescent cells. These complexes dissociated from promoters once cells reached late G1, coincident with gene activation. Interestingly, recruitment of HDAC1 complexes to promoters depended absolutely on p107 and p130, and required an intact E2F-binding site. In contrast, mSin3B recruitment to certain promoters did not require p107 or p130, suggesting that recruitment of this corepressor can occur via E2F-dependent and -independent mechanisms. Remarkably, loss of pRB had no effect on HDAC1 or mSin3B recruitment. p107/p130 deficiency triggered a dramatic loss of E2F4 nuclear localization as well as transcriptional derepression, which is suggested by nucleosome mapping studies to be the result of localized hyperacetylation of nucleosomes proximal to E2F-binding sites. Taken together, these findings show that p130 escorts E2F4 into the nucleus and, together with corepressor complexes that contain mSin3B and/or HDAC1, directly represses transcription from target genes as cells withdraw from the cell cycle.

Figure 1

In vivo promoter occupancy by E2F and pRB family proteins in mouse cells. (A) Wild-type 3T3 cells were rendered quiescent by serum deprivation. Cells were stimulated to re-enter the cell cycle by serum addition, harvested at the indicated time points, and examined by FACS analysis. DNA content was determined by propidium iodide (p.i.) staining and is plotted versus cell number. (B) Schematic of promoters analyzed in this study. Boxes represent previously identified E2F-binding sites. For each schematic, lower arrows indicate positions of PCR primers used to detect promoter fragments, whereas upper arrows represent the major transcription start site as determined in earlier studies. (C,D) ChIP analysis of synchronized wild-type 3T3 cells. Promoters are underlined. Input represents 0.5% of total amount of chromatin added to each immunoprecipitation reaction. The mock lane corresponds to a negative control immunoprecipitation using an irrelevant antibody. Proximal promoter sequences (G₀ and S_prox) were amplified by PCR using primers specified in the schematic, whereas distal sequences (S_distal) were detected with primers corresponding to regions 1–2 kb upstream of the E2F-binding site(s). PCR products were detected by autoradiography. PCR products shown in the input, mock, and specific immunoprecipitation lanes were obtained in the same experiment.

Figure 2

Detection of corepressors associated with E2F-responsive promoters in growing cells and cells in different cell cycle stages. (A) Analysis of in vivo promoter occupancy in asynchronous cultures of wild-type 3T3 cells. Chromatin immunoprecipitations were performed as described in Figure 1 using the indicated antibodies. (B) 3T3 cells were brought to quiescence by serum deprivation and subsequently stimulated to re-enter the cell cycle by the addition of serum. Chromatin was prepared at 0 h (G₀), 12 h (late-G₁ phase), and 18 h (S phase) following cell cycle re-entry. Chromatin immunoprecipitations were performed as described in Figure 1. (C) Presence of mSin3B and HDAC1 in nuclear extracts. Wild-type 3T3 cells were harvested at the indicated time points upon release from quiescence. Nuclear extracts were prepared and analyzed by Western blotting using the specified antibodies. The mSin3B band is indicated by the small arrow. The top band observed in the mSin3B blot comigrates with a band detected by anti-mSin3A antibody (data not shown). The same blot was stripped and reprobed sequentially. Sp1 serves as a nuclear marker. (D) Promoter occupancy of quiescent MEFs. Wild-type primary MEFs were rendered quiescent by serum withdrawal, and promoter occupancy of E2F-responsive genes was determined by ChIP. Enrichment of proximal and distal promoter sequences was performed as described in Figure 1.

Figure 3

Dependency of E2F4 recruitment on pRB family members in vivo. Wild-type, p107^−/−; p130^−/−, and RB^−/− primary MEFs were arrested by serum deprivation and analyzed by ChIP as in Figure 1 using the indicated antibodies. Interestingly, p107 binding is increased at several promoters in RB^−/− MEFs, but not in the wild-type controls. It is possible that this phenomenon is related to the observed up-regulation of p107 protein levels in RB^−/− cells (Hurford et al. 1997).

Figure 4

(A) Dependency of mSin3B/HDAC1 corepressor recruitment on pRB family members in vivo. Wild-type, p107^−/−; p130^−/−, and RB^−/− primary MEFs were arrested by serum deprivation and analyzed by ChIP as in Figure 1 using the indicated antibodies. (B) ChIP analysis of corepressor recruitment in p107^−/− and p130^−/− quiescent primary MEFs. (C) Analysis of gene expression in wild-type versus p107^−/−; p130^−/− primary MEFs. Cells of low passage number were synchronized as in Figure 1. Total RNA was prepared at each of the indicated time points and subjected to RT–PCR analysis by use of cDNA-specific primers. Actin gene expression is used as a loading control. (−) Lane corresponding to a no-template control.

Figure 5

Subcellular localization of E2F4 in quiescent cells depends on pRB family members. Nuclear and cytoplasmic fractions of quiescent cells were prepared and analyzed by immunoblotting using anti-E2F4 antibody. To verify the purity of each fraction, the same filter was stripped and subsequently reprobed with anti-Sp1 and anti-Eps15 antibodies, which serve as nuclear and cytoplasmic markers, respectively.

Figure 6

A functional E2F-binding site is required for recruitment of E2F and corepressors. (A) B-myb promoter occupancy in wild-type NIH-3T3 during quiescence. ChIPs using the indicated antibodies were performed as before. (B) NIH-3T3 cell lines were stably transfected with B-myb reporter constructs, in which promoter DNA (positions −536 to −88 relative to the translation start site) is linked to a luciferase gene. Stable cell lines were generated with wild-type and E2F-site mutant B-myb transgenes. Cells were brought to quiescence by serum deprivation and analyzed by ChIP. Small arrows represent PCR primers used to distinguish endogenous (1 and 2) and transgenic (1 and 3) promoters. (C) Luciferase activity was measured by luminometry using extracts from synchronized cells harvested at G₀ and S phase, and normalized on the basis of cell number.

Figure 7

Nucleosome mapping and histone acetylation of the E2F1 promoter. (A) Three promoter-proximal nucleosomes were identified by nucleosome mapping. Chromatin from quiescent wild-type 3T3 cells was partially digested with micrococcal nuclease, and primer extension was performed by use of a set of primer pairs spanning the E2F1 promoter region. Extension products were subjected to ligation-mediated PCR (LM–PCR), followed by acrylamide gel electrophoresis (see Materials and Methods). Amplification products were visualized by autoradiography, and approximate nucleosome boundaries were deduced. (B) Nucleosome positions were confirmed by PCR of genomic vs. MNase-digested chromatin using primer pairs that are internal to the putative nucleosomes or flank the E2F binding sites. Reduction in band intensity in the MNase-treated lanes indicates lack of nucleosome protection. (C) Schematic of nucleosome positioning on the E2F1 promoter. Boxes represent E2F-binding sites, and the arrow corresponds to the major transcription start site. Ovals are enclosed with dotted lines to indicate that nucleosomal positioning is approximate and may be dynamic. (D) Acetylation of nucleosomes at the E2F1 promoter. Chromatin from quiescent primary MEFs was digested extensively with micrococcal nuclease (MNase) to produce mononucleosomes. Chromatin immunoprecipitations were then performed using antibodies against acetylated histones H3 and H4, and enrichment was detected by PCR using nucleosome-specific primers (indicated for each of three promoter-proximal nucleosomes) deduced from mapping data in A and B.

Figure 8

Model describing transcriptional regulation by E2F and pRB families of proteins in vivo. In quiescent MEFs, E2F4 is escorted into the nucleus by p130. E2F4/p130 then binds to target promoters and recruits a corepressor complex containing mSin3B and HDAC1, although mSin3B may also be recruited by E2F-independent mechanisms. The degree of nucleosome acetylation is determined by the opposing properties of the E2F4/p130/mSin3B/HDAC1 corepressor complex and a putative HAT activity that may be present at the promoter and poised to activate transcription. Corepressor activity maintains the balance of nucleosome acetylation in an underacetylated state. Once cells are stimulated to re-enter the cell cycle, pocket proteins are inactivated by cyclin/cdk complexes, leading to the dissociation of the corepressor complexes. E2F4, lacking a nuclear localization domain, is then excluded from the nucleus. HAT activity, which may be recruited by nuclear activator E2Fs (primarily E2F1 and E2F3) or which may already be present at the promoter, stimulates nucleosome acetylation, leading to gene activation.