Activation of the early B-cell-specific mb-1 (Ig-alpha) gene by Pax-5 is dependent on an unmethylated Ets binding site

Abstract

Methylation of cytosine in CpG dinucleotides promotes transcriptional repression in mammals by blocking transcription factor binding and recruiting methyl-binding proteins that initiate chromatin remodeling. Here, we use a novel cell-based system to show that retrovirally expressed Pax-5 protein activates endogenous early B-cell-specific mb-1 genes in plasmacytoma cells, but only when the promoter is hypomethylated. CpG methylation does not directly affect binding of the promoter by Pax-5. Instead, methylation of an adjacent CpG interferes with assembly of ternary complexes comprising Pax-5 and Ets proteins. In electrophoretic mobility shift assays, recruitment of Ets-1 is blocked by methylation of the Ets site (5'CCGGAG) on the antisense strand. In transfection assays, selective methylation of a single CpG within the Pax-5-dependent Ets site greatly reduces mb-1 promoter activity. Prior demethylation of the endogenous mb-1 promoter is required for its activation by Pax-5 in transduced cells. Although B-lineage cells have only unmethylated mb-1 genes and do not modulate methylation of the mb-1 promoter during development, other tissues feature high percentages of methylated alleles. Together, these studies demonstrate a novel DNA methylation-dependent mechanism for regulating transcriptional activity through the inhibition of DNA-dependent protein-protein interactions.

FIG. 1.

Pax-5 activates transcription of endogenous mb-1 genes in the 558LμM cell line. (A) 558LμM cells were transduced with retroviral vectors expressing GFP alone (cGFP) or the indicated FLAG-tagged factors and analyzed 3 dpt for cell surface expression of mIgM. mIgM expression is indicative of mb-1 transcription (D) and Ig-α production (E). (B) Western blotting of whole-cell lysates for expression of retrovirally expressed FLAG-tagged proteins (indicated above). Top: Detection of retrovirally expressed proteins using anti-FLAG antibodies. Bottom: Detection of endogenous Sp1 as a loading control. (C) Flow cytometric analysis of sorted 558LμM populations analyzed by MS-SNuPE. Boxes indicate gates used during cell sorting. (D) Real-time RT-PCR quantitation of mb-1 transcripts in sorted cGFP and Pax-5-expressing mIgM⁻ and mIgM⁺ 558LμM cells. (E) Western blotting of sorted cGFP and Pax-5(GFP)-expressing mIgM⁻ and mIgM⁺ 558LμM whole-cell lysates using Pax-5-, Ig-α-, or Sp1-specific antibodies. The pre-B-cell line PD36 served as a positive control for all three antibodies.

FIG. 2.

Methylation of the Pax-5-dependent Ets binding site prevents ternary complex assembly. EMSA was performed with recombinant Pax-5(1-149) and Ets-1(280-440) proteins as previously described (46). CpG methylation status of probe DNAs is indicated above as hemimethylated on sense or antisense strands, or bimethylated on both strands. Pax-5 and Pax-5-Ets-1 ternary complexes are indicated at right. The mb-1 probe sequence is shown below. Protein-DNA contacts made by Pax-5 (closed circles) or Ets-1 (open squares) in the crystal structure are indicated (14). The two CpG dinucleotides in the probe are boxed. Effects of modifying the downstream CpG were only tested with methylation of both strands (Methyl control).

FIG. 3.

Methylation of the Pax-5-dependent Ets site in the minimal mb-1 promoter inhibits transcriptional activation. M12.4.1 B cells were transiently transfected with the indicated pGL3 luciferase reporter constructs. Left panel: HpaII methylation of the SV40 promoter construct results in a 67.3% decrease in luciferase activity. Right panel: Luciferase activities of HpaII methylated constructs were corrected for the effects of methylation of the luciferase gene as determined at left. Black bars, unmethylated reporter constructs; gray bars, HpaII methylase-treated reporter constructs.

FIG. 4.

Methylation of the Ets-binding site CpG correlates with an inability to activate endogenous mb-1 gene transcription. Shown are the results of MS-SNuPE (see Materials and Methods) analysis of the antisense strand Pax-5-dependent Ets site in DNA isolated from sorted cGFP and Pax-5-expressing mIgM⁻ and mIgM⁺ 558LμM cells (see Fig. 1C). Percent methylation was determined as follows: dCTP cpm/(dCTP cpm + dTTP cpm) · 100%. Black bars indicate percentages of alleles methylated at the Pax-5-dependent Ets site.

FIG.5.

Pax-5 DBD-expressing clones exhibit differential transcription of the mb-1 gene. (A) Retrovirally expressed Pax-5 DBD activates mb-1 transcription in 558LμM cells similar to full-length Pax-5, as determined by surface mIgM expression. (B) DBD-expressing cells were cloned by limiting dilution, expanded, and analyzed for mIgM expression by flow cytometry (upper panels). Expression of cell surface mIgM in two clones, DBD 6.6 and DBD 8.4, was efficiently activated by Pax-5 DBD. In contrast, expression of mIgM was only weakly detected on the surface of DBD 7.3 and DBD 9.2. Treatment of these cells with 2 μM 5-azaC for 48 h resulted in upregulation of surface mIgM expression (lower panels). (C) Real-time RT-PCR quantitation of mb-1 transcripts in the DBD-expressing clones. (D) Western blot analysis of the indicated whole-cell lysates for Pax-5, Ig-α, and Sp1 expression. PD36 pre-B cells served as a positive control, and detection of Sp1 served as a loading control. (E) MS-SNuPE analysis of the antisense strand Pax-5-dependent Ets site was performed using DNA isolated from the DBD-expressing clones. Black bars show the percentage of alleles methylated at the Pax-5-dependent Ets site in the indicated population.

FIG. 6.

Expression of Ets partner proteins in mb-1-expressing and -nonexpressing DBD clones. (A) EMSA detection of Pax-5-Ets ternary complexes. Nuclear extracts (0.5 μg) prepared from cGFP-transduced 558LμM, DBD 7.3, and DBD 6.6 cells were used in EMSAs to detect binding to the mb-1 ternary complex probe. cGFP extracts were tested alone or with increasing concentrations of recombinant Pax-5(1-149). Supershifting with anti-Ets-1 antisera and anti-Pax-5 antibodies detected these proteins in ternary complexes. Bands indicated by an asterisk are faster-migrating complexes that did not react with the Ets-1 antibody but contained Pax-5. The presence of a fast-migrating band below Pax-5 in lanes 8, 12 and 16 is an artifact generated by the anti-Ets-1 antiserum that was not consistently observed. In lanes 18 to 23, nuclear extracts and recombinant Pax-5(1-149) were tested with the antisense hemimethylated ternary complex probe (see Fig. 2). (B) Western blotting of cGFP-transduced 558LμM cells, DBD 7.3, DBD 6.6, DBD 9.2, and DBD 8.4 nuclear extracts (25 μg) probed with anti-Ets-1 antisera. The faster-migrating band is Ets-1(p50). The slower-migrating band is likely an alternatively spliced form of Ets-1, or a highly homologous protein that cross-reacts with the anti-Ets-1 antisera.

FIG. 7.

Differential activation of mb-1 transcription by Pax-5 in 558LμM clones. (A) 558LμM cells were cloned by limiting dilution prior to transduction with retroviruses for expression of full-length Pax-5. 558LμM is the parent population. μM.2, μM.6, μM.5, and μM.10 are subclones derived from 558LμM. After cloning by limiting dilution, cells were transduced either with cGFP or Pax-5-expressing retroviruses and analyzed for mIgM expression at 3 dpt. (B) MS-SNuPE analysis of the antisense strand Pax-5-dependent Ets site was performed using DNA isolated from the 558LμM parent population and clones. Black bars show the percentage of alleles methylated at the Pax-5-dependent Ets site in the indicated population.

FIG. 8.

Methylation of the Pax-5-dependent Ets site in non-B-cell tissues and sorted ex vivo B cells at different stages of development. MS-SNuPE analysis of the antisense strand Pax-5-dependent Ets site was performed using DNA isolated from the indicated tissues and ex vivo-sorted cell populations. Black bars indicate the percentage of alleles methylated at the Pax-5-dependent Ets site. B.M., bone marrow-derived. Pax-5^−/− pre-B cells were derived from bone marrow of Pax-5 knockout mice (38). The phenotype of the J558L plamacytoma cells (the parent cell line of 558LμM) most resembles bone marrow-derived plasma cells.