Transcription factor Sp3 is silenced through SUMO modification by PIAS1

Abstract

Sp3 is a ubiquitous transcription factor closely related to Sp1. Here we show that Sp3 is a target for SUMO modification in vivo and in vitro. SUMO modification of Sp3 occurs at a single lysine located between the second glutamine-rich activation domain and the DNA-binding domain. Mutational analyses identified the sequence IKXE as essential for SUMO conjugation to Sp3. We identified the protein inhibitor of activated STAT1 (PIAS1) as an interaction partner of Sp3 and Ubc9. Moreover, PIAS1 strongly stimulated SUMO conjugation to Sp3, thus acting as an E3 ligase for SUMO conjugation to Sp3. All mutations that prevented SUMO modification in vitro strongly enhanced the transcriptional activity of Sp3, showing that SUMO modification silences Sp3 activity. SUMO-modified Sp3 bound to DNA with similar specificity and affinity as unmodified Sp3. However, DNA-bound Sp3 did not act as a substrate for SUMO modification.

Fig. 1. Sp3 is SUMO modified in vivo. (A) Schematic representation of HA- and FLAG-tagged wild-type Sp3 protein Sp3WT and the Sp3 mutant Sp3SD expressed in SL2 cells (Braun and Suske, 1999) and in MEFs deficient of endogenous Sp3 (H.Göllner and G.Suske, unpublished data). Grey boxes indicate the two glutamine-rich activation domains A and B, and three black stripes the zinc fingers of the DNA-binding domain (DBD) of Sp3. The ID of Sp3 is depicted by hatched stripes. Amino acids that are deleted in the Sp3SD mutant protein are shown. The single lysine within this sequence is underlined. (B) Western blot analyses of epitope-tagged Sp3WT and mutant Sp3SD protein. HA- and FLAG-tagged Sp3WT- or Sp3SD-expressing SL2 cells (lanes 2 and 3) and MEFs (lanes 4, 5 and 6) were lysed with SDS-containing buffer. Proteins were separated on 7.5% SDS– polyacrylamide gels and blotted to PVDF membranes. Membranes were subsequently incubated with HA- (αHA) or Sp3-specific (αSp3c) antibodies as indicated. Arrows point to the covalently modified wild-type Sp3WT protein. Asterisks depict C-terminally deleted degradation products of Sp3 and Sp3SD that were detectable with the αHA antiserum but not with the αSp3c antibodies that recognize an epitope at the Sp3 C-terminal end. Lane 1 contains affinity-purified epitope-tagged Sp3 protein (Sp3pur.) (Braun et al., 2001) lacking the covalent modification. (C) GFP fusion vectors (3 µg) for GFP–Sp3WT, GFP–Sp3K/R, GFP–SUMO-1 and GFP–SUMO-2 were transiently transfected in Ishikawa cells as indicated. Cells were lysed and equal amounts of total cellular proteins (20 µg per lane) were separated on a 6.0% SDS–polyacrylamide gel and blotted to PVDF membranes. Detection was by immunoblotting with αGFP antibodies. The arrows point to SUMO-modified GFP–Sp3WT. The occurrence of two GFP–SUMO-2 forms is most likely due to incomplete processing.

Fig. 2. In vitro SUMOylation and deSUMOylation of Sp3 fragments. (A) Schematic drawing of the conjugation pathway leading to SUMOylation of Sp3. The free carboxyl group of the C-terminal glycine of SUMO forms an isopeptide bond with the ε-amino group of a lysine (K) in Sp3. The reaction is mediated by the ATP-dependent heterodimeric E1 enzyme Aos1/Uba2 and the E2 enzyme Ubc9 that form thioesters (S) with SUMO. (B) Affinity-purified epitope-tagged Sp3WT (lanes 1–3) and Sp3SD (lanes 5–7) were subjected to in vitro SUMOylation reactions in the presence or absence of recombinant E1, Ubc9 and SUMO-1 as indicated. Sp3 and SUMO-modified Sp3 (arrow) were detected by western blot analysis using anti-HA antibodies. Lane 4 (HA/FL-Sp3) contains whole-cell extract from Sp3-expressing SL2 cells. (C) Bacterially expressed GST fusion proteins GST–Sp3WT, GST–Sp3kee and GST–Sp3BID bound to GST–Sepharose were subjected to in vitro SUMOylation reactions in the presence or absence of recombinant E1, Ubc9 and SUMO-1 as indicated. The GST–Sp3BID protein contains the second glutamine-rich activation domain (B domain) and the ID with the IKEE motif lacking the transactivation domain A and the C-terminal DNA-binding domain of Sp3. In the GST–Sp3kee protein, the KEE wild-type sequence of the ID is replaced by three alanine residues. Reaction products were detected by western blot analysis using anti-Sp3 (αSp3) and anti-SUMO-1 (αSUMO-1) antibodies as indicated. Arrows point to the SUMOylated Sp3 fragments. (D) SUMO-1 and SUMO-2 were equally conjugated to Sp3. Epitope-tagged recombinant Sp3 wild-type (Sp3WT) or the Sp3SD mutant was subjected to SUMO modification with equal concentrations of SUMO-1 and SUMO-2 (5 ng/µl each). Detection was by immunoblotting with αHA antibodies. (E) DeSUMOylation of SUMO-1-modified Sp3 by the isopeptidase Ulp1. The GST–Sp3BID fragment (see panel C) bound to glutathione–Sepharose was SUMOylated in vitro and subsequently incubated with recombinant ULP1 isopeptidase at 16 or 30°C for 30 or 60 min, as indicated. Detection was by immunoblotting with αSp3 antibodies.

Fig. 3. Identification of PIAS1 as an interaction partner of Sp3 and Ubc9. (A) Interaction of PIAS1 with the ID of Sp3 in Saccharomyces cerevisiae. Yeast cells containing a LexA-driven LacZ reporter construct were transformed with expression constructs for LexA, LexA-Sp3ID or LexA-Sp3ID/kee (baits) along with a construct in which the Gal4 activation domain is fused to the 500 C-terminal amino acids of PIAS1 (Gal4-PIAS1, prey). In the LexA-Sp3ID/kee construct, the KEE sequence of the SUMOylation motif is replaced by three alanine residues. β-galactosidase activity was visualized by addition of 0.5% X-gal to the agar. (B) In vitro association of PIAS1 with Sp3 and SUMO-1-modified Sp3. Sp3 (small isoform) was in vitro translated in the presence of [³⁵S]methionine and subsequently subjected to in vitro SUMO-1 conjugation. The reaction that contained unmodified Sp3 and SUMO-modified Sp3 (lane 8) was incubated with similar amounts of the glutathione matrix (lane 2), immobilized GST (lane 3), GST–Ubc9 (lane 4) or GST–PIAS1 (lane 6). In lane 5, unmodified ³⁵S-labelled Sp3 was incubated with GST–PIAS1. Bound Sp3 proteins were resolved by SDS–PAGE and visualized by fluorography. Lanes 7 and 8 contain 10% of the input ³⁵S-labelled Sp3 protein. Numbers on the left indicate the molecular mass of protein markers in kDa. (C) In vitro association of Ubc9 with PIAS1. PIAS1 was in vitro translated in the presence of [³⁵S]methionine and incubated with glutathione–Sepharose matrix (lane 2) or with ∼2 µg of immobilized GST (lanes 3 and 4) or GST–Ubc9 (lanes 5 and 6). Bound PIAS1 protein was resolved by SDS–PAGE and visualized by fluorography. Lane 7 contains 10% of the input ³⁵S-labelled PIAS1 protein. Numbers on the left indicate the molecular mass of protein markers in kDa.

Fig. 4. PIAS1 stimulates SUMO conjugation to Sp3. (A) Purified HA/FLAG-tagged Sp3 from SL2 cells was subjected to in vitro SUMO-1 (lanes 1–10) or SUMO-2 (lanes 11–16) modification in the presence of 10 mM glutathione (GSH; lanes 1 and 2), GST–PIAS1 (lanes 3–6 and 14–16) or GST (lanes 7–10 and 11–13). Reactions contained one-tenth of E1 and Ubc9 enzymes used in the experiments shown in Figure 2. After various time points, reactions were stopped by addition of Laemmli buffer. Proteins were resolved by SDS–PAGE and Sp3 detected by immunoblotting with αHA antibodies. (B) Schematic outline of the conjugation pathway leading to SUMO modification of Sp3. PIAS1 that interacted specifically with Ubc9 and SUMO-modified Sp3 acts as an E3 ligase for SUMO conjugation to Sp3.

Fig. 5. Point mutations that prevent SUMO modification in vitro strongly enhance Sp3 activation capacity. (A) Identification of amino acids essential for SUMO modification of Sp3 in vitro. The wild-type IKEE sequence in GST–Sp3 was mutated to IREE, IKDE, IKED, VKEE, RKEE and IEEK (mutated amino acids are underlined) and the recombinant GST–Sp3 mutant proteins were subjected to in vitro SUMO modification. GST–Sp3 and GST–Sp3 mutants were detected by immunoblotting using αGST antibodies. The arrow points to SUMO-modified GST–Sp3. (B) SL2 cells were transfected with 4 µg of BCAT-2 plasmid along with 20 or 200 ng of expression plasmids for Sp3 or Sp3 mutants as indicated. Amino acids in the Sp3 mutants that differ from the wild-type IKEE sequence are underlined. SL2 cells were lysed and CAT activities determined. Fold activation values were calculated from CAT activities in relation to the empty expression vector (pPac), which has been given the arbitrary value of 1.

Fig. 6. Subcellular localization of Sp3 and SUMO-1 in MEFs and Ishikawa cells. (A) Sp3–/– MEFs were transfected with 1 µg of an expression construct for GFP–Sp3. The intracellular distribution of GFP–Sp3 was detected by intrinsic green fluorescence of the GFP tag. Endogenous SUMO-1 localization was detected with a rabbit anti-SUMO-1 antibody and a CY3-conjugated secondary antibody. (B) Ishikawa cells were transfected with 1 µg of an expression construct for GFP–SUMO-1. Visualization was by the intrinsic green fluorescence of the GFP moiety. Endogenous Sp3 localization was detected with a rabbit anti-Sp3 antibody and a CY3-conjugated secondary antibody.

Fig. 7. SUMO-modified Sp3 binds specifically DNA. (A) A C-terminal Sp3 fragment (Sp3-320C) was subjected to in vitro conjugation with SUMO-1 in the absence (–) or presence (+) of enzymes. Subsequently, reactions were analysed by immunoblotting (top right, αSp3) and EMSA. All DNA-binding reactions contained 0.1 ng of ³²P-labelled GC oligonucleotide and various amounts (1- to 20-fold molar excess) of unlabelled GC or HNF3 oligonucleotides, as indicated. (B) Purified HA/FLAG-tagged Sp3 was subjected to in vitro conjugation with SUMO-1 or SUMO-2 and analysed by immunoblotting (top right, αHA) and southwestern analysis. For southwestern analysis, SUMOylation reaction products were separated by 8% SDS–PAGE, transferred to nitrocellulose and subsequently incubated with ³²P-labelled GC-box oligonucleotide in the absence (lanes 1– 3) or presence (lanes 4–6) of 100-fold molar excess of a specific competitor (GC box) or an unspecific (HNF3 site) (lanes 7–9) oligonucleotide. (C) Sp3 is not a target for SUMOylation when bound to DNA. Epitope-tagged recombinant Sp3 was subjected to SUMO-1 modification in the absence (lane 3) or presence of 10 and 100 ng of GC-box oligonucleotide (lanes 1 and 2) or HNF3-binding site oligonucleotide (lanes 4 and 5). Reaction products were separated by 8% SDS–PAGE and analysed by immunoblotting with αHA antibodies.