TAF4/4b x TAF12 displays a unique mode of DNA binding and is required for core promoter function of a subset of genes

Abstract

The major core promoter-binding factor in polymerase II transcription machinery is TFIID, a complex consisting of TBP, the TATA box-binding protein, and 13 to 14 TBP-associated factors (TAFs). Previously we found that the histone H2A-like TAF paralogs TAF4 and TAF4b possess DNA-binding activity. Whether TAF4/TAF4b DNA binding directs TFIID to a specific core promoter element or facilitates TFIID binding to established core promoter elements is not known. Here we analyzed the mode of TAF4b.TAF12 DNA binding and show that this complex binds DNA with high affinity. The DNA length required for optimal binding is approximately 70 bp. Although the complex displays a weak sequence preference, the nucleotide composition is less important than the length of the DNA for high affinity binding. Comparative expression profiling of wild-type and a DNA-binding mutant of TAF4 revealed common core promoter features in the down-regulated genes that include a TATA-box and an Initiator. Further examination of the PEL98 gene from this group showed diminished Initiator activity and TFIID occupancy in TAF4 DNA-binding mutant cells. These findings suggest that DNA binding by TAF4/4b-TAF12 facilitates the association of TFIID with the core promoter of a subset of genes.

FIGURE 1.

TAF4b and TAF12 bind DNA as a heterodimer. A, TAF4b (amino acids 561–769) and His₆-TAF12 (full-length) were expressed in E. coli, refolded together as described under “Experimental Procedures,” purified on nickel beads, and run on an SDS-PAGE. The locations of TAF4b and TAF12 are indicated. B, EMSA analysis of the gel-filtration purified TAF4b·TAF12 using the AdML core promoter (−52 to +18) as a probe. Two pmol of TAF4b·TAF12 complex was incubated with 50 fmol of DNA probe (lane 1), and with increasing amounts of non-labeled DNA (lanes 2–7). The molar ratio between the protein complex and DNA is indicated at the top of each lane. C, determination of the apparent K_d of TAF4b·TAF12·DNA. DNA binding analysis by EMSA of increasing amounts of purified TAF4b·TAF12 complex in the presence of excess of DNA (AdML promoter). The graph shows the densitometric measurements of the bound DNA as a function of protein concentration (nanomolar). The apparent K_d is the concentration of the complex required to achieve 50% of maximal binding.

FIGURE 2.

TAF4b·TAF12 displays sequence preference. A, graphic presentation of the different DNA fragments used for binding reactions with the purified TAF4b·TAF12 complex. The right panel shows an ethidium bromide-stained polyacrylamide gel with equal amounts of the DNA fragments. B and C, EMSAs were performed with purified TAF4b·TAF12 and radiolabeled AdML (B) or A20 (C) promoter fragments. Competition was by 2 and 5 m excess of unlabeled AdML, IkB, A20, and control fragments as indicated at the top. Lane 1 is the probe in the absence of protein, and lane 2 is a binding reaction in the absence of competitor.

FIGURE 3.

The optimal length of DNA for TAF4b·TAF12 binding is half the size of nucleosomal DNA. A, the TAF4b·TAF12 complex was incubated with a radiolabeled oligonucleotide containing a 70-bp AdML promoter (WT) in the absence (lane 2) or the presence (lanes 3–10) of cold DNA competitors as indicated at the top of the lanes. The sequences of the DNA used as competitors are shown below. B, EMSA experiment as in A using equivalent molar amounts of different length DNAs whose sequences are shown in A. The relative amount of bound DNA is indicated at the bottom. C, competition experiment as in A. Sequences of competitor DNA are shown at the bottom. Mutated nucleotides are in lowercase letters.

FIGURE 4.

TAF4 DNA binding is not required for TAF4-mediated growth suppression. In A: top panel, schematic representation TAF4CRII TAF4CRIImDB relative to the full-length TAF4. The mutation in TAF4CRIImDB corresponds to amino acids 1011–1051 of the spacer domain. Lower panel, TAF4CRII and TAF4CRIImDB were fused to glutathione S-transferase, expressed in E. coli, and analyzed for binding to DNA-cellulose beads (DNA lanes). Binding to empty cellulose beads (Empty beads lanes) served as a control. The input represents 10% of the protein used for binding. 20% of the eluted proteins were analyzed by SDS-PAGE and silver staining. Positions of the protein are marked on the left, and the proteins fused in binding assays are indicated at the bottom. The asterisk indicates the bovine serum albumin that is added to the binding and elution buffers. B, TAF4^−/− fibroblasts were transfected with HA-TAF4CRII and HA-TAF4CRIImDB, and an empty expression vector as a control. Stable clones were analyzed by immunoblot using anti-HA and anti-tubulin monoclonal antibodies. C, total cell extracts from TAF4CRII and TAF4CRIImDB cell lines were immunoprecipitated and assayed with non-relevant control and anti-HA antibodies as indicated at the top. The immunoprecipitated complexes were then subjected to immunoblot analysis with antibodies against a subset of TAFs and TBP antibodies as indicated.

FIGURE 5.

Gene expression differences between TAF4CRII and TAF4CRIImDB cell lines. A list of some of some differentially expressed genes is shown in the left. The full list is shown in supplemental file 2. A and B, changes in down-regulated (A) and up-regulated (B) selected genes are shown. Reverse transcription-real-time PCR was performed on the indicated genes using RNA from the TAF4CRII and TAF4CRIImDB. Results of three independent RNA preparations are shown.

FIGURE 6.

A, proximal promoter sequences (from −100 to +50) of genes down-regulated in TAF4CRIImDB cells were retrieved from the Database of Transcription Start Sites and analyzed by the ClustalW2 program, which compares the sequences and provides a consensus sequence (top panel). Alignment of the AdML proximal promoter to the consensus sequence derived from the ClustalW2 analysis of the down-regulated genes is shown in the lower panel. Locations of the TATA-like and Initiator sequences are underlined. Homologous sequences are boxed. B, TAF4CRII and TAF4CRIImDB cells were transfected with luciferase reporter plasmids directed by the wild-type or initiator mutant Pel98 promoter. For control, the PMM2 promoter was also transfected. Rous sarcoma virus promoter-driven Renilla reporter plasmids were cotransfected with each plasmid to normalize for transfection efficiency. Luciferase activities were measured 24 h after transfection, and the relative luciferase activity is presented. The data represent the mean ± S.D. of three independent experiments each with independent duplicates. C, TAF4CRII and TAF4CRIImDB cells were subjected to ChIP with antibodies, indicated at the bottom, against TAF4 (anti-HA tag), TBP, and a non-relevant protein as control. The immunoprecipitated chromatin was analyzed by semi-quantitative PCR using primers for pel98 and PMM2 promoters. Quantified results, normalized to the input, were derived from three independent experiments and are presented as enrichment fold relative to the control antibodies.