Genome-wide analyses reveal properties of redundant and specific promoter occupancy within the ETS gene family

Abstract

The conservation of in vitro DNA-binding properties within families of transcription factors presents a challenge for achieving in vivo specificity. To uncover the mechanisms regulating specificity within the ETS gene family, we have used chromatin immunoprecipitation coupled with genome-wide promoter microarrays to query the occupancy of three ETS proteins in a human T-cell line. Unexpectedly, redundant occupancy was frequently detected, while specific occupancy was less likely. Redundant binding correlated with housekeeping classes of genes, whereas specific binding examples represented more specialized genes. Bioinformatics approaches demonstrated that redundant binding correlated with consensus ETS-binding sequences near transcription start sites. In contrast, specific binding sites diverged dramatically from the consensus and were found further from transcription start sites. One route to specificity was found--a highly divergent binding site that facilitates ETS1 and RUNX1 cooperative DNA binding. The specific and redundant DNA-binding modes suggest two distinct roles for members of the ETS transcription factor family.

Figure 1.

Conservation of mammalian ETS domains. (A) Phylogram tree of human ETS domain sequences. The amino acid sequence of all 27 human ETS domains were aligned by Clustal W (Thompson et al. 1994). The horizontal branch lengths relate to predicted evolutionary distance. (Longer branches are more divergent.) Nine clades with multiple highly similar domains and three additional singlet domains, indicated as numbers 1–12. ETS genes expressed in Jurkat T cells with mRNA levels above one copy per cell are highlighted in yellow (Hollenhorst et al. 2004). (B) ETS domain consensus binding sites. Illustrated sites were selected in vitro by SELEX method for the indicated mouse ETS proteins (Brown and McKnight 1992; Nye et al. 1992; Mao et al. 1994; Ray-Gallet et al. 1995; Shore and Sharrocks 1995; John et al. 1996). Sequence logos were created from PWM by enoLOGOS (Workman et al. 2005) with the height of each base related to reported frequency at that position. The selected ETV1, ETV2, and GABPα consensus sites were reported (Brown and McKnight 1992) without the necessary frequency distribution data to build a PWM.

Figure 2.

Specific and redundant promoter occupancy of ETS proteins. ChIP from the Jurkat human T-cell line with antibodies specific to the indicated ETS proteins. (A) Gene-specific region analysis. ChIP DNA was PCR-amplified with gene-specific primers. The ChIP enrichment is the ratio of the quantitative PCR signal of specific genomic regions over background genomic DNA (mean of two negative control genomic regions). Bars indicate the mean and standard error of the mean from three independent ChIP experiments. (B,C) Genome-wide occupancy analysis. ChIP DNA was amplified, labeled, and hybridized to a promoter microarray for 17,000 human genes representing sequences between −5 kb and +2 kb relative to the TSS. A bound promoter includes one or more peaks as defined by at least one probe with a P(X) value of <0.001. Data represent the average of two biologically independent replicates. Diagrams illustrate the number of promoter regions bound by ETS1, ELF1, GABPα, and RUNX1, and combinations thereof.

Figure 3.

Validation of redundant and specific bound segments from genomic occupancy data sets. (A) Stringent classification of redundant versus specific data sets. Bound segments were identified regardless of promoter annotation. To identify specific binding events, the stringencies of an “unbound” score was reduced [minimum P(X) value >0.01] to minimize false negatives. The probe with the lowest P(X) value from each bound segment was taken to represent that segment for that ETS protein. To compare with occupancy, the value of this representative probe was plotted versus the highest −log P(X) value for the other ETS protein within 1 kb of this probe. Shaded areas define the three data sets used for the comparisons in the remainder of the figure (size indicated). ETS1-specific and dual-bound segments were identified by the ETS1 segment report. (Dual-bound segments identified by the ELF1 segment report were essentially the same.) ELF1-specific segments were identified by the ELF1 segment report. (B–D) Quantitative ChIP confirmed specific and redundant occupancy. ChIP DNA obtained with specific antibodies, as indicated, was analyzed by quantitative PCR, as in Figure 2A. The scale on the Y-axis was interrupted to show a broad range of values. Segments were assigned to a gene by the closest TSS. In B, the EGR1 promoter, a well-characterized ELK1 target, served as an antibody positive control. The other 19 tested segments were randomly selected from the “dual-bound” data set from A. In C, 10 segments were randomly selected from the ETS1-specific data set from A. In D, 12 segments were selected from the ELF1-specific data set with preference for those with the least evidence of ETS1 occupancy [highest ETS1 P(X) values].

Figure 4.

Sequence characteristics of redundantly and specifically bound segments. (A) ETS1 and ELF1 dual-bound segments correlate with a strong match to a consensus ETS-binding site. The most overrepresented complex PWM identified by MEME (E = 1 × 10⁻³⁰) in dual-bound segments is illustrated by a sequence logo, as in Figure 1B. (B) Distances between TSS and bound segments (from Fig. 3) showed proximal bias of dual occupancy. The distance from the bound segment to the nearest TSS in the Ensembl database was measured by using the location of the oligonucleotide probe with the lowest P(X) in each segment in the dual-bound or ETS1-specific data sets. Distances were binned and frequencies were plotted. The number of segments analyzed is indicated in parenthesis. (No nearby gene was identified for nine dual-bound segments and seven ETS1-specific segments). The mean distances from start were significantly different (362 bp for dual-bound; 532 bp for specific segments; t-test, P = 0.0002). (C) Distances between TSS and the best match to ETS-binding consensus showed proximal bias of dual occupancy. PATSER was used with the PWM (shown in A) to search for the best consensus match within 1500 bp of sequence upstream of and downstream from the TSS in the dual-bound or ETS1-specific data sets (from Fig. 3) as well as a set of 937 randomly selected genes. The position of the highest-scoring match to the PWM in each 3000-bp region surrounding the TSS was binned and plotted. The mean distance from the TSS to the best PWM match was significantly shorter for dual regions (386 bp) versus ETS1-specific (608 bp; t-test, P < 0.0001) or randomly selected regions (604 bp; t-test, P < 0.0001).

Figure 5.

RUNX1 and ETS1 co-occupancy correlates with a sequence similar to ETS- and RUNX1-binding sites. (A) Dual occupancy criteria. The maximum −log P(X) value of ETS1 and RUNX1 for each promoter region represented on the array is plotted. Eight promoter regions had a −log P(X) value of >5 for RUNX1 and >4 for ETS1 (circled). (B) Quantitative ChIP validated ETS1 and RUNX1 co-occupancy. ChIP DNA was analyzed by quantitative PCR and gene-specific primers, as in Figure 3B, for each of these eight promoter regions. (C) A ETS1/RUNX1 composite site. (Top) The most overrepresented sequence identified by MEME analysis of 87 ETS1- and RUNX1-bound segments (E = 4 × 10⁻³³). (Bottom) The in vitro-derived binding sites for RUNX1 (Meyers et al. 1993) and ETS1 (Nye et al. 1992).

Figure 6.

ETS1 and RUNX1 bind DNA cooperatively to the MEME-derived composite site. Equilibrium binding curves for ETS1 and a 35-bp region of the MDS025 promoter (Fig. 5B) that displays a GGAA core (left) or with a single nucleotide change in the core to GGAG (right), which is also represented in the MEME-derived PWM. Experiments performed in the presence (gray squares) or absence (black circles) of 30 nM RUNX1 (1–302 fragment) and indicated ETS1. The K_D was derived by curve fitting by nonlinear least-squares analysis with fraction of DNA bound = 1/(1 + K_D/[ETS1]). ETS1-only binding to the GGAG site was below the level necessary for quantification by this assay.