Unbiased location analysis of E2F1-binding sites suggests a widespread role for E2F1 in the human genome

Abstract

The E2F family of transcription factors regulates basic cellular processes. Here, we take an unbiased approach towards identifying E2F1 target genes by examining localization of E2F1-binding sites using high-density oligonucleotide tiling arrays. To begin, we developed a statistically-based methodology for analysis of ChIP-chip data obtained from arrays that represent 30 Mb of the human genome. Using this methodology, we identified regions bound by E2F1, MYC, and RNA Polymerase II (POLR2A). We found a large number of binding sites for all three factors; extrapolation suggests there may be approximately 20,000-30,000 E2F1- and MYC-binding sites and approximately 12,000-17,000 active promoters in HeLa cells. In contrast to our results for MYC, we find that the majority of E2F1-binding sites (>80%) are located in core promoters and that 50% of the sites overlap transcription starts. Only a small fraction of E2F1 sites possess the canonical binding motif. Surprisingly, we found that approximately 30% of genes in the 30-Mb region possessed an E2F1 binding site in a core promoter and E2F1 was bound near to 83% of POLR2A-bound sites. To determine if these results were representative of the entire human genome, we performed ChIP-chip analyses of approximately 24,000 promoters and confirmed that greater than 20% of the promoters were bound by E2F1. Our results suggest that E2F1 is recruited to promoters via a method distinct from recognition of the known consensus site and point toward a new understanding of E2F1 as a factor that contributes to the regulation of a large fraction of human genes.

Figure 1.

Confirmation of ChIP and amplicons. Primers specific for the MCM4 promoter and for a region of chromosome 21 were used as positive and negative controls, respectively, for analysis of (A) ChIP or (B) amplicon samples that had been immunoprecipitated with an E2F1 antibody or a nonspecific rabbit IgG.

Figure 2.

Peak-calling on a single array trace. The hybridization data for a portion of ENr232 are shown. Above the trace, four different levels of peak-calling stringency are indicated (L1–L4; see Results for explanation of levels). As the stringency is lowered to L4, more peaks are called.

Figure 3.

Combining array data sets. (A) A schematic illustration of the “combine-first” approach. (B) A schematic illustration of the “peak-first” approach. (C) An example of peak-calling and combination (at L1 for each array) on the same region from ENr223 from three independent arrays. The maximum bar height (log₂) is 5.44 for “array A”; 2.10 for “array B”; and 4.18 for “array C”. The final derived peak is shown by the black rectangle on the top line and extends from chr6:74156406 to 74157748. All three arrays contributed significantly to the set of peaks; for the total set of 205 L1 peaks, 100 were found in all three arrays. (D) Comparison of binding site predictions (at L1) for peak-first and combine-first approaches for HeLa E2F1 data. Note that there are fewer “peak-first” predictions and that nearly all “peak-first” predictions (96%) are in the “combine-first” set. See Results and Supplemental Methods for additional description.

Figure 4.

Most E2F1-binding sites are found in both HeLa and MCF7 cells. (A) Raw array data (one array for each cell type shown) and predicted E2F1-binding sites (L1) from ENr324 (chrX) in HeLa and MCF7 cells. Predicted sites (indicated as HeLa TFBS and MCF7 TFBS) are the results of using our standard analysis approach on three arrays from each cell type (see Results). (B) Pie chart showing that 75% of MCF7 sites overlap a HeLa site. (TFBS) Transcription factor binding site.

Figure 5.

A speculative model for E2F1 recruitment. (A) Classical E2F1 sites. At a subset of sites (mostly associated with cell cycle and DNA repair genes), E2F1 plays a major role in controlling transcriptional output by binding directly to a consensus site and helping to recruit the transcriptional machinery. (B) Cooperative E2F1 sites. At these sites, E2F1 binds cooperatively with other DNA-bound factors to sites that resemble the E2F consensus motif. (C) Inverted recruitment of E2F1. Here, E2F1 does not directly bind DNA, but perhaps is recruited to the promoter via interaction of the transactivation domain with general transcription factors such as TBP or TFIIH to play a role after pre-initiation complex formation. See Discussion for description.