Mapping functional transcription factor networks from gene expression data

Abstract

A critical step in understanding how a genome functions is determining which transcription factors (TFs) regulate each gene. Accordingly, extensive effort has been devoted to mapping TF networks. In Saccharomyces cerevisiae, protein-DNA interactions have been identified for most TFs by ChIP-chip, and expression profiling has been done on strains deleted for most TFs. These studies revealed that there is little overlap between the genes whose promoters are bound by a TF and those whose expression changes when the TF is deleted, leaving us without a definitive TF network for any eukaryote and without an efficient method for mapping functional TF networks. This paper describes NetProphet, a novel algorithm that improves the efficiency of network mapping from gene expression data. NetProphet exploits a fundamental observation about the nature of TF networks: The response to disrupting or overexpressing a TF is strongest on its direct targets and dissipates rapidly as it propagates through the network. Using S. cerevisiae data, we show that NetProphet can predict thousands of direct, functional regulatory interactions, using only gene expression data. The targets that NetProphet predicts for a TF are at least as likely to have sites matching the TF's binding specificity as the targets implicated by ChIP. Unlike most ChIP targets, the NetProphet targets also show evidence of functional regulation. This suggests a surprising conclusion: The best way to begin mapping direct, functional TF-promoter interactions may not be by measuring binding. We also show that NetProphet yields new insights into the functions of several yeast TFs, including a well-studied TF, Cbf1, and a completely unstudied TF, Eds1.

Figure 1.

TF-promoter binding potential for the top 4000 NetProphet predictions (red), all direct targets implicated by ChIP hits in the Yeastract or Tnet data bases (blue), and targets implicated by ChIP hits that are also predicted by NetProphet (green). The high stringency threshold for each PWM was set such that ∼10% of ChIP-implicated targets have PWM scores exceeding the threshold and hence count as “PWM supported.” The medium and low stringency thresholds were set such that ∼33% and ∼50% of ChIP-implicated targets for each TF have PWM scores exceeding the threshold, respectively. For the high, medium, and low stringency PWM cutoffs, chance inclusion was 6.4%, 22.1%, and 36.8%, respectively.

Figure 2.

Evidence supporting NetProphet predictions as a function of NetProphet rank. (A) Percentage of predictions supported by binding potential at the high stringency threshold (green, solid) and expectation for randomly selected targets (green, dashed). (B) Percentage of NetProphet predictions supported by ChIP hits (blue, solid) and expectation for randomly selected targets (blue, dashed). All points represent groups of NetProphet predictions that are significantly enriched for predictions with PWM support (panel A) or ChIP support (panel B), P < 0.05.

Figure 3.

Evaluation of top 4000 predictions from NetProphet (red), Inferelator (green), and GENIE3 (blue). (A) For each method, percentage of predictions supported by binding potential at the high stringency PWM threshold, ChIP data, or both. (B) Percentage of TFs for which at least one of the top five targets predicted by each method is supported by either binding potential or ChIP hits or both. (See Supplemental Methods for additional details.)

Figure 4.

Effect of Cbf1 on expression of acid phosphatases in cells grown in synthetic complete medium with 10 mM inorganic phosphate (red) or on cells grown in YPD (blue). (A) Expression of PHO5. (B) Combined expression of PHO11 and PHO12, which have so much sequence similarity that we were not able to distinguish their transcripts. Error bars representing one standard error of the mean of two technical replicates were too small to be seen in the figure.

Figure 5.

(A) The top seven NetProphet-predicted targets of Eds1 are all in the pathway for conversion of cytosolic citrate to lysine. (B) Log₂-fold change of EDS1 and five lysine biosynthesis genes relative to wild-type cells in an eds1 deletion mutant (two replicate cultures) and the same deletion mutant complemented by overexpression of Eds1 under the control of the tetO₂ promoter (cultures of two independent transformants).