PASTAA: identifying transcription factors associated with sets of co-regulated genes

Abstract

Motivation: A major challenge in regulatory genomics is the identification of associations between functional categories of genes (e.g. tissues, metabolic pathways) and their regulating transcription factors (TFs). While, for a limited number of categories, the regulating TFs are already known, still for many functional categories the responsible factors remain to be elucidated.

Results: We put forward a novel method (PASTAA) for detecting transcriptions factors associated with functional categories, which utilizes the prediction of binding affinities of a TF to promoters. This binding strength information is compared to the likelihood of membership of the corresponding genes in the functional category under study. Coherence between the two ranked datasets is seen as an indicator of association between a TF and the category. PASTAA is applied primarily to the determination of TFs driving tissue-specific expression. We show that PASTAA is capable of recovering many TFs acting tissue specifically and, in addition, provides novel associations so far not detected by alternative methods. The application of PASTAA to detect TFs involved in the regulation of tissue-specific gene expression revealed a remarkable number of experimentally supported associations. The validated success for various datasets implies that PASTAA can directly be applied for the detection of TFs associated with newly derived gene sets.

Availability: The PASTAA source code as well as a corresponding web interface is freely available at http://trap.molgen.mpg.de.

Fig. 1.

The PASTAA workflow.

Fig. 2.

Cut-off space for the hypergeometric test. (A) The −log hypergeometric P-values (indicated by colour) for ABF1_01 and the Abf1 in vitro dataset depending on the cut-off combination employed for the predicted affinity and PBM binding values. The most significant target enrichment (P-value 7.3 × 10⁻²⁵³) is found when using the top 800 genes according to PBM and top 900 genes according to affinity. The steepest increase in −log P-values is found at the origin of the plot. (B) Same analysis as in (A) but for the factor PHO4_01 and the Pho4 ChIP–chip dataset (phosphate-deprived condition). According to the fact that Pho4 has far less targets than Abf1 an optimal hypergeometric P-value of 7.9 × 10⁻²⁰ is found when using only the top 300 genes according to ChIP–chip data and top 100 genes according to affinity.

Fig. 3.

TFs are over-expressed in their top ranking tissues. Height of bins indicates the number of TFs expressed in the associated tissue of given rank based on the real sequence data (dark blue) or on the results obtained from 10 random sequence sets (light blue). Error bars show the 95% confidence interval for the results obtained from the 10 random sequence sets. Tissues top ranking for a given TF express the factor more often than expected, while bottom ranking tissues express the TF equally or less often than expected. The enrichment is particularly significant for the first three bins corresponding to all three top ranking TF–tissue associations (P-value of enrichment for bins 1–3 combined: 2.2 × 10⁻¹²). The general trend in the light blue bins indicates the technical bias caused by the different number of ESTs in each tissue category.