A Semi-Supervised Method for Predicting Transcription Factor-Gene Interactions in Escherichia coli

by Jason Ernst, Qasim K. Beg, Krin A. Kay, Gabor Balazsi, Zoltán N. Oltvai, and Ziv Bar-Joseph
PLoS Computational Biology 4(3): e1000044, 2008.

Abstract
While Escherichia coli has one of the most comprehensive datasets of experimentally verified transcriptional regulatory interactions of any organism, it is still far from complete. This presents a problem when trying to combine gene expression and regulatory interactions to model transcriptional regulatory networks. Using the available regulatory interactions to predict new interactions may lead to better coverage and more accurate models. Here, we develop, SEREND (SEmi-supervised REgulatory Network Discoverer), a semi-supervised learning method that uses a curated database of verified transcriptional factor-gene interactions, DNA sequence binding motifs, and a compendium of gene expression data in order to make thousands of new predictions about transcription factor-gene interactions, including whether the transcription factor activates or represses the gene. Using genome-wide binding datasets for several transcription factors we demonstrate that our semi-supervised classification strategy improves the prediction of targets for a given transcription factor. To further demonstrate the utility of our inferred interactions we generated a new microarray gene expression dataset for the aerobic to anaerobic shift response in E. coli. We used our inferred interactions with the verified interactions to reconstruct a dynamic regulatory network for this response. The network reconstructed when using our inferred interactions was better able to correctly identify known regulators and suggested additional activators and repressors as having important roles during the aerobic-anaerobic shift interface.


  • TF-gene Interaction Predictions

  • Aerobic-anaerobic Expression Data in GEO

  • ChIP-chip gene sets used in validation

  • SEREND Java implementation (Weka library is included; version log)

  • To view the aerobic-anaerobic shift response maps from the paper in the DREM software, download DREM and this zip file. The zip file contains the aerobic-anaerobic shift response data, the settings files, and the cmd launch scripts for both the curated and prediction extended TF-gene interaction input, and the version of the EBI UniProt Ecoli K12 GO Annotations used in the paper. Place the unzipped files in the root of the drem directory.