A semi-supervised method for predicting transcription factor-gene interactions in Escherichia coli

• Published in: PLoS computational biology 2008-03, Vol.4 (3), p.e1000044-e1000044
• Main Authors: Ernst, Jason, Beg, Qasim K, Kay, Krin A, Balázsi, Gábor, Oltvai, Zoltán N, Bar-Joseph, Ziv
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Base Sequence; Computational Biology/Sequence Motif Analysis; Computational Biology/Systems Biology; Computational Biology/Transcriptional Regulation; E coli; Escherichia coli - physiology; Escherichia coli Proteins - metabolism; Experiments; Gene expression; Gene Expression Profiling - methods; Gene Expression Regulation, Bacterial - physiology; Genomics; Hypothesis testing; Methods; Microbiology; Molecular Sequence Data; Ontology; Pattern Recognition, Automated - methods; Protein Interaction Mapping - methods; Proteins; R&D; Research & development; Sequence Analysis, DNA - methods; Transcription Factors - metabolism
• ISSN: 1553-7358; 1553-734X; 1553-7358
• DOI: 10.1371/journal.pcbi.1000044

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.