Transcription factor-DNA binding via machine learning ensembles

The network of interactions between transcription factors (TFs) and their regulatory gene targets governs many of the behaviors and responses of cells. Construction of a transcriptional regulatory network involves three interrelated problems, defined for any regulator: finding (1) its target genes, (2) its binding motif and (3) its DNA binding sites. Many tools have been developed in the last decade to solve these problems. However, performance of algorithms for these has not been consistent for all transcription factors. Because machine learning algorithms have shown advantages in integrating information of different types, we investigate a machine-based approach to integrating predictions from an ensemble of commonly used motif exploration algorithms.Published versio