We present MEDUSA, an integrative method for learning motif models of transcription factor binding sites by incorporating promoter sequence and gene expression data. We use a modern large-margin machine learning approach, based on boosting, to enablefeature selection from the high-dimensional search space of candidate binding sequences while avoiding overfitting. At each iteration of the algorithm, MEDUSA builds a motif model whose presence in the promoter region of a gene, coupled with activity ofa regulator in an experiment, is predictive of differential expression. In this way, we learn motifs that are functional and predictive of regulatory response rather than motifs that are simply overrepresented in promoter sequences. Moreover, MEDUSA produces a model of the transcriptional control logic that can predict the expression of any gene in the organism, given the sequence of the promoter region of the target gene and the expression state of a set of known or putative transcription factors and signaling molecules. Each motif model is either a fe-length sequence, a dimer, or a PSSM that is built by agglomerative probabilistic clustering of sequences with similar boosting loss. By applying MEDUSA to a set of environmental stress response expression data in yeast, we learn motifs whose ability to predict differential expression of target genes outperforms motifs from the TRANSFAC dataset and from a previously published candidate set of PSSMs. We also show that MEDUSA retrieves many experimentallyconfirmed binding sites associated with environmental stress response from the literature.
展开▼