Toucan: deciphering the cis-regulatory logic of coregulated genes.

@article{citeulike:456231, abstract = {TOUCAN is a Java application for the rapid discovery of significant cis-regulatory elements from sets of coexpressed or coregulated genes. Biologists can automatically (i) retrieve genes and intergenic regions, (ii) identify putative regulatory regions, (iii) score sequences for known transcription factor binding sites, (iv) identify candidate motifs for unknown binding sites, and (v) detect those statistically over-represented sites that are characteristic for a gene set. Genes or intergenic regions are retrieved from Ensembl or EMBL, together with orthologs and supporting information. Orthologs are aligned and syntenic regions are selected as candidate regulatory regions. Putative sites for known transcription factors are detected using our MotifScanner, which scores position weight matrices using a probabilistic model. New motifs are detected using our MotifSampler based on Gibbs sampling. Binding sites characteristic for a gene set--and thus statistically over-represented with respect to a reference sequence set--are found using a binomial test. We have validated Toucan by analyzing muscle-specific genes, liver-specific genes and E2F target genes; we have easily detected many known binding sites within intergenic DNA and identified new biologically plausible sites for known and unknown transcription factors. Software available at http://www.esat.kuleuven.ac. be/ approximately dna/BioI/Software.html.}, address = {Department of Electrical Engineering (ESAT-SCD), Katholieke Universiteit Leuven, Kasteelpark Arenberg 10, 3001 Heverlee, Leuven, Belgium. stein.aerts@esat.kuleuven.ac.be}, author = {Aerts, S. and Thijs, G. and Coessens, B. and Staes, M. and Moreau, Y. and De Moor, B. }, citeulike-article-id = {456231}, doi = {http://dx.doi.org/10.1093/nar/gkg268}, issn = {1362-4962}, journal = {Nucleic Acids Res}, keywords = {p-value}, month = {March}, number = {6}, pages = {1753--1764}, posted-at = {2008-01-08 10:25:38}, priority = {3}, title = {Toucan: deciphering the cis-regulatory logic of coregulated genes.}, url = {http://dx.doi.org/10.1093/nar/gkg268}, volume = {31}, year = {2003} }

TY - JOUR ID - citeulike:456231 L3 - citeulike-article-id:456231 TI - Toucan: deciphering the cis-regulatory logic of coregulated genes. JF - Nucleic Acids Res VL - 31 IS - 6 SP - 1753 EP - 1764 AD - Department of Electrical Engineering (ESAT-SCD), Katholieke Universiteit Leuven, Kasteelpark Arenberg 10, 3001 Heverlee, Leuven, Belgium. stein.aerts@esat.kuleuven.ac.be SN - 1362-4962 N2 - TOUCAN is a Java application for the rapid discovery of significant cis-regulatory elements from sets of coexpressed or coregulated genes. Biologists can automatically (i) retrieve genes and intergenic regions, (ii) identify putative regulatory regions, (iii) score sequences for known transcription factor binding sites, (iv) identify candidate motifs for unknown binding sites, and (v) detect those statistically over-represented sites that are characteristic for a gene set. Genes or intergenic regions are retrieved from Ensembl or EMBL, together with orthologs and supporting information. Orthologs are aligned and syntenic regions are selected as candidate regulatory regions. Putative sites for known transcription factors are detected using our MotifScanner, which scores position weight matrices using a probabilistic model. New motifs are detected using our MotifSampler based on Gibbs sampling. Binding sites characteristic for a gene set--and thus statistically over-represented with respect to a reference sequence set--are found using a binomial test. We have validated Toucan by analyzing muscle-specific genes, liver-specific genes and E2F target genes; we have easily detected many known binding sites within intergenic DNA and identified new biologically plausible sites for known and unknown transcription factors. Software available at http://www.esat.kuleuven.ac. be/ approximately dna/BioI/Software.html. KW - p-value AU - Aerts, S AU - Thijs, G AU - Coessens, B AU - Staes, M AU - Moreau, Y AU - De Moor, B PY - 2003/03/15/ UR - http://dx.doi.org/10.1093/nar/gkg268 ER -