Detailing regulatory networks through large scale data integration Export

@article{citeulike:5938773, abstract = {Motivation: Much of a cell's regulatory response to changing environments occurs at the transcriptional level. Particularly in higher organisms, transcription factors (TFs), microRNAs and epigenetic modifications can combine to form a complex regulatory network. Part of this system can be modeled as a collection of regulatory modules: co-regulated genes, the conditions under which they are co-regulated and sequence-level regulatory motifs. Results: We present the Combinatorial Algorithm for Expression and Sequence-based Cluster Extraction (COALESCE) system for regulatory module prediction. The algorithm is efficient enough to discover expression biclusters and putative regulatory motifs in metazoan genomes (>20 000 genes) and very large microarray compendia (>10 000 conditions). Using Bayesian data integration, it can also include diverse supporting data types such as evolutionary conservation or nucleosome placement. We validate its performance using a functional evaluation of co-clustered genes, known yeast and Escherichea coli TF targets, synthetic data and various metazoan data compendia. In all cases, COALESCE performs as well or better than current biclustering and motif prediction tools, with high accuracy in functional and TF/target assignments and zero false positives on synthetic data. COALESCE provides an efficient and flexible platform within which large, diverse data collections can be integrated to predict metazoan regulatory networks. Availability: Source code (C++) is available at http://function.princeton.edu/sleipnir, and supporting data and a web interface are provided at http://function.princeton.edu/coalesce. Contact: ogt@cs.princeton.edu; hcoller@princeton.edu. Supplementary information: Supplementary data are available at Bioinformatics online. 10.1093/bioinformatics/btp588}, author = {Huttenhower, Curtis and Mutungu, K. Tsheko and Indik, Natasha and Yang, Woongcheol and Schroeder, Mark and Forman, Joshua J. and Troyanskaya, Olga G. and Coller, Hilary A.}, booktitle = {Bioinformatics}, citeulike-article-id = {5938773}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btp588}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/content/btp588v1/.abstract}, citeulike-linkout-2 = {http://bioinformatics.oxfordjournals.org/content/btp588v1/.full.pdf}, citeulike-linkout-3 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/25/24/3267}, citeulike-linkout-4 = {http://view.ncbi.nlm.nih.gov/pubmed/19825796}, citeulike-linkout-5 = {http://www.hubmed.org/display.cgi?uids=19825796}, day = {15}, doi = {10.1093/bioinformatics/btp588}, issn = {1460-2059}, journal = {Bioinformatics}, keywords = {bayesian-integration, biclustering, data-integration, e-coli, module, motif}, month = {December}, number = {24}, pages = {3267--3274}, posted-at = {2009-10-14 11:08:07}, priority = {2}, title = {Detailing regulatory networks through large scale data integration}, url = {http://dx.doi.org/10.1093/bioinformatics/btp588}, volume = {25}, year = {2009} }

TY - JOUR ID - citeulike:5938773 L3 - citeulike-article-id:5938773 N2 - Motivation: Much of a cell's regulatory response to changing environments occurs at the transcriptional level. Particularly in higher organisms, transcription factors (TFs), microRNAs and epigenetic modifications can combine to form a complex regulatory network. Part of this system can be modeled as a collection of regulatory modules: co-regulated genes, the conditions under which they are co-regulated and sequence-level regulatory motifs. Results: We present the Combinatorial Algorithm for Expression and Sequence-based Cluster Extraction (COALESCE) system for regulatory module prediction. The algorithm is efficient enough to discover expression biclusters and putative regulatory motifs in metazoan genomes (>20 000 genes) and very large microarray compendia (>10 000 conditions). Using Bayesian data integration, it can also include diverse supporting data types such as evolutionary conservation or nucleosome placement. We validate its performance using a functional evaluation of co-clustered genes, known yeast and Escherichea coli TF targets, synthetic data and various metazoan data compendia. In all cases, COALESCE performs as well or better than current biclustering and motif prediction tools, with high accuracy in functional and TF/target assignments and zero false positives on synthetic data. COALESCE provides an efficient and flexible platform within which large, diverse data collections can be integrated to predict metazoan regulatory networks. Availability: Source code (C++) is available at http://function.princeton.edu/sleipnir, and supporting data and a web interface are provided at http://function.princeton.edu/coalesce. Contact: ogt@cs.princeton.edu; hcoller@princeton.edu. Supplementary information: Supplementary data are available at Bioinformatics online. 10.1093/bioinformatics/btp588 IS - 24 JF - Bioinformatics SN - 1460-2059 EP - 3274 TI - Detailing regulatory networks through large scale data integration VL - 25 T2 - Bioinformatics SP - 3267 KW - bayesian-integration KW - biclustering KW - data-integration KW - e-coli KW - module KW - motif AU - Huttenhower, Curtis AU - Mutungu, Tsheko AU - Indik, Natasha AU - Yang, Woongcheol AU - Schroeder, Mark AU - Forman, Joshua AU - Troyanskaya, Olga AU - Coller, Hilary PY - 2009/12/15/ UR - http://dx.doi.org/10.1093/bioinformatics/btp588 ER -