Reliable prediction of regulator targets using 12 Drosophila genomes Export

@article{citeulike:1928757, abstract = {10.1101/gr.7090407 Gene expression is regulated pre- and post-transcriptionally via -regulatory DNA and RNA motifs. Identification of individual functional instances of such motifs in genome sequences is a major goal for inferring regulatory networks yet has been hampered due to the motifs\^{a}€™ short lengths that lead to many chance matches and poor signal-to-noise ratios. In this paper, we develop a general methodology for the comparative identification of functional motif instances across many related species, using a phylogenetic framework that accounts for the evolutionary relationships between species, allows for motif movements, and is robust against missing data due to artifacts in sequencing, assembly, or alignment. We also provide a robust statistical framework for evaluating motif confidence, which enables us to translate evolutionary conservation into a confidence measure for each motif instance, correcting for varying motif length, composition, and background conservation of the target regions. We predict targets of fly transcription factors and miRNAs in alignments of 12 recently sequenced species. When compared to extensive genome-wide experimental data, predicted targets are of high quality, matching and surpassing ChIP-chip microarrays and recovering miRNA targets with high sensitivity. The resulting regulatory network suggests significant redundancy between pre- and post-transcriptional regulation of gene expression.}, address = {Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, USA;}, author = {Kheradpour, Pouya and Stark, Alexander and Roy, Sushmita and Kellis, Manolis}, citeulike-article-id = {1928757}, citeulike-linkout-0 = {http://dx.doi.org/10.1101/gr.7090407}, citeulike-linkout-1 = {http://genome.cshlp.org/content/17/12/1919.abstract}, citeulike-linkout-2 = {http://genome.cshlp.org/content/17/12/1919.full.pdf}, citeulike-linkout-3 = {http://www.genome.org/cgi/content/abstract/17/12/1919}, citeulike-linkout-4 = {http://view.ncbi.nlm.nih.gov/pubmed/17989251}, citeulike-linkout-5 = {http://www.hubmed.org/display.cgi?uids=17989251}, day = {7}, doi = {10.1101/gr.7090407}, issn = {1088-9051}, journal = {Genome Research}, keywords = {target-prediction}, month = {December}, number = {12}, pages = {1919--1931}, posted-at = {2008-02-27 14:50:59}, priority = {2}, title = {Reliable prediction of regulator targets using 12 Drosophila genomes}, url = {http://dx.doi.org/10.1101/gr.7090407}, volume = {17}, year = {2007} }

TY - JOUR ID - citeulike:1928757 L3 - citeulike-article-id:1928757 N2 - 10.1101/gr.7090407 Gene expression is regulated pre- and post-transcriptionally via -regulatory DNA and RNA motifs. Identification of individual functional instances of such motifs in genome sequences is a major goal for inferring regulatory networks yet has been hampered due to the motifs’ short lengths that lead to many chance matches and poor signal-to-noise ratios. In this paper, we develop a general methodology for the comparative identification of functional motif instances across many related species, using a phylogenetic framework that accounts for the evolutionary relationships between species, allows for motif movements, and is robust against missing data due to artifacts in sequencing, assembly, or alignment. We also provide a robust statistical framework for evaluating motif confidence, which enables us to translate evolutionary conservation into a confidence measure for each motif instance, correcting for varying motif length, composition, and background conservation of the target regions. We predict targets of fly transcription factors and miRNAs in alignments of 12 recently sequenced species. When compared to extensive genome-wide experimental data, predicted targets are of high quality, matching and surpassing ChIP-chip microarrays and recovering miRNA targets with high sensitivity. The resulting regulatory network suggests significant redundancy between pre- and post-transcriptional regulation of gene expression. IS - 12 JF - Genome Research SN - 1088-9051 AD - Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, USA; EP - 1931 TI - Reliable prediction of regulator targets using 12 Drosophila genomes VL - 17 SP - 1919 KW - target-prediction AU - Kheradpour, Pouya AU - Stark, Alexander AU - Roy, Sushmita AU - Kellis, Manolis PY - 2007/12/07/ UR - http://dx.doi.org/10.1101/gr.7090407 ER -