A transcription factor affinity-based code for mammalian transcription initiation Export

@article{megraw09, abstract = {10.1101/gr.085449.108 The recent arrival of large-scale cap analysis of gene expression (CAGE) data sets in mammals provides a wealth of quantitative information on coding and noncoding RNA polymerase II transcription start sites (TSS). Genome-wide CAGE studies reveal that a large fraction of TSS exhibit peaks where the vast majority of associated tags map to a particular location (\^{a}¼45\%), whereas other active regions contain a broader distribution of initiation events. The presence of a strong single peak suggests that transcription at these locations may be mediated by position-specific sequence features. We therefore propose a new model for single-peaked TSS based solely on known transcription factors (TFs) and their respective regions of positional enrichment. This probabilistic model leads to near-perfect classification results in cross-validation (auROC = 0.98), and performance in genomic scans demonstrates that TSS prediction with both high accuracy and spatial resolution is achievable for a specific but large subgroup of mammalian promoters. The interpretable model structure suggests a DNA code in which canonical sequence features such as TATA-box, Initiator, and GC content do play a significant role, but many additional TFs show distinct spatial biases with respect to TSS location and are important contributors to the accurate prediction of single-peak transcription initiation sites. The model structure also reveals that CAGE tag clusters distal from annotated gene starts have distinct characteristics compared to those close to gene 5\^{a}²-ends. Using this high-resolution single-peak model, we predict TSS for \^{a}¼70\% of mammalian microRNAs based on currently available data.}, author = {Megraw, Molly and Pereira, Fernando and Jensen, Shane T. and Ohler, Uwe and Hatzigeorgiou, Artemis G.}, citeulike-article-id = {3888928}, citeulike-linkout-0 = {http://dx.doi.org/10.1101/gr.085449.108}, citeulike-linkout-1 = {http://genome.cshlp.org/content/gr.085449.108v1//.abstract}, citeulike-linkout-2 = {http://genome.cshlp.org/content/gr.085449.108v1//.full.pdf}, citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/19141595}, citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=19141595}, day = {13}, doi = {10.1101/gr.085449.108}, issn = {1088-9051}, journal = {Genome Research}, keywords = {microrna, microrna-regulation, microrna-transcriptional-regulation, transcription, transcription\_factor}, month = {April}, number = {4}, pages = {644--656}, posted-at = {2009-10-22 14:40:10}, priority = {2}, title = {A transcription factor affinity-based code for mammalian transcription initiation}, url = {http://dx.doi.org/10.1101/gr.085449.108}, volume = {19}, year = {2009} }

TY - JOUR ID - megraw09 L3 - citeulike-article-id:3888928 N2 - 10.1101/gr.085449.108 The recent arrival of large-scale cap analysis of gene expression (CAGE) data sets in mammals provides a wealth of quantitative information on coding and noncoding RNA polymerase II transcription start sites (TSS). Genome-wide CAGE studies reveal that a large fraction of TSS exhibit peaks where the vast majority of associated tags map to a particular location (â¼45%), whereas other active regions contain a broader distribution of initiation events. The presence of a strong single peak suggests that transcription at these locations may be mediated by position-specific sequence features. We therefore propose a new model for single-peaked TSS based solely on known transcription factors (TFs) and their respective regions of positional enrichment. This probabilistic model leads to near-perfect classification results in cross-validation (auROC = 0.98), and performance in genomic scans demonstrates that TSS prediction with both high accuracy and spatial resolution is achievable for a specific but large subgroup of mammalian promoters. The interpretable model structure suggests a DNA code in which canonical sequence features such as TATA-box, Initiator, and GC content do play a significant role, but many additional TFs show distinct spatial biases with respect to TSS location and are important contributors to the accurate prediction of single-peak transcription initiation sites. The model structure also reveals that CAGE tag clusters distal from annotated gene starts have distinct characteristics compared to those close to gene 5â²-ends. Using this high-resolution single-peak model, we predict TSS for â¼70% of mammalian microRNAs based on currently available data. IS - 4 JF - Genome Research SN - 1088-9051 EP - 656 TI - A transcription factor affinity-based code for mammalian transcription initiation VL - 19 SP - 644 KW - microrna KW - microrna-regulation KW - microrna-transcriptional-regulation KW - transcription KW - transcription_factor AU - Megraw, Molly AU - Pereira, Fernando AU - Jensen, Shane AU - Ohler, Uwe AU - Hatzigeorgiou, Artemis PY - 2009/04/13/ UR - http://dx.doi.org/10.1101/gr.085449.108 ER -