@article {326, title = {A transcription factor affinity-based code for mammalian transcription initiation.}, journal = {Genome Res}, volume = {19}, year = {2009}, month = {2009 Apr}, pages = {644-56}, abstract = {

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 ( approximately 45\%), 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\&$\#$39;-ends. Using this high-resolution single-peak model, we predict TSS for approximately 70\% of mammalian microRNAs based on currently available data.

[Links to Tools and Supplementary Materials]

}, keywords = {Base Composition, Databases, Genetic, DNA, Gene Expression Regulation, Genome, Human, Humans, Promoter Regions, Genetic, RNA Polymerase II, TATA Box, Transcription Factors, Transcription Initiation Site, Transcription, Genetic}, issn = {1088-9051}, doi = {10.1101/gr.085449.108}, author = {Megraw, Molly and Pereira, Fernando and Jensen, Shane T and Ohler, Uwe and Hatzigeorgiou, Artemis G} }