@article {319, title = {Paired-end analysis of transcription start sites in Arabidopsis reveals plant-specific promoter signatures.}, journal = {Plant Cell}, volume = {26}, year = {2014}, month = {2014 Jul}, pages = {2746-60}, abstract = {

Understanding plant gene promoter architecture has long been a challenge due to the lack of relevant large-scale data sets and analysis methods. Here, we present a publicly available, large-scale transcription start site (TSS) data set in plants using a high-resolution method for analysis of 5\&$\#$39; ends of mRNA transcripts. Our data set is produced using the paired-end analysis of transcription start sites (PEAT) protocol, providing millions of TSS locations from wild-type Columbia-0 Arabidopsis thaliana whole root samples. Using this data set, we grouped TSS reads into \"TSS tag clusters\" and categorized clusters into three spatial initiation patterns: narrow peak, broad with peak, and weak peak. We then designed a machine learning model that predicts the presence of TSS tag clusters with outstanding sensitivity and specificity for all three initiation patterns. We used this model to analyze the transcription factor binding site content of promoters exhibiting these initiation patterns. In contrast to the canonical notions of TATA-containing and more broad \"TATA-less\" promoters, the model shows that, in plants, the vast majority of transcription start sites are TATA free and are defined by a large compendium of known DNA sequence binding elements. We present results on the usage of these elements and provide our Plant PEAT Peaks (3PEAT) model that predicts the presence of TSSs directly from sequence.

[Link to Additional Data and Supplementary Materials]

}, keywords = {Arabidopsis, Arabidopsis Proteins, Binding Sites, Cluster Analysis, DNA, Plant, Gene Expression Regulation, Plant, Genome, Plant, Models, Genetic, Nucleotide Motifs, Plant Roots, Promoter Regions, Genetic, RNA, Messenger, RNA, Plant, Sequence Analysis, DNA, Species Specificity, TATA Box, Transcription Factors, Transcription Initiation Site}, issn = {1532-298X}, doi = {10.1105/tpc.114.125617}, author = {Morton, Taj and Petricka, Jalean and Corcoran, David L and Li, Song and Winter, Cara M and Carda, Alexa and Benfey, Philip N and Ohler, Uwe and Megraw, Molly} } @article {331, title = {MicroRNA promoter element discovery in Arabidopsis.}, journal = {RNA}, volume = {12}, year = {2006}, month = {2006 Sep}, pages = {1612-9}, abstract = {

In this study we present a method of identifying Arabidopsis miRNA promoter elements using known transcription factor binding motifs. We provide a comparative analysis of the representation of these elements in miRNA promoters, protein-coding gene promoters, and random genomic sequences. We report five transcription factor (TF) binding motifs that show evidence of overrepresentation in miRNA promoter regions relative to the promoter regions of protein-coding genes. This investigation is based on the analysis of 800-nucleotide regions upstream of 63 experimentally verified Transcription Start Sites (TSS) for miRNA primary transcripts in Arabidopsis. While the TATA-box binding motif was also previously reported by Xie and colleagues, the transcription factors AtMYC2, ARF, SORLREP3, and LFY are identified for the first time as overrepresented binding motifs in miRNA promoters.

}, keywords = {Arabidopsis, Base Sequence, Binding Sites, Databases, Genetic, Feedback, Physiological, Genes, Plant, MicroRNAs, Promoter Regions, Genetic, TATA Box, Transcription Factors, Transcription Initiation Site}, issn = {1355-8382}, doi = {10.1261/rna.130506}, author = {Megraw, Molly and Baev, Vesselin and Rusinov, Ventsislav and Jensen, Shane T and Kalantidis, Kriton and Hatzigeorgiou, Artemis G} }