@article {311, title = {NanoCAGE-XL and CapFilter: an approach to genome wide identification of high confidence transcription start sites.}, journal = {BMC Genomics}, volume = {16}, year = {2015}, month = {2015}, pages = {597}, abstract = {

BACKGROUND: Identifying the transcription start sites (TSS) of genes is essential for characterizing promoter regions. Several protocols have been developed to capture the 5\&$\#$39; end of transcripts via Cap Analysis of Gene Expression (CAGE) or linker-ligation strategies such as Paired-End Analysis of Transcription Start Sites (PEAT), but often require large amounts of tissue. More recently, nanoCAGE was developed for sequencing on the Illumina GAIIx to overcome these difficulties.

RESULTS: Here we present the first publicly available adaptation of nanoCAGE for sequencing on recent ultra-high throughput platforms such as Illumina HiSeq-2000, and CapFilter, a computational pipeline that greatly increases confidence in TSS identification. We report excellent gene coverage, reproducibility, and precision in transcription start site discovery for samples from Arabidopsis thaliana roots.

CONCLUSION: nanoCAGE-XL together with CapFilter allows for genome wide identification of high confidence transcription start sites in large eukaryotic genomes.

[Link to Protocol, Additional Data, and Supplementary Materials]

[Link to CapFilter Software]

}, keywords = {Arabidopsis, Genes, Plant, Genome, Plant, Nanotechnology, Plant Roots, Promoter Regions, Genetic, Sequence Analysis, DNA, Software, Transcription Initiation Site}, issn = {1471-2164}, doi = {10.1186/s12864-015-1670-6}, author = {Cumbie, Jason S and Ivanchenko, Maria G and Megraw, Molly} } @article {313, title = {TIPR: transcription initiation pattern recognition on a genome scale.}, journal = {Bioinformatics}, volume = {31}, year = {2015}, month = {2015 Dec 1}, pages = {3725-32}, abstract = {

MOTIVATION: The computational identification of gene transcription start sites (TSSs) can provide insights into the regulation and function of genes without performing expensive experiments, particularly in organisms with incomplete annotations. High-resolution general-purpose TSS prediction remains a challenging problem, with little recent progress on the identification and differentiation of TSSs which are arranged in different spatial patterns along the chromosome.

RESULTS: In this work, we present the Transcription Initiation Pattern Recognizer (TIPR), a sequence-based machine learning model that identifies TSSs with high accuracy and resolution for multiple spatial distribution patterns along the genome, including broadly distributed TSS patterns that have previously been difficult to characterize. TIPR predicts not only the locations of TSSs but also the expected spatial initiation pattern each TSS will form along the chromosome-a novel capability for TSS prediction algorithms. As spatial initiation patterns are associated with spatiotemporal expression patterns and gene function, this capability has the potential to improve gene annotations and our understanding of the regulation of transcription initiation. The high nucleotide resolution of this model locates TSSs within 10 nucleotides or less on average.

CONTACT: megrawm@science.oregonstate.edu.

[Software and Supplementary Materials Link]

}, keywords = {Algorithms, Genomics, Machine Learning, Molecular Sequence Annotation, Sequence Analysis, DNA, Software, Transcription Initiation Site, Transcription Initiation, Genetic}, issn = {1367-4811}, doi = {10.1093/bioinformatics/btv464}, author = {Morton, Taj and Wong, Weng-Keen and Megraw, Molly} } @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} }