@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 {320, title = {Sustained-input switches for transcription factors and microRNAs are central building blocks of eukaryotic gene circuits.}, journal = {Genome Biol}, volume = {14}, year = {2013}, month = {2013}, pages = {R85}, abstract = {

WaRSwap is a randomization algorithm that for the first time provides a practical network motif discovery method for large multi-layer networks, for example those that include transcription factors, microRNAs, and non-regulatory protein coding genes. The algorithm is applicable to systems with tens of thousands of genes, while accounting for critical aspects of biological networks, including self-loops, large hubs, and target rearrangements. We validate WaRSwap on a newly inferred regulatory network from Arabidopsis thaliana, and compare outcomes on published Drosophila and human networks. Specifically, sustained input switches are among the few over-represented circuits across this diverse set of eukaryotes.

}, keywords = {Algorithms, Animals, Arabidopsis, Computational Biology, Drosophila melanogaster, Gene Expression Regulation, Gene Regulatory Networks, Humans, MicroRNAs, Molecular Sequence Annotation, Nucleic Acid Conformation, Software, Transcription Factors}, issn = {1474-760X}, doi = {10.1186/gb-2013-14-8-r85}, author = {Megraw, Molly and Mukherjee, Sayan and Ohler, Uwe} } @article {324, title = {miRGen 2.0: a database of microRNA genomic information and regulation.}, journal = {Nucleic Acids Res}, volume = {38}, year = {2010}, month = {2010 Jan}, pages = {D137-41}, abstract = {

MicroRNAs are small, non-protein coding RNA molecules known to regulate the expression of genes by binding to the 3\&$\#$39;UTR region of mRNAs. MicroRNAs are produced from longer transcripts which can code for more than one mature miRNAs. miRGen 2.0 is a database that aims to provide comprehensive information about the position of human and mouse microRNA coding transcripts and their regulation by transcription factors, including a unique compilation of both predicted and experimentally supported data. Expression profiles of microRNAs in several tissues and cell lines, single nucleotide polymorphism locations, microRNA target prediction on protein coding genes and mapping of miRNA targets of co-regulated miRNAs on biological pathways are also integrated into the database and user interface. The miRGen database will be continuously maintained and freely available at http://www.microrna.gr/mirgen/.

}, keywords = {3{\textquoteright} Untranslated Regions, Algorithms, Animals, Cell Line, Tumor, Computational Biology, Databases, Genetic, Databases, Nucleic Acid, Humans, Information Storage and Retrieval, Internet, Mice, MicroRNAs, Polymorphism, Single Nucleotide, Software, Transcription Factors}, issn = {1362-4962}, doi = {10.1093/nar/gkp888}, author = {Alexiou, Panagiotis and Vergoulis, Thanasis and Gleditzsch, Martin and Prekas, George and Dalamagas, Theodore and Megraw, Molly and Grosse, Ivo and Sellis, Timos and Hatzigeorgiou, Artemis G} }