<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Cumbie, Jason S</style></author><author><style face="normal" font="default" size="100%">Ivanchenko, Maria G</style></author><author><style face="normal" font="default" size="100%">Megraw, Molly</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">NanoCAGE-XL and CapFilter: an approach to genome wide identification of high confidence transcription start sites.</style></title><secondary-title><style face="normal" font="default" size="100%">BMC Genomics</style></secondary-title><alt-title><style face="normal" font="default" size="100%">BMC Genomics</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Arabidopsis</style></keyword><keyword><style  face="normal" font="default" size="100%">Genes, Plant</style></keyword><keyword><style  face="normal" font="default" size="100%">Genome, Plant</style></keyword><keyword><style  face="normal" font="default" size="100%">Nanotechnology</style></keyword><keyword><style  face="normal" font="default" size="100%">Plant Roots</style></keyword><keyword><style  face="normal" font="default" size="100%">Promoter Regions, Genetic</style></keyword><keyword><style  face="normal" font="default" size="100%">Sequence Analysis, DNA</style></keyword><keyword><style  face="normal" font="default" size="100%">Software</style></keyword><keyword><style  face="normal" font="default" size="100%">Transcription Initiation Site</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2015</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2015</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">16</style></volume><pages><style face="normal" font="default" size="100%">597</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;&lt;b&gt;BACKGROUND: &lt;/b&gt;Identifying the transcription start sites (TSS) of genes is essential for characterizing promoter regions. Several protocols have been developed to capture the 5&amp;#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.&lt;/p&gt;&lt;p&gt;&lt;b&gt;RESULTS: &lt;/b&gt;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.&lt;/p&gt;&lt;p&gt;&lt;b&gt;CONCLUSION: &lt;/b&gt;nanoCAGE-XL together with CapFilter allows for genome wide identification of high confidence transcription start sites in large eukaryotic genomes.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;http://megraw-dev.cgrb.oregonstate.edu/nanocage&quot;&gt;[Link to Protocol, Additional Data, and Supplementary Materials]&lt;/a&gt;&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;http://megraw-dev.cgrb.oregonstate.edu/capfilter&quot;&gt;[Link to CapFilter Software]&lt;/a&gt;&lt;/p&gt;</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Morton, Taj</style></author><author><style face="normal" font="default" size="100%">Wong, Weng-Keen</style></author><author><style face="normal" font="default" size="100%">Megraw, Molly</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">TIPR: transcription initiation pattern recognition on a genome scale.</style></title><secondary-title><style face="normal" font="default" size="100%">Bioinformatics</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Bioinformatics</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Algorithms</style></keyword><keyword><style  face="normal" font="default" size="100%">Genomics</style></keyword><keyword><style  face="normal" font="default" size="100%">Machine Learning</style></keyword><keyword><style  face="normal" font="default" size="100%">Molecular Sequence Annotation</style></keyword><keyword><style  face="normal" font="default" size="100%">Sequence Analysis, DNA</style></keyword><keyword><style  face="normal" font="default" size="100%">Software</style></keyword><keyword><style  face="normal" font="default" size="100%">Transcription Initiation Site</style></keyword><keyword><style  face="normal" font="default" size="100%">Transcription Initiation, Genetic</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2015</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2015 Dec 1</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">31</style></volume><pages><style face="normal" font="default" size="100%">3725-32</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;&lt;b&gt;MOTIVATION: &lt;/b&gt;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.&lt;/p&gt;&lt;p&gt;&lt;b&gt;RESULTS: &lt;/b&gt;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.&lt;/p&gt;&lt;p&gt;&lt;b&gt;CONTACT: &lt;/b&gt;megrawm@science.oregonstate.edu.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;http://megraw-dev.cgrb.oregonstate.edu/TIPR&quot;&gt;[Software and Supplementary Materials Link]&lt;/a&gt;&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">23</style></issue></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Megraw, Molly</style></author><author><style face="normal" font="default" size="100%">Mukherjee, Sayan</style></author><author><style face="normal" font="default" size="100%">Ohler, Uwe</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Sustained-input switches for transcription factors and microRNAs are central building blocks of eukaryotic gene circuits.</style></title><secondary-title><style face="normal" font="default" size="100%">Genome Biol</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Genome Biol.</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Algorithms</style></keyword><keyword><style  face="normal" font="default" size="100%">Animals</style></keyword><keyword><style  face="normal" font="default" size="100%">Arabidopsis</style></keyword><keyword><style  face="normal" font="default" size="100%">Computational Biology</style></keyword><keyword><style  face="normal" font="default" size="100%">Drosophila melanogaster</style></keyword><keyword><style  face="normal" font="default" size="100%">Gene Expression Regulation</style></keyword><keyword><style  face="normal" font="default" size="100%">Gene Regulatory Networks</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">MicroRNAs</style></keyword><keyword><style  face="normal" font="default" size="100%">Molecular Sequence Annotation</style></keyword><keyword><style  face="normal" font="default" size="100%">Nucleic Acid Conformation</style></keyword><keyword><style  face="normal" font="default" size="100%">Software</style></keyword><keyword><style  face="normal" font="default" size="100%">Transcription Factors</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2013</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2013</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">14</style></volume><pages><style face="normal" font="default" size="100%">R85</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;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.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">8</style></issue></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Alexiou, Panagiotis</style></author><author><style face="normal" font="default" size="100%">Vergoulis, Thanasis</style></author><author><style face="normal" font="default" size="100%">Gleditzsch, Martin</style></author><author><style face="normal" font="default" size="100%">Prekas, George</style></author><author><style face="normal" font="default" size="100%">Dalamagas, Theodore</style></author><author><style face="normal" font="default" size="100%">Megraw, Molly</style></author><author><style face="normal" font="default" size="100%">Grosse, Ivo</style></author><author><style face="normal" font="default" size="100%">Sellis, Timos</style></author><author><style face="normal" font="default" size="100%">Hatzigeorgiou, Artemis G</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">miRGen 2.0: a database of microRNA genomic information and regulation.</style></title><secondary-title><style face="normal" font="default" size="100%">Nucleic Acids Res</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Nucleic Acids Res.</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">3' Untranslated Regions</style></keyword><keyword><style  face="normal" font="default" size="100%">Algorithms</style></keyword><keyword><style  face="normal" font="default" size="100%">Animals</style></keyword><keyword><style  face="normal" font="default" size="100%">Cell Line, Tumor</style></keyword><keyword><style  face="normal" font="default" size="100%">Computational Biology</style></keyword><keyword><style  face="normal" font="default" size="100%">Databases, Genetic</style></keyword><keyword><style  face="normal" font="default" size="100%">Databases, Nucleic Acid</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">Information Storage and Retrieval</style></keyword><keyword><style  face="normal" font="default" size="100%">Internet</style></keyword><keyword><style  face="normal" font="default" size="100%">Mice</style></keyword><keyword><style  face="normal" font="default" size="100%">MicroRNAs</style></keyword><keyword><style  face="normal" font="default" size="100%">Polymorphism, Single Nucleotide</style></keyword><keyword><style  face="normal" font="default" size="100%">Software</style></keyword><keyword><style  face="normal" font="default" size="100%">Transcription Factors</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2010</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2010 Jan</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">38</style></volume><pages><style face="normal" font="default" size="100%">D137-41</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;MicroRNAs are small, non-protein coding RNA molecules known to regulate the expression of genes by binding to the 3&amp;#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/.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">Database issue</style></issue></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Sethupathy, Praveen</style></author><author><style face="normal" font="default" size="100%">Megraw, Molly</style></author><author><style face="normal" font="default" size="100%">Hatzigeorgiou, Artemis G</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">A guide through present computational approaches for the identification of mammalian microRNA targets.</style></title><secondary-title><style face="normal" font="default" size="100%">Nat Methods</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Nat. Methods</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">3' Untranslated Regions</style></keyword><keyword><style  face="normal" font="default" size="100%">5' Untranslated Regions</style></keyword><keyword><style  face="normal" font="default" size="100%">Animals</style></keyword><keyword><style  face="normal" font="default" size="100%">Computational Biology</style></keyword><keyword><style  face="normal" font="default" size="100%">Gene Targeting</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">MicroRNAs</style></keyword><keyword><style  face="normal" font="default" size="100%">Predictive Value of Tests</style></keyword><keyword><style  face="normal" font="default" size="100%">RNA, Messenger</style></keyword><keyword><style  face="normal" font="default" size="100%">Sensitivity and Specificity</style></keyword><keyword><style  face="normal" font="default" size="100%">Software</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2006</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2006 Nov</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">3</style></volume><pages><style face="normal" font="default" size="100%">881-6</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Computational microRNA (miRNA) target prediction is a field in flux. Here we present a guide through five widely used mammalian target prediction programs. We include an analysis of the performance of these individual programs and of various combinations of these programs. For this analysis we compiled several benchmark data sets of experimentally supported miRNA-target gene interactions. Based on the results, we provide a discussion on the status of target prediction and also suggest a stepwise approach toward predicting and selecting miRNA targets for experimental testing.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">11</style></issue></record></records></xml>