@ARTICLE{SonZieRae06, author = {Sonnenburg, S\"oren and Zien, Alexander and R\"atsch, Gunnar}, title = "{ARTS: Accurate Recognition of Transcription Starts in Human}", journal = "Bioinformatics", year = "2006", volume = "22", pages = "e472--e480", number = "14", abstract = "We develop new methods for finding transcription start sites (TSS) of RNA Polymerase II binding genes in genomic DNA sequences. Employing Support Vector Machines with advanced sequence kernels, we achieve drastically higher prediction accuracies than state-of-the-art methods. Motivation: One of the most important features of genomic DNA are the protein-coding genes. While it is of great value to identify those genes and the encoded proteins, it is also crucial to understand how their transcription is regulated. To this end one has to identify the corresponding promoters and the contained transcription factor binding sites. TSS finders can be used to locate potential promoters. They may also be used in combination with other signal and content detectors to resolve entire gene structures. Results: We have developed a novel kernel based method called ARTS that accurately recognizes transcription start sites in human. The application of otherwise too computationally expensive Support Vector Machines was made possible due to the use of efficient training and evaluation techniques using suffix tries. In a carefully designed experimental study, we compare our TSS finder to state-of-the-art methods from the literature: McPromoter, Eponine and FirstEF. For given false positive rates within a reasonable range, we consistently achieve considerably higher true positive rates. For instance, ARTS finds about 35\\% true positives at a false positive rate of 1/1000, where the other methods find about a half (18\\%).", authorurls = "http://www.first.fhg.de/sonne and http://www.kyb.tuebingen.mpg.de/\\textasciitilde zien and http://www.fml.tuebingen.mpg.de/\\textasciitilde raetsch", dataset = "http://www.fml.tuebingen.mpg.de/raetsch/projects/arts/", pdf = "http://bioinformatics.oxfordjournals.org/cgi/content/abstract/22/14/e472" }