Reliable prediction of Drosha processing sites improves microRNA gene prediction. Export

@article{citeulike:949037, abstract = {MOTIVATION: Mature microRNAs (miRNAs) are processed from long hairpin transcripts. Even though it is only the first of several steps, the initial Drosha processing defines the mature product and is characteristic for all miRNA genes. Methods that can separate between true and false processing sites are therefore essential to miRNA gene discovery. RESULTS: We present a classifier that predicts 5' Drosha processing sites in hairpins that are candidate miRNAs. The classifier, called Microprocessor SVM, correctly predicts the processing site for 50 percent of known human 5' miRNAs, and 90 percent of its predictions are within two nucleotides of the true site. Another classifier that is trained on the output from the Microprocessor SVM outperforms existing methods for prediction of unconserved miRNAs. Reanalysis of characteristics and supporting evidence for a set of newly annotated miRNAs shows that some miRNAs may be misannotated. This suggests that expressed hairpins should not be annotated as miRNAs until they are verified to be Drosha and Dicer substrates. AVAILABILITY: The classifiers are publicly available at https://demo1.interagon.com/miRNA/. SUPPLEMENTARY INFORMATION: Supplementary data is available at Bioinformatics online.}, address = {Department of Computer and Information Science, Norwegian University of Science and Technology, NO-7052 Trondheim, Norway.}, author = {Helvik, Snorre A A. and Sn{\o}ve, Ola and S{\ae}trom, P\r{a}l}, citeulike-article-id = {949037}, citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/17105718}, citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=17105718}, day = {14}, issn = {1460-2059}, journal = {Bioinformatics}, keywords = {bioinformatics, drosha, microrna, ncrna}, month = {November}, posted-at = {2006-11-17 01:14:58}, priority = {2}, title = {Reliable prediction of Drosha processing sites improves microRNA gene prediction.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/17105718}, year = {2006} }

TY - JOUR ID - citeulike:949037 L3 - citeulike-article-id:949037 N2 - MOTIVATION: Mature microRNAs (miRNAs) are processed from long hairpin transcripts. Even though it is only the first of several steps, the initial Drosha processing defines the mature product and is characteristic for all miRNA genes. Methods that can separate between true and false processing sites are therefore essential to miRNA gene discovery. RESULTS: We present a classifier that predicts 5' Drosha processing sites in hairpins that are candidate miRNAs. The classifier, called Microprocessor SVM, correctly predicts the processing site for 50 percent of known human 5' miRNAs, and 90 percent of its predictions are within two nucleotides of the true site. Another classifier that is trained on the output from the Microprocessor SVM outperforms existing methods for prediction of unconserved miRNAs. Reanalysis of characteristics and supporting evidence for a set of newly annotated miRNAs shows that some miRNAs may be misannotated. This suggests that expressed hairpins should not be annotated as miRNAs until they are verified to be Drosha and Dicer substrates. AVAILABILITY: The classifiers are publicly available at https://demo1.interagon.com/miRNA/. SUPPLEMENTARY INFORMATION: Supplementary data is available at Bioinformatics online. JF - Bioinformatics SN - 1460-2059 AD - Department of Computer and Information Science, Norwegian University of Science and Technology, NO-7052 Trondheim, Norway. TI - Reliable prediction of Drosha processing sites improves microRNA gene prediction. KW - bioinformatics KW - drosha KW - microrna KW - ncrna AU - Helvik, Snorre A AU - Snøve, Ola AU - Sætrom, Pål PY - 2006/11/14/ UR - http://view.ncbi.nlm.nih.gov/pubmed/17105718 ER -