Predicts 5' Drosha processing sites in hairpins that are candidate miRNAs. Microprocessor SVM correctly predicts the processing site for 50% of known human 5' miRNAs, and 90% of its predictions are within two nucleotides of the true site. The Microprocessor SVM shows good performance when separating miRNAs from random hairpins, despite that SVM was not trained for this purpose.
Department of Computer and Information Science, Norwegian University of Science and Technology, Trondheim, Norway; Interagon AS, Laboratoriesenteret, Trondheim, Norway; Department of Cancer Research and Molecular Medicine, Faculty of Medicine, Norwegian University of Science and Technology, Trondheim, Norway
Microprocessor SVM funding source(s)
Supported by the bioinformatics platform of the Norwegian Research Council’s Functional Genomics Program (FUGE).