Welcome to the InfoSci Platform
MicroRNA Precursor Prediction Using SVM with RNA Pairing Continuity Feature

MicroRNA Precursor Prediction Using SVM with RNA Pairing Continuity Feature

Huan Yang, Yan Wang, Trupti Joshi, Dong Xu, Shoupeng Yu, Yanchun Liang
Copyright: © 2011 |Pages: 10
ISBN13: 9781609600648|ISBN10: 1609600649|EISBN13: 9781609600662
DOI: 10.4018/978-1-60960-064-8.ch007
Cite Chapter Cite Chapter

MLA

Yang, Huan, et al. "MicroRNA Precursor Prediction Using SVM with RNA Pairing Continuity Feature." Interdisciplinary Research and Applications in Bioinformatics, Computational Biology, and Environmental Sciences, edited by Limin Angela Liu, et al., IGI Global, 2011, pp. 73-82. https://doi.org/10.4018/978-1-60960-064-8.ch007

APA

Yang, H., Wang, Y., Joshi, T., Xu, D., Yu, S., & Liang, Y. (2011). MicroRNA Precursor Prediction Using SVM with RNA Pairing Continuity Feature. In L. Liu, D. Wei, & Y. Li (Eds.), Interdisciplinary Research and Applications in Bioinformatics, Computational Biology, and Environmental Sciences (pp. 73-82). IGI Global. https://doi.org/10.4018/978-1-60960-064-8.ch007

Chicago

Yang, Huan, et al. "MicroRNA Precursor Prediction Using SVM with RNA Pairing Continuity Feature." In Interdisciplinary Research and Applications in Bioinformatics, Computational Biology, and Environmental Sciences, edited by Limin Angela Liu, Dongqing Wei, and Yixue Li, 73-82. Hershey, PA: IGI Global, 2011. https://doi.org/10.4018/978-1-60960-064-8.ch007

Export Reference

Mendeley
Favorite

Abstract

MicroRNAs (miRNAs) are endogenous single-stranded non-coding RNAs of ~22 nucleotides in length and they act as post-transcriptional regulators in bacteria, animals and plants. Almost all current methods for computational prediction of miRNAs use hairpin structure and minimum of free energy as characteristics to identify putative pre-miRNAs from a pool of candidates. We discovered a new effective feature named “basic-n-units” (BNU) to distinguish pre-miRNAs from pseudo ones. This feature describes pairing continuity of RNA secondary structure. Simulation results show that a classification method, called Triplet-SVM-classifier, achieved an accuracy of 97.24% when this BNU feature was used. This is a 3% increase caused solely by adding this new feature. We anticipate that this BNU feature may increase the accuracy for most classification methods.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.