2010
DOI: 10.1016/j.jtbi.2010.02.037
|View full text |Cite
|
Sign up to set email alerts
|

New syntax to describe local continuous structure-sequence information for recognizing new pre-miRNAs

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
5
0

Year Published

2011
2011
2014
2014

Publication Types

Select...
4
2

Relationship

1
5

Authors

Journals

citations
Cited by 6 publications
(5 citation statements)
references
References 24 publications
0
5
0
Order By: Relevance
“…Therefore, several studies have developed different ab initio miRNA prediction methods that are based mainly on characteristic features of miRNA, arising from the sequence and secondary structures. Examples of these are tripletSVM, 13 miPred 14 microPred, 15 MiPred, 16 ProMir, 17 SSCprofiler, 18,19 and the algorithm developed by Wang et al 20 Issues in the existing ab initio miRNA prediction methods include a poorer performance, an inability to being applied to multi-species data, and an inability to balance between specificity and sensitivity; these issues have not been addressed completely or successfully. For instance, tripletSVM, 13 which is a Support Vector Machine (SVM)-based classifier, achieves an average accuracy on a cross-species test of 90% but cannot predict multiloop hairpins.…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…Therefore, several studies have developed different ab initio miRNA prediction methods that are based mainly on characteristic features of miRNA, arising from the sequence and secondary structures. Examples of these are tripletSVM, 13 miPred 14 microPred, 15 MiPred, 16 ProMir, 17 SSCprofiler, 18,19 and the algorithm developed by Wang et al 20 Issues in the existing ab initio miRNA prediction methods include a poorer performance, an inability to being applied to multi-species data, and an inability to balance between specificity and sensitivity; these issues have not been addressed completely or successfully. For instance, tripletSVM, 13 which is a Support Vector Machine (SVM)-based classifier, achieves an average accuracy on a cross-species test of 90% but cannot predict multiloop hairpins.…”
Section: Resultsmentioning
confidence: 99%
“…The classifier MiPred 16 provides a web server to predict miRNAs but also does not support an analysis of pre-miRNA sequences with multiple loops. Wang et al 20 uses a new syntax to represent structure and sequence information, but it only achieves a sensitivity of 81.98% and a specificity of 87.16% on a human test set. More importantly, no existing methods provide an easy-to-use GUI program to predict miRNAs.…”
Section: Resultsmentioning
confidence: 99%
“…The next generation of computational tools relied on more sophisticated machine learning algorithms such as support vector machines (SVMs) capable of taking into account multiple biological features such as free energy of the hairpin structure, paired bases, loop length, and stem conservation to predict novel miRNAs [19][20][21][22][23][24][25][26][27]. Two very effective computational studies utilized Hidden Markov Models (HMM) and a Bayesian classifier [28,29], to simultaneously consider sequence and structure features at the nucleotide level for predicting miRNA genes.…”
Section: Introductionmentioning
confidence: 99%
“…Within the RISC, miRNAs regulate gene expression by mainly in either way: mRNA cleavage or translational repression [1][2][3][4] . So far, thousands of miRNAs have been identified in animals, plants, and fungi by experiments or computational methods [5][6] . At the same time, each miRNA is thought to have hundreds of target mRNAs based on experimental or bioinformatics analysis [7][8][9] .…”
Section: Introductionmentioning
confidence: 99%