|
Registro Completo |
|
Biblioteca(s): |
Embrapa Soja. |
|
Data corrente: |
25/04/2018 |
|
Data da última atualização: |
25/04/2018 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
LOPES, I. de O. N.; SCHLIEP, A.; CARVALHO, A. C. P. de L. F. de. |
|
Afiliação: |
IVANI DE OLIVEIRA NEGRAO LOPES, CNPSO; ALEXANDER SCHLIEP; ANDRÉ C. P. de L. F de CARVALHO. |
|
Título: |
The discriminant power of RNA features for pre-miRNA recognition. |
|
Ano de publicação: |
2014 |
|
Fonte/Imprenta: |
BMC Bioinformatics, London, v. 15, p.124, 2014. |
|
ISSN: |
1471-2105 |
|
Idioma: |
Inglês |
|
Conteúdo: |
Computational discovery of microRNAs (miRNA) is based on pre-determined sets of features from miRNA precursors (pre-miRNA). Some feature sets are composed of sequence-structure patterns commonly found in pre-miRNAs, while others are a combination of more sophisticated RNA features. In this work, we analyze the discriminant power of seven feature sets, which are used in six pre-miRNA prediction tools. The analysis is based on the classification performance achieved with these feature sets for the training algorithms used in these tools. We also evaluate feature discrimination through the F-score and feature importance in the induction of random forests. Small or non-significant differences were found among the estimated classification performances of classifiers induced using sets with diversification of features, despite the wide differences in their dimension. Inspired in these results, we obtained a lower-dimensional feature set, which achieved a sensitivity of 90% and a specificity of 95%. These estimates are within 0.1% of the maximal values obtained with any feature set (SELECT, Section? Results and discussion?) while it is 34 times faster to compute. Even compared to another feature set (FS2, see Section? Results and discussion?), which is the computationally least expensive feature set of those from the literature which perform within 0.1% of the maximal values, it is 34 times faster to compute. The results obtained by the tools used as references in the experiments carried out showed that five out of these six tools have lower sensitivity or specificity. In miRNA discovery the number of putative miRNA loci is in the order of millions. Analysis of putative pre-miRNAs using a computationally expensive feature set would be wasteful or even unfeasible for large genomes. In this work, we propose a relatively inexpensive feature set and explore most of the learning aspects implemented in current ab-initio pre-miRNA prediction tools, which may lead to the development of efficient ab-initio pre-miRNA discovery tools. The material to reproduce the main results from this paper can be downloaded from http://bioinformatics.rutgers. edu/Static/Software/discriminant.tar.gz MenosComputational discovery of microRNAs (miRNA) is based on pre-determined sets of features from miRNA precursors (pre-miRNA). Some feature sets are composed of sequence-structure patterns commonly found in pre-miRNAs, while others are a combination of more sophisticated RNA features. In this work, we analyze the discriminant power of seven feature sets, which are used in six pre-miRNA prediction tools. The analysis is based on the classification performance achieved with these feature sets for the training algorithms used in these tools. We also evaluate feature discrimination through the F-score and feature importance in the induction of random forests. Small or non-significant differences were found among the estimated classification performances of classifiers induced using sets with diversification of features, despite the wide differences in their dimension. Inspired in these results, we obtained a lower-dimensional feature set, which achieved a sensitivity of 90% and a specificity of 95%. These estimates are within 0.1% of the maximal values obtained with any feature set (SELECT, Section? Results and discussion?) while it is 34 times faster to compute. Even compared to another feature set (FS2, see Section? Results and discussion?), which is the computationally least expensive feature set of those from the literature which perform within 0.1% of the maximal values, it is 34 times faster to compute. The results obtained by the tools used as references in the experiments c... Mostrar Tudo |
|
Palavras-Chave: |
Bioinformática. |
|
Categoria do assunto: |
-- |
|
Marc: |
LEADER 02702naa a2200169 a 4500
001 2090871
005 2018-04-25
008 2014 bl uuuu u00u1 u #d
022 $a1471-2105
100 1 $aLOPES, I. de O. N.
245 $aThe discriminant power of RNA features for pre-miRNA recognition.$h[electronic resource]
260 $c2014
520 $aComputational discovery of microRNAs (miRNA) is based on pre-determined sets of features from miRNA precursors (pre-miRNA). Some feature sets are composed of sequence-structure patterns commonly found in pre-miRNAs, while others are a combination of more sophisticated RNA features. In this work, we analyze the discriminant power of seven feature sets, which are used in six pre-miRNA prediction tools. The analysis is based on the classification performance achieved with these feature sets for the training algorithms used in these tools. We also evaluate feature discrimination through the F-score and feature importance in the induction of random forests. Small or non-significant differences were found among the estimated classification performances of classifiers induced using sets with diversification of features, despite the wide differences in their dimension. Inspired in these results, we obtained a lower-dimensional feature set, which achieved a sensitivity of 90% and a specificity of 95%. These estimates are within 0.1% of the maximal values obtained with any feature set (SELECT, Section? Results and discussion?) while it is 34 times faster to compute. Even compared to another feature set (FS2, see Section? Results and discussion?), which is the computationally least expensive feature set of those from the literature which perform within 0.1% of the maximal values, it is 34 times faster to compute. The results obtained by the tools used as references in the experiments carried out showed that five out of these six tools have lower sensitivity or specificity. In miRNA discovery the number of putative miRNA loci is in the order of millions. Analysis of putative pre-miRNAs using a computationally expensive feature set would be wasteful or even unfeasible for large genomes. In this work, we propose a relatively inexpensive feature set and explore most of the learning aspects implemented in current ab-initio pre-miRNA prediction tools, which may lead to the development of efficient ab-initio pre-miRNA discovery tools. The material to reproduce the main results from this paper can be downloaded from http://bioinformatics.rutgers. edu/Static/Software/discriminant.tar.gz
653 $aBioinformática
700 1 $aSCHLIEP, A.
700 1 $aCARVALHO, A. C. P. de L. F. de
773 $tBMC Bioinformatics, London$gv. 15, p.124, 2014.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Soja (CNPSO) |
|
