Prediction of RNA secondary structure by maximizing pseudo-expected accuracy

Michiaki Hamada, Kengo Sato, Kiyoshi Asai

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Background: Recent studies have revealed the importance of considering the entire distribution of possible secondary structures in RNA secondary structure predictions; therefore, a new type of estimator is proposed including the maximum expected accuracy (MEA) estimator. The MEA-based estimators have been designed to maximize the expected accuracy of the base-pairs and have achieved the highest level of accuracy. Those methods, however, do not give the single best prediction of the structure, but employ parameters to control the trade-off between the sensitivity and the positive predictive value (PPV). It is unclear what parameter value we should use, and even the well-trained default parameter value does not, in general, give the best result in popular accuracy measures to each RNA sequence.Results: Instead of using the expected values of the popular accuracy measures for RNA secondary structure prediction, which is difficult to be calculated, the pseudo-expected accuracy, which can easily be computed from base-pairing probabilities, is introduced. It is shown that the pseudo-expected accuracy is a good approximation in terms of sensitivity, PPV, MCC, or F-score. The pseudo-expected accuracy can be approximately maximized for each RNA sequence by stochastic sampling. It is also shown that well-balanced secondary structures between sensitivity and PPV can be predicted with a small computational overhead by combining the pseudo-expected accuracy of MCC or F-score with the γ-centroid estimator.Conclusions: This study gives not only a method for predicting the secondary structure that balances between sensitivity and PPV, but also a general method for approximately maximizing the (pseudo-)expected accuracy with respect to various evaluation measures including MCC and F-score.

Original languageEnglish
Article number586
JournalBMC Bioinformatics
Volume11
DOIs
Publication statusPublished - 2010 Nov 30
Externally publishedYes

Fingerprint

RNA Secondary Structure
RNA
Base Pairing
Prediction
Secondary Structure
Estimator
Structure Prediction
Sampling
Centroid
Expected Value
Pairing
Trade-offs
Maximise
Entire

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Applied Mathematics
  • Structural Biology

Cite this

Prediction of RNA secondary structure by maximizing pseudo-expected accuracy. / Hamada, Michiaki; Sato, Kengo; Asai, Kiyoshi.

In: BMC Bioinformatics, Vol. 11, 586, 30.11.2010.

Research output: Contribution to journalArticle

@article{90125991a66e4e3989c76dfeebe46ca8,
title = "Prediction of RNA secondary structure by maximizing pseudo-expected accuracy",
abstract = "Background: Recent studies have revealed the importance of considering the entire distribution of possible secondary structures in RNA secondary structure predictions; therefore, a new type of estimator is proposed including the maximum expected accuracy (MEA) estimator. The MEA-based estimators have been designed to maximize the expected accuracy of the base-pairs and have achieved the highest level of accuracy. Those methods, however, do not give the single best prediction of the structure, but employ parameters to control the trade-off between the sensitivity and the positive predictive value (PPV). It is unclear what parameter value we should use, and even the well-trained default parameter value does not, in general, give the best result in popular accuracy measures to each RNA sequence.Results: Instead of using the expected values of the popular accuracy measures for RNA secondary structure prediction, which is difficult to be calculated, the pseudo-expected accuracy, which can easily be computed from base-pairing probabilities, is introduced. It is shown that the pseudo-expected accuracy is a good approximation in terms of sensitivity, PPV, MCC, or F-score. The pseudo-expected accuracy can be approximately maximized for each RNA sequence by stochastic sampling. It is also shown that well-balanced secondary structures between sensitivity and PPV can be predicted with a small computational overhead by combining the pseudo-expected accuracy of MCC or F-score with the γ-centroid estimator.Conclusions: This study gives not only a method for predicting the secondary structure that balances between sensitivity and PPV, but also a general method for approximately maximizing the (pseudo-)expected accuracy with respect to various evaluation measures including MCC and F-score.",
author = "Michiaki Hamada and Kengo Sato and Kiyoshi Asai",
year = "2010",
month = "11",
day = "30",
doi = "10.1186/1471-2105-11-586",
language = "English",
volume = "11",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",

}

TY - JOUR

T1 - Prediction of RNA secondary structure by maximizing pseudo-expected accuracy

AU - Hamada, Michiaki

AU - Sato, Kengo

AU - Asai, Kiyoshi

PY - 2010/11/30

Y1 - 2010/11/30

N2 - Background: Recent studies have revealed the importance of considering the entire distribution of possible secondary structures in RNA secondary structure predictions; therefore, a new type of estimator is proposed including the maximum expected accuracy (MEA) estimator. The MEA-based estimators have been designed to maximize the expected accuracy of the base-pairs and have achieved the highest level of accuracy. Those methods, however, do not give the single best prediction of the structure, but employ parameters to control the trade-off between the sensitivity and the positive predictive value (PPV). It is unclear what parameter value we should use, and even the well-trained default parameter value does not, in general, give the best result in popular accuracy measures to each RNA sequence.Results: Instead of using the expected values of the popular accuracy measures for RNA secondary structure prediction, which is difficult to be calculated, the pseudo-expected accuracy, which can easily be computed from base-pairing probabilities, is introduced. It is shown that the pseudo-expected accuracy is a good approximation in terms of sensitivity, PPV, MCC, or F-score. The pseudo-expected accuracy can be approximately maximized for each RNA sequence by stochastic sampling. It is also shown that well-balanced secondary structures between sensitivity and PPV can be predicted with a small computational overhead by combining the pseudo-expected accuracy of MCC or F-score with the γ-centroid estimator.Conclusions: This study gives not only a method for predicting the secondary structure that balances between sensitivity and PPV, but also a general method for approximately maximizing the (pseudo-)expected accuracy with respect to various evaluation measures including MCC and F-score.

AB - Background: Recent studies have revealed the importance of considering the entire distribution of possible secondary structures in RNA secondary structure predictions; therefore, a new type of estimator is proposed including the maximum expected accuracy (MEA) estimator. The MEA-based estimators have been designed to maximize the expected accuracy of the base-pairs and have achieved the highest level of accuracy. Those methods, however, do not give the single best prediction of the structure, but employ parameters to control the trade-off between the sensitivity and the positive predictive value (PPV). It is unclear what parameter value we should use, and even the well-trained default parameter value does not, in general, give the best result in popular accuracy measures to each RNA sequence.Results: Instead of using the expected values of the popular accuracy measures for RNA secondary structure prediction, which is difficult to be calculated, the pseudo-expected accuracy, which can easily be computed from base-pairing probabilities, is introduced. It is shown that the pseudo-expected accuracy is a good approximation in terms of sensitivity, PPV, MCC, or F-score. The pseudo-expected accuracy can be approximately maximized for each RNA sequence by stochastic sampling. It is also shown that well-balanced secondary structures between sensitivity and PPV can be predicted with a small computational overhead by combining the pseudo-expected accuracy of MCC or F-score with the γ-centroid estimator.Conclusions: This study gives not only a method for predicting the secondary structure that balances between sensitivity and PPV, but also a general method for approximately maximizing the (pseudo-)expected accuracy with respect to various evaluation measures including MCC and F-score.

UR - http://www.scopus.com/inward/record.url?scp=78649469968&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649469968&partnerID=8YFLogxK

U2 - 10.1186/1471-2105-11-586

DO - 10.1186/1471-2105-11-586

M3 - Article

VL - 11

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

M1 - 586

ER -