A non-parametric bayesian approach for predicting rna secondary structures

Kengo Sato, Michiaki Hamada, Toutai Mituyama, Kiyoshi Asai, Yasubumi Sakakibara

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Since many functional RNAs form stable secondary structures which are related to their functions, RNA secondary structure prediction is a crucial problem in bioinformatics. We propose a novel model for generating RNA secondary structures based on a non-parametric Bayesian approach, called hierarchical Dirichlet processes for stochastic context-free grammars (HDP-SCFGs). Here non-parametric means that some meta-parameters, such as the number of non-terminal symbols and production rules, do not have to be fixed. Instead their distributions are inferred in order to be adapted (in the Bayesian sense) to the training sequences provided. The results of our RNA secondary structure predictions show that HDP-SCFGs are more accurate than the MFE-based and other generative models.

Original languageEnglish
Pages (from-to)727-742
Number of pages16
JournalJournal of Bioinformatics and Computational Biology
Volume8
Issue number4
DOIs
Publication statusPublished - 2010 Aug

Fingerprint

Bayes Theorem
RNA
Stochastic Processes
Context free grammars
Bioinformatics
Computational Biology

Keywords

  • non-parametric Bayesian
  • RNA secondary structure prediction
  • stochastic context-free grammars

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology
  • Computer Science Applications

Cite this

A non-parametric bayesian approach for predicting rna secondary structures. / Sato, Kengo; Hamada, Michiaki; Mituyama, Toutai; Asai, Kiyoshi; Sakakibara, Yasubumi.

In: Journal of Bioinformatics and Computational Biology, Vol. 8, No. 4, 08.2010, p. 727-742.

Research output: Contribution to journalArticle

@article{b6f4748536564d099f583f28a331c99e,
title = "A non-parametric bayesian approach for predicting rna secondary structures",
abstract = "Since many functional RNAs form stable secondary structures which are related to their functions, RNA secondary structure prediction is a crucial problem in bioinformatics. We propose a novel model for generating RNA secondary structures based on a non-parametric Bayesian approach, called hierarchical Dirichlet processes for stochastic context-free grammars (HDP-SCFGs). Here non-parametric means that some meta-parameters, such as the number of non-terminal symbols and production rules, do not have to be fixed. Instead their distributions are inferred in order to be adapted (in the Bayesian sense) to the training sequences provided. The results of our RNA secondary structure predictions show that HDP-SCFGs are more accurate than the MFE-based and other generative models.",
keywords = "non-parametric Bayesian, RNA secondary structure prediction, stochastic context-free grammars",
author = "Kengo Sato and Michiaki Hamada and Toutai Mituyama and Kiyoshi Asai and Yasubumi Sakakibara",
year = "2010",
month = "8",
doi = "10.1142/S0219720010004926",
language = "English",
volume = "8",
pages = "727--742",
journal = "Journal of Bioinformatics and Computational Biology",
issn = "0219-7200",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "4",

}

TY - JOUR

T1 - A non-parametric bayesian approach for predicting rna secondary structures

AU - Sato, Kengo

AU - Hamada, Michiaki

AU - Mituyama, Toutai

AU - Asai, Kiyoshi

AU - Sakakibara, Yasubumi

PY - 2010/8

Y1 - 2010/8

N2 - Since many functional RNAs form stable secondary structures which are related to their functions, RNA secondary structure prediction is a crucial problem in bioinformatics. We propose a novel model for generating RNA secondary structures based on a non-parametric Bayesian approach, called hierarchical Dirichlet processes for stochastic context-free grammars (HDP-SCFGs). Here non-parametric means that some meta-parameters, such as the number of non-terminal symbols and production rules, do not have to be fixed. Instead their distributions are inferred in order to be adapted (in the Bayesian sense) to the training sequences provided. The results of our RNA secondary structure predictions show that HDP-SCFGs are more accurate than the MFE-based and other generative models.

AB - Since many functional RNAs form stable secondary structures which are related to their functions, RNA secondary structure prediction is a crucial problem in bioinformatics. We propose a novel model for generating RNA secondary structures based on a non-parametric Bayesian approach, called hierarchical Dirichlet processes for stochastic context-free grammars (HDP-SCFGs). Here non-parametric means that some meta-parameters, such as the number of non-terminal symbols and production rules, do not have to be fixed. Instead their distributions are inferred in order to be adapted (in the Bayesian sense) to the training sequences provided. The results of our RNA secondary structure predictions show that HDP-SCFGs are more accurate than the MFE-based and other generative models.

KW - non-parametric Bayesian

KW - RNA secondary structure prediction

KW - stochastic context-free grammars

UR - http://www.scopus.com/inward/record.url?scp=77955572164&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955572164&partnerID=8YFLogxK

U2 - 10.1142/S0219720010004926

DO - 10.1142/S0219720010004926

M3 - Article

AN - SCOPUS:77955572164

VL - 8

SP - 727

EP - 742

JO - Journal of Bioinformatics and Computational Biology

JF - Journal of Bioinformatics and Computational Biology

SN - 0219-7200

IS - 4

ER -