DFA7, a new method to distinguish between intron-containing and intronless genes

Chenglong Yu, Mo Deng, Lu Zheng, Rong Lucy He, Jie Yang, Stephen S.T. Yau

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Intron-containing and intronless genes have different biological properties and statistical characteristics. Here we propose a new computational method to distinguish between intron-containing and intronless gene sequences. Seven feature parameters α, β, γ, λ, θ, φ, and σ based on detrended fluctuation analysis (DFA) are fully used, and thus we can compute a 7-dimensional feature vector for any given gene sequence to be discriminated. Furthermore, support vector machine (SVM) classifier with Gaussian radial basis kernel function is performed on this feature space to classify the genes into introncontaining and intronless. We investigate the performance of the proposed method in comparison with other state-of-the-art algorithms on biological datasets. The experimental results show that our new method significantly improves the accuracy over those existing techniques.

LanguageEnglish
Article numbere101363
JournalPLoS ONE
Volume9
Issue number7
DOIs
Publication statusPublished - 18 Jul 2014

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Yu, C., Deng, M., Zheng, L., He, R. L., Yang, J., & Yau, S. S. T. (2014). DFA7, a new method to distinguish between intron-containing and intronless genes. PLoS ONE, 9(7), [e101363]. https://doi.org/10.1371/journal.pone.0101363
Yu, Chenglong ; Deng, Mo ; Zheng, Lu ; He, Rong Lucy ; Yang, Jie ; Yau, Stephen S.T. / DFA7, a new method to distinguish between intron-containing and intronless genes. In: PLoS ONE. 2014 ; Vol. 9, No. 7.
@article{90203964d8ca4ea99f86b732b0883803,
title = "DFA7, a new method to distinguish between intron-containing and intronless genes",
abstract = "Intron-containing and intronless genes have different biological properties and statistical characteristics. Here we propose a new computational method to distinguish between intron-containing and intronless gene sequences. Seven feature parameters α, β, γ, λ, θ, φ, and σ based on detrended fluctuation analysis (DFA) are fully used, and thus we can compute a 7-dimensional feature vector for any given gene sequence to be discriminated. Furthermore, support vector machine (SVM) classifier with Gaussian radial basis kernel function is performed on this feature space to classify the genes into introncontaining and intronless. We investigate the performance of the proposed method in comparison with other state-of-the-art algorithms on biological datasets. The experimental results show that our new method significantly improves the accuracy over those existing techniques.",
author = "Chenglong Yu and Mo Deng and Lu Zheng and He, {Rong Lucy} and Jie Yang and Yau, {Stephen S.T.}",
year = "2014",
month = "7",
day = "18",
doi = "10.1371/journal.pone.0101363",
language = "English",
volume = "9",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "7",

}

Yu, C, Deng, M, Zheng, L, He, RL, Yang, J & Yau, SST 2014, 'DFA7, a new method to distinguish between intron-containing and intronless genes', PLoS ONE, vol. 9, no. 7, e101363. https://doi.org/10.1371/journal.pone.0101363

DFA7, a new method to distinguish between intron-containing and intronless genes. / Yu, Chenglong; Deng, Mo; Zheng, Lu; He, Rong Lucy; Yang, Jie; Yau, Stephen S.T.

In: PLoS ONE, Vol. 9, No. 7, e101363, 18.07.2014.

Research output: Contribution to journalArticle

TY - JOUR

T1 - DFA7, a new method to distinguish between intron-containing and intronless genes

AU - Yu, Chenglong

AU - Deng, Mo

AU - Zheng, Lu

AU - He, Rong Lucy

AU - Yang, Jie

AU - Yau, Stephen S.T.

PY - 2014/7/18

Y1 - 2014/7/18

N2 - Intron-containing and intronless genes have different biological properties and statistical characteristics. Here we propose a new computational method to distinguish between intron-containing and intronless gene sequences. Seven feature parameters α, β, γ, λ, θ, φ, and σ based on detrended fluctuation analysis (DFA) are fully used, and thus we can compute a 7-dimensional feature vector for any given gene sequence to be discriminated. Furthermore, support vector machine (SVM) classifier with Gaussian radial basis kernel function is performed on this feature space to classify the genes into introncontaining and intronless. We investigate the performance of the proposed method in comparison with other state-of-the-art algorithms on biological datasets. The experimental results show that our new method significantly improves the accuracy over those existing techniques.

AB - Intron-containing and intronless genes have different biological properties and statistical characteristics. Here we propose a new computational method to distinguish between intron-containing and intronless gene sequences. Seven feature parameters α, β, γ, λ, θ, φ, and σ based on detrended fluctuation analysis (DFA) are fully used, and thus we can compute a 7-dimensional feature vector for any given gene sequence to be discriminated. Furthermore, support vector machine (SVM) classifier with Gaussian radial basis kernel function is performed on this feature space to classify the genes into introncontaining and intronless. We investigate the performance of the proposed method in comparison with other state-of-the-art algorithms on biological datasets. The experimental results show that our new method significantly improves the accuracy over those existing techniques.

UR - http://www.scopus.com/inward/record.url?scp=84904539711&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0101363

DO - 10.1371/journal.pone.0101363

M3 - Article

VL - 9

JO - PLoS ONE

T2 - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 7

M1 - e101363

ER -