Computational prediction of nucleosome positioning by calculating the relative fragment frequency index of nucleosomal sequences

Ryu Ogawa, Noriyuki Kitagawa, Hiroki Ashida, Rintaro Saito, Masaru Tomita

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

We developed an accurate method to predict nucleosome positioning from genome sequences by refining the previously developed method of Peckham et al. (2007) [19]. Here, we used the relative fragment frequency index we developed and a support vector machine to screen for nucleosomal and linker DNA sequences. Our twofold cross-validation revealed that the accuracy of our method based on the area under the receiver operating characteristic curve was 81%, whereas that of Peckham's method was 75% when both of two nucleosomal sequence data obtained from independent experiments were used for validation. We suggest that our method is more effective in predicting nucleosome positioning.

Original languageEnglish
Pages (from-to)1498-1502
Number of pages5
JournalFEBS Letters
Volume584
Issue number8
DOIs
Publication statusPublished - 2010 Apr

Fingerprint

Nucleosomes
DNA sequences
Refining
Support vector machines
Genes
ROC Curve
Experiments
Genome

Keywords

  • Computational prediction
  • Nucleosome
  • Support vector machine

ASJC Scopus subject areas

  • Biochemistry
  • Biophysics
  • Cell Biology
  • Genetics
  • Molecular Biology
  • Structural Biology

Cite this

Computational prediction of nucleosome positioning by calculating the relative fragment frequency index of nucleosomal sequences. / Ogawa, Ryu; Kitagawa, Noriyuki; Ashida, Hiroki; Saito, Rintaro; Tomita, Masaru.

In: FEBS Letters, Vol. 584, No. 8, 04.2010, p. 1498-1502.

Research output: Contribution to journalArticle

Ogawa, Ryu ; Kitagawa, Noriyuki ; Ashida, Hiroki ; Saito, Rintaro ; Tomita, Masaru. / Computational prediction of nucleosome positioning by calculating the relative fragment frequency index of nucleosomal sequences. In: FEBS Letters. 2010 ; Vol. 584, No. 8. pp. 1498-1502.
@article{06a74f81b4ae4dbda6a4381f5cd075ff,
title = "Computational prediction of nucleosome positioning by calculating the relative fragment frequency index of nucleosomal sequences",
abstract = "We developed an accurate method to predict nucleosome positioning from genome sequences by refining the previously developed method of Peckham et al. (2007) [19]. Here, we used the relative fragment frequency index we developed and a support vector machine to screen for nucleosomal and linker DNA sequences. Our twofold cross-validation revealed that the accuracy of our method based on the area under the receiver operating characteristic curve was 81{\%}, whereas that of Peckham's method was 75{\%} when both of two nucleosomal sequence data obtained from independent experiments were used for validation. We suggest that our method is more effective in predicting nucleosome positioning.",
keywords = "Computational prediction, Nucleosome, Support vector machine",
author = "Ryu Ogawa and Noriyuki Kitagawa and Hiroki Ashida and Rintaro Saito and Masaru Tomita",
year = "2010",
month = "4",
doi = "10.1016/j.febslet.2010.02.067",
language = "English",
volume = "584",
pages = "1498--1502",
journal = "FEBS Letters",
issn = "0014-5793",
publisher = "Elsevier",
number = "8",

}

TY - JOUR

T1 - Computational prediction of nucleosome positioning by calculating the relative fragment frequency index of nucleosomal sequences

AU - Ogawa, Ryu

AU - Kitagawa, Noriyuki

AU - Ashida, Hiroki

AU - Saito, Rintaro

AU - Tomita, Masaru

PY - 2010/4

Y1 - 2010/4

N2 - We developed an accurate method to predict nucleosome positioning from genome sequences by refining the previously developed method of Peckham et al. (2007) [19]. Here, we used the relative fragment frequency index we developed and a support vector machine to screen for nucleosomal and linker DNA sequences. Our twofold cross-validation revealed that the accuracy of our method based on the area under the receiver operating characteristic curve was 81%, whereas that of Peckham's method was 75% when both of two nucleosomal sequence data obtained from independent experiments were used for validation. We suggest that our method is more effective in predicting nucleosome positioning.

AB - We developed an accurate method to predict nucleosome positioning from genome sequences by refining the previously developed method of Peckham et al. (2007) [19]. Here, we used the relative fragment frequency index we developed and a support vector machine to screen for nucleosomal and linker DNA sequences. Our twofold cross-validation revealed that the accuracy of our method based on the area under the receiver operating characteristic curve was 81%, whereas that of Peckham's method was 75% when both of two nucleosomal sequence data obtained from independent experiments were used for validation. We suggest that our method is more effective in predicting nucleosome positioning.

KW - Computational prediction

KW - Nucleosome

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=77951297858&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951297858&partnerID=8YFLogxK

U2 - 10.1016/j.febslet.2010.02.067

DO - 10.1016/j.febslet.2010.02.067

M3 - Article

VL - 584

SP - 1498

EP - 1502

JO - FEBS Letters

JF - FEBS Letters

SN - 0014-5793

IS - 8

ER -