Support vector machine for prediction of meiotic recombination hotspots and coldspots in Saccharomyces cerevisiae

Jianhong Weng, Tong Zhou, Xiao Sun, Zuhong Lu

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A method for predicting hotspots and coldspots using support vector machine (SVM) based on statistical learning theory is developed. This method is applied to published 303 hot and 48 cold open reading frames (ORFs) in Saccharomyces cerevisiae. The sequence features of general dinucleotide abundance and dinucleotide abundance based on codon usage are extracted, and then the data sets are classified with different parameters and kernel functions combined with the method of two-fold cross validation. The result indicates that 87.47% accuracy can be reached when classifying hot and cold ORF sequences with the kernel of radial basis function combined with dinucleotide abundance based on codon usage.

Original languageEnglish (US)
Pages (from-to)112-116
Number of pages5
JournalJournal of Southeast University (English Edition)
Volume22
Issue number1
StatePublished - Mar 2006
Externally publishedYes

Fingerprint

Yeast
Support vector machines

Keywords

  • Coldspot
  • Dinucleotide abundance
  • Hotspot
  • Meiotic recombination
  • Support vector machine

ASJC Scopus subject areas

  • General

Cite this

Support vector machine for prediction of meiotic recombination hotspots and coldspots in Saccharomyces cerevisiae. / Weng, Jianhong; Zhou, Tong; Sun, Xiao; Lu, Zuhong.

In: Journal of Southeast University (English Edition), Vol. 22, No. 1, 03.2006, p. 112-116.

Research output: Contribution to journalArticle

@article{bc63b86c473a40bfa8cd226883e0026f,
title = "Support vector machine for prediction of meiotic recombination hotspots and coldspots in Saccharomyces cerevisiae",
abstract = "A method for predicting hotspots and coldspots using support vector machine (SVM) based on statistical learning theory is developed. This method is applied to published 303 hot and 48 cold open reading frames (ORFs) in Saccharomyces cerevisiae. The sequence features of general dinucleotide abundance and dinucleotide abundance based on codon usage are extracted, and then the data sets are classified with different parameters and kernel functions combined with the method of two-fold cross validation. The result indicates that 87.47{\%} accuracy can be reached when classifying hot and cold ORF sequences with the kernel of radial basis function combined with dinucleotide abundance based on codon usage.",
keywords = "Coldspot, Dinucleotide abundance, Hotspot, Meiotic recombination, Support vector machine",
author = "Jianhong Weng and Tong Zhou and Xiao Sun and Zuhong Lu",
year = "2006",
month = "3",
language = "English (US)",
volume = "22",
pages = "112--116",
journal = "Journal of Southeast University (English Edition)",
issn = "1003-7985",
publisher = "Southeast University",
number = "1",

}

TY - JOUR

T1 - Support vector machine for prediction of meiotic recombination hotspots and coldspots in Saccharomyces cerevisiae

AU - Weng, Jianhong

AU - Zhou, Tong

AU - Sun, Xiao

AU - Lu, Zuhong

PY - 2006/3

Y1 - 2006/3

N2 - A method for predicting hotspots and coldspots using support vector machine (SVM) based on statistical learning theory is developed. This method is applied to published 303 hot and 48 cold open reading frames (ORFs) in Saccharomyces cerevisiae. The sequence features of general dinucleotide abundance and dinucleotide abundance based on codon usage are extracted, and then the data sets are classified with different parameters and kernel functions combined with the method of two-fold cross validation. The result indicates that 87.47% accuracy can be reached when classifying hot and cold ORF sequences with the kernel of radial basis function combined with dinucleotide abundance based on codon usage.

AB - A method for predicting hotspots and coldspots using support vector machine (SVM) based on statistical learning theory is developed. This method is applied to published 303 hot and 48 cold open reading frames (ORFs) in Saccharomyces cerevisiae. The sequence features of general dinucleotide abundance and dinucleotide abundance based on codon usage are extracted, and then the data sets are classified with different parameters and kernel functions combined with the method of two-fold cross validation. The result indicates that 87.47% accuracy can be reached when classifying hot and cold ORF sequences with the kernel of radial basis function combined with dinucleotide abundance based on codon usage.

KW - Coldspot

KW - Dinucleotide abundance

KW - Hotspot

KW - Meiotic recombination

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=33745159677&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745159677&partnerID=8YFLogxK

M3 - Article

VL - 22

SP - 112

EP - 116

JO - Journal of Southeast University (English Edition)

JF - Journal of Southeast University (English Edition)

SN - 1003-7985

IS - 1

ER -