schliessen

Filtern

 

Bibliotheken

Prediction of ketoacyl synthase family using reduced amino acid alphabets

Ketoacyl synthases are enzymes involved in fatty acid synthesis and can be classified into five families based on primary sequence similarity. Different families have different catalytic mechanisms. Developing cost-effective computational models to identify the family of ketoacyl synthases will be h... Full description

Journal Title: Journal of Industrial Microbiology & Biotechnology 2012, Vol.39(4), pp.579-584
Main Author: Chen, Wei
Other Authors: Feng, Pengmian , Lin, Hao
Format: Electronic Article Electronic Article
Language: English
Subjects:
ID: ISSN: 1367-5435 ; E-ISSN: 1476-5535 ; DOI: 10.1007/s10295-011-1047-z
Link: http://dx.doi.org/10.1007/s10295-011-1047-z
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: springer_jour10.1007/s10295-011-1047-z
title: Prediction of ketoacyl synthase family using reduced amino acid alphabets
format: Article
creator:
  • Chen, Wei
  • Feng, Pengmian
  • Lin, Hao
subjects:
  • Ketoacyl synthase family
  • Reduced amino acid alphabet
  • Support vector machine
  • -Peptide
ispartof: Journal of Industrial Microbiology & Biotechnology, 2012, Vol.39(4), pp.579-584
description: Ketoacyl synthases are enzymes involved in fatty acid synthesis and can be classified into five families based on primary sequence similarity. Different families have different catalytic mechanisms. Developing cost-effective computational models to identify the family of ketoacyl synthases will be helpful for enzyme engineering and in knowing individual enzymes’ catalytic mechanisms. In this work, a support vector machine-based method was developed to predict ketoacyl synthase family using the n -peptide composition of reduced amino acid alphabets. In jackknife cross-validation, the model based on the 2-peptide composition of a reduced amino acid alphabet of size 13 yielded the best overall accuracy of 96.44% with average accuracy of 93.36%, which is superior to other state-of-the-art methods. This result suggests that the information provided by n -peptide compositions of reduced amino acid alphabets provides efficient means for enzyme family classification and that the proposed model can be efficiently used for ketoacyl synthase family annotation.
language: eng
source:
identifier: ISSN: 1367-5435 ; E-ISSN: 1476-5535 ; DOI: 10.1007/s10295-011-1047-z
fulltext: fulltext
issn:
  • 1476-5535
  • 14765535
  • 1367-5435
  • 13675435
url: Link


@attributes
ID404015699
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordid10.1007/s10295-011-1047-z
sourceidspringer_jour
recordidTN_springer_jour10.1007/s10295-011-1047-z
sourcesystemOther
pqid929959760
galeid283836312
display
typearticle
titlePrediction of ketoacyl synthase family using reduced amino acid alphabets
creatorChen, Wei ; Feng, Pengmian ; Lin, Hao
ispartofJournal of Industrial Microbiology & Biotechnology, 2012, Vol.39(4), pp.579-584
identifier
subjectKetoacyl synthase family ; Reduced amino acid alphabet ; Support vector machine ; -Peptide
descriptionKetoacyl synthases are enzymes involved in fatty acid synthesis and can be classified into five families based on primary sequence similarity. Different families have different catalytic mechanisms. Developing cost-effective computational models to identify the family of ketoacyl synthases will be helpful for enzyme engineering and in knowing individual enzymes’ catalytic mechanisms. In this work, a support vector machine-based method was developed to predict ketoacyl synthase family using the n -peptide composition of reduced amino acid alphabets. In jackknife cross-validation, the model based on the 2-peptide composition of a reduced amino acid alphabet of size 13 yielded the best overall accuracy of 96.44% with average accuracy of 93.36%, which is superior to other state-of-the-art methods. This result suggests that the information provided by n -peptide compositions of reduced amino acid alphabets provides efficient means for enzyme family classification and that the proposed model can be efficiently used for ketoacyl synthase family annotation.
languageeng
source
version9
lds50peer_reviewed
links
openurl$$Topenurl_article
openurlfulltext$$Topenurlfull_article
backlink$$Uhttp://dx.doi.org/10.1007/s10295-011-1047-z$$EView_full_text_in_Springer_(Subscribers_only)
search
creatorcontrib
0Chen, Wei
1Feng, Pengmian
2Lin, Hao
titlePrediction of ketoacyl synthase family using reduced amino acid alphabets
descriptionKetoacyl synthases are enzymes involved in fatty acid synthesis and can be classified into five families based on primary sequence similarity. Different families have different catalytic mechanisms. Developing cost-effective computational models to identify the family of ketoacyl synthases will be helpful for enzyme engineering and in knowing individual enzymes’ catalytic mechanisms. In this work, a support vector machine-based method was developed to predict ketoacyl synthase family using the n -peptide composition of reduced amino acid alphabets. In jackknife cross-validation, the model based on the 2-peptide composition of a reduced amino acid alphabet of size 13 yielded the best overall accuracy of 96.44% with average accuracy of 93.36%, which is superior to other state-of-the-art methods. This result suggests that the information provided by n -peptide compositions of reduced amino acid alphabets provides efficient means for enzyme family classification and that the proposed model can be efficiently used for ketoacyl synthase family annotation.
subject
0Ketoacyl synthase family
1Reduced amino acid alphabet
2Support vector machine
3-Peptide
general
010.1007/s10295-011-1047-z
1English
2Springer Science & Business Media B.V.
3SpringerLink
sourceidspringer_jour
recordidspringer_jour10.1007/s10295-011-1047-z
issn
01476-5535
114765535
21367-5435
313675435
rsrctypearticle
creationdate2012
addtitle
0Journal of Industrial Microbiology & Biotechnology
1Official Journal of the Society for Industrial Microbiology and Biotechnology
2J Ind Microbiol Biotechnol
searchscopespringer_journals_complete
scopespringer_journals_complete
lsr30VSR-Enriched:[pqid, pages, galeid]
sort
titlePrediction of ketoacyl synthase family using reduced amino acid alphabets
authorChen, Wei ; Feng, Pengmian ; Lin, Hao
creationdate20120400
facets
frbrgroupid7227062065681585313
frbrtype5
languageeng
creationdate2012
topic
0Ketoacyl Synthase Family
1Reduced Amino Acid Alphabet
2Support Vector Machine
3-Peptide
collectionSpringerLink
prefilterarticles
rsrctypearticles
creatorcontrib
0Chen, Wei
1Feng, Pengmian
2Lin, Hao
jtitleJournal Of Industrial Microbiology &Amp; Biotechnology
toplevelpeer_reviewed
delivery
delcategoryRemote Search Resource
fulltextfulltext
addata
aulast
0Chen
1Feng
2Lin
aufirst
0Wei
1Pengmian
2Hao
au
0Chen, Wei
1Feng, Pengmian
2Lin, Hao
atitlePrediction of ketoacyl synthase family using reduced amino acid alphabets
jtitleJournal of Industrial Microbiology & Biotechnology
stitleJ Ind Microbiol Biotechnol
addtitleOfficial Journal of the Society for Industrial Microbiology and Biotechnology
risdate201204
volume39
issue4
spage579
epage584
issn1367-5435
eissn1476-5535
genrearticle
ristypeJOUR
abstractKetoacyl synthases are enzymes involved in fatty acid synthesis and can be classified into five families based on primary sequence similarity. Different families have different catalytic mechanisms. Developing cost-effective computational models to identify the family of ketoacyl synthases will be helpful for enzyme engineering and in knowing individual enzymes’ catalytic mechanisms. In this work, a support vector machine-based method was developed to predict ketoacyl synthase family using the n -peptide composition of reduced amino acid alphabets. In jackknife cross-validation, the model based on the 2-peptide composition of a reduced amino acid alphabet of size 13 yielded the best overall accuracy of 96.44% with average accuracy of 93.36%, which is superior to other state-of-the-art methods. This result suggests that the information provided by n -peptide compositions of reduced amino acid alphabets provides efficient means for enzyme family classification and that the proposed model can be efficiently used for ketoacyl synthase family annotation.
copBerlin/Heidelberg
pubSpringer-Verlag
doi10.1007/s10295-011-1047-z
pages579-584
date2012-04