Predicting linear B‐cell epitopes using string kernels
Identifieur interne : 002A61 ( Main/Exploration ); précédent : 002A60; suivant : 002A62Predicting linear B‐cell epitopes using string kernels
Auteurs : Yasser El-Manzalawy [États-Unis] ; Drena Dobbs [États-Unis] ; Vasant Honavar [États-Unis]Source :
- Journal of Molecular Recognition [ 0952-3499 ] ; 2008-07.
English descriptors
- Teeft :
- Abcpred, Amino, Amino acids, Average ranks, Bcipep, Bcipep database, Bcpred, Bcpred method, Bcpreds, Best performance, Bioinformatics, Blind test, Chen, Continuous epitopes, Copyright, Coronavirus, Data sets, Database, Demsar, Different methods, Direct comparisons, Epitope, Epitope length, Epitope prediction, Epitope prediction methods, Feature space, Input space, Iowa state university, John wiley sons, Kernel, Kernel function, Linear epitope, Linear epitopes, Lodhi, Mismatch, Msmtch, Multiple hypothesis comparisons, Other methods, Pellequer, Peptide, Physicochemical properties, Positive peptides, Prediction accuracy, Propensity, Propensity scale, Raghava, Receptor, Recognit, Relative performance, Respiratory syndrome, Saha, Sars, Sequence identity, Sequence identity cutoff, Server, Sollner, Spct, Spectrum kernel, String kernels, Subsequence, Subsequence kernel, Substring, Training data, Unique epitopes, Vefold.
Abstract
The identification and characterization of B‐cell epitopes play an important role in vaccine design, immunodiagnostic tests, and antibody production. Therefore, computational tools for reliably predicting linear B‐cell epitopes are highly desirable. We evaluated Support Vector Machine (SVM) classifiers trained utilizing five different kernel methods using fivefold cross‐validation on a homology‐reduced data set of 701 linear B‐cell epitopes, extracted from Bcipep database, and 701 non‐epitopes, randomly extracted from SwissProt sequences. Based on the results of our computational experiments, we propose BCPred, a novel method for predicting linear B‐cell epitopes using the subsequence kernel. We show that the predictive performance of BCPred (AUC = 0.758) outperforms 11 SVM‐based classifiers developed and evaluated in our experiments as well as our implementation of AAP (AUC = 0.7), a recently proposed method for predicting linear B‐cell epitopes using amino acid pair antigenicity. Furthermore, we compared BCPred with AAP and ABCPred, a method that uses recurrent neural networks, using two data sets of unique B‐cell epitopes that had been previously used to evaluate ABCPred. Analysis of the data sets used and the results of this comparison show that conclusions about the relative performance of different B‐cell epitope prediction methods drawn on the basis of experiments using data sets of unique B‐cell epitopes are likely to yield overly optimistic estimates of performance of evaluated methods. This argues for the use of carefully homology‐reduced data sets in comparing B‐cell epitope prediction methods to avoid misleading conclusions about how different methods compare to each other. Our homology‐reduced data set and implementations of BCPred as well as the APP method are publicly available through our web‐based server, BCPREDS, at: http://ailab.cs.iastate.edu/bcpreds/. Copyright © 2008 John Wiley & Sons, Ltd.
Url:
DOI: 10.1002/jmr.893
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000B27
- to stream Istex, to step Curation: 000B27
- to stream Istex, to step Checkpoint: 000775
- to stream Main, to step Merge: 002A87
- to stream Main, to step Curation: 002A61
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Predicting linear B‐cell epitopes using string kernels</title>
<author><name sortKey="El Anzalawy, Yasser" sort="El Anzalawy, Yasser" uniqKey="El Anzalawy Y" first="Yasser" last="El-Manzalawy">Yasser El-Manzalawy</name>
</author>
<author><name sortKey="Dobbs, Drena" sort="Dobbs, Drena" uniqKey="Dobbs D" first="Drena" last="Dobbs">Drena Dobbs</name>
</author>
<author><name sortKey="Honavar, Vasant" sort="Honavar, Vasant" uniqKey="Honavar V" first="Vasant" last="Honavar">Vasant Honavar</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:6483283356B180D4365629B79073ABBEDE5C41A3</idno>
<date when="2008" year="2008">2008</date>
<idno type="doi">10.1002/jmr.893</idno>
<idno type="url">https://api.istex.fr/ark:/67375/WNG-WGM67G2V-3/fulltext.pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000B27</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000B27</idno>
<idno type="wicri:Area/Istex/Curation">000B27</idno>
<idno type="wicri:Area/Istex/Checkpoint">000775</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000775</idno>
<idno type="wicri:doubleKey">0952-3499:2008:El Anzalawy Y:predicting:linear:b</idno>
<idno type="wicri:Area/Main/Merge">002A87</idno>
<idno type="wicri:Area/Main/Curation">002A61</idno>
<idno type="wicri:Area/Main/Exploration">002A61</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main">Predicting linear B‐cell epitopes using string kernels</title>
<author><name sortKey="El Anzalawy, Yasser" sort="El Anzalawy, Yasser" uniqKey="El Anzalawy Y" first="Yasser" last="El-Manzalawy">Yasser El-Manzalawy</name>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Artificial Intelligence Laboratory, Iowa State University, Ames, IA 50010</wicri:regionArea>
<orgName type="university">Université d'État de l'Iowa</orgName>
<placeName><settlement type="city">Ames (Iowa)</settlement>
<region type="state">Iowa</region>
</placeName>
</affiliation>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Department of Computer Science, Iowa State University, Ames, IA 50010</wicri:regionArea>
<orgName type="university">Université d'État de l'Iowa</orgName>
<placeName><settlement type="city">Ames (Iowa)</settlement>
<region type="state">Iowa</region>
</placeName>
</affiliation>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Bioinformatics and Computational Biology Graduate Program, Iowa State University, Ames, IA 50010</wicri:regionArea>
<orgName type="university">Université d'État de l'Iowa</orgName>
<placeName><settlement type="city">Ames (Iowa)</settlement>
<region type="state">Iowa</region>
</placeName>
</affiliation>
<affiliation wicri:level="1"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Center for Computational Intelligence, Learning and Discovery, lowa State University, Ames, IA 50010</wicri:regionArea>
<wicri:noRegion>IA 50010</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country>
</affiliation>
<affiliation wicri:level="4"><country xml:lang="fr" wicri:curation="lc">États-Unis</country>
<wicri:regionArea>Correspondence address: 226 Atanasoff Hall, Iowa State University, Ames, IA 50010</wicri:regionArea>
<orgName type="university">Université d'État de l'Iowa</orgName>
<placeName><settlement type="city">Ames (Iowa)</settlement>
<region type="state">Iowa</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Dobbs, Drena" sort="Dobbs, Drena" uniqKey="Dobbs D" first="Drena" last="Dobbs">Drena Dobbs</name>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Department of Genetics, Development and Cell Biology, Iowa State University, Ames, IA 50010</wicri:regionArea>
<orgName type="university">Université d'État de l'Iowa</orgName>
<placeName><settlement type="city">Ames (Iowa)</settlement>
<region type="state">Iowa</region>
</placeName>
</affiliation>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Bioinformatics and Computational Biology Graduate Program, Iowa State University, Ames, IA 50010</wicri:regionArea>
<orgName type="university">Université d'État de l'Iowa</orgName>
<placeName><settlement type="city">Ames (Iowa)</settlement>
<region type="state">Iowa</region>
</placeName>
</affiliation>
<affiliation wicri:level="1"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Center for Computational Intelligence, Learning and Discovery, lowa State University, Ames, IA 50010</wicri:regionArea>
<wicri:noRegion>IA 50010</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Honavar, Vasant" sort="Honavar, Vasant" uniqKey="Honavar V" first="Vasant" last="Honavar">Vasant Honavar</name>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Artificial Intelligence Laboratory, Iowa State University, Ames, IA 50010</wicri:regionArea>
<orgName type="university">Université d'État de l'Iowa</orgName>
<placeName><settlement type="city">Ames (Iowa)</settlement>
<region type="state">Iowa</region>
</placeName>
</affiliation>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Department of Computer Science, Iowa State University, Ames, IA 50010</wicri:regionArea>
<orgName type="university">Université d'État de l'Iowa</orgName>
<placeName><settlement type="city">Ames (Iowa)</settlement>
<region type="state">Iowa</region>
</placeName>
</affiliation>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Department of Genetics, Development and Cell Biology, Iowa State University, Ames, IA 50010</wicri:regionArea>
<orgName type="university">Université d'État de l'Iowa</orgName>
<placeName><settlement type="city">Ames (Iowa)</settlement>
<region type="state">Iowa</region>
</placeName>
</affiliation>
<affiliation wicri:level="1"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Center for Computational Intelligence, Learning and Discovery, lowa State University, Ames, IA 50010</wicri:regionArea>
<wicri:noRegion>IA 50010</wicri:noRegion>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="j" type="main">Journal of Molecular Recognition</title>
<title level="j" type="alt">JOURNAL OF MOLECULAR RECOGNITION</title>
<idno type="ISSN">0952-3499</idno>
<idno type="eISSN">1099-1352</idno>
<imprint><biblScope unit="vol">21</biblScope>
<biblScope unit="issue">4</biblScope>
<biblScope unit="page" from="243">243</biblScope>
<biblScope unit="page" to="255">255</biblScope>
<biblScope unit="page-count">13</biblScope>
<publisher>John Wiley & Sons, Ltd.</publisher>
<pubPlace>Chichester, UK</pubPlace>
<date type="published" when="2008-07">2008-07</date>
</imprint>
<idno type="ISSN">0952-3499</idno>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0952-3499</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="Teeft" xml:lang="en"><term>Abcpred</term>
<term>Amino</term>
<term>Amino acids</term>
<term>Average ranks</term>
<term>Bcipep</term>
<term>Bcipep database</term>
<term>Bcpred</term>
<term>Bcpred method</term>
<term>Bcpreds</term>
<term>Best performance</term>
<term>Bioinformatics</term>
<term>Blind test</term>
<term>Chen</term>
<term>Continuous epitopes</term>
<term>Copyright</term>
<term>Coronavirus</term>
<term>Data sets</term>
<term>Database</term>
<term>Demsar</term>
<term>Different methods</term>
<term>Direct comparisons</term>
<term>Epitope</term>
<term>Epitope length</term>
<term>Epitope prediction</term>
<term>Epitope prediction methods</term>
<term>Feature space</term>
<term>Input space</term>
<term>Iowa state university</term>
<term>John wiley sons</term>
<term>Kernel</term>
<term>Kernel function</term>
<term>Linear epitope</term>
<term>Linear epitopes</term>
<term>Lodhi</term>
<term>Mismatch</term>
<term>Msmtch</term>
<term>Multiple hypothesis comparisons</term>
<term>Other methods</term>
<term>Pellequer</term>
<term>Peptide</term>
<term>Physicochemical properties</term>
<term>Positive peptides</term>
<term>Prediction accuracy</term>
<term>Propensity</term>
<term>Propensity scale</term>
<term>Raghava</term>
<term>Receptor</term>
<term>Recognit</term>
<term>Relative performance</term>
<term>Respiratory syndrome</term>
<term>Saha</term>
<term>Sars</term>
<term>Sequence identity</term>
<term>Sequence identity cutoff</term>
<term>Server</term>
<term>Sollner</term>
<term>Spct</term>
<term>Spectrum kernel</term>
<term>String kernels</term>
<term>Subsequence</term>
<term>Subsequence kernel</term>
<term>Substring</term>
<term>Training data</term>
<term>Unique epitopes</term>
<term>Vefold</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">The identification and characterization of B‐cell epitopes play an important role in vaccine design, immunodiagnostic tests, and antibody production. Therefore, computational tools for reliably predicting linear B‐cell epitopes are highly desirable. We evaluated Support Vector Machine (SVM) classifiers trained utilizing five different kernel methods using fivefold cross‐validation on a homology‐reduced data set of 701 linear B‐cell epitopes, extracted from Bcipep database, and 701 non‐epitopes, randomly extracted from SwissProt sequences. Based on the results of our computational experiments, we propose BCPred, a novel method for predicting linear B‐cell epitopes using the subsequence kernel. We show that the predictive performance of BCPred (AUC = 0.758) outperforms 11 SVM‐based classifiers developed and evaluated in our experiments as well as our implementation of AAP (AUC = 0.7), a recently proposed method for predicting linear B‐cell epitopes using amino acid pair antigenicity. Furthermore, we compared BCPred with AAP and ABCPred, a method that uses recurrent neural networks, using two data sets of unique B‐cell epitopes that had been previously used to evaluate ABCPred. Analysis of the data sets used and the results of this comparison show that conclusions about the relative performance of different B‐cell epitope prediction methods drawn on the basis of experiments using data sets of unique B‐cell epitopes are likely to yield overly optimistic estimates of performance of evaluated methods. This argues for the use of carefully homology‐reduced data sets in comparing B‐cell epitope prediction methods to avoid misleading conclusions about how different methods compare to each other. Our homology‐reduced data set and implementations of BCPred as well as the APP method are publicly available through our web‐based server, BCPREDS, at: http://ailab.cs.iastate.edu/bcpreds/. Copyright © 2008 John Wiley & Sons, Ltd.</div>
</front>
</TEI>
<affiliations><list><country><li>États-Unis</li>
</country>
<region><li>Iowa</li>
</region>
<settlement><li>Ames (Iowa)</li>
</settlement>
<orgName><li>Université d'État de l'Iowa</li>
</orgName>
</list>
<tree><country name="États-Unis"><region name="Iowa"><name sortKey="El Anzalawy, Yasser" sort="El Anzalawy, Yasser" uniqKey="El Anzalawy Y" first="Yasser" last="El-Manzalawy">Yasser El-Manzalawy</name>
</region>
<name sortKey="Dobbs, Drena" sort="Dobbs, Drena" uniqKey="Dobbs D" first="Drena" last="Dobbs">Drena Dobbs</name>
<name sortKey="Dobbs, Drena" sort="Dobbs, Drena" uniqKey="Dobbs D" first="Drena" last="Dobbs">Drena Dobbs</name>
<name sortKey="Dobbs, Drena" sort="Dobbs, Drena" uniqKey="Dobbs D" first="Drena" last="Dobbs">Drena Dobbs</name>
<name sortKey="El Anzalawy, Yasser" sort="El Anzalawy, Yasser" uniqKey="El Anzalawy Y" first="Yasser" last="El-Manzalawy">Yasser El-Manzalawy</name>
<name sortKey="El Anzalawy, Yasser" sort="El Anzalawy, Yasser" uniqKey="El Anzalawy Y" first="Yasser" last="El-Manzalawy">Yasser El-Manzalawy</name>
<name sortKey="El Anzalawy, Yasser" sort="El Anzalawy, Yasser" uniqKey="El Anzalawy Y" first="Yasser" last="El-Manzalawy">Yasser El-Manzalawy</name>
<name sortKey="El Anzalawy, Yasser" sort="El Anzalawy, Yasser" uniqKey="El Anzalawy Y" first="Yasser" last="El-Manzalawy">Yasser El-Manzalawy</name>
<name sortKey="El Anzalawy, Yasser" sort="El Anzalawy, Yasser" uniqKey="El Anzalawy Y" first="Yasser" last="El-Manzalawy">Yasser El-Manzalawy</name>
<name sortKey="Honavar, Vasant" sort="Honavar, Vasant" uniqKey="Honavar V" first="Vasant" last="Honavar">Vasant Honavar</name>
<name sortKey="Honavar, Vasant" sort="Honavar, Vasant" uniqKey="Honavar V" first="Vasant" last="Honavar">Vasant Honavar</name>
<name sortKey="Honavar, Vasant" sort="Honavar, Vasant" uniqKey="Honavar V" first="Vasant" last="Honavar">Vasant Honavar</name>
<name sortKey="Honavar, Vasant" sort="Honavar, Vasant" uniqKey="Honavar V" first="Vasant" last="Honavar">Vasant Honavar</name>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Sante/explor/MersV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 002A61 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 002A61 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Sante |area= MersV1 |flux= Main |étape= Exploration |type= RBID |clé= ISTEX:6483283356B180D4365629B79073ABBEDE5C41A3 |texte= Predicting linear B‐cell epitopes using string kernels }}
This area was generated with Dilib version V0.6.33. |