Improved prediction of MHC class I binders/non-binders peptides through artificial neural network using variable learning rate: SARS corona virus, a case study.
Identifieur interne : 001393 ( Main/Exploration ); précédent : 001392; suivant : 001394Improved prediction of MHC class I binders/non-binders peptides through artificial neural network using variable learning rate: SARS corona virus, a case study.
Auteurs : Sudhir Singh Soam [Inde] ; Bharat Bhasker ; Bhartendu Nath MishraSource :
- Advances in experimental medicine and biology [ 0065-2598 ] ; 2011.
Descripteurs français
- KwdFr :
- Algorithmes, Allèles, Antigènes d'histocompatibilité de classe I (génétique), Antigènes d'histocompatibilité de classe I (métabolisme), Bases de données génétiques, Biologie informatique, Gènes MHC de classe I, Humains, Intelligence artificielle, Liaison aux protéines, Protéomique (), Sites de fixation, Virus du SRAS (génétique), Virus du SRAS (immunologie), Virus du SRAS (métabolisme).
- MESH :
- génétique : Antigènes d'histocompatibilité de classe I, Virus du SRAS.
- immunologie : Virus du SRAS.
- métabolisme : Antigènes d'histocompatibilité de classe I, Virus du SRAS.
- Algorithmes, Allèles, Bases de données génétiques, Biologie informatique, Gènes MHC de classe I, Humains, Intelligence artificielle, Liaison aux protéines, Protéomique, Sites de fixation.
English descriptors
- KwdEn :
- Algorithms, Alleles, Artificial Intelligence, Binding Sites, Computational Biology, Databases, Genetic, Genes, MHC Class I, Histocompatibility Antigens Class I (genetics), Histocompatibility Antigens Class I (metabolism), Humans, Neural Networks, Computer, Protein Binding, Proteomics (statistics & numerical data), SARS Virus (genetics), SARS Virus (immunology), SARS Virus (metabolism).
- MESH :
- chemical , genetics : Histocompatibility Antigens Class I.
- chemical , metabolism : Histocompatibility Antigens Class I.
- genetics : SARS Virus.
- immunology : SARS Virus.
- metabolism : SARS Virus.
- statistics & numerical data : Proteomics.
- Algorithms, Alleles, Artificial Intelligence, Binding Sites, Computational Biology, Databases, Genetic, Genes, MHC Class I, Humans, Neural Networks, Computer, Protein Binding.
Abstract
Fundamental step of an adaptive immune response to pathogen or vaccine is the binding of short peptides (also called epitopes) to major histocompatibility complex (MHC) molecules. The various prediction algorithms are being used to capture the MHC peptide binding preference, allowing the rapid scan of entire pathogen proteomes for peptide likely to bind MHC, saving the cost, effort, and time. However, the number of known binders/non-binders (BNB) to a specific MHC molecule is limited in many cases, which still poses a computational challenge for prediction. The training data should be adequate to predict BNB using any machine learning approach. In this study, variable learning rate has been demonstrated for training artificial neural network and predicting BNB for small datasets. The approach can be used for large datasets as well. The dataset for different MHC class I alleles for SARS Corona virus (Tor2 Replicase polyprotein 1ab) has been used for training and prediction of BNB. A total of 90 datasets (nine different MHC class I alleles with tenfold cross validation) have been retrieved from IEDB database for BNB. For fixed learning rate approach, the best value of AROC is 0.65, and in most of the cases it is 0.5, which shows the poor predictions. In case of variable learning rate, of the 90 datasets the value of AROC for 76 datasets is between 0.806 and 1.0 and for 7 datasets the value is between 0.7 and 0.8 and for rest of 7 datasets it is between 0.5 and 0.7, which indicates very good performance in most of the cases.
DOI: 10.1007/978-1-4419-7046-6_22
PubMed: 21431562
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PubMed, to step Corpus: 000D25
- to stream PubMed, to step Curation: 000D25
- to stream PubMed, to step Checkpoint: 000D09
- to stream Ncbi, to step Merge: 000254
- to stream Ncbi, to step Curation: 000254
- to stream Ncbi, to step Checkpoint: 000254
- to stream Main, to step Merge: 001395
- to stream Main, to step Curation: 001393
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Improved prediction of MHC class I binders/non-binders peptides through artificial neural network using variable learning rate: SARS corona virus, a case study.</title>
<author><name sortKey="Soam, Sudhir Singh" sort="Soam, Sudhir Singh" uniqKey="Soam S" first="Sudhir Singh" last="Soam">Sudhir Singh Soam</name>
<affiliation wicri:level="1"><nlm:affiliation>Department of Biotechnology, Institute of Engeneering & Technology, UP Technical University, Lucknow, India. profbnmishra@gmail.com</nlm:affiliation>
<country xml:lang="fr">Inde</country>
<wicri:regionArea>Department of Biotechnology, Institute of Engeneering & Technology, UP Technical University, Lucknow</wicri:regionArea>
<wicri:noRegion>Lucknow</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Bhasker, Bharat" sort="Bhasker, Bharat" uniqKey="Bhasker B" first="Bharat" last="Bhasker">Bharat Bhasker</name>
</author>
<author><name sortKey="Mishra, Bhartendu Nath" sort="Mishra, Bhartendu Nath" uniqKey="Mishra B" first="Bhartendu Nath" last="Mishra">Bhartendu Nath Mishra</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="2011">2011</date>
<idno type="RBID">pubmed:21431562</idno>
<idno type="pmid">21431562</idno>
<idno type="doi">10.1007/978-1-4419-7046-6_22</idno>
<idno type="wicri:Area/PubMed/Corpus">000D25</idno>
<idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Corpus" wicri:corpus="PubMed">000D25</idno>
<idno type="wicri:Area/PubMed/Curation">000D25</idno>
<idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Curation">000D25</idno>
<idno type="wicri:Area/PubMed/Checkpoint">000D09</idno>
<idno type="wicri:explorRef" wicri:stream="Checkpoint" wicri:step="PubMed">000D09</idno>
<idno type="wicri:Area/Ncbi/Merge">000254</idno>
<idno type="wicri:Area/Ncbi/Curation">000254</idno>
<idno type="wicri:Area/Ncbi/Checkpoint">000254</idno>
<idno type="wicri:doubleKey">0065-2598:2011:Soam S:improved:prediction:of</idno>
<idno type="wicri:Area/Main/Merge">001395</idno>
<idno type="wicri:Area/Main/Curation">001393</idno>
<idno type="wicri:Area/Main/Exploration">001393</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Improved prediction of MHC class I binders/non-binders peptides through artificial neural network using variable learning rate: SARS corona virus, a case study.</title>
<author><name sortKey="Soam, Sudhir Singh" sort="Soam, Sudhir Singh" uniqKey="Soam S" first="Sudhir Singh" last="Soam">Sudhir Singh Soam</name>
<affiliation wicri:level="1"><nlm:affiliation>Department of Biotechnology, Institute of Engeneering & Technology, UP Technical University, Lucknow, India. profbnmishra@gmail.com</nlm:affiliation>
<country xml:lang="fr">Inde</country>
<wicri:regionArea>Department of Biotechnology, Institute of Engeneering & Technology, UP Technical University, Lucknow</wicri:regionArea>
<wicri:noRegion>Lucknow</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Bhasker, Bharat" sort="Bhasker, Bharat" uniqKey="Bhasker B" first="Bharat" last="Bhasker">Bharat Bhasker</name>
</author>
<author><name sortKey="Mishra, Bhartendu Nath" sort="Mishra, Bhartendu Nath" uniqKey="Mishra B" first="Bhartendu Nath" last="Mishra">Bhartendu Nath Mishra</name>
</author>
</analytic>
<series><title level="j">Advances in experimental medicine and biology</title>
<idno type="ISSN">0065-2598</idno>
<imprint><date when="2011" type="published">2011</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithms</term>
<term>Alleles</term>
<term>Artificial Intelligence</term>
<term>Binding Sites</term>
<term>Computational Biology</term>
<term>Databases, Genetic</term>
<term>Genes, MHC Class I</term>
<term>Histocompatibility Antigens Class I (genetics)</term>
<term>Histocompatibility Antigens Class I (metabolism)</term>
<term>Humans</term>
<term>Neural Networks, Computer</term>
<term>Protein Binding</term>
<term>Proteomics (statistics & numerical data)</term>
<term>SARS Virus (genetics)</term>
<term>SARS Virus (immunology)</term>
<term>SARS Virus (metabolism)</term>
</keywords>
<keywords scheme="KwdFr" xml:lang="fr"><term>Algorithmes</term>
<term>Allèles</term>
<term>Antigènes d'histocompatibilité de classe I (génétique)</term>
<term>Antigènes d'histocompatibilité de classe I (métabolisme)</term>
<term>Bases de données génétiques</term>
<term>Biologie informatique</term>
<term>Gènes MHC de classe I</term>
<term>Humains</term>
<term>Intelligence artificielle</term>
<term>Liaison aux protéines</term>
<term>Protéomique ()</term>
<term>Sites de fixation</term>
<term>Virus du SRAS (génétique)</term>
<term>Virus du SRAS (immunologie)</term>
<term>Virus du SRAS (métabolisme)</term>
</keywords>
<keywords scheme="MESH" type="chemical" qualifier="genetics" xml:lang="en"><term>Histocompatibility Antigens Class I</term>
</keywords>
<keywords scheme="MESH" type="chemical" qualifier="metabolism" xml:lang="en"><term>Histocompatibility Antigens Class I</term>
</keywords>
<keywords scheme="MESH" qualifier="genetics" xml:lang="en"><term>SARS Virus</term>
</keywords>
<keywords scheme="MESH" qualifier="génétique" xml:lang="fr"><term>Antigènes d'histocompatibilité de classe I</term>
<term>Virus du SRAS</term>
</keywords>
<keywords scheme="MESH" qualifier="immunologie" xml:lang="fr"><term>Virus du SRAS</term>
</keywords>
<keywords scheme="MESH" qualifier="immunology" xml:lang="en"><term>SARS Virus</term>
</keywords>
<keywords scheme="MESH" qualifier="metabolism" xml:lang="en"><term>SARS Virus</term>
</keywords>
<keywords scheme="MESH" qualifier="métabolisme" xml:lang="fr"><term>Antigènes d'histocompatibilité de classe I</term>
<term>Virus du SRAS</term>
</keywords>
<keywords scheme="MESH" qualifier="statistics & numerical data" xml:lang="en"><term>Proteomics</term>
</keywords>
<keywords scheme="MESH" xml:lang="en"><term>Algorithms</term>
<term>Alleles</term>
<term>Artificial Intelligence</term>
<term>Binding Sites</term>
<term>Computational Biology</term>
<term>Databases, Genetic</term>
<term>Genes, MHC Class I</term>
<term>Humans</term>
<term>Neural Networks, Computer</term>
<term>Protein Binding</term>
</keywords>
<keywords scheme="MESH" xml:lang="fr"><term>Algorithmes</term>
<term>Allèles</term>
<term>Bases de données génétiques</term>
<term>Biologie informatique</term>
<term>Gènes MHC de classe I</term>
<term>Humains</term>
<term>Intelligence artificielle</term>
<term>Liaison aux protéines</term>
<term>Protéomique</term>
<term>Sites de fixation</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Fundamental step of an adaptive immune response to pathogen or vaccine is the binding of short peptides (also called epitopes) to major histocompatibility complex (MHC) molecules. The various prediction algorithms are being used to capture the MHC peptide binding preference, allowing the rapid scan of entire pathogen proteomes for peptide likely to bind MHC, saving the cost, effort, and time. However, the number of known binders/non-binders (BNB) to a specific MHC molecule is limited in many cases, which still poses a computational challenge for prediction. The training data should be adequate to predict BNB using any machine learning approach. In this study, variable learning rate has been demonstrated for training artificial neural network and predicting BNB for small datasets. The approach can be used for large datasets as well. The dataset for different MHC class I alleles for SARS Corona virus (Tor2 Replicase polyprotein 1ab) has been used for training and prediction of BNB. A total of 90 datasets (nine different MHC class I alleles with tenfold cross validation) have been retrieved from IEDB database for BNB. For fixed learning rate approach, the best value of AROC is 0.65, and in most of the cases it is 0.5, which shows the poor predictions. In case of variable learning rate, of the 90 datasets the value of AROC for 76 datasets is between 0.806 and 1.0 and for 7 datasets the value is between 0.7 and 0.8 and for rest of 7 datasets it is between 0.5 and 0.7, which indicates very good performance in most of the cases.</div>
</front>
</TEI>
<affiliations><list><country><li>Inde</li>
</country>
</list>
<tree><noCountry><name sortKey="Bhasker, Bharat" sort="Bhasker, Bharat" uniqKey="Bhasker B" first="Bharat" last="Bhasker">Bharat Bhasker</name>
<name sortKey="Mishra, Bhartendu Nath" sort="Mishra, Bhartendu Nath" uniqKey="Mishra B" first="Bhartendu Nath" last="Mishra">Bhartendu Nath Mishra</name>
</noCountry>
<country name="Inde"><noRegion><name sortKey="Soam, Sudhir Singh" sort="Soam, Sudhir Singh" uniqKey="Soam S" first="Sudhir Singh" last="Soam">Sudhir Singh Soam</name>
</noRegion>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Sante/explor/CovidV2/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001393 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001393 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Sante |area= CovidV2 |flux= Main |étape= Exploration |type= RBID |clé= pubmed:21431562 |texte= Improved prediction of MHC class I binders/non-binders peptides through artificial neural network using variable learning rate: SARS corona virus, a case study. }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Exploration/RBID.i -Sk "pubmed:21431562" \ | HfdSelect -Kh $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd \ | NlmPubMed2Wicri -a CovidV2
This area was generated with Dilib version V0.6.33. |