EnSVMB: Metagenomics Fragments Classification using Ensemble SVM and BLAST.
Identifieur interne : 000D21 ( PubMed/Checkpoint ); précédent : 000D20; suivant : 000D22EnSVMB: Metagenomics Fragments Classification using Ensemble SVM and BLAST.
Auteurs : Yuan Jiang [République populaire de Chine] ; Jun Wang [République populaire de Chine] ; Dawen Xia [République populaire de Chine] ; Guoxian Yu [République populaire de Chine]Source :
- Scientific reports [ 2045-2322 ] ; 2017.
Descripteurs français
- KwdFr :
- MESH :
English descriptors
- KwdEn :
- MESH :
- genetics : Base Sequence.
- methods : Sequence Analysis, DNA.
- Algorithms, Classification, Humans, Metagenomics, Sensitivity and Specificity, Software, Support Vector Machine.
Abstract
Metagenomics brings in new discoveries and insights into the uncultured microbial world. One fundamental task in metagenomics analysis is to determine the taxonomy of raw sequence fragments. Modern sequencing technologies produce relatively short fragments and greatly increase the number of fragments, and thus make the taxonomic classification considerably more difficult than before. Therefore, fast and accurate techniques are called to classify large-scale fragments. We propose EnSVM (Ensemble Support Vector Machine) and its advanced method called EnSVMB (EnSVM with BLAST) to accurately classify fragments. EnSVM divides fragments into a large confident (or small diffident) set, based on whether the fragments get consistent (or inconsistent) predictions from linear SVMs trained with different k-mers. Empirical study shows that sensitivity and specificity of EnSVM on confident set are higher than 90% and 97%, but on diffident set are lower than 60% and 75%. To further improve the performance on diffident set, EnSVMB takes advantage of best hits of BLAST to reclassify fragments in that set. Experimental results show EnSVM can efficiently and effectively divide fragments into confident and diffident sets, and EnSVMB achieves higher accuracy, sensitivity and more true positives than related state-of-the-art methods and holds comparable specificity with the best of them.
DOI: 10.1038/s41598-017-09947-y
PubMed: 28842700
Affiliations:
Links toward previous steps (curation, corpus...)
Links to Exploration step
pubmed:28842700Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">EnSVMB: Metagenomics Fragments Classification using Ensemble SVM and BLAST.</title><author><name sortKey="Jiang, Yuan" sort="Jiang, Yuan" uniqKey="Jiang Y" first="Yuan" last="Jiang">Yuan Jiang</name><affiliation wicri:level="1"><nlm:affiliation>College of Computer and Information Science, Southwest University, Chongqing, China.</nlm:affiliation><country xml:lang="fr">République populaire de Chine</country><wicri:regionArea>College of Computer and Information Science, Southwest University, Chongqing</wicri:regionArea><wicri:noRegion>Chongqing</wicri:noRegion></affiliation></author><author><name sortKey="Wang, Jun" sort="Wang, Jun" uniqKey="Wang J" first="Jun" last="Wang">Jun Wang</name><affiliation wicri:level="1"><nlm:affiliation>College of Computer and Information Science, Southwest University, Chongqing, China.</nlm:affiliation><country xml:lang="fr">République populaire de Chine</country><wicri:regionArea>College of Computer and Information Science, Southwest University, Chongqing</wicri:regionArea><wicri:noRegion>Chongqing</wicri:noRegion></affiliation></author><author><name sortKey="Xia, Dawen" sort="Xia, Dawen" uniqKey="Xia D" first="Dawen" last="Xia">Dawen Xia</name><affiliation wicri:level="1"><nlm:affiliation>College of Data Science and Information Engineering, Guizhou Minzu University, Guiyang, China.</nlm:affiliation><country xml:lang="fr">République populaire de Chine</country><wicri:regionArea>College of Data Science and Information Engineering, Guizhou Minzu University, Guiyang</wicri:regionArea><wicri:noRegion>Guiyang</wicri:noRegion></affiliation></author><author><name sortKey="Yu, Guoxian" sort="Yu, Guoxian" uniqKey="Yu G" first="Guoxian" last="Yu">Guoxian Yu</name><affiliation wicri:level="1"><nlm:affiliation>College of Computer and Information Science, Southwest University, Chongqing, China. gxyu@swu.edu.cn.</nlm:affiliation><country xml:lang="fr">République populaire de Chine</country><wicri:regionArea>College of Computer and Information Science, Southwest University, Chongqing</wicri:regionArea><wicri:noRegion>Chongqing</wicri:noRegion></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">PubMed</idno><date when="2017">2017</date><idno type="RBID">pubmed:28842700</idno><idno type="pmid">28842700</idno><idno type="doi">10.1038/s41598-017-09947-y</idno><idno type="wicri:Area/PubMed/Corpus">000B84</idno><idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Corpus" wicri:corpus="PubMed">000B84</idno><idno type="wicri:Area/PubMed/Curation">000B84</idno><idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Curation">000B84</idno><idno type="wicri:Area/PubMed/Checkpoint">000D21</idno><idno type="wicri:explorRef" wicri:stream="Checkpoint" wicri:step="PubMed">000D21</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">EnSVMB: Metagenomics Fragments Classification using Ensemble SVM and BLAST.</title><author><name sortKey="Jiang, Yuan" sort="Jiang, Yuan" uniqKey="Jiang Y" first="Yuan" last="Jiang">Yuan Jiang</name><affiliation wicri:level="1"><nlm:affiliation>College of Computer and Information Science, Southwest University, Chongqing, China.</nlm:affiliation><country xml:lang="fr">République populaire de Chine</country><wicri:regionArea>College of Computer and Information Science, Southwest University, Chongqing</wicri:regionArea><wicri:noRegion>Chongqing</wicri:noRegion></affiliation></author><author><name sortKey="Wang, Jun" sort="Wang, Jun" uniqKey="Wang J" first="Jun" last="Wang">Jun Wang</name><affiliation wicri:level="1"><nlm:affiliation>College of Computer and Information Science, Southwest University, Chongqing, China.</nlm:affiliation><country xml:lang="fr">République populaire de Chine</country><wicri:regionArea>College of Computer and Information Science, Southwest University, Chongqing</wicri:regionArea><wicri:noRegion>Chongqing</wicri:noRegion></affiliation></author><author><name sortKey="Xia, Dawen" sort="Xia, Dawen" uniqKey="Xia D" first="Dawen" last="Xia">Dawen Xia</name><affiliation wicri:level="1"><nlm:affiliation>College of Data Science and Information Engineering, Guizhou Minzu University, Guiyang, China.</nlm:affiliation><country xml:lang="fr">République populaire de Chine</country><wicri:regionArea>College of Data Science and Information Engineering, Guizhou Minzu University, Guiyang</wicri:regionArea><wicri:noRegion>Guiyang</wicri:noRegion></affiliation></author><author><name sortKey="Yu, Guoxian" sort="Yu, Guoxian" uniqKey="Yu G" first="Guoxian" last="Yu">Guoxian Yu</name><affiliation wicri:level="1"><nlm:affiliation>College of Computer and Information Science, Southwest University, Chongqing, China. gxyu@swu.edu.cn.</nlm:affiliation><country xml:lang="fr">République populaire de Chine</country><wicri:regionArea>College of Computer and Information Science, Southwest University, Chongqing</wicri:regionArea><wicri:noRegion>Chongqing</wicri:noRegion></affiliation></author></analytic><series><title level="j">Scientific reports</title><idno type="eISSN">2045-2322</idno><imprint><date when="2017" type="published">2017</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithms</term><term>Base Sequence (genetics)</term><term>Classification</term><term>Humans</term><term>Metagenomics</term><term>Sensitivity and Specificity</term><term>Sequence Analysis, DNA (methods)</term><term>Software</term><term>Support Vector Machine</term></keywords><keywords scheme="KwdFr" xml:lang="fr"><term>Algorithmes</term><term>Analyse de séquence d'ADN ()</term><term>Classification</term><term>Humains</term><term>Logiciel</term><term>Machine à vecteur de support</term><term>Métagénomique</term><term>Sensibilité et spécificité</term><term>Séquence nucléotidique (génétique)</term></keywords><keywords scheme="MESH" qualifier="genetics" xml:lang="en"><term>Base Sequence</term></keywords><keywords scheme="MESH" qualifier="génétique" xml:lang="fr"><term>Séquence nucléotidique</term></keywords><keywords scheme="MESH" qualifier="methods" xml:lang="en"><term>Sequence Analysis, DNA</term></keywords><keywords scheme="MESH" xml:lang="en"><term>Algorithms</term><term>Classification</term><term>Humans</term><term>Metagenomics</term><term>Sensitivity and Specificity</term><term>Software</term><term>Support Vector Machine</term></keywords><keywords scheme="MESH" xml:lang="fr"><term>Algorithmes</term><term>Analyse de séquence d'ADN</term><term>Classification</term><term>Humains</term><term>Logiciel</term><term>Machine à vecteur de support</term><term>Métagénomique</term><term>Sensibilité et spécificité</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Metagenomics brings in new discoveries and insights into the uncultured microbial world. One fundamental task in metagenomics analysis is to determine the taxonomy of raw sequence fragments. Modern sequencing technologies produce relatively short fragments and greatly increase the number of fragments, and thus make the taxonomic classification considerably more difficult than before. Therefore, fast and accurate techniques are called to classify large-scale fragments. We propose EnSVM (Ensemble Support Vector Machine) and its advanced method called EnSVMB (EnSVM with BLAST) to accurately classify fragments. EnSVM divides fragments into a large confident (or small diffident) set, based on whether the fragments get consistent (or inconsistent) predictions from linear SVMs trained with different k-mers. Empirical study shows that sensitivity and specificity of EnSVM on confident set are higher than 90% and 97%, but on diffident set are lower than 60% and 75%. To further improve the performance on diffident set, EnSVMB takes advantage of best hits of BLAST to reclassify fragments in that set. Experimental results show EnSVM can efficiently and effectively divide fragments into confident and diffident sets, and EnSVMB achieves higher accuracy, sensitivity and more true positives than related state-of-the-art methods and holds comparable specificity with the best of them.</div></front></TEI><pubmed><MedlineCitation Status="MEDLINE" Owner="NLM"><PMID Version="1">28842700</PMID><DateCompleted><Year>2019</Year><Month>04</Month><Day>08</Day></DateCompleted><DateRevised><Year>2019</Year><Month>04</Month><Day>08</Day></DateRevised><Article PubModel="Electronic"><Journal><ISSN IssnType="Electronic">2045-2322</ISSN><JournalIssue CitedMedium="Internet"><Volume>7</Volume><Issue>1</Issue><PubDate><Year>2017</Year><Month>08</Month><Day>25</Day></PubDate></JournalIssue><Title>Scientific reports</Title><ISOAbbreviation>Sci Rep</ISOAbbreviation></Journal><ArticleTitle>EnSVMB: Metagenomics Fragments Classification using Ensemble SVM and BLAST.</ArticleTitle><Pagination><MedlinePgn>9440</MedlinePgn></Pagination><ELocationID EIdType="doi" ValidYN="Y">10.1038/s41598-017-09947-y</ELocationID><Abstract><AbstractText>Metagenomics brings in new discoveries and insights into the uncultured microbial world. One fundamental task in metagenomics analysis is to determine the taxonomy of raw sequence fragments. Modern sequencing technologies produce relatively short fragments and greatly increase the number of fragments, and thus make the taxonomic classification considerably more difficult than before. Therefore, fast and accurate techniques are called to classify large-scale fragments. We propose EnSVM (Ensemble Support Vector Machine) and its advanced method called EnSVMB (EnSVM with BLAST) to accurately classify fragments. EnSVM divides fragments into a large confident (or small diffident) set, based on whether the fragments get consistent (or inconsistent) predictions from linear SVMs trained with different k-mers. Empirical study shows that sensitivity and specificity of EnSVM on confident set are higher than 90% and 97%, but on diffident set are lower than 60% and 75%. To further improve the performance on diffident set, EnSVMB takes advantage of best hits of BLAST to reclassify fragments in that set. Experimental results show EnSVM can efficiently and effectively divide fragments into confident and diffident sets, and EnSVMB achieves higher accuracy, sensitivity and more true positives than related state-of-the-art methods and holds comparable specificity with the best of them.</AbstractText></Abstract><AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Jiang</LastName><ForeName>Yuan</ForeName><Initials>Y</Initials><AffiliationInfo><Affiliation>College of Computer and Information Science, Southwest University, Chongqing, China.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Wang</LastName><ForeName>Jun</ForeName><Initials>J</Initials><Identifier Source="ORCID">0000-0002-5890-0365</Identifier><AffiliationInfo><Affiliation>College of Computer and Information Science, Southwest University, Chongqing, China.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Xia</LastName><ForeName>Dawen</ForeName><Initials>D</Initials><AffiliationInfo><Affiliation>College of Data Science and Information Engineering, Guizhou Minzu University, Guiyang, China.</Affiliation></AffiliationInfo><AffiliationInfo><Affiliation>College of National Culture and Cognitive Science, Guizhou Minzu University, Guiyang, China.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Yu</LastName><ForeName>Guoxian</ForeName><Initials>G</Initials><Identifier Source="ORCID">0000-0002-1667-6705</Identifier><AffiliationInfo><Affiliation>College of Computer and Information Science, Southwest University, Chongqing, China. gxyu@swu.edu.cn.</Affiliation></AffiliationInfo></Author></AuthorList><Language>eng</Language><PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType><PublicationType UI="D013485">Research Support, Non-U.S. Gov't</PublicationType></PublicationTypeList><ArticleDate DateType="Electronic"><Year>2017</Year><Month>08</Month><Day>25</Day></ArticleDate></Article><MedlineJournalInfo><Country>England</Country><MedlineTA>Sci Rep</MedlineTA><NlmUniqueID>101563288</NlmUniqueID><ISSNLinking>2045-2322</ISSNLinking></MedlineJournalInfo><CitationSubset>IM</CitationSubset><MeshHeadingList><MeshHeading><DescriptorName UI="D000465" MajorTopicYN="N">Algorithms</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D001483" MajorTopicYN="N">Base Sequence</DescriptorName><QualifierName UI="Q000235" MajorTopicYN="Y">genetics</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D002965" MajorTopicYN="N">Classification</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D006801" MajorTopicYN="N">Humans</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D056186" MajorTopicYN="Y">Metagenomics</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D012680" MajorTopicYN="N">Sensitivity and Specificity</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D017422" MajorTopicYN="N">Sequence Analysis, DNA</DescriptorName><QualifierName UI="Q000379" MajorTopicYN="Y">methods</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D012984" MajorTopicYN="N">Software</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D060388" MajorTopicYN="N">Support Vector Machine</DescriptorName></MeshHeading></MeshHeadingList></MedlineCitation><PubmedData><History><PubMedPubDate PubStatus="received"><Year>2017</Year><Month>04</Month><Day>07</Day></PubMedPubDate><PubMedPubDate PubStatus="accepted"><Year>2017</Year><Month>08</Month><Day>01</Day></PubMedPubDate><PubMedPubDate PubStatus="entrez"><Year>2017</Year><Month>8</Month><Day>27</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="pubmed"><Year>2017</Year><Month>8</Month><Day>27</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="medline"><Year>2019</Year><Month>4</Month><Day>9</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate></History><PublicationStatus>epublish</PublicationStatus><ArticleIdList><ArticleId IdType="pubmed">28842700</ArticleId><ArticleId IdType="doi">10.1038/s41598-017-09947-y</ArticleId><ArticleId IdType="pii">10.1038/s41598-017-09947-y</ArticleId><ArticleId IdType="pmc">PMC5573435</ArticleId></ArticleIdList><ReferenceList><Reference><Citation>Nat Methods. 2011 May;8(5):367</Citation><ArticleIdList><ArticleId IdType="pubmed">21527926</ArticleId></ArticleIdList></Reference><Reference><Citation>Genome Biol. 2002;3(2):REVIEWS0003</Citation><ArticleIdList><ArticleId IdType="pubmed">11864374</ArticleId></ArticleIdList></Reference><Reference><Citation>Bioinformatics. 2016 Apr 1;32(7):1023-32</Citation><ArticleIdList><ArticleId IdType="pubmed">26589281</ArticleId></ArticleIdList></Reference><Reference><Citation>Bioinformatics. 2011 Jan 1;27(1):127-9</Citation><ArticleIdList><ArticleId IdType="pubmed">21062764</ArticleId></ArticleIdList></Reference><Reference><Citation>J Comput Biol. 2000 Feb-Apr;7(1-2):203-14</Citation><ArticleIdList><ArticleId IdType="pubmed">10890397</ArticleId></ArticleIdList></Reference><Reference><Citation>BMC Bioinformatics. 2011 Aug 09;12:328</Citation><ArticleIdList><ArticleId IdType="pubmed">21827705</ArticleId></ArticleIdList></Reference><Reference><Citation>BMC Genomics. 2013 Sep 22;14:641</Citation><ArticleIdList><ArticleId IdType="pubmed">24053649</ArticleId></ArticleIdList></Reference><Reference><Citation>Nat Methods. 2007 Jan;4(1):63-72</Citation><ArticleIdList><ArticleId IdType="pubmed">17179938</ArticleId></ArticleIdList></Reference><Reference><Citation>BMC Bioinformatics. 2009 Feb 11;10:56</Citation><ArticleIdList><ArticleId IdType="pubmed">19210774</ArticleId></ArticleIdList></Reference><Reference><Citation>Genome Res. 2007 Mar;17(3):377-86</Citation><ArticleIdList><ArticleId IdType="pubmed">17255551</ArticleId></ArticleIdList></Reference><Reference><Citation>Genome Res. 2001 Aug;11(8):1404-9</Citation><ArticleIdList><ArticleId IdType="pubmed">11483581</ArticleId></ArticleIdList></Reference><Reference><Citation>Nat Methods. 2008 Jan;5(1):16-8</Citation><ArticleIdList><ArticleId IdType="pubmed">18165802</ArticleId></ArticleIdList></Reference><Reference><Citation>Trends Genet. 2008 Mar;24(3):133-41</Citation><ArticleIdList><ArticleId IdType="pubmed">18262675</ArticleId></ArticleIdList></Reference><Reference><Citation>Nat Methods. 2009 Sep;6(9):673-6</Citation><ArticleIdList><ArticleId IdType="pubmed">19648916</ArticleId></ArticleIdList></Reference><Reference><Citation>PLoS One. 2008;3(11):e3703</Citation><ArticleIdList><ArticleId IdType="pubmed">19002248</ArticleId></ArticleIdList></Reference><Reference><Citation>PLoS One. 2012;7(6):e38581</Citation><ArticleIdList><ArticleId IdType="pubmed">22745671</ArticleId></ArticleIdList></Reference><Reference><Citation>Bioinformatics. 2009 Jul 15;25(14):1754-60</Citation><ArticleIdList><ArticleId IdType="pubmed">19451168</ArticleId></ArticleIdList></Reference><Reference><Citation>Genome Biol. 2014 Mar 03;15(3):R46</Citation><ArticleIdList><ArticleId IdType="pubmed">24580807</ArticleId></ArticleIdList></Reference><Reference><Citation>Brief Bioinform. 2015 Sep;16(5):884-900</Citation><ArticleIdList><ArticleId IdType="pubmed">25433466</ArticleId></ArticleIdList></Reference><Reference><Citation>Science. 2005 Apr 22;308(5721):554-7</Citation><ArticleIdList><ArticleId IdType="pubmed">15845853</ArticleId></ArticleIdList></Reference><Reference><Citation>Nucleic Acids Res. 2012 Jul;40(12):e94</Citation><ArticleIdList><ArticleId IdType="pubmed">22434876</ArticleId></ArticleIdList></Reference><Reference><Citation>Nucleic Acids Res. 1997 Sep 1;25(17):3389-402</Citation><ArticleIdList><ArticleId IdType="pubmed">9254694</ArticleId></ArticleIdList></Reference><Reference><Citation>Nucleic Acids Res. 2012 Jan;40(Database issue):D130-5</Citation><ArticleIdList><ArticleId IdType="pubmed">22121212</ArticleId></ArticleIdList></Reference></ReferenceList></PubmedData></pubmed><affiliations><list><country><li>République populaire de Chine</li></country></list><tree><country name="République populaire de Chine"><noRegion><name sortKey="Jiang, Yuan" sort="Jiang, Yuan" uniqKey="Jiang Y" first="Yuan" last="Jiang">Yuan Jiang</name></noRegion><name sortKey="Wang, Jun" sort="Wang, Jun" uniqKey="Wang J" first="Jun" last="Wang">Jun Wang</name><name sortKey="Xia, Dawen" sort="Xia, Dawen" uniqKey="Xia D" first="Dawen" last="Xia">Dawen Xia</name><name sortKey="Yu, Guoxian" sort="Yu, Guoxian" uniqKey="Yu G" first="Guoxian" last="Yu">Guoxian Yu</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Sante/explor/MersV1/Data/PubMed/Checkpoint
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000D21 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PubMed/Checkpoint/biblio.hfd -nk 000D21 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Sante
|area= MersV1
|flux= PubMed
|étape= Checkpoint
|type= RBID
|clé= pubmed:28842700
|texte= EnSVMB: Metagenomics Fragments Classification using Ensemble SVM and BLAST.
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/PubMed/Checkpoint/RBID.i -Sk "pubmed:28842700" \
| HfdSelect -Kh $EXPLOR_AREA/Data/PubMed/Checkpoint/biblio.hfd \
| NlmPubMed2Wicri -a MersV1
| This area was generated with Dilib version V0.6.33. |  |