<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-01250752</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-17T01:41:56+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Spaced seeds improve k-mer-based metagenomic classification</title>
            <author role="aut">
              <persName>
                <forename type="first">Karel</forename>
                <surname>Brinda</surname>
              </persName>
              <email type="md5">cb2ed19981057458d0e5d588da887a59</email>
              <email type="domain">inria.fr</email>
              <ptr type="url" target="https://brinda.eu"/>
              <idno type="idhal" notation="string">karel-brinda</idno>
              <idno type="idhal" notation="numeric">5549</idno>
              <idno type="halauthorid" notation="string">22377-5549</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0200-557X</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=TTaAd_MAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/225143240</idno>
              <affiliation ref="#struct-1001627"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Maciej</forename>
                <surname>Sykulski</surname>
              </persName>
              <idno type="halauthorid">670300-0</idno>
              <affiliation ref="#struct-1001627"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gregory</forename>
                <surname>Kucherov</surname>
              </persName>
              <email type="md5">3c853852fa7a519883147931dba1c2e2</email>
              <email type="domain">univ-mlv.fr</email>
              <idno type="idhal" notation="string">gregory-kucherov</idno>
              <idno type="idhal" notation="numeric">14903</idno>
              <idno type="halauthorid" notation="string">555-14903</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/F-7875-2016</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-5899-5424</idno>
              <idno type="IDREF">https://www.idref.fr/093602189</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/F-7875-2016</idno>
              <orgName ref="#struct-441569"/>
              <affiliation ref="#struct-1001627"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Karel</forename>
                <surname>Břinda</surname>
              </persName>
              <email type="md5">cb2ed19981057458d0e5d588da887a59</email>
              <email type="domain">inria.fr</email>
            </editor>
            <funder ref="#projanr-37872"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2024-11-18 15:26:24</date>
              <date type="whenModified">2025-10-01 14:24:03</date>
              <date type="whenReleased">2024-11-18 20:12:48</date>
              <date type="whenProduced">2015-07-25</date>
              <date type="whenEndEmbargoed">2024-11-18</date>
              <ref type="file" target="https://hal.science/hal-01250752v1/document">
                <date notBefore="2024-11-18"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-01250752v1/file/1502.06256v3.pdf" id="file-4788948-4170370">
                <date notBefore="2024-11-18"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/1502.06256"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="197293">
                <persName>
                  <forename>Karel</forename>
                  <surname>Břinda</surname>
                </persName>
                <email type="md5">cb2ed19981057458d0e5d588da887a59</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01250752</idno>
            <idno type="halUri">https://hal.science/hal-01250752</idno>
            <idno type="halBibtex">brinda:hal-01250752</idno>
            <idno type="halRefHtml">&lt;i&gt;Bioinformatics&lt;/i&gt;, 2015, &lt;a target="_blank" href="https://dx.doi.org/10.1093/bioinformatics/btv419"&gt;&amp;#x27E8;10.1093/bioinformatics/btv419&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Bioinformatics, 2015, &amp;#x27E8;10.1093/bioinformatics/btv419&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-4788948-4170370"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="ENPC" corresp="PARISTECH">École nationale des ponts et chaussées </idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="PARISTECH">ParisTech</idno>
            <idno type="stamp" n="ENPC-LIGM" corresp="ENPC">Laboratoire d'informatique Gaspard-Monge</idno>
            <idno type="stamp" n="LIGM" corresp="ENPC">Laboratoire d'informatique Gaspard-Monge</idno>
            <idno type="stamp" n="CV_LIGM" corresp="CV_UNIV-MLV">CV des membres du LIGM</idno>
            <idno type="stamp" n="LIGM_MOA" corresp="LIGM">Models and Algorithms</idno>
            <idno type="stamp" n="ESIEE-PARIS">ESIEE Paris</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="UNIV-EIFFEL">Université Gustave Eiffel</idno>
            <idno type="stamp" n="U-EIFFEL">Université Gustave Eiffel</idno>
            <idno type="stamp" n="TEST3-HALCNRS">TEST3-HALCNRS</idno>
            <idno type="stamp" n="LIGM_ADA" corresp="LIGM">Algorithmique Discrète et Applications</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Spaced seeds improve k-mer-based metagenomic classification</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Karel</forename>
                    <surname>Brinda</surname>
                  </persName>
                  <email type="md5">cb2ed19981057458d0e5d588da887a59</email>
                  <email type="domain">inria.fr</email>
                  <ptr type="url" target="https://brinda.eu"/>
                  <idno type="idhal" notation="string">karel-brinda</idno>
                  <idno type="idhal" notation="numeric">5549</idno>
                  <idno type="halauthorid" notation="string">22377-5549</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0200-557X</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=TTaAd_MAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/225143240</idno>
                  <affiliation ref="#struct-1001627"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Maciej</forename>
                    <surname>Sykulski</surname>
                  </persName>
                  <idno type="halauthorid">670300-0</idno>
                  <affiliation ref="#struct-1001627"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gregory</forename>
                    <surname>Kucherov</surname>
                  </persName>
                  <email type="md5">3c853852fa7a519883147931dba1c2e2</email>
                  <email type="domain">univ-mlv.fr</email>
                  <idno type="idhal" notation="string">gregory-kucherov</idno>
                  <idno type="idhal" notation="numeric">14903</idno>
                  <idno type="halauthorid" notation="string">555-14903</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/F-7875-2016</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-5899-5424</idno>
                  <idno type="IDREF">https://www.idref.fr/093602189</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/F-7875-2016</idno>
                  <orgName ref="#struct-441569"/>
                  <affiliation ref="#struct-1001627"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">3436</idno>
                <idno type="issn">1367-4803</idno>
                <idno type="eissn">1367-4811</idno>
                <title level="j">Bioinformatics</title>
                <imprint>
                  <publisher>Oxford University Press (OUP)</publisher>
                  <date type="datePub">2015-07-25</date>
                </imprint>
              </monogr>
              <idno type="arxiv">1502.06256</idno>
              <idno type="doi">10.1093/bioinformatics/btv419</idno>
              <ref type="publisher">http://bioinformatics.oxfordjournals.org/content/early/2015/08/10/bioinformatics.btv419.abstract</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-ds">Computer Science [cs]/Data Structures and Algorithms [cs.DS]</classCode>
              <classCode scheme="halDomain" n="info.info-bi">Computer Science [cs]/Bioinformatics [q-bio.QM]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Motivation: Metagenomics is a powerful approach to study genetic content of environmental samples, which has been strongly promoted by next-generation sequencing technologies. To cope with massive data involved in modern metagenomic projects, recent tools rely on the analysis of k-mers shared between the read to be classified and sampled reference genomes.Results: Within this general framework, we show that spaced seeds provide a significant improvement of classification accuracy, as opposed to traditional contiguous k-mers. We support this thesis through a series of different computational experiments, including simulations of large-scale metagenomic projects.Availability and implementation, Supplementary information: Scripts and programs used in this study, as well as supplementary material, are available from http://github.com/gregorykucherov/spaced-seeds-for-metagenomics.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1001627" status="OLD">
          <idno type="IdRef">142877891</idno>
          <idno type="RNSR">200212717U</idno>
          <orgName>Laboratoire d'Informatique Gaspard-Monge</orgName>
          <orgName type="acronym">LIGM</orgName>
          <date type="start">2020-01-01</date>
          <date type="end">2024-12-31</date>
          <desc>
            <address>
              <addrLine>Université Gustave Eiffel, Cité Descartes, Bâtiment Copernic, 5 bd Descartes, 77454 Marne-la-Vallée Cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://ligm.u-pem.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301545" type="direct"/>
            <relation name="UMR8049" active="#struct-441569" type="direct"/>
            <relation active="#struct-580722" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-301545" status="OLD">
          <idno type="ROR">https://ror.org/02nwvxz07</idno>
          <orgName>École nationale des ponts et chaussées</orgName>
          <orgName type="acronym">ENPC</orgName>
          <date type="start">1747-02-14</date>
          <date type="end">2024-12-31</date>
          <desc>
            <address>
              <addrLine>École nationale des ponts et chaussées, 6-8 avenue Blaise-Pascal, Cité Descartes, Champs-sur-Marne, 77455 Marne-la-Vallée cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://ecoledesponts.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-580722" status="VALID">
          <idno type="ROR">https://ror.org/03x42jk29</idno>
          <orgName>Université Gustave Eiffel</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Cité Descartes, 5 Boulevard Descartes • Champs-sur-Marne, 77454 Marne-la-Vallée Cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-gustave-eiffel.fr/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-37872" status="VALID">
          <idno type="anr">ANR-11-BINF-0001</idno>
          <idno type="program">Bio-informatique</idno>
          <orgName>ABS4NGS</orgName>
          <desc>Solutions Algorithmiques, Bioinformatiques et Logicielles pour le Séquençage Haut Débit</desc>
          <date type="start">2011</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>