<?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-03176011</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="2026-05-15T17:50:05+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Exploring short k-mer profiles in cells and mobile elements from Archaea highlights the major influence of both the ecological niche and evolutionary history</title>
            <author role="aut">
              <persName>
                <forename type="first">Ariane</forename>
                <surname>Bize</surname>
              </persName>
              <email type="md5">c8439707a326d63bfe04554874447afd</email>
              <email type="domain">inrae.fr</email>
              <idno type="idhal" notation="string">ariane-bize</idno>
              <idno type="idhal" notation="numeric">801302</idno>
              <idno type="halauthorid" notation="string">356204-801302</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-4023-8665</idno>
              <idno type="IDREF">https://www.idref.fr/147944171</idno>
              <affiliation ref="#struct-1002496"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Cédric</forename>
                <surname>Midoux</surname>
              </persName>
              <email type="md5">fd8ea27e0a81a7ff2cff6bec31f841df</email>
              <email type="domain">inrae.fr</email>
              <idno type="idhal" notation="string">cedric-midoux</idno>
              <idno type="idhal" notation="numeric">734961</idno>
              <idno type="halauthorid" notation="string">54016-734961</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7964-0929</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=lAzGLCIAAAAJ&amp;hl=fr</idno>
              <affiliation ref="#struct-1002434"/>
              <affiliation ref="#struct-1124613"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mahendra</forename>
                <surname>Mariadassou</surname>
              </persName>
              <email type="md5">c882a6dc628496d648db8b6db85dc44c</email>
              <email type="domain">inrae.fr</email>
              <idno type="idhal" notation="string">mahendra-mariadassou</idno>
              <idno type="idhal" notation="numeric">172671</idno>
              <idno type="halauthorid" notation="string">54017-172671</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-2986-354X</idno>
              <idno type="IDREF">https://www.idref.fr/142892092</idno>
              <affiliation ref="#struct-1002434"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Sophie</forename>
                <surname>Schbath</surname>
              </persName>
              <email type="md5">463aaa2d4284e848acecbb778b7f9a11</email>
              <email type="domain">inrae.fr</email>
              <idno type="idhal" notation="string">sophie-schbath</idno>
              <idno type="idhal" notation="numeric">183444</idno>
              <idno type="halauthorid" notation="string">22422-183444</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-3574-8222</idno>
              <idno type="IDREF">https://www.idref.fr/07553424X</idno>
              <affiliation ref="#struct-1002434"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Patrick</forename>
                <surname>Forterre</surname>
              </persName>
              <email type="md5">600b8072fc09d4f83c7d1c7dc04d1474</email>
              <email type="domain">igmors.u-psud.fr</email>
              <idno type="idhal" notation="numeric">994526</idno>
              <idno type="halauthorid" notation="string">136228-994526</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1843-7214</idno>
              <idno type="IDREF">https://www.idref.fr/082097291</idno>
              <idno type="VIAF">https://viaf.org/viaf/17419239</idno>
              <idno type="ISNI">http://isni.org/isni/0000000040235868</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Violette</forename>
                <surname>da Cunha</surname>
              </persName>
              <email type="md5">c944734c8aea13f5687f98e5a5177fb3</email>
              <email type="domain">pasteur.fr</email>
              <idno type="idhal" notation="string">da-cunha-violette</idno>
              <idno type="idhal" notation="numeric">748649</idno>
              <idno type="halauthorid" notation="string">17981-748649</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-9035-7825</idno>
              <idno type="IDREF">https://www.idref.fr/165826657</idno>
              <idno type="VIAF">https://viaf.org/viaf/297006700</idno>
              <idno type="ISNI">http://isni.org/isni/000000040190954X</idno>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Ariane</forename>
                <surname>Bize</surname>
              </persName>
              <email type="md5">c8439707a326d63bfe04554874447afd</email>
              <email type="domain">inrae.fr</email>
            </editor>
            <funder ref="#projanr-42804"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2021-03-22 09:37:33</date>
              <date type="whenModified">2026-03-30 11:42:48</date>
              <date type="whenReleased">2021-05-31 10:45:54</date>
              <date type="whenProduced">2021-03-16</date>
              <date type="whenEndEmbargoed">2021-03-22</date>
              <ref type="file" target="https://hal.inrae.fr/hal-03176011v1/document">
                <date notBefore="2021-03-22"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.inrae.fr/hal-03176011v1/file/2021_kmers_Archaea_mobile-elements.pdf" id="file-3176011-2846758">
                <date notBefore="2021-03-22"/>
              </ref>
              <ref type="externalLink" target="https://bmcgenomics.biomedcentral.com/track/pdf/10.1186/s12864-021-07471-y"/>
              <fs>
                <f name="inra_etatDocument_local" notation="numeric">
                  <numeric>0</numeric>
                </f>
                <f name="inra_etatDocument_local" notation="string" n="0">
                  <string>inra_etatDocument_local_0</string>
                </f>
                <f name="inra_publicVise_local" notation="string" n="SC">
                  <string>Scientists</string>
                </f>
              </fs>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="555206">
                <persName>
                  <forename>Ariane</forename>
                  <surname>Bize</surname>
                </persName>
                <email type="md5">c8439707a326d63bfe04554874447afd</email>
                <email type="domain">inrae.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03176011</idno>
            <idno type="halUri">https://hal.inrae.fr/hal-03176011</idno>
            <idno type="halBibtex">bize:hal-03176011</idno>
            <idno type="halRefHtml">&lt;i&gt;BMC Genomics&lt;/i&gt;, 2021, 22, &lt;a target="_blank" href="https://dx.doi.org/10.1186/s12864-021-07471-y"&gt;&amp;#x27E8;10.1186/s12864-021-07471-y&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">BMC Genomics, 2021, 22, &amp;#x27E8;10.1186/s12864-021-07471-y&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3176011-2846758"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="INRAE">Institut National de Recherche en Agriculture, Alimentation et Environnement</idno>
            <idno type="stamp" n="INRAE-UPSACLAY" corresp="UNIV-PARIS-SACLAY">INRAE-UPSACLAY</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="GS-ENGINEERING">Graduate School Sciences de l'Ingénierie et des Systèmes</idno>
            <idno type="stamp" n="GS-MATHEMATIQUES">Graduate School Mathématiques</idno>
            <idno type="stamp" n="GS-COMPUTER-SCIENCE">Graduate School Computer Science</idno>
            <idno type="stamp" n="GS-BIOSPHERA">Graduate School Biologie, Société, Ecologie &amp; Environnement, Ressources, Agriculture &amp; Alimentation</idno>
            <idno type="stamp" n="MAIAGE">MaIAGE</idno>
            <idno type="stamp" n="MICA-UNITES">MICA-Unités </idno>
            <idno type="stamp" n="MATHNUM">Département MathNum</idno>
            <idno type="stamp" n="PROSE">PROSE</idno>
            <idno type="stamp" n="BIOINFOMICS">Infrastructure de Recherche INRAE en bioinformatique</idno>
            <idno type="stamp" n="TEST-MATHNUM">Test MathNum</idno>
            <idno type="stamp" n="APT_TEST">APT_TEST</idno>
            <idno type="stamp" n="ANR-ONE-HEALTH">ANR-ONE-HEALTH</idno>
            <idno type="stamp" n="ANR-ONE-HEALTH-REF-ANR" corresp="ANR-ONE-HEALTH">ANR-ONE-HEALTH-REF-ANR</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">Exploring short k-mer profiles in cells and mobile elements from Archaea highlights the major influence of both the ecological niche and evolutionary history</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Ariane</forename>
                    <surname>Bize</surname>
                  </persName>
                  <email type="md5">c8439707a326d63bfe04554874447afd</email>
                  <email type="domain">inrae.fr</email>
                  <idno type="idhal" notation="string">ariane-bize</idno>
                  <idno type="idhal" notation="numeric">801302</idno>
                  <idno type="halauthorid" notation="string">356204-801302</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-4023-8665</idno>
                  <idno type="IDREF">https://www.idref.fr/147944171</idno>
                  <affiliation ref="#struct-1002496"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Cédric</forename>
                    <surname>Midoux</surname>
                  </persName>
                  <email type="md5">fd8ea27e0a81a7ff2cff6bec31f841df</email>
                  <email type="domain">inrae.fr</email>
                  <idno type="idhal" notation="string">cedric-midoux</idno>
                  <idno type="idhal" notation="numeric">734961</idno>
                  <idno type="halauthorid" notation="string">54016-734961</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7964-0929</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=lAzGLCIAAAAJ&amp;hl=fr</idno>
                  <affiliation ref="#struct-1002434"/>
                  <affiliation ref="#struct-1124613"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mahendra</forename>
                    <surname>Mariadassou</surname>
                  </persName>
                  <email type="md5">c882a6dc628496d648db8b6db85dc44c</email>
                  <email type="domain">inrae.fr</email>
                  <idno type="idhal" notation="string">mahendra-mariadassou</idno>
                  <idno type="idhal" notation="numeric">172671</idno>
                  <idno type="halauthorid" notation="string">54017-172671</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-2986-354X</idno>
                  <idno type="IDREF">https://www.idref.fr/142892092</idno>
                  <affiliation ref="#struct-1002434"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Sophie</forename>
                    <surname>Schbath</surname>
                  </persName>
                  <email type="md5">463aaa2d4284e848acecbb778b7f9a11</email>
                  <email type="domain">inrae.fr</email>
                  <idno type="idhal" notation="string">sophie-schbath</idno>
                  <idno type="idhal" notation="numeric">183444</idno>
                  <idno type="halauthorid" notation="string">22422-183444</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-3574-8222</idno>
                  <idno type="IDREF">https://www.idref.fr/07553424X</idno>
                  <affiliation ref="#struct-1002434"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Patrick</forename>
                    <surname>Forterre</surname>
                  </persName>
                  <email type="md5">600b8072fc09d4f83c7d1c7dc04d1474</email>
                  <email type="domain">igmors.u-psud.fr</email>
                  <idno type="idhal" notation="numeric">994526</idno>
                  <idno type="halauthorid" notation="string">136228-994526</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1843-7214</idno>
                  <idno type="IDREF">https://www.idref.fr/082097291</idno>
                  <idno type="VIAF">https://viaf.org/viaf/17419239</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000040235868</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Violette</forename>
                    <surname>da Cunha</surname>
                  </persName>
                  <email type="md5">c944734c8aea13f5687f98e5a5177fb3</email>
                  <email type="domain">pasteur.fr</email>
                  <idno type="idhal" notation="string">da-cunha-violette</idno>
                  <idno type="idhal" notation="numeric">748649</idno>
                  <idno type="halauthorid" notation="string">17981-748649</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-9035-7825</idno>
                  <idno type="IDREF">https://www.idref.fr/165826657</idno>
                  <idno type="VIAF">https://viaf.org/viaf/297006700</idno>
                  <idno type="ISNI">http://isni.org/isni/000000040190954X</idno>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">333</idno>
                <idno type="issn">1471-2164</idno>
                <title level="j">BMC Genomics</title>
                <imprint>
                  <publisher>BioMed Central</publisher>
                  <biblScope unit="volume">22</biblScope>
                  <date type="datePub">2021-03-16</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1186/s12864-021-07471-y</idno>
              <idno type="pubmed">33726663</idno>
              <idno type="wos">000630096300002</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Host transfer</term>
                <term xml:lang="en">Hyperthermophily</term>
                <term xml:lang="en">Halophily</term>
                <term xml:lang="en">Signature</term>
                <term xml:lang="en">Multivariate analysis</term>
                <term xml:lang="en">Codon composition</term>
                <term xml:lang="en">5-mer</term>
                <term xml:lang="en">Plasmid</term>
                <term xml:lang="en">Virus</term>
                <term xml:lang="en">Extrachromosomal element</term>
              </keywords>
              <classCode scheme="halDomain" n="sdv.bibs">Life Sciences [q-bio]/Quantitative Methods [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>Background: K-mer-based methods have greatly advanced in recent years, largely driven by the realization of their biological significance and by the advent of next-generation sequencing. Their speed and their independence from the annotation process are major advantages. Their utility in the study of the mobilome has recently emerged and they seem a priori adapted to the patchy gene distribution and the lack of universal marker genes of viruses and plasmids. To provide a framework for the interpretation of results from k-mer based methods applied to archaea or their mobilome, we analyzed the 5-mer DNA profiles of close to 600 archaeal cells, viruses and plasmids. Archaea is one of the three domains of life. Archaea seem enriched in extremophiles and are associated with a high diversity of viral and plasmid families, many of which are specific to this domain. We explored the dataset structure by multivariate and statistical analyses, seeking to identify the underlying factors. Results: For cells, the 5-mer profiles were inconsistent with the phylogeny of archaea. At a finer taxonomic level, the influence of the taxonomy and the environmental constraints on 5-mer profiles was very strong. These two factors were interdependent to a significant extent, and the respective weights of their contributions varied according to the clade. A convergent adaptation was observed for the class Halobacteria, for which a strong 5-mer signature was identified. For mobile elements, coevolution with the host had a clear influence on their 5-mer profile. This enabled us to identify one previously known and one new case of recent host transfer based on the atypical composition of the mobile elements involved. Beyond the effect of coevolution, extrachromosomal elements strikingly retain the specific imprint of their own viral or plasmid taxonomic family in their 5-mer profile.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1002496" status="VALID">
          <idno type="RNSR">200518614R</idno>
          <orgName>Procédés biotechnologiques au service de l'environnement</orgName>
          <orgName type="acronym">UR PROSE</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>1 rue Pierre-Gilles de GennesCS 10030 92761 Antony Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www6.jouy.inrae.fr/prose/</ref>
          </desc>
          <listRelation>
            <relation name="UR1461" active="#struct-577435" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1002434" status="VALID">
          <idno type="RNSR">201521778L</idno>
          <orgName>Mathématiques et Informatique Appliquées du Génome à l'Environnement [Jouy-En-Josas]</orgName>
          <orgName type="acronym">MaIAGE</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Bât. 233, Domaine de Vilvert - 78352 Jouy-en-Josas Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://maiage.inrae.fr</ref>
          </desc>
          <listRelation>
            <relation name="UPR 1404" active="#struct-577435" type="direct"/>
          </listRelation>
        </org>
        <org type="department" xml:id="struct-1124613" status="VALID">
          <orgName>IR BioInfOmics</orgName>
          <date type="start">2019-01-01</date>
          <desc>
            <address>
              <addrLine>Jouy-en-Josas - Toulouse - Versailles</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://bioinfomics.inrae.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-577435" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-577435" status="VALID">
          <idno type="ROR">https://ror.org/003vg9w96</idno>
          <orgName>Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement</orgName>
          <orgName type="acronym">INRAE</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-42804" status="VALID">
          <idno type="anr">ANR-17-CE05-0011</idno>
          <orgName>VIRAME</orgName>
          <desc>Caractérisation in situ du contenu génomique de virus d'archées méthanogènes au sein de bioprocédés de fermentation de déchets organiques</desc>
          <date type="start">2017</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>