<?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-00652903</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="2026-05-03T09:54:16+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Comparative annotation and scaling-out challenges for paraphyletic strategies</title>
            <author role="aut">
              <persName>
                <forename type="first">David James</forename>
                <surname>Sherman</surname>
              </persName>
              <email type="md5">82cf71ec73c088f818e7fad6edb14666</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">david-james-sherman</idno>
              <idno type="idhal" notation="numeric">1356</idno>
              <idno type="halauthorid" notation="string">12133-1356</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-2316-1005</idno>
              <idno type="IDREF">https://www.idref.fr/09147101X</idno>
              <orgName ref="#struct-300009"/>
              <affiliation ref="#struct-3102"/>
              <affiliation ref="#struct-55998"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Natalia</forename>
                <surname>Golenetskaya</surname>
              </persName>
              <idno type="halauthorid">532297-0</idno>
              <orgName ref="#struct-300009"/>
              <affiliation ref="#struct-3102"/>
              <affiliation ref="#struct-55998"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Tiphaine</forename>
                <surname>Martin</surname>
              </persName>
              <email type="md5">0f3a9eb0749fa4205e71b03a0aae6f7e</email>
              <email type="domain">labri.fr</email>
              <idno type="idhal" notation="numeric">928665</idno>
              <idno type="halauthorid" notation="string">40609-928665</idno>
              <affiliation ref="#struct-55998"/>
              <affiliation ref="#struct-388828"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Pascal</forename>
                <surname>Durrens</surname>
              </persName>
              <email type="md5">a0a2273567930587107d598bd8dcc762</email>
              <email type="domain">labri.fr</email>
              <idno type="idhal" notation="string">pascal-durrens</idno>
              <idno type="idhal" notation="numeric">3548</idno>
              <idno type="halauthorid" notation="string">3190-3548</idno>
              <idno type="IDREF">https://www.idref.fr/225317915</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-3948-7106</idno>
              <affiliation ref="#struct-3102"/>
              <affiliation ref="#struct-55998"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>David James</forename>
                <surname>Sherman</surname>
              </persName>
              <email type="md5">522d454709d787a25d2b80b9dff834f5</email>
              <email type="domain">inria.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2011-12-16 15:28:53</date>
              <date type="whenModified">2025-05-26 14:36:02</date>
              <date type="whenReleased">2011-12-16 15:28:53</date>
              <date type="whenProduced">2011-10</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="123988">
                <persName>
                  <forename>David James</forename>
                  <surname>Sherman</surname>
                </persName>
                <email type="md5">522d454709d787a25d2b80b9dff834f5</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00652903</idno>
            <idno type="halUri">https://inria.hal.science/hal-00652903</idno>
            <idno type="halBibtex">sherman:hal-00652903</idno>
            <idno type="halRefHtml">&lt;i&gt;EMBO Symposium on Comparative Genomics of Eukaryotic Microorganisms: Understanding the Complexity of Diversity&lt;/i&gt;, EMBO, Oct 2011, San Feliu de Guixols, Spain</idno>
            <idno type="halRef">EMBO Symposium on Comparative Genomics of Eukaryotic Microorganisms: Understanding the Complexity of Diversity, EMBO, Oct 2011, San Feliu de Guixols, Spain</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="ENSEIRB">Ecole Nationale Supérieure d'Electronique, Informatique et Radiocommunications de Bordeaux</idno>
            <idno type="stamp" n="INRIA-BORDEAUX">INRIA Bordeaux - Sud-Ouest</idno>
            <idno type="stamp" n="LABRI">Laboratoire Bordelais de Recherche en Informatique</idno>
            <idno type="stamp" n="UNIV-BORDEAUX">Université de Bordeaux</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="LABRI-MABIOVIS" corresp="LABRI">Modèles et algorithmes pour la bioinformatique et la visualisation d'informations</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="INRIA-300009">Inria 300009</idno>
            <idno type="stamp" n="UNIVERSITE-BORDEAUX">Université de Bordeaux</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Comparative annotation and scaling-out challenges for paraphyletic strategies</title>
                <author role="aut">
                  <persName>
                    <forename type="first">David James</forename>
                    <surname>Sherman</surname>
                  </persName>
                  <email type="md5">82cf71ec73c088f818e7fad6edb14666</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">david-james-sherman</idno>
                  <idno type="idhal" notation="numeric">1356</idno>
                  <idno type="halauthorid" notation="string">12133-1356</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-2316-1005</idno>
                  <idno type="IDREF">https://www.idref.fr/09147101X</idno>
                  <orgName ref="#struct-300009"/>
                  <affiliation ref="#struct-3102"/>
                  <affiliation ref="#struct-55998"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Natalia</forename>
                    <surname>Golenetskaya</surname>
                  </persName>
                  <idno type="halauthorid">532297-0</idno>
                  <orgName ref="#struct-300009"/>
                  <affiliation ref="#struct-3102"/>
                  <affiliation ref="#struct-55998"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Tiphaine</forename>
                    <surname>Martin</surname>
                  </persName>
                  <email type="md5">0f3a9eb0749fa4205e71b03a0aae6f7e</email>
                  <email type="domain">labri.fr</email>
                  <idno type="idhal" notation="numeric">928665</idno>
                  <idno type="halauthorid" notation="string">40609-928665</idno>
                  <affiliation ref="#struct-55998"/>
                  <affiliation ref="#struct-388828"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Pascal</forename>
                    <surname>Durrens</surname>
                  </persName>
                  <email type="md5">a0a2273567930587107d598bd8dcc762</email>
                  <email type="domain">labri.fr</email>
                  <idno type="idhal" notation="string">pascal-durrens</idno>
                  <idno type="idhal" notation="numeric">3548</idno>
                  <idno type="halauthorid" notation="string">3190-3548</idno>
                  <idno type="IDREF">https://www.idref.fr/225317915</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-3948-7106</idno>
                  <affiliation ref="#struct-3102"/>
                  <affiliation ref="#struct-55998"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>EMBO Symposium on Comparative Genomics of Eukaryotic Microorganisms: Understanding the Complexity of Diversity</title>
                  <date type="start">2011-10</date>
                  <settlement>San Feliu de Guixols</settlement>
                  <country key="ES">Spain</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>EMBO</name>
                </respStmt>
                <imprint>
                  <date type="datePub">2011-10</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">bioinformatics</term>
                <term xml:lang="en">genome annotation</term>
                <term xml:lang="en">databases</term>
                <term xml:lang="en">map-reduce</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-bi">Computer Science [cs]/Bioinformatics [q-bio.QM]</classCode>
              <classCode scheme="halDomain" n="sdv.bibs">Life Sciences [q-bio]/Quantitative Methods [q-bio.QM]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Many challenges accompany new paraphyletic strategies for genome sequencing, where dense sets of closely related species and their strains are analyzed as a group. The data volumes are considerable, and quality of the data can also be less that what these labs have come to expect from genomes produced by traditional sequencing centers. But the principal problem is comparative annotation, which should exploit the comparative nature of the project, and use the comparison between the related species to improve the annotation process. Drawing on a number of large-scale comparative genomics projects we have developed over the past twelve years, we will illustrate these challenges, and extrapolate the needs of collaborative, robust, comparative methods for this kind of multi-genome project.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-3102" status="VALID">
          <idno type="IdRef">155054465</idno>
          <idno type="ISNI">0000000122898198</idno>
          <idno type="RNSR">199511665F</idno>
          <idno type="ROR">https://ror.org/03adqg323</idno>
          <idno type="Wikidata">Q3214395</idno>
          <orgName>Laboratoire Bordelais de Recherche en Informatique</orgName>
          <orgName type="acronym">LaBRI</orgName>
          <date type="start">1988-01-01</date>
          <desc>
            <address>
              <addrLine>Domaine Universitaire 351, cours de la Libération 33405 Talence Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.labri.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-259761" type="direct"/>
            <relation active="#struct-300366" type="direct"/>
            <relation name="UMR5800 / URA1304" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-55998" status="OLD">
          <idno type="RNSR">200919004X</idno>
          <orgName>Models and Algorithms for the Genome</orgName>
          <orgName type="acronym">MAGNOME</orgName>
          <date type="start">2009-07-01</date>
          <date type="end">2014-12-31</date>
          <desc>
            <address>
              <addrLine>Inria Bordeaux</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-104751" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-259761" type="direct"/>
            <relation name="UMR5800" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-388828" status="VALID">
          <orgName>Modèles et algorithmes pour la Bioinformatique et la Visualisation d'informations;</orgName>
          <orgName type="acronym">MABIOVIS</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-3102" type="direct"/>
            <relation active="#struct-259761" type="indirect"/>
            <relation active="#struct-300366" type="indirect"/>
            <relation name="UMR5800 / URA1304" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-259761" status="VALID">
          <idno type="IdRef">175206562</idno>
          <idno type="ROR">https://ror.org/057qpr032</idno>
          <orgName>Université de Bordeaux</orgName>
          <orgName type="acronym">UB</orgName>
          <desc>
            <address>
              <addrLine>35, place Pey Berland - 33076 Bordeaux</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.u-bordeaux.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300366" status="VALID">
          <orgName>École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </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="laboratory" xml:id="struct-104751" status="VALID">
          <idno type="RNSR">200818243Z</idno>
          <idno type="ROR">https://ror.org/03tjcj052</idno>
          <orgName>Centre Inria de l'Université de Bordeaux</orgName>
          <desc>
            <address>
              <addrLine>200, avenue de la Vieille Tour, 33405 Talence</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/bordeaux/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>