<?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 inria-00448741</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="2026-05-14T03:25:23+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Back-translation for discovering distant protein homologies</title>
            <author role="aut">
              <persName>
                <forename type="first">Marta</forename>
                <forename type="middle">L.</forename>
                <surname>Gîrdea</surname>
              </persName>
              <email type="md5">2604ac2e4b42c68f4bafde72802cc5fb</email>
              <email type="domain">ed.univ-lille1.fr</email>
              <idno type="idhal" notation="numeric">866290</idno>
              <idno type="halauthorid" notation="string">437578-866290</idno>
              <affiliation ref="#struct-2546"/>
              <affiliation ref="#struct-56017"/>
            </author>
            <author role="crp">
              <persName>
                <forename type="first">Laurent</forename>
                <surname>Noé</surname>
              </persName>
              <email type="md5">c1a17645cacd9dce632a26ae18ed3e95</email>
              <email type="domain">univ-lille.fr</email>
              <idno type="idhal" notation="string">noe</idno>
              <idno type="idhal" notation="numeric">85</idno>
              <idno type="halauthorid" notation="string">27907-85</idno>
              <idno type="ARXIV">https://arxiv.org/a/noe_l_1</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1170-8376</idno>
              <idno type="GOOGLE SCHOLAR">http://scholar.google.fr/citations?user=G9j_QA4AAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/093601948</idno>
              <affiliation ref="#struct-2546"/>
              <affiliation ref="#struct-56017"/>
            </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-2546"/>
              <affiliation ref="#struct-56017"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Laurent</forename>
                <surname>Noé</surname>
              </persName>
              <email type="md5">c1a17645cacd9dce632a26ae18ed3e95</email>
              <email type="domain">univ-lille.fr</email>
            </editor>
            <funder ref="#projanr-28531"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2010-01-25 21:43:54</date>
              <date type="whenModified">2025-02-26 15:33:49</date>
              <date type="whenReleased">2010-01-26 08:27:39</date>
              <date type="whenProduced">2009-09</date>
              <date type="whenEndEmbargoed">2010-01-25</date>
              <ref type="file" target="https://inria.hal.science/inria-00448741v1/document">
                <date notBefore="2010-01-25"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://inria.hal.science/inria-00448741v1/file/patharticle.pdf" id="file-448741-378592">
                <date notBefore="2010-01-25"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/1001.4603"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="108724">
                <persName>
                  <forename>Laurent</forename>
                  <surname>Noé</surname>
                </persName>
                <email type="md5">c1a17645cacd9dce632a26ae18ed3e95</email>
                <email type="domain">univ-lille.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">inria-00448741</idno>
            <idno type="halUri">https://inria.hal.science/inria-00448741</idno>
            <idno type="halBibtex">girdea:inria-00448741</idno>
            <idno type="halRefHtml">&lt;i&gt;the 9th International Workshop in Algorithms in Bioinformatics (WABI)&lt;/i&gt;, Sep 2009, Philadelphia, United States. pp.108-120, &lt;a target="_blank" href="https://dx.doi.org/10.1007/978-3-642-04241-6_10"&gt;&amp;#x27E8;10.1007/978-3-642-04241-6_10&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">the 9th International Workshop in Algorithms in Bioinformatics (WABI), Sep 2009, Philadelphia, United States. pp.108-120, &amp;#x27E8;10.1007/978-3-642-04241-6_10&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-448741-378592"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-LILLE3">Université de Lille Sciences humaines et sociales</idno>
            <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="INRIA-LILLE">INRIA Lille - Nord Europe</idno>
            <idno type="stamp" n="LIFL">Laboratoire d'Informatique Fondamentale de Lille</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="CV_LIGM" corresp="CV_UNIV-MLV">CV des membres du LIGM</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="CRISTAL">Centre de Recherche en Informatique, Signal et Automatique de Lille (CRISTAL)</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="CRISTAL-BONSAI" corresp="CRISTAL">CRISTAL-BONSAI</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="TEST3-HALCNRS">TEST3-HALCNRS</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="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Back-translation for discovering distant protein homologies</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Marta</forename>
                    <forename type="middle">L.</forename>
                    <surname>Gîrdea</surname>
                  </persName>
                  <email type="md5">2604ac2e4b42c68f4bafde72802cc5fb</email>
                  <email type="domain">ed.univ-lille1.fr</email>
                  <idno type="idhal" notation="numeric">866290</idno>
                  <idno type="halauthorid" notation="string">437578-866290</idno>
                  <affiliation ref="#struct-2546"/>
                  <affiliation ref="#struct-56017"/>
                </author>
                <author role="crp">
                  <persName>
                    <forename type="first">Laurent</forename>
                    <surname>Noé</surname>
                  </persName>
                  <email type="md5">c1a17645cacd9dce632a26ae18ed3e95</email>
                  <email type="domain">univ-lille.fr</email>
                  <idno type="idhal" notation="string">noe</idno>
                  <idno type="idhal" notation="numeric">85</idno>
                  <idno type="halauthorid" notation="string">27907-85</idno>
                  <idno type="ARXIV">https://arxiv.org/a/noe_l_1</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1170-8376</idno>
                  <idno type="GOOGLE SCHOLAR">http://scholar.google.fr/citations?user=G9j_QA4AAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/093601948</idno>
                  <affiliation ref="#struct-2546"/>
                  <affiliation ref="#struct-56017"/>
                </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-2546"/>
                  <affiliation ref="#struct-56017"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>the 9th International Workshop in Algorithms in Bioinformatics (WABI)</title>
                  <date type="start">2009-09</date>
                  <settlement>Philadelphia</settlement>
                  <country key="US">United States</country>
                </meeting>
                <imprint>
                  <biblScope unit="serie">Proceedings of the 9th International Workshop in Algorithms in Bioinformatics</biblScope>
                  <biblScope unit="volume">5724</biblScope>
                  <biblScope unit="pp">108-120</biblScope>
                  <date type="datePub">2009</date>
                </imprint>
              </monogr>
              <idno type="arxiv">1001.4603</idno>
              <idno type="doi">10.1007/978-3-642-04241-6_10</idno>
              <ref target="http://www.lifl.fr/~noe/files/pp_WABI09.pdf" type="seeAlso"/>
              <ref type="publisher">http://www.springerlink.com/content/3236004m84465n7j/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Back translation</term>
                <term xml:lang="en">Protein Alignment</term>
                <term xml:lang="en">Protein Comparison</term>
                <term xml:lang="en">Frame-shift</term>
              </keywords>
              <classCode scheme="acm" n="J.3.0">J.: Computer Applications/J.3: LIFE AND MEDICAL SCIENCES/J.3.0: Biology and genetics</classCode>
              <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>Frameshift mutations in protein-coding DNA sequences produce a drastic change in the resulting protein sequence, which prevents classic protein alignment methods from revealing the proteins' common origin. Moreover, when a large number of substitutions are additionally involved in the divergence, the homology detection becomes difficult even at the DNA level. To cope with this situation, we propose a novel method to infer distant homology relations of two proteins, that accounts for frameshift and point mutations that may have affected the coding sequences. We design a dynamic programming alignment algorithm over memory-efficient graph representations of the complete set of putative DNA sequences of each protein, with the goal of determining the two putative DNA sequences which have the best scoring alignment under a powerful scoring system designed to reflect the most probable evolutionary process. This allows us to uncover evolutionary information that is not captured by traditional alignment methods, which is confirmed by biologically significant examples.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-2546" status="OLD">
          <orgName>Laboratoire d'Informatique Fondamentale de Lille</orgName>
          <orgName type="acronym">LIFL</orgName>
          <desc>
            <address>
              <addrLine>Bâtiment M3 59655 Villeneuve d'Ascq Cédex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lifl.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-92973" type="direct"/>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-301700" type="direct"/>
            <relation name="UMR8022" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-56017" status="OLD">
          <idno type="RNSR">200718281V</idno>
          <orgName>Sequential Learning</orgName>
          <orgName type="acronym">SEQUOIA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/sequoia</ref>
          </desc>
          <listRelation>
            <relation active="#struct-2546" type="direct"/>
            <relation active="#struct-92973" type="indirect"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-301700" type="indirect"/>
            <relation name="UMR8022" active="#struct-441569" type="indirect"/>
            <relation active="#struct-104752" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-92973" status="OLD">
          <idno type="IdRef">026404184</idno>
          <idno type="ROR">https://ror.org/0546v5182</idno>
          <orgName>Université de Lille, Sciences et Technologies</orgName>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>Cité Scientifique - 59655 Villeneuve d'Ascq Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lille1.fr/</ref>
          </desc>
        </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>
        <org type="institution" xml:id="struct-301700" status="OLD">
          <idno type="IdRef">026404524</idno>
          <idno type="ISNI">0000000121517701</idno>
          <idno type="ROR">https://ror.org/025b4c754</idno>
          <orgName>Université de Lille, Sciences Humaines et Sociales</orgName>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>Domaine universitaire du "Pont de Bois"Rue du Barreau BP 60149 59653 Villeneuve d'Ascq Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lille3.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="laboratory" xml:id="struct-104752" status="VALID">
          <idno type="RNSR">200818245B</idno>
          <idno type="ROR">https://ror.org/04eej9726</idno>
          <orgName>Centre Inria de l'Université de Lille</orgName>
          <desc>
            <address>
              <addrLine>Parc Scientifique de la Haute Borne 40, avenue Halley Bât.A, Park Plaza 59650 Villeneuve d'Ascq</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/lille/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-28531" status="VALID">
          <idno type="anr">ANR-07-BLAN-0367</idno>
          <idno type="program">Blanc</idno>
          <orgName>FLASH</orgName>
          <desc>Comparison of Complete Genomes: an algorithmic and statistical approach to investigate the mechanisms of bacterial genome evolution</desc>
          <date type="start">2007</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>