<?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-01955978</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="2026-04-29T08:49:30+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Construction of a de Bruijn Graph for Assembly from a Truncated Suffix Tree</title>
            <author role="aut">
              <persName>
                <forename type="first">Bastien</forename>
                <surname>Cazaux</surname>
              </persName>
              <email type="md5">9801dd5f380a8ef2148c88eb68f25fc8</email>
              <email type="domain">lirmm.fr</email>
              <idno type="idhal" notation="string">cazaux-bastien</idno>
              <idno type="idhal" notation="numeric">3129</idno>
              <idno type="halauthorid" notation="string">23494-3129</idno>
              <idno type="IDREF">https://www.idref.fr/226877523</idno>
              <affiliation ref="#struct-388224"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Thierry</forename>
                <surname>Lecroq</surname>
              </persName>
              <email type="md5">73a06c28c0c1674df8a2929677efdf11</email>
              <email type="domain">univ-rouen.fr</email>
              <idno type="idhal" notation="string">thierry-lecroq</idno>
              <idno type="idhal" notation="numeric">21817</idno>
              <idno type="halauthorid" notation="string">10003-21817</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1900-3397</idno>
              <idno type="IDREF">https://www.idref.fr/059058463</idno>
              <affiliation ref="#struct-525290"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Eric</forename>
                <surname>Rivals</surname>
              </persName>
              <email type="md5">2948fa0e637f8fdead28884bcc311d7f</email>
              <email type="domain">lirmm.fr</email>
              <idno type="idhal" notation="string">eric-rivals</idno>
              <idno type="idhal" notation="numeric">2002</idno>
              <idno type="halauthorid" notation="string">23559-2002</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-3791-3973</idno>
              <idno type="IDREF">https://www.idref.fr/118021850</idno>
              <affiliation ref="#struct-388224"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Thierry</forename>
                <surname>Lecroq</surname>
              </persName>
              <email type="md5">73a06c28c0c1674df8a2929677efdf11</email>
              <email type="domain">univ-rouen.fr</email>
            </editor>
            <funder ref="#projanr-23506"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2019-01-14 18:15:54</date>
              <date type="whenModified">2025-11-13 16:30:08</date>
              <date type="whenReleased">2020-10-07 08:31:04</date>
              <date type="whenProduced">2015-03-02</date>
              <date type="whenEndEmbargoed">2020-10-05</date>
              <ref type="file" target="https://hal.science/hal-01955978v1/document">
                <date notBefore="2020-10-05"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-01955978v1/file/lata2015-1.pdf" id="file-2957709-2606649">
                <date notBefore="2020-10-05"/>
              </ref>
              <ref type="annex" n="0" target="https://hal.science/hal-01955978v1/file/presentation-lata15-03.pdf" id="file-2957709-2606650">
                <date notBefore="2019-01-14"/>
              </ref>
              <ref type="externalLink" target="http://www-igm.univ-mlv.fr/%7Elecroq/articles/lata2015-1.pdf"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="495076">
                <persName>
                  <forename>Thierry</forename>
                  <surname>Lecroq</surname>
                </persName>
                <email type="md5">73a06c28c0c1674df8a2929677efdf11</email>
                <email type="domain">univ-rouen.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01955978</idno>
            <idno type="halUri">https://hal.science/hal-01955978</idno>
            <idno type="halBibtex">cazaux:hal-01955978</idno>
            <idno type="halRefHtml">&lt;i&gt;LATA: Language and Automata Theory and Applications&lt;/i&gt;, Mar 2015, Nice, France. pp.109-120, &lt;a target="_blank" href="https://dx.doi.org/10.1007/978-3-319-15579-1_8"&gt;&amp;#x27E8;10.1007/978-3-319-15579-1_8&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">LATA: Language and Automata Theory and Applications, Mar 2015, Nice, France. pp.109-120, &amp;#x27E8;10.1007/978-3-319-15579-1_8&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2957709-2606649"/><ref corresp="#file-2957709-2606650"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INSA-ROUEN">Institut National des Sciences Appliquées de Rouen</idno>
            <idno type="stamp" n="LITIS">Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes</idno>
            <idno type="stamp" n="MAB" corresp="LIRMM">Méthodes et Algorithmes pour la Bioinformatique</idno>
            <idno type="stamp" n="LIRMM">Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier</idno>
            <idno type="stamp" n="COMUE-NORMANDIE">Normandie Université</idno>
            <idno type="stamp" n="MIPS">Mathématiques, Informatique, Physique et Systèmes</idno>
            <idno type="stamp" n="UNIV-MONTPELLIER">Université de Montpellier</idno>
            <idno type="stamp" n="UNIROUEN">Université de Rouen Normandie</idno>
            <idno type="stamp" n="UNILEHAVRE">Université Le Havre Normandie</idno>
            <idno type="stamp" n="INSA-GROUPE">Groupe INSA</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="UM-2015-2021" corresp="UNIV-MONTPELLIER">Université de Montpellier (2015-2021)</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">Construction of a de Bruijn Graph for Assembly from a Truncated Suffix Tree</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Bastien</forename>
                    <surname>Cazaux</surname>
                  </persName>
                  <email type="md5">9801dd5f380a8ef2148c88eb68f25fc8</email>
                  <email type="domain">lirmm.fr</email>
                  <idno type="idhal" notation="string">cazaux-bastien</idno>
                  <idno type="idhal" notation="numeric">3129</idno>
                  <idno type="halauthorid" notation="string">23494-3129</idno>
                  <idno type="IDREF">https://www.idref.fr/226877523</idno>
                  <affiliation ref="#struct-388224"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Thierry</forename>
                    <surname>Lecroq</surname>
                  </persName>
                  <email type="md5">73a06c28c0c1674df8a2929677efdf11</email>
                  <email type="domain">univ-rouen.fr</email>
                  <idno type="idhal" notation="string">thierry-lecroq</idno>
                  <idno type="idhal" notation="numeric">21817</idno>
                  <idno type="halauthorid" notation="string">10003-21817</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1900-3397</idno>
                  <idno type="IDREF">https://www.idref.fr/059058463</idno>
                  <affiliation ref="#struct-525290"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Eric</forename>
                    <surname>Rivals</surname>
                  </persName>
                  <email type="md5">2948fa0e637f8fdead28884bcc311d7f</email>
                  <email type="domain">lirmm.fr</email>
                  <idno type="idhal" notation="string">eric-rivals</idno>
                  <idno type="idhal" notation="numeric">2002</idno>
                  <idno type="halauthorid" notation="string">23559-2002</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-3791-3973</idno>
                  <idno type="IDREF">https://www.idref.fr/118021850</idno>
                  <affiliation ref="#struct-388224"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">9th International Conference on Language and Automata Theory and Applications</title>
                <meeting>
                  <title>LATA: Language and Automata Theory and Applications</title>
                  <date type="start">2015-03-02</date>
                  <date type="end">2015-03-06</date>
                  <settlement>Nice</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint>
                  <biblScope unit="volume">LNCS</biblScope>
                  <biblScope unit="issue">8977</biblScope>
                  <biblScope unit="pp">109-120</biblScope>
                  <date type="datePub">2015-02-24</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/978-3-319-15579-1_8</idno>
              <ref type="publisher">http://grammars.grlmc.com/LATA2015/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Dynamic Update</term>
                <term xml:lang="en">Space Complexity</term>
                <term xml:lang="en">Assembly</term>
                <term xml:lang="en">de Bruijn Graph</term>
                <term xml:lang="en">Data Structures</term>
                <term xml:lang="en">Text Algorithms</term>
                <term xml:lang="en">Stringology</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halDomain" n="info.info-ds">Computer Science [cs]/Data Structures and Algorithms [cs.DS]</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>In the life sciences, determining the sequence of bio-molecules is essential step towards the understanding of their functions and interactions inside an organism. Powerful technologies allows to get huge quantities of short sequencing reads that need to be assemble to infer the complete target sequence. These constraints favour the use of a version de Bruijn Graph (DBG) dedicated to assembly. The de Bruijn Graph is usually built directly from the reads, which is time and space consuming. Given a set R of input words, well-known data structures, like the generalised suffix tree, can index all the substrings of words in R. In the context of DBG assembly, only substrings of length k + 1 and some of length k are useful. A truncated version of the suffix tree can index those efficiently. As indexes are exploited for numerous purposes in bioinformatics, as read cleaning, filtering, or even analysis, it is important to enable the community to reuse an existing index to build the DBG directly from it. In an earlier work we provided the first algorithms when starting from a suffix tree or suffix array. Here, we exhibit an algorithm that exploits a reduced version of the truncated suffix tree and computes the DBG from it. Importantly, a variation of this algorithm is also shown to compute the contracted DBG, which offers great benefits in practice. Both algorithms are linear in time and space in the size of the output.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-388224" status="OLD">
          <orgName>Méthodes et Algorithmes pour la Bioinformatique</orgName>
          <orgName type="acronym">MAB</orgName>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <addrLine>LIRMM, 161 rue Ada, 34000 Montpellier</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.lirmm.fr/equipes/MAB/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-181" type="direct"/>
            <relation name="UMR5506" active="#struct-410122" type="indirect"/>
            <relation name="UMR5506" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-525290" status="OLD">
          <orgName>Equipe Traitement de l'information en Biologie Santé</orgName>
          <orgName type="acronym">LITIS - TIBS</orgName>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.litislab.fr/equipe/tibs/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-23832" type="direct"/>
            <relation active="#struct-300317" type="indirect"/>
            <relation active="#struct-455934" type="indirect"/>
            <relation name="EA4108" active="#struct-300318" type="indirect"/>
            <relation active="#struct-301288" type="indirect"/>
            <relation active="#struct-301232" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-181" status="OLD">
          <idno type="IdRef">139590827</idno>
          <idno type="ISNI">0000000405990488</idno>
          <idno type="RNSR">199111950H</idno>
          <idno type="ROR">https://ror.org/013yean28</idno>
          <orgName>Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier</orgName>
          <orgName type="acronym">LIRMM</orgName>
          <date type="start">1995-01-01</date>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <addrLine>161 rue Ada - 34095 Montpellier</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.lirmm.fr</ref>
          </desc>
          <listRelation>
            <relation name="UMR5506" active="#struct-410122" type="direct"/>
            <relation name="UMR5506" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-410122" status="OLD">
          <idno type="ISNI">0000000120970141</idno>
          <idno type="ROR">https://ror.org/051escj72</idno>
          <orgName>Université de Montpellier</orgName>
          <orgName type="acronym">UM</orgName>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <addrLine>163 rue Auguste Broussonnet - 34090 Montpellier</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.umontpellier.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-23832" status="OLD">
          <idno type="IdRef">110731867</idno>
          <idno type="RNSR">200615352R</idno>
          <orgName>Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes</orgName>
          <orgName type="acronym">LITIS</orgName>
          <date type="start">2006-01-01</date>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <addrLine>Avenue de l'Université 76800 Saint-Étienne-du-Rouvray</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.litislab.eu</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300317" type="direct"/>
            <relation active="#struct-455934" type="indirect"/>
            <relation name="EA4108" active="#struct-300318" type="direct"/>
            <relation active="#struct-301288" type="direct"/>
            <relation active="#struct-301232" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300317" status="VALID">
          <idno type="IdRef">031308570</idno>
          <idno type="ISNI">0000000121731046</idno>
          <idno type="ROR">https://ror.org/05v509s40</idno>
          <orgName>Université Le Havre Normandie</orgName>
          <orgName type="acronym">ULH</orgName>
          <date type="start">1984-08-27</date>
          <desc>
            <address>
              <addrLine>25 rue Philippe Lebon - BP 1123 - 76063 Le Havre Cedex France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-lehavre.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-455934" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-455934" status="VALID">
          <idno type="IdRef">190906332</idno>
          <idno type="ISNI">0000000417859671 </idno>
          <idno type="ROR">https://ror.org/01k40cz91</idno>
          <orgName>Normandie Université</orgName>
          <orgName type="acronym">NU</orgName>
          <date type="start">2015-01-01</date>
          <desc>
            <address>
              <addrLine>Esplanade de la Paix - CS 14032 - 14032 Caen Cedex 5</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.normandie-univ.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300318" status="VALID">
          <idno type="IdRef">026403919</idno>
          <idno type="ISNI">0000000121083034</idno>
          <idno type="ROR">https://ror.org/03nhjew95</idno>
          <orgName>Université de Rouen Normandie</orgName>
          <orgName type="acronym">UNIROUEN</orgName>
          <date type="start">1966-01-01</date>
          <desc>
            <address>
              <addrLine>1, rue Thomas Becket 76821 Mont-Saint-Aignan Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-rouen.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-455934" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-301288" status="VALID">
          <idno type="IdRef">033364346</idno>
          <idno type="ISNI">0000000121908462</idno>
          <idno type="ROR">https://ror.org/020ws7586</idno>
          <orgName>Institut national des sciences appliquées Rouen Normandie</orgName>
          <orgName type="acronym">INSA Rouen Normandie</orgName>
          <date type="start">1985-01-01</date>
          <desc>
            <address>
              <addrLine>Avenue de l’Université 76801 Saint-Étienne-du-Rouvray Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.insa-rouen.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301232" type="direct"/>
            <relation active="#struct-455934" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301232" status="VALID">
          <idno type="IdRef">162105150</idno>
          <orgName>Institut National des Sciences Appliquées</orgName>
          <orgName type="acronym">INSA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-23506" status="VALID">
          <idno type="anr">ANR-12-BS02-0008</idno>
          <idno type="program">BLANC</idno>
          <orgName>Colib'read</orgName>
          <desc>Méthodes d'extraction d'information biologique dans les données HTS non assemblées</desc>
          <date type="start">2012</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>