<?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-05375444</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="2026-05-15T11:06:00+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">De-Bruijn graph partitioning for scalable and accurate DNA storage processing</title>
            <author role="aut">
              <persName>
                <forename type="first">Florestan</forename>
                <surname>de Moor</surname>
              </persName>
              <email type="md5">bc7a5fcaa31c94db7bd4e30961b2d013</email>
              <email type="domain">ens-rennes.fr</email>
              <idno type="idhal" notation="string">florestan-de-moor</idno>
              <idno type="idhal" notation="numeric">179471</idno>
              <idno type="halauthorid" notation="string">39851-179471</idno>
              <affiliation ref="#struct-491655"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Olivier</forename>
                <surname>Boullé</surname>
              </persName>
              <email type="md5">8a351d74190bf0e6674d3458cc4cb4d9</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="numeric">1175243</idno>
              <idno type="halauthorid" notation="string">2613476-1175243</idno>
              <affiliation ref="#struct-491655"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Dominique</forename>
                <surname>Lavenier</surname>
              </persName>
              <email type="md5">92982e780b88c8e8bdbaf33561e3a6e7</email>
              <email type="domain">irisa.fr</email>
              <idno type="idhal" notation="string">dominique-lavenier</idno>
              <idno type="idhal" notation="numeric">1401</idno>
              <idno type="halauthorid" notation="string">19677-1401</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-2557-680X</idno>
              <affiliation ref="#struct-491655"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Dominique</forename>
                <surname>Lavenier</surname>
              </persName>
              <email type="md5">92982e780b88c8e8bdbaf33561e3a6e7</email>
              <email type="domain">irisa.fr</email>
            </editor>
            <funder ref="#projanr-69604"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-11-20 17:57:19</date>
              <date type="whenModified">2026-01-23 09:12:07</date>
              <date type="whenReleased">2025-11-20 18:59:25</date>
              <date type="whenProduced">2025-11-01</date>
              <date type="whenEndEmbargoed">2025-11-20</date>
              <ref type="file" target="https://hal.science/hal-05375444v1/document">
                <date notBefore="2025-11-20"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-05375444v1/file/btaf618.pdf" id="file-5375444-4598515">
                <date notBefore="2025-11-20"/>
              </ref>
              <ref type="annex" n="0" target="https://hal.science/hal-05375444v1/file/btaf618_supplementary_data.pdf" id="file-5375444-4598516">
                <date notBefore="2025-11-20"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="102250">
                <persName>
                  <forename>Dominique</forename>
                  <surname>Lavenier</surname>
                </persName>
                <email type="md5">92982e780b88c8e8bdbaf33561e3a6e7</email>
                <email type="domain">irisa.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05375444</idno>
            <idno type="halUri">https://hal.science/hal-05375444</idno>
            <idno type="halBibtex">demoor:hal-05375444</idno>
            <idno type="halRefHtml">&lt;i&gt;Bioinformatics&lt;/i&gt;, 2025, 41 (11), pp.1-9. &lt;a target="_blank" href="https://dx.doi.org/10.1093/bioinformatics/btaf618"&gt;&amp;#x27E8;10.1093/bioinformatics/btaf618&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Bioinformatics, 2025, 41 (11), pp.1-9. &amp;#x27E8;10.1093/bioinformatics/btaf618&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-5375444-4598515"/><ref corresp="#file-5375444-4598516"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-RENNES1">Université de Rennes 1</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="UNIV-UBS">Université de Bretagne Sud</idno>
            <idno type="stamp" n="INSA-RENNES">Institut National des Sciences Appliquées de Rennes</idno>
            <idno type="stamp" n="INRIA-RENNES">INRIA Rennes - Bretagne Atlantique</idno>
            <idno type="stamp" n="IRISA">Irisa</idno>
            <idno type="stamp" n="IRISA_SET">IRISA_SET</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="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="UR1-HAL">Publications labos UR1 dans HAL-Rennes 1</idno>
            <idno type="stamp" n="UR1-MATH-STIC">UR1 - publications Maths-STIC</idno>
            <idno type="stamp" n="UR1-UFR-ISTIC">UFR ISTIC Informatique et électronique</idno>
            <idno type="stamp" n="TEST-UR-CSS">TEST Université de Rennes CSS</idno>
            <idno type="stamp" n="UNIV-RENNES">Université de Rennes</idno>
            <idno type="stamp" n="INRIA-RENGRE">INRIA-RENGRE</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="UR1-MATH-NUM">Pôle UnivRennes - Mathématiques - Numérique </idno>
            <idno type="stamp" n="MOLECULARXIV">PEPR Molecularxiv</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">De-Bruijn graph partitioning for scalable and accurate DNA storage processing</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Florestan</forename>
                    <surname>de Moor</surname>
                  </persName>
                  <email type="md5">bc7a5fcaa31c94db7bd4e30961b2d013</email>
                  <email type="domain">ens-rennes.fr</email>
                  <idno type="idhal" notation="string">florestan-de-moor</idno>
                  <idno type="idhal" notation="numeric">179471</idno>
                  <idno type="halauthorid" notation="string">39851-179471</idno>
                  <affiliation ref="#struct-491655"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Olivier</forename>
                    <surname>Boullé</surname>
                  </persName>
                  <email type="md5">8a351d74190bf0e6674d3458cc4cb4d9</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="numeric">1175243</idno>
                  <idno type="halauthorid" notation="string">2613476-1175243</idno>
                  <affiliation ref="#struct-491655"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Dominique</forename>
                    <surname>Lavenier</surname>
                  </persName>
                  <email type="md5">92982e780b88c8e8bdbaf33561e3a6e7</email>
                  <email type="domain">irisa.fr</email>
                  <idno type="idhal" notation="string">dominique-lavenier</idno>
                  <idno type="idhal" notation="numeric">1401</idno>
                  <idno type="halauthorid" notation="string">19677-1401</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-2557-680X</idno>
                  <affiliation ref="#struct-491655"/>
                </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>
                  <biblScope unit="volume">41</biblScope>
                  <biblScope unit="issue">11</biblScope>
                  <biblScope unit="pp">1-9</biblScope>
                  <date type="datePub">2025-11-01</date>
                  <date type="dateEpub">2025-11-09</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1093/bioinformatics/btaf618</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">bioinformatics</term>
                <term xml:lang="en">Consensus</term>
                <term xml:lang="en">Clustering</term>
                <term xml:lang="en">DNA Storage</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</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>Abstract Motivation DNA-based data storage offers a compelling solution for long-term, high-density archiving. In this framework, accurately reconstructing high-quality encoded sequences after sequencing is critical, as it directly impacts the design of error-correcting codes optimized for DNA storage. Furthermore, efficient and scalable processing is essential to manage the large volumes of data expected in such applications. Results We introduce a novel method based on de-Bruijn graph partitioning, enabling fast and accurate processing of sequencing data regardless of the underlying sequencing technology and without requiring prior knowledge of the information encoded in the oligonucleotides. Evaluated on both synthetic and real datasets, the method achieves excellent precision and recall. It is implemented in C++ within the software ConCluD and optimized for multi-core servers. Our experiments show that a dataset of 89 million reads, corresponding to a 10 GB fasta file, can be fully processed in less than a minute on a standard 32-cores server. Availability and implementation The ConCluD software and the scripts to reproduce the experiments from this paper are available at https://gitlab.inria.fr/pim/org.pim.dnarxiv under the GNU AGPLv3 licence. An archival snapshot of the repository is also provided at https://doi.org/10.5281/zenodo.17160067.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-491655" status="VALID">
          <idno type="RNSR">201221037U</idno>
          <idno type="ROR">https://ror.org/00rttk466</idno>
          <orgName>Scalable, Optimized and Parallel Algorithms for Genomics</orgName>
          <orgName type="acronym">GenScale</orgName>
          <date type="start">2013-01-01</date>
          <date type="end">2029-02-28</date>
          <desc>
            <address>
              <addrLine>Campus de Beaulieu 35042 Rennes cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.inria.fr/equipes/genscale</ref>
          </desc>
          <listRelation>
            <relation active="#struct-419153" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-491231" type="direct"/>
            <relation active="#struct-490899" type="indirect"/>
            <relation active="#struct-105160" type="indirect"/>
            <relation active="#struct-117606" type="indirect"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation active="#struct-172265" type="indirect"/>
            <relation active="#struct-247362" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation name="UMR6074" active="#struct-441569" type="indirect"/>
            <relation active="#struct-481355" type="indirect"/>
            <relation active="#struct-302102" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-419153" status="VALID">
          <idno type="RNSR">198018249C</idno>
          <idno type="ROR">https://ror.org/04040yw90</idno>
          <orgName>Centre Inria de l'Université de Rennes</orgName>
          <desc>
            <address>
              <addrLine>Campus de beaulieu35042 Rennes cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/rennes</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>
        <org type="department" xml:id="struct-491231" status="VALID">
          <orgName>GESTION DES DONNÉES ET DE LA CONNAISSANCE</orgName>
          <orgName type="acronym">IRISA-D7</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.irisa.fr/fr/departements/d7-gestion-donnees-connaissance</ref>
          </desc>
          <listRelation>
            <relation active="#struct-490899" type="direct"/>
            <relation active="#struct-105160" type="indirect"/>
            <relation active="#struct-117606" type="indirect"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation active="#struct-172265" type="indirect"/>
            <relation active="#struct-247362" type="indirect"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation name="UMR6074" active="#struct-441569" type="indirect"/>
            <relation active="#struct-481355" type="indirect"/>
            <relation active="#struct-302102" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-490899" status="VALID">
          <idno type="IdRef">026386909</idno>
          <idno type="ISNI">0000 0001 2298 7270</idno>
          <idno type="RNSR">200012163A</idno>
          <idno type="ROR">https://ror.org/00myn0z94</idno>
          <orgName>Institut de Recherche en Informatique et Systèmes Aléatoires</orgName>
          <orgName type="acronym">IRISA</orgName>
          <date type="start">2017-01-01</date>
          <desc>
            <address>
              <addrLine>Avenue du général LeclercCampus de Beaulieu 35042 RENNES CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.irisa.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-105160" type="direct"/>
            <relation active="#struct-117606" type="direct"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation active="#struct-172265" type="direct"/>
            <relation active="#struct-247362" type="direct"/>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation name="UMR6074" active="#struct-441569" type="direct"/>
            <relation active="#struct-481355" type="direct"/>
            <relation active="#struct-302102" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-105160" status="VALID">
          <idno type="IdRef">26693823X</idno>
          <idno type="ROR">https://ror.org/015m7wh34</idno>
          <orgName>Université de Rennes</orgName>
          <orgName type="acronym">UR</orgName>
          <desc>
            <address>
              <addrLine>Campus de Beaulieu, 263 avenue Général Leclerc, CS 74205, 35042 RENNES CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-rennes.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-117606" status="VALID">
          <idno type="ROR">https://ror.org/04xaa4j22</idno>
          <orgName>Institut National des Sciences Appliquées - Rennes</orgName>
          <orgName type="acronym">INSA Rennes</orgName>
          <desc>
            <address>
              <addrLine>20, avenue des Buttes de Coësmes - CS 70839 - 35708 Rennes cedex 7</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.insa-rennes.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301232" 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>
        <org type="institution" xml:id="struct-172265" status="VALID">
          <idno type="IdRef">05017746X</idno>
          <idno type="ISNI">0000000121680285</idno>
          <idno type="ROR">https://ror.org/04ed7fw48</idno>
          <orgName>Université de Bretagne Sud</orgName>
          <orgName type="acronym">UBS</orgName>
          <date type="start">1995-02-07</date>
          <desc>
            <address>
              <addrLine>BP 92116 - 56321 Lorient cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-ubs.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-247362" status="VALID">
          <idno type="ROR">https://ror.org/03rxtdc22</idno>
          <orgName>École normale supérieure - Rennes</orgName>
          <orgName type="acronym">ENS Rennes</orgName>
          <desc>
            <address>
              <addrLine>Campus de Ker Lann - avenue Robert Schuman - 35170 Bruz</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ens-rennes.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-411575" status="VALID">
          <idno type="IdRef">184443237</idno>
          <idno type="ROR">https://ror.org/019tcpt25</idno>
          <orgName>CentraleSupélec</orgName>
          <desc>
            <address>
              <addrLine>3, rue Joliot Curie,Plateau de Moulon,91192 GIF-SUR-YVETTE Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.centralesupelec.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-481355" status="VALID">
          <idno type="IdRef">202743233</idno>
          <idno type="ROR">https://ror.org/030hj3061</idno>
          <orgName>IMT Atlantique</orgName>
          <orgName type="acronym">IMT Atlantique</orgName>
          <date type="start">2017-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Brest : Technopôle Brest-Iroise CS 8381829238 BREST Cedex 3 -Campus Nantes : 4, rue Alfred Kastler- La chantrerie 44300 NANTES -Campus Rennes :  2 Rue de la Châtaigneraie, 35510 CESSON SEVIGNE</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.imt-atlantique.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-302102" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-302102" status="VALID">
          <idno type="IdRef">192427156</idno>
          <idno type="ISNI">000000012202567X</idno>
          <idno type="ROR">https://ror.org/025vp2923</idno>
          <idno type="Wikidata">Q27962533</idno>
          <orgName>Institut Mines-Télécom [Paris]</orgName>
          <orgName type="acronym">IMT</orgName>
          <date type="start">2012-03-01</date>
          <desc>
            <address>
              <addrLine>19 Place Marguerite Perey, 91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.imt.fr/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-69604" status="VALID">
          <idno type="anr">ANR-22-PEXM-0005</idno>
          <orgName>Applications</orgName>
          <desc>Stockage de données massives sur ADN et polymères artificiels</desc>
          <date type="start">2022</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>