<?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-03684406</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="2026-05-03T14:59:52+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Inverted Repeats Scaffolding for a Dedicated Chloroplast Genome Assembler</title>
            <author role="aut">
              <persName>
                <forename type="first">Victor</forename>
                <surname>Epain</surname>
              </persName>
              <email type="md5">1a8d65e7666e994ba2ca287050173fbb</email>
              <email type="domain">laposte.net</email>
              <idno type="idhal" notation="string">victor-epain</idno>
              <idno type="idhal" notation="numeric">753386</idno>
              <idno type="halauthorid" notation="string">47647-753386</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0049-0954</idno>
              <idno type="IDREF">https://www.idref.fr/276523881</idno>
              <orgName ref="#struct-300009"/>
              <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>
              <orgName ref="#struct-441569"/>
              <affiliation ref="#struct-491655"/>
            </author>
            <author role="crp">
              <persName>
                <forename type="first">Rumen</forename>
                <surname>Andonov</surname>
              </persName>
              <email type="md5">6202364738a4b62b40a91f99971bd4b3</email>
              <email type="domain">irisa.fr</email>
              <idno type="idhal" notation="string">rumen-andonov</idno>
              <idno type="idhal" notation="numeric">180618</idno>
              <idno type="halauthorid" notation="string">11666-180618</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-4842-7102</idno>
              <idno type="IDREF">https://www.idref.fr/110438221</idno>
              <affiliation ref="#struct-491655"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Rumen</forename>
                <surname>Andonov</surname>
              </persName>
              <email type="md5">6202364738a4b62b40a91f99971bd4b3</email>
              <email type="domain">irisa.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2022-06-03 12:05:52</date>
              <date type="whenModified">2026-04-10 09:32:07</date>
              <date type="whenReleased">2022-06-03 14:45:05</date>
              <date type="whenProduced">2022-06-03</date>
              <date type="whenEndEmbargoed">2022-06-03</date>
              <ref type="file" target="https://inria.hal.science/hal-03684406v1/document">
                <date notBefore="2022-06-03"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-03684406v1/file/wabi2022.pdf" id="file-3684406-3219841">
                <date notBefore="2022-06-03"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="115735">
                <persName>
                  <forename>Rumen</forename>
                  <surname>Andonov</surname>
                </persName>
                <email type="md5">6202364738a4b62b40a91f99971bd4b3</email>
                <email type="domain">irisa.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03684406</idno>
            <idno type="halUri">https://inria.hal.science/hal-03684406</idno>
            <idno type="halBibtex">epain:hal-03684406</idno>
            <idno type="halRefHtml">2022</idno>
            <idno type="halRef">2022</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-3684406-3219841"/></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="TDS-MACS">Réseau de recherche en Théorie des Systèmes Distribués, Modélisation, Analyse et Contrôle des Systèmes</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="INRIA-300009">Inria 300009</idno>
            <idno type="stamp" n="UR1-MATH-NUM">Pôle UnivRennes - Mathématiques - Numérique </idno>
          </seriesStmt>
          <notesStmt/>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Inverted Repeats Scaffolding for a Dedicated Chloroplast Genome Assembler</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Victor</forename>
                    <surname>Epain</surname>
                  </persName>
                  <email type="md5">1a8d65e7666e994ba2ca287050173fbb</email>
                  <email type="domain">laposte.net</email>
                  <idno type="idhal" notation="string">victor-epain</idno>
                  <idno type="idhal" notation="numeric">753386</idno>
                  <idno type="halauthorid" notation="string">47647-753386</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0049-0954</idno>
                  <idno type="IDREF">https://www.idref.fr/276523881</idno>
                  <orgName ref="#struct-300009"/>
                  <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>
                  <orgName ref="#struct-441569"/>
                  <affiliation ref="#struct-491655"/>
                </author>
                <author role="crp">
                  <persName>
                    <forename type="first">Rumen</forename>
                    <surname>Andonov</surname>
                  </persName>
                  <email type="md5">6202364738a4b62b40a91f99971bd4b3</email>
                  <email type="domain">irisa.fr</email>
                  <idno type="idhal" notation="string">rumen-andonov</idno>
                  <idno type="idhal" notation="numeric">180618</idno>
                  <idno type="halauthorid" notation="string">11666-180618</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-4842-7102</idno>
                  <idno type="IDREF">https://www.idref.fr/110438221</idno>
                  <affiliation ref="#struct-491655"/>
                </author>
              </analytic>
              <monogr>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Elementary longest path problem</term>
                <term xml:lang="en">NP-Complete problem</term>
                <term xml:lang="en">Integer programming</term>
                <term xml:lang="en">Contig</term>
                <term xml:lang="en">Scaffolding</term>
                <term xml:lang="en">Assembly graph</term>
                <term xml:lang="en">De Bruijn graph</term>
                <term xml:lang="en">Inverted repeats</term>
                <term xml:lang="en">Genome assembly</term>
                <term xml:lang="en">Applied computing</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-bi">Computer Science [cs]/Bioinformatics [q-bio.QM]</classCode>
              <classCode scheme="halDomain" n="info.info-ro">Computer Science [cs]/Operations Research [math.OC]</classCode>
              <classCode scheme="halTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halOldTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halTreeTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>This paper describes a novel assembly approach for chloroplast genomes. It contains two modular steps. In the first step, based on the hypothesis that chloroplasts genomes are over-represented compared to the nuclear genome in the plant's cell, we assemble contigs with a De Bruijn graph based approach using short reads with a high k-mer coverage. Connections between oriented contigs are also provided here. The second step determines the order and the orientation of the contigs (scaffolding). Taking advantage of the knowledge that chloroplast genomes posses well studied circular structure, we develop a particular formulation of the scaffolding problem, called Nested Inverted Fragments Scaffolding. It aims to assemble highly conserved inverted repeats. We formulate it as an optimisation problem and we prove that it is NP-Complete. To solve the problem we propose and implement an integer linear programming formulation. We evaluate our method on a set of real instances (a benchmark of 42 chloroplast genomes) and show that it obtains notable achievements with respect to the quality of the results. To further estimate the performance of our scaffolding module, we test it on huge artificially created instances. The results demonstrate an excellent behaviour of our integer formulation as even very large instances have been solved at the first Branch &amp;amp; Bounds node.</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>
    </back>
  </text>
</TEI>