<?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-04798144</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="2026-05-23T11:06:41+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Automated evaluation of multiple sequence alignment methods to handle third generation sequencing errors</title>
            <author role="aut">
              <persName>
                <forename type="first">Coralie</forename>
                <surname>Rohmer</surname>
              </persName>
              <idno type="halauthorid">2955516-0</idno>
              <affiliation ref="#struct-410272"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Hélène</forename>
                <surname>Touzet</surname>
              </persName>
              <email type="md5">6a52b4e5886eb4668de1e48b13573e22</email>
              <email type="domain">univ-lille.fr</email>
              <idno type="idhal" notation="string">helene-touzet</idno>
              <idno type="idhal" notation="numeric">177644</idno>
              <idno type="halauthorid" notation="string">38923-177644</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-5305-9987</idno>
              <idno type="IDREF">https://www.idref.fr/10394074X</idno>
              <affiliation ref="#struct-410272"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Antoine</forename>
                <surname>Limasset</surname>
              </persName>
              <email type="md5">6de70c50e6f0b920c15c07d64a6b83f3</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">antoine-limasset</idno>
              <idno type="idhal" notation="numeric">180632</idno>
              <idno type="halauthorid" notation="string">30639-180632</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0669-4141</idno>
              <idno type="IDREF">https://www.idref.fr/223503908</idno>
              <affiliation ref="#struct-410272"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Helene</forename>
                <surname>Touzet</surname>
              </persName>
              <email type="md5">6a52b4e5886eb4668de1e48b13573e22</email>
              <email type="domain">univ-lille.fr</email>
            </editor>
            <funder ref="#projanr-42656"/>
            <funder ref="#projanr-55832"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2024-11-22 13:47:52</date>
              <date type="whenModified">2025-01-20 14:08:55</date>
              <date type="whenReleased">2024-11-28 13:32:56</date>
              <date type="whenProduced">2024-09-20</date>
              <date type="whenEndEmbargoed">2024-11-22</date>
              <ref type="file" target="https://hal.science/hal-04798144v1/document">
                <date notBefore="2024-11-22"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-04798144v1/file/peerj-17731.pdf" id="file-4798144-4189449">
                <date notBefore="2024-11-22"/>
              </ref>
              <ref type="externalLink" target="https://doi.org/10.7717/peerj.17731"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="121428">
                <persName>
                  <forename>Helene</forename>
                  <surname>Touzet</surname>
                </persName>
                <email type="md5">6a52b4e5886eb4668de1e48b13573e22</email>
                <email type="domain">univ-lille.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04798144</idno>
            <idno type="halUri">https://hal.science/hal-04798144</idno>
            <idno type="halBibtex">rohmer:hal-04798144</idno>
            <idno type="halRefHtml">&lt;i&gt;PeerJ&lt;/i&gt;, 2024, 12, pp.e17731. &lt;a target="_blank" href="https://dx.doi.org/10.7717/peerj.17731"&gt;&amp;#x27E8;10.7717/peerj.17731&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">PeerJ, 2024, 12, pp.e17731. &amp;#x27E8;10.7717/peerj.17731&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-4798144-4189449"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="CRISTAL">Centre de Recherche en Informatique, Signal et Automatique de Lille (CRISTAL)</idno>
            <idno type="stamp" n="CRISTAL-BONSAI" corresp="CRISTAL">CRISTAL-BONSAI</idno>
            <idno type="stamp" n="UNIV-LILLE">Université de Lille</idno>
            <idno type="stamp" n="ANR">ANR</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>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Automated evaluation of multiple sequence alignment methods to handle third generation sequencing errors</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Coralie</forename>
                    <surname>Rohmer</surname>
                  </persName>
                  <idno type="halauthorid">2955516-0</idno>
                  <affiliation ref="#struct-410272"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Hélène</forename>
                    <surname>Touzet</surname>
                  </persName>
                  <email type="md5">6a52b4e5886eb4668de1e48b13573e22</email>
                  <email type="domain">univ-lille.fr</email>
                  <idno type="idhal" notation="string">helene-touzet</idno>
                  <idno type="idhal" notation="numeric">177644</idno>
                  <idno type="halauthorid" notation="string">38923-177644</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-5305-9987</idno>
                  <idno type="IDREF">https://www.idref.fr/10394074X</idno>
                  <affiliation ref="#struct-410272"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Antoine</forename>
                    <surname>Limasset</surname>
                  </persName>
                  <email type="md5">6de70c50e6f0b920c15c07d64a6b83f3</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">antoine-limasset</idno>
                  <idno type="idhal" notation="numeric">180632</idno>
                  <idno type="halauthorid" notation="string">30639-180632</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0669-4141</idno>
                  <idno type="IDREF">https://www.idref.fr/223503908</idno>
                  <affiliation ref="#struct-410272"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">104712</idno>
                <idno type="issn">2167-8359</idno>
                <title level="j">PeerJ</title>
                <imprint>
                  <publisher>PeerJ</publisher>
                  <biblScope unit="volume">12</biblScope>
                  <biblScope unit="pp">e17731</biblScope>
                  <date type="datePub">2024-09-20</date>
                </imprint>
              </monogr>
              <idno type="doi">10.7717/peerj.17731</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Subjects Bioinformatics</term>
                <term xml:lang="en">Benchmark</term>
                <term xml:lang="en">Oxford nanopore</term>
                <term xml:lang="en">Pacific bioscience</term>
                <term xml:lang="en">Heterozygosity</term>
                <term xml:lang="en">Sequencing errors</term>
                <term xml:lang="en">Multiple sequence alignment</term>
                <term xml:lang="en">Computational Biology Long reads</term>
                <term xml:lang="en">Subjects Bioinformatics Computational Biology Long reads Multiple sequence alignment Sequencing errors Heterozygosity Pacific bioscience Oxford nanopore Benchmark</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halDomain" n="sdv">Life Sciences [q-bio]</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>Most third-generation sequencing (TGS) processing tools rely on multiple sequence alignment (MSA) methods to manage sequencing errors. Despite the broad range of MSA approaches available, a limited selection of implementations are commonly used in practice for this type of application, and no comprehensive comparative assessment of existing tools has been undertaken to date. In this context, we have developed an automatic pipeline, named MSA Limit, designed to facilitate the execution and evaluation of diverse MSA methods across a spectrum of conditions representative of TGS reads. MSA Limit offers insights into alignment accuracy, time efficiency, and memory utilization. It serves as a valuable resource for both users and developers, aiding in the assessment of algorithmic performance and assisting users in selecting the most appropriate tool for their specific experimental settings. Through a series of experiments using real and simulated data, we demonstrate the value of such exploration. Our findings reveal that in certain scenarios, popular methods may not consistently exhibit optimal efficiency and that the choice of the most effective method varies depending on factors such as sequencing depth, genome characteristics, and read error patterns. MSA Limit is an open source and freely available tool. All code and data pertaining to it and this manuscript are available at https://gitlab.cristal.univ-lille.fr/crohmer/msa-limit .</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-410272" status="VALID">
          <idno type="IdRef">18388695X</idno>
          <idno type="RNSR">201521249L</idno>
          <idno type="ROR">https://ror.org/05vrs3189</idno>
          <idno type="Wikidata">Q116959497</idno>
          <orgName>Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189</orgName>
          <orgName type="acronym">CRIStAL</orgName>
          <date type="start">2015-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Lille - Campus scientifique - Bâtiment ESPRIT - Avenue Henri Poincaré - 59655 Villeneuve d’Ascq</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cristal.univ-lille.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR9189" active="#struct-120930" type="direct"/>
            <relation name="UMR9189" active="#struct-374570" type="direct"/>
            <relation name="UMR9189" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-120930" status="VALID">
          <idno type="IdRef">256304629</idno>
          <idno type="ISNI">0000000122034461</idno>
          <idno type="ROR">https://ror.org/01x441g73</idno>
          <orgName>Centrale Lille</orgName>
          <desc>
            <address>
              <addrLine>École Centrale de Lille - Cité Scientifique - CS 20048 59651 Villeneuve d'Ascq Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://centralelille.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-374570" status="VALID">
          <idno type="IdRef">223446556</idno>
          <idno type="ISNI">0000 0001 2242 6780</idno>
          <idno type="ROR">https://ror.org/02kzqn938</idno>
          <idno type="Wikidata">Q3551621</idno>
          <orgName>Université de Lille</orgName>
          <desc>
            <address>
              <addrLine>EPE Université de Lille. -- 42 rue Paul Duez, 59000 Lille</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-lille.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>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-42656" status="VALID">
          <idno type="anr">ANR-16-CE23-0001</idno>
          <orgName>ASTER</orgName>
          <desc>Algorithmes et outils logiciels pour le séquençage d'ARN de troisième génération</desc>
          <date type="start">2016</date>
        </org>
        <org type="anrProject" xml:id="projanr-55832" status="VALID">
          <idno type="anr">ANR-21-CE45-0012</idno>
          <orgName>Agate</orgName>
          <desc>Structures de graphe adaptées pour l'exploration de données de séquençage de troisième génération</desc>
          <date type="start">2021</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>