<?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-02354733</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="2026-05-25T08:44:05+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Stochastic Sampling of Structural Contexts Improves the Scalability and Accuracy of RNA 3D Modules Identification</title>
            <author role="aut">
              <persName>
                <forename type="first">Roman</forename>
                <surname>Sarrazin-Gendron</surname>
              </persName>
              <idno type="idhal" notation="numeric">798211</idno>
              <idno type="halauthorid" notation="string">1706112-798211</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0291-547X</idno>
              <affiliation ref="#struct-134741"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Hua-Ting</forename>
                <surname>Yao</surname>
              </persName>
              <email type="md5">e7ae7cfe1ab531876f8fdc598aef6dcc</email>
              <email type="domain">polytechnique.org</email>
              <idno type="idhal" notation="string">hua-ting-yao</idno>
              <idno type="idhal" notation="numeric">744772</idno>
              <idno type="halauthorid" notation="string">2539308-744772</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1720-5737</idno>
              <idno type="IDREF">https://www.idref.fr/263509818</idno>
              <affiliation ref="#struct-2071"/>
              <affiliation ref="#struct-134741"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Vladimir</forename>
                <surname>Reinharz</surname>
              </persName>
              <idno type="halauthorid">680324-0</idno>
              <orgName ref="#struct-134741"/>
              <affiliation ref="#struct-417738"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Carlos</forename>
                <forename type="middle">G</forename>
                <surname>Oliver</surname>
              </persName>
              <idno type="halauthorid">1706113-0</idno>
              <affiliation ref="#struct-134741"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Yann</forename>
                <surname>Ponty</surname>
              </persName>
              <email type="md5">42fb37addd44a7405a61aa6c233dfb61</email>
              <email type="domain">lix.polytechnique.fr</email>
              <idno type="idhal" notation="string">yann-ponty</idno>
              <idno type="idhal" notation="numeric">3138</idno>
              <idno type="halauthorid" notation="string">2539307-3138</idno>
              <idno type="IDREF">https://www.idref.fr/113491611</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7615-3930</idno>
              <affiliation ref="#struct-1051971"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jérôme</forename>
                <surname>Waldispühl</surname>
              </persName>
              <email type="md5">8dc84cbc5596b2fdc287ac3043b6a6ca</email>
              <email type="domain">cs.mcgill.ca</email>
              <idno type="idhal" notation="numeric">885072</idno>
              <idno type="halauthorid" notation="string">516255-885072</idno>
              <affiliation ref="#struct-134741"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Yann</forename>
                <surname>Ponty</surname>
              </persName>
              <email type="md5">42fb37addd44a7405a61aa6c233dfb61</email>
              <email type="domain">lix.polytechnique.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2019-11-07 21:30:01</date>
              <date type="whenWritten">2019</date>
              <date type="whenModified">2025-08-20 10:41:54</date>
              <date type="whenReleased">2019-11-08 09:13:56</date>
              <date type="whenProduced">2020-05-10</date>
              <date type="whenEndEmbargoed">2019-11-07</date>
              <ref type="file" target="https://inria.hal.science/hal-02354733v1/document">
                <date notBefore="2019-11-07"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-02354733v1/file/BayesPairing2_recomb_submitted.pdf" id="file-2354733-2259182">
                <date notBefore="2019-11-07"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="117983">
                <persName>
                  <forename>Yann</forename>
                  <surname>Ponty</surname>
                </persName>
                <email type="md5">42fb37addd44a7405a61aa6c233dfb61</email>
                <email type="domain">lix.polytechnique.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02354733</idno>
            <idno type="halUri">https://inria.hal.science/hal-02354733</idno>
            <idno type="halBibtex">sarrazingendron:hal-02354733</idno>
            <idno type="halRefHtml">&lt;i&gt;RECOMB 2020 - 24th Annual International Conference on Research in Computational Molecular Biology&lt;/i&gt;, May 2020, Padova, Italy</idno>
            <idno type="halRef">RECOMB 2020 - 24th Annual International Conference on Research in Computational Molecular Biology, May 2020, Padova, Italy</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2354733-2259182"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="X">École polytechnique</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="LIX" corresp="X">Laboratoire d'informatique de l'Ecole polytechnique</idno>
            <idno type="stamp" n="X-DEP-INFO">Département d'informatique de l’École polytechnique</idno>
            <idno type="stamp" n="IP_PARIS">Institut Polytechnique de Paris</idno>
            <idno type="stamp" n="DEPARTEMENT-DE-MATHEMATIQUES">Collection du Département de Mathématiques</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">Stochastic Sampling of Structural Contexts Improves the Scalability and Accuracy of RNA 3D Modules Identification</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Roman</forename>
                    <surname>Sarrazin-Gendron</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">798211</idno>
                  <idno type="halauthorid" notation="string">1706112-798211</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0291-547X</idno>
                  <affiliation ref="#struct-134741"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Hua-Ting</forename>
                    <surname>Yao</surname>
                  </persName>
                  <email type="md5">e7ae7cfe1ab531876f8fdc598aef6dcc</email>
                  <email type="domain">polytechnique.org</email>
                  <idno type="idhal" notation="string">hua-ting-yao</idno>
                  <idno type="idhal" notation="numeric">744772</idno>
                  <idno type="halauthorid" notation="string">2539308-744772</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1720-5737</idno>
                  <idno type="IDREF">https://www.idref.fr/263509818</idno>
                  <affiliation ref="#struct-2071"/>
                  <affiliation ref="#struct-134741"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Vladimir</forename>
                    <surname>Reinharz</surname>
                  </persName>
                  <idno type="halauthorid">680324-0</idno>
                  <orgName ref="#struct-134741"/>
                  <affiliation ref="#struct-417738"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Carlos</forename>
                    <forename type="middle">G</forename>
                    <surname>Oliver</surname>
                  </persName>
                  <idno type="halauthorid">1706113-0</idno>
                  <affiliation ref="#struct-134741"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Yann</forename>
                    <surname>Ponty</surname>
                  </persName>
                  <email type="md5">42fb37addd44a7405a61aa6c233dfb61</email>
                  <email type="domain">lix.polytechnique.fr</email>
                  <idno type="idhal" notation="string">yann-ponty</idno>
                  <idno type="idhal" notation="numeric">3138</idno>
                  <idno type="halauthorid" notation="string">2539307-3138</idno>
                  <idno type="IDREF">https://www.idref.fr/113491611</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7615-3930</idno>
                  <affiliation ref="#struct-1051971"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jérôme</forename>
                    <surname>Waldispühl</surname>
                  </persName>
                  <email type="md5">8dc84cbc5596b2fdc287ac3043b6a6ca</email>
                  <email type="domain">cs.mcgill.ca</email>
                  <idno type="idhal" notation="numeric">885072</idno>
                  <idno type="halauthorid" notation="string">516255-885072</idno>
                  <affiliation ref="#struct-134741"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>RECOMB 2020 - 24th Annual International Conference on Research in Computational Molecular Biology</title>
                  <date type="start">2020-05-10</date>
                  <date type="end">2020-05-13</date>
                  <settlement>Padova</settlement>
                  <country key="IT">Italy</country>
                </meeting>
                <imprint>
                  <biblScope unit="serie">Proceedings of RECOMB - 24th Annual International Conference on Research in Computational Molecular Biology - 2020</biblScope>
                  <date type="datePub">2020</date>
                </imprint>
              </monogr>
              <ref type="publisher">https://www.recomb2020.org/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-bi">Computer Science [cs]/Bioinformatics [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>RNA structures possess multiple levels of structural organization. Secondary structures are made of canonical (i.e. Watson-Crick and Wobble) helices, connected by loops whose local conformations are critical determinants of global 3D architectures. Such local 3D structures consist of conserved sets of non-canonical base pairs, called RNA modules. Their prediction from sequence data is thus a milestone toward 3D structure modelling. Unfortunately, the computational efficiency and scope of the current 3D module identification methods are too limited yet to benefit from all the knowledge accumulated in modules databases. Here, we introduce BayesPairing 2, a new sequence search algorithm leveraging secondary structure tree decomposition which allows to reduce the computational complexity and improve predictions on new sequences. We benchmarked our methods on 75 modules and 6360 RNA sequences, and report accuracies that are comparable to the state of the art, with considerable running time improvements. When identifying 200 modules on a single sequence, BayesPairing 2 is over 100 times faster than its previous version, opening new doors for genome-wide applications.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-134741" status="VALID">
          <idno type="ROR">https://ror.org/01pxwe438</idno>
          <orgName>McGill University = Université McGill [Montréal, Canada]</orgName>
          <desc>
            <address>
              <addrLine>845, rue Sherbrooke O. Montréal (Québec) Canada H3A 0G4</addrLine>
              <country key="CA"/>
            </address>
            <ref type="url">http://www.mcgill.ca/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-2071" status="VALID">
          <idno type="IdRef">196509955</idno>
          <idno type="ISNI">0000000403673665</idno>
          <idno type="RNSR">200519331V</idno>
          <idno type="ROR">https://ror.org/04afed728</idno>
          <idno type="Wikidata">Q16009025</idno>
          <orgName>Laboratoire d'informatique de l'École polytechnique [Palaiseau]</orgName>
          <orgName type="acronym">LIX</orgName>
          <date type="start">2005-01-01</date>
          <desc>
            <address>
              <addrLine>1 Rue Honoré d’Estienne d’Orves, Bâtiment Alain Turing, 91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.lix.polytechnique.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300340" type="direct"/>
            <relation active="#struct-563936" type="indirect"/>
            <relation name="UMR7161" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-417738" status="VALID">
          <orgName>Institute for Basic Science [Daejeon]</orgName>
          <orgName type="acronym">IBS</orgName>
          <desc>
            <address>
              <addrLine>55, Expo-ro, Yuseong-gu, Daejeon, Korea, 34126</addrLine>
              <country key="KR"/>
            </address>
            <ref type="url">https://www.ibs.re.kr/eng.do</ref>
          </desc>
        </org>
        <org type="researchteam" xml:id="struct-1051971" status="VALID">
          <orgName>Algorithms and Models for Integrative BIOlogy</orgName>
          <orgName type="acronym">AMIBIO</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>Laboratoire d'Informatique de l'École polytechniqueRoute de Saclay91128 Palaiseau CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.lix.polytechnique.fr/amibio/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-2071" type="direct"/>
            <relation active="#struct-300340" type="indirect"/>
            <relation active="#struct-563936" type="indirect"/>
            <relation name="UMR7161" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300340" status="VALID">
          <idno type="IdRef">027309320</idno>
          <idno type="ISNI">0000000121581279</idno>
          <idno type="ROR">https://ror.org/05hy3tk52</idno>
          <idno type="Wikidata">Q273626</idno>
          <orgName>École polytechnique</orgName>
          <orgName type="acronym">X</orgName>
          <date type="start">1794-03-11</date>
          <desc>
            <address>
              <addrLine>Route de Saclay, 91128 Palaiseau Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.polytechnique.edu/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-563936" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-563936" status="VALID">
          <idno type="IdRef">238327159</idno>
          <idno type="ISNI">0000000502717600</idno>
          <idno type="ROR">https://ror.org/042tfbd02</idno>
          <idno type="Wikidata">Q48759778</idno>
          <orgName>Institut Polytechnique de Paris</orgName>
          <orgName type="acronym">IP Paris</orgName>
          <date type="start">2019-06-02</date>
          <desc>
            <address>
              <addrLine>Route de Saclay, 91120 Palaiseau Cedex, France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.ip-paris.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>
    </back>
  </text>
</TEI>