<?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-01632912v3</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="2026-05-03T01:53:26+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Biological Sequence Modeling with Convolutional Kernel Networks</title>
            <author role="aut">
              <persName>
                <forename type="first">Dexiong</forename>
                <surname>Chen</surname>
              </persName>
              <idno type="halauthorid">1260439-0</idno>
              <affiliation ref="#struct-445108"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Laurent</forename>
                <surname>Jacob</surname>
              </persName>
              <email type="md5">dbec3b6fb92e033bef40ca61135d8ec2</email>
              <email type="domain">univ-lyon1.fr</email>
              <ptr type="url" target="https://laurent-jacob.github.io"/>
              <idno type="idhal" notation="string">laurent-jacob</idno>
              <idno type="idhal" notation="numeric">21877</idno>
              <idno type="halauthorid" notation="string">5203-21877</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7826-2719</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=54bOCmQAAAAJ&amp;hl=fr</idno>
              <idno type="IDREF">https://www.idref.fr/176737952</idno>
              <idno type="IDREF">https://www.idref.fr/145903338</idno>
              <affiliation ref="#struct-543496"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Julien</forename>
                <surname>Mairal</surname>
              </persName>
              <email type="md5">413829dab28a0224ec5dc6d17391bece</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="numeric">1034832</idno>
              <idno type="halauthorid" notation="string">1401562-1034832</idno>
              <idno type="IDREF">https://www.idref.fr/152125256</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-6991-2110</idno>
              <orgName ref="#struct-300009"/>
              <affiliation ref="#struct-445108"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Julien</forename>
                <surname>Mairal</surname>
              </persName>
              <email type="md5">413829dab28a0224ec5dc6d17391bece</email>
              <email type="domain">inria.fr</email>
            </editor>
            <funder ref="#projanr-41136"/>
            <funder ref="#projanr-43304"/>
            <funder ref="#projeurop-711804"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1">
              <date type="whenSubmitted">2017-11-10 17:16:49</date>
            </edition>
            <edition n="v2">
              <date type="whenSubmitted">2018-10-08 08:49:52</date>
            </edition>
            <edition n="v3" type="current">
              <date type="whenSubmitted">2019-01-29 16:05:53</date>
              <date type="whenModified">2025-10-27 11:00:05</date>
              <date type="whenReleased">2019-01-29 16:33:40</date>
              <date type="whenProduced">2019-09-15</date>
              <date type="whenEndEmbargoed">2019-01-29</date>
              <ref type="file" target="https://inria.hal.science/hal-01632912v3/document">
                <date notBefore="2019-01-29"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-01632912v3/file/biorxiv.pdf" id="file-1998455-2014844">
                <date notBefore="2019-01-29"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="123308">
                <persName>
                  <forename>Julien</forename>
                  <surname>Mairal</surname>
                </persName>
                <email type="md5">413829dab28a0224ec5dc6d17391bece</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01632912</idno>
            <idno type="halUri">https://inria.hal.science/hal-01632912</idno>
            <idno type="halBibtex">chen:hal-01632912</idno>
            <idno type="halRefHtml">&lt;i&gt;Bioinformatics&lt;/i&gt;, 2019, 35 (18), pp.3294-3302. &lt;a target="_blank" href="https://dx.doi.org/10.1093/bioinformatics/btz094"&gt;&amp;#x27E8;10.1093/bioinformatics/btz094&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Bioinformatics, 2019, 35 (18), pp.3294-3302. &amp;#x27E8;10.1093/bioinformatics/btz094&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1998455-2014844"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UGA">HAL Grenoble Alpes</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-LYON1">Université Claude Bernard - Lyon I</idno>
            <idno type="stamp" n="INPG">Institut polytechnique de Grenoble</idno>
            <idno type="stamp" n="INRIA-RHA">INRIA Grenoble - Rhône-Alpes</idno>
            <idno type="stamp" n="INSMI">CNRS-INSMI - INstitut des Sciences Mathématiques et de leurs Interactions</idno>
            <idno type="stamp" n="OPENAIRE">OpenAIRE</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="LJK">Laboratoire Jean Kuntzmann</idno>
            <idno type="stamp" n="LJK_GI" corresp="LJK">Département Géométrie et Images</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="LJK-GI-THOTH" corresp="LJK_GI">Apprentissage de modèles visuels à partir de données massives</idno>
            <idno type="stamp" n="INRIA-RENGRE">INRIA-RENGRE</idno>
            <idno type="stamp" n="INRIA-300009">Inria 300009</idno>
            <idno type="stamp" n="LBBE" corresp="UNIV-LYON1">Laboratoire de biométrie et biologie évolutive </idno>
            <idno type="stamp" n="UDL">UDL</idno>
            <idno type="stamp" n="UNIV-LYON">Université de Lyon</idno>
            <idno type="stamp" n="UGA-COMUE">Université Grenoble Alpes [2016-2019]</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="INRIAARTDOI">INRIAARTDOI</idno>
            <idno type="stamp" n="TEST3-HALCNRS">TEST3-HALCNRS</idno>
            <idno type="stamp" n="TEST4-HALCNRS">collection test</idno>
            <idno type="stamp" n="TEST5-HALCNRS">collection test 5</idno>
            <idno type="stamp" n="INEE-CNRS">Institut écologie et environnement du CNRS</idno>
            <idno type="stamp" n="TEST-UGA">TEST-UGA</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">Biological Sequence Modeling with Convolutional Kernel Networks</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Dexiong</forename>
                    <surname>Chen</surname>
                  </persName>
                  <idno type="halauthorid">1260439-0</idno>
                  <affiliation ref="#struct-445108"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Laurent</forename>
                    <surname>Jacob</surname>
                  </persName>
                  <email type="md5">dbec3b6fb92e033bef40ca61135d8ec2</email>
                  <email type="domain">univ-lyon1.fr</email>
                  <ptr type="url" target="https://laurent-jacob.github.io"/>
                  <idno type="idhal" notation="string">laurent-jacob</idno>
                  <idno type="idhal" notation="numeric">21877</idno>
                  <idno type="halauthorid" notation="string">5203-21877</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7826-2719</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=54bOCmQAAAAJ&amp;hl=fr</idno>
                  <idno type="IDREF">https://www.idref.fr/176737952</idno>
                  <idno type="IDREF">https://www.idref.fr/145903338</idno>
                  <affiliation ref="#struct-543496"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Julien</forename>
                    <surname>Mairal</surname>
                  </persName>
                  <email type="md5">413829dab28a0224ec5dc6d17391bece</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="numeric">1034832</idno>
                  <idno type="halauthorid" notation="string">1401562-1034832</idno>
                  <idno type="IDREF">https://www.idref.fr/152125256</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-6991-2110</idno>
                  <orgName ref="#struct-300009"/>
                  <affiliation ref="#struct-445108"/>
                </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">35</biblScope>
                  <biblScope unit="issue">18</biblScope>
                  <biblScope unit="pp">3294–3302</biblScope>
                  <date type="datePub">2019-09-15</date>
                  <date type="dateEpub">2019-02-07</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1093/bioinformatics/btz094</idno>
            </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="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</classCode>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
              <classCode scheme="halDomain" n="info.info-cr">Computer Science [cs]/Cryptography and Security [cs.CR]</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>The growing number of annotated biological sequences available makes it possible to learn genotype-phenotype relationships from data with increasingly high accuracy. When large quantities of labeled samples are available for training a model, convolutional neural networks can be used to predict the phenotype of unannotated sequences with good accuracy. Unfortunately, their performance with medium- or small-scale datasets is mitigated, which requires inventing new data-efficient approaches. In this paper, we introduce a hybrid approach between convolutional neural networks and kernel methods to model biological sequences. Our method enjoys the ability of convolutional neural networks to learn data representations that are adapted to a specific task, while the kernel point of view yields algorithms that perform significantly better when the amount of training data is small. We illustrate these advantages for transcription factor binding prediction and protein homology detection, and we demonstrate that our model is also simple to interpret, which is crucial for discovering predictive motifs in sequences. The source code is freely available at https://gitlab.inria.fr/dchen/CKN-seq.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-445108" status="OLD">
          <idno type="IdRef">242196691</idno>
          <idno type="RNSR">201622034K</idno>
          <orgName>Apprentissage de modèles à partir de données massives</orgName>
          <orgName type="acronym">Thoth</orgName>
          <date type="start">2016-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/thoth</ref>
          </desc>
          <listRelation>
            <relation active="#struct-2497" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-1042161" type="direct"/>
            <relation active="#struct-89889" type="indirect"/>
            <relation name="UMR5224" active="#struct-441569" type="indirect"/>
            <relation active="#struct-445543" type="indirect"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-543496" status="OLD">
          <orgName>Statistique en grande dimension pour la génomique [LBBE]</orgName>
          <date type="end">2020-12-31</date>
          <desc>
            <address>
              <addrLine>LBBE43 Bld du 11 Novembre 1918 69622 VILLEURBANNE CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://lbbe.univ-lyon1.fr/-Equipe-Statistique-en-Grande-.html</ref>
          </desc>
          <listRelation>
            <relation active="#struct-543488" type="direct"/>
            <relation active="#struct-10025" type="indirect"/>
            <relation active="#struct-194495" type="indirect"/>
            <relation active="#struct-301088" type="indirect"/>
            <relation active="#struct-301767" type="indirect"/>
            <relation name="UMR5558" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-2497" status="VALID">
          <idno type="RNSR">199218244V</idno>
          <idno type="ROR">https://ror.org/00n8d6z93</idno>
          <orgName>Centre Inria de l'Université Grenoble Alpes</orgName>
          <desc>
            <address>
              <addrLine>Inovallée655 avenue de l'Europe38330 Montbonnot</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/grenoble</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="laboratory" xml:id="struct-1042161" status="OLD">
          <idno type="IdRef">184945011</idno>
          <idno type="ISNI">000000040383676X</idno>
          <idno type="RNSR">200711891Z</idno>
          <idno type="ROR">https://ror.org/04ett5b41</idno>
          <orgName>Laboratoire Jean Kuntzmann</orgName>
          <orgName type="acronym">LJK</orgName>
          <date type="start">2016-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Bâtiment IMAG, CS 40700, F-38058 Grenoble Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://ljk.imag.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-89889" type="direct"/>
            <relation active="#struct-300009" type="direct"/>
            <relation name="UMR5224" active="#struct-441569" type="direct"/>
            <relation active="#struct-445543" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-89889" status="OLD">
          <idno type="IdRef">026388804</idno>
          <idno type="ROR">https://ror.org/05sbt2524</idno>
          <orgName>Institut polytechnique de Grenoble - Grenoble Institute of Technology</orgName>
          <orgName type="acronym">Grenoble INP</orgName>
          <date type="start">2007-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>46 avenue Félix Viallet 38031 Grenoble Cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.grenoble-inp.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-445543" status="OLD">
          <idno type="IdRef">188399275</idno>
          <idno type="ROR">https://ror.org/02rx3b187</idno>
          <orgName>Université Grenoble Alpes [2016-2019]</orgName>
          <orgName type="acronym">UGA [2016-2019]</orgName>
          <date type="start">2016-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>38058 Grenoble cedex</addrLine>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="department" xml:id="struct-543488" status="OLD">
          <orgName>Département PEGASE [LBBE]</orgName>
          <orgName type="acronym">PEGASE</orgName>
          <date type="end">2020-12-31</date>
          <desc>
            <address>
              <addrLine>LBBE 43 Bld du 11 Novembre 1918 69622 VILLEURBANNE CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://lbbe.univ-lyon1.fr/-Departement-PEGASE-.html</ref>
          </desc>
          <listRelation>
            <relation active="#struct-10025" type="direct"/>
            <relation active="#struct-194495" type="indirect"/>
            <relation active="#struct-301088" type="indirect"/>
            <relation active="#struct-301767" type="indirect"/>
            <relation name="UMR5558" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-10025" status="VALID">
          <idno type="IdRef">15069671X</idno>
          <idno type="ISNI">0000000403863493</idno>
          <idno type="RNSR">199411998X</idno>
          <idno type="ROR">https://ror.org/03skt0t88</idno>
          <orgName>Laboratoire de Biométrie et Biologie Evolutive - UMR 5558</orgName>
          <orgName type="acronym">LBBE</orgName>
          <date type="start">1995-01-01</date>
          <desc>
            <address>
              <addrLine>43 Bld du 11 Novembre 1918 69622 VILLEURBANNE CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://lbbe.univ-lyon1.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-194495" type="direct"/>
            <relation active="#struct-301088" type="indirect"/>
            <relation active="#struct-301767" type="direct"/>
            <relation name="UMR5558" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-194495" status="VALID">
          <idno type="IdRef">026402823</idno>
          <idno type="ISNI">0000000121686185</idno>
          <idno type="ROR">https://ror.org/029brtt94</idno>
          <orgName>Université Claude Bernard Lyon 1</orgName>
          <orgName type="acronym">UCBL</orgName>
          <desc>
            <address>
              <addrLine>43, boulevard du 11 novembre 1918, 69622 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon1.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301088" status="VALID">
          <idno type="ROR">https://ror.org/01rk35k63</idno>
          <orgName>Université de Lyon</orgName>
          <desc>
            <address>
              <addrLine>92 rue Pasteur - CS 30122, 69361 Lyon Cedex 07</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-lyon.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-301767" status="VALID">
          <idno type="ROR">https://ror.org/01c7wz417</idno>
          <orgName>VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement</orgName>
          <orgName type="acronym">VAS</orgName>
          <date type="start">2010-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Lyon, VetAgro Sup, 69280 Marcy l'Etoile (campus vétérinaire); Université de Clermont, VetAgro Sup, 63370 Lempdes (campus agronomique)</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.vetagro-sup.fr/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-41136" status="VALID">
          <idno type="anr">ANR-14-CE23-0003</idno>
          <idno type="program">Appel à projets générique</idno>
          <orgName>MACARON</orgName>
          <desc>Apprentissage statistique à grande échelle et applications</desc>
          <date type="start">2014</date>
        </org>
        <org type="anrProject" xml:id="projanr-43304" status="VALID">
          <idno type="anr">ANR-17-CE23-0011</idno>
          <orgName>FAST-BIG</orgName>
          <desc>Tests Statistiques efficaces pour les données de grande dimension: application à l'imagerie cérébrale et la génétique</desc>
          <date type="start">2017</date>
        </org>
        <org type="europeanProject" xml:id="projeurop-711804" status="VALID">
          <idno type="number">714381</idno>
          <idno type="program">ERC-2016-STG</idno>
          <idno type="call">ERC-2016-STG</idno>
          <orgName>SOLARIS</orgName>
          <desc>Large-Scale Learning with Deep Kernel Machines</desc>
          <date type="start">2017-03-01</date>
          <date type="end">2022-02-28</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>