<?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-01239568</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="2026-05-19T11:11:24+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Suggesting valid pharmacogenes by mining linked data</title>
            <author role="aut">
              <persName>
                <forename type="first">Kevin</forename>
                <surname>Dalleau</surname>
              </persName>
              <email type="md5">8f944d705b833e7b69f57c67c12fda81</email>
              <email type="domain">loria.fr</email>
              <idno type="idhal" notation="string">kevin-dalleau</idno>
              <idno type="idhal" notation="numeric">16248</idno>
              <idno type="halauthorid" notation="string">35048-16248</idno>
              <idno type="IDREF">https://www.idref.fr/227824776</idno>
              <affiliation ref="#struct-205125"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ndeye</forename>
                <surname>Coumba Ndiaye</surname>
              </persName>
              <idno type="halauthorid">581693-0</idno>
              <affiliation ref="#struct-223041"/>
            </author>
            <author role="crp">
              <persName>
                <forename type="first">Adrien</forename>
                <surname>Coulet</surname>
              </persName>
              <email type="md5">cbac31e20d8f0cbf0f870c991a79335e</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">coulet</idno>
              <idno type="idhal" notation="numeric">1742</idno>
              <idno type="halauthorid" notation="string">11918-1742</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1466-062X</idno>
              <idno type="IDREF">https://www.idref.fr/134214099</idno>
              <affiliation ref="#struct-205125"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Adrien</forename>
                <surname>Coulet</surname>
              </persName>
              <email type="md5">cbac31e20d8f0cbf0f870c991a79335e</email>
              <email type="domain">inria.fr</email>
            </editor>
            <funder ref="#projanr-42001"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2015-12-08 17:54:29</date>
              <date type="whenWritten">2015-09-15</date>
              <date type="whenModified">2025-11-04 12:00:34</date>
              <date type="whenReleased">2015-12-09 11:01:19</date>
              <date type="whenProduced">2015-12-08</date>
              <date type="whenEndEmbargoed">2015-12-07</date>
              <ref type="file" target="https://inria.hal.science/hal-01239568v1/document">
                <date notBefore="2015-12-07"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-01239568v1/file/SWAT4LS_2015_paper_5.pdf" id="file-1239568-1317623">
                <date notBefore="2015-12-07"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="110882">
                <persName>
                  <forename>Adrien</forename>
                  <surname>Coulet</surname>
                </persName>
                <email type="md5">cbac31e20d8f0cbf0f870c991a79335e</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01239568</idno>
            <idno type="halUri">https://inria.hal.science/hal-01239568</idno>
            <idno type="halBibtex">dalleau:hal-01239568</idno>
            <idno type="halRefHtml">&lt;i&gt;Semantic Web Applications and Tools for Life Sciences (SWAT4LS) 2015&lt;/i&gt;, Dec 2015, Cambridge, United Kingdom</idno>
            <idno type="halRef">Semantic Web Applications and Tools for Life Sciences (SWAT4LS) 2015, Dec 2015, Cambridge, United Kingdom</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1239568-1317623"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <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="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="LORIA2">Publications du LORIA</idno>
            <idno type="stamp" n="INRIA-NANCY-GRAND-EST">INRIA Nancy - Grand Est</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="UNIV-LORRAINE">Université de Lorraine</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="LORIA">Laboratoire Lorrain de Recherche en Informatique et ses Applications</idno>
            <idno type="stamp" n="LORIA-NLPKD" corresp="LORIA">Department of Natural Language Processing &amp; Knowledge Discovery</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="CENTRALESUPELEC-SACLAY" corresp="UNIV-PARIS-SACLAY">CENTRALESUPELEC-SACLAY</idno>
            <idno type="stamp" n="IGE-PCV-UL">IGE-PCV - Interactions Gène-Environnement en Physiopathologie Cardio-Vasculaire</idno>
            <idno type="stamp" n="BMS-UL">Pôle scientifique Biologie, Médecine, Santé de l'Université de Lorraine</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="INRIA_WEB">Inria &amp; web</idno>
            <idno type="stamp" n="AM2I-UL">Pôle scientifique Automatique, Mathématiques, Informatique et leurs Intéractions de l'Université de Lorraine</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">Suggesting valid pharmacogenes by mining linked data</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Kevin</forename>
                    <surname>Dalleau</surname>
                  </persName>
                  <email type="md5">8f944d705b833e7b69f57c67c12fda81</email>
                  <email type="domain">loria.fr</email>
                  <idno type="idhal" notation="string">kevin-dalleau</idno>
                  <idno type="idhal" notation="numeric">16248</idno>
                  <idno type="halauthorid" notation="string">35048-16248</idno>
                  <idno type="IDREF">https://www.idref.fr/227824776</idno>
                  <affiliation ref="#struct-205125"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ndeye</forename>
                    <surname>Coumba Ndiaye</surname>
                  </persName>
                  <idno type="halauthorid">581693-0</idno>
                  <affiliation ref="#struct-223041"/>
                </author>
                <author role="crp">
                  <persName>
                    <forename type="first">Adrien</forename>
                    <surname>Coulet</surname>
                  </persName>
                  <email type="md5">cbac31e20d8f0cbf0f870c991a79335e</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">coulet</idno>
                  <idno type="idhal" notation="numeric">1742</idno>
                  <idno type="halauthorid" notation="string">11918-1742</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1466-062X</idno>
                  <idno type="IDREF">https://www.idref.fr/134214099</idno>
                  <affiliation ref="#struct-205125"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Semantic Web Applications and Tools for Life Sciences (SWAT4LS) 2015</title>
                  <date type="start">2015-12-08</date>
                  <date type="end">2015-12-09</date>
                  <settlement>Cambridge</settlement>
                  <country key="GB">United Kingdom</country>
                </meeting>
                <imprint>
                  <biblScope unit="serie">Proceedings of the Semantic Web Applications and Tools for Life Sciences (SWAT4LS) 2015</biblScope>
                  <date type="datePub">2015-12-08</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en"> pharmacogenes</term>
                <term xml:lang="en"> pharmacogenomics</term>
                <term xml:lang="en"> random forest</term>
                <term xml:lang="en"> Link prediction</term>
                <term xml:lang="en"> Data mining</term>
                <term xml:lang="en"> Linked Open Data</term>
                <term xml:lang="en">Linked Data</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-db">Computer Science [cs]/Databases [cs.DB]</classCode>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halDomain" n="info.info-bi">Computer Science [cs]/Bioinformatics [q-bio.QM]</classCode>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</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>A standard task in pharmacogenomics research is identifying genes that may be involved in drug response variability, i.e., pharmacogenes. Because genomic experiments tended to generate many false positives, computational approaches based on the use of background knowledge have been proposed. Until now, those have used only molecular networks or the biomedical literature. Here we propose a novel method that consumes an eclectic set of linked data sources to help validating uncertain drug–gene relationships. One of the advantages relies on that linked data are implemented in a standard framework that facilitates the joint use of various sources, making easy the consideration of features of various origins. Consequently, we propose an initial selection of linked data sources relevant to pharmacogenomics. We formatted these data to train a random forest algorithm , producing a model that enables classifying drug–gene pairs as related or not, thus confirming the validity of candidate pharmacogenes. Our model achieve the performance of F-measure=0.92, on a 100 folds cross-validation. A list of top candidates is provided and their obtention is discussed.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-205125" status="OLD">
          <idno type="RNSR">200818291B</idno>
          <orgName>Knowledge  representation, reasonning</orgName>
          <orgName type="acronym">ORPAILLEUR</orgName>
          <date type="start">2008-01-01</date>
          <date type="end">2020-06-30</date>
          <desc>
            <address>
              <addrLine>Centre Inria de l'Université de Lorraine , 615 Rue du Jardin-Botanique, 54600 Villers-lès-Nancy</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/orpailleur</ref>
          </desc>
          <listRelation>
            <relation active="#struct-129671" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-423086" type="direct"/>
            <relation active="#struct-206040" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-413289" type="indirect"/>
            <relation name="UMR7503" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-223041" status="OLD">
          <idno type="IdRef">185415075</idno>
          <idno type="RNSR">201320745X</idno>
          <idno type="IdUnivLorraine">[UL]RNB--</idno>
          <idno type="ROR">https://ror.org/01evjjx71</idno>
          <orgName>Interactions Gène-Environnement en Physiopathologie Cardio-Vasculaire</orgName>
          <orgName type="acronym">IGE-PCV</orgName>
          <date type="start">2013-01-01</date>
          <date type="end">2023-12-31</date>
          <desc>
            <address>
              <addrLine>Université de Lorraine, 30 rue Lionnois, 54000 Nancy</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://ige-pcv.univ-lorraine.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMRS1122" active="#struct-303623" type="direct"/>
            <relation active="#struct-413289" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-129671" status="VALID">
          <idno type="RNSR">198618246Y</idno>
          <idno type="ROR">https://ror.org/03fcjvn64</idno>
          <orgName>Centre Inria de l'Université de Lorraine</orgName>
          <desc>
            <address>
              <addrLine>615 rue du Jardin Botanique 54600 Villers-lès-Nancy</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/nancy</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-423086" status="VALID">
          <orgName>Department of Natural Language Processing &amp; Knowledge Discovery</orgName>
          <orgName type="acronym">LORIA - NLPKD</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr/en/research/departments/natural-language-processing-and-knowledge-discovery/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-206040" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-413289" type="indirect"/>
            <relation name="UMR7503" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-206040" status="VALID">
          <idno type="IdRef">067077927</idno>
          <idno type="ISNI">0000000121795429</idno>
          <idno type="RNSR">198912571S</idno>
          <idno type="IdUnivLorraine">[UL]RSI--</idno>
          <idno type="ROR">https://ror.org/02vnf0c38</idno>
          <orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
          <orgName type="acronym">LORIA</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation active="#struct-413289" type="direct"/>
            <relation name="UMR7503" active="#struct-441569" type="direct"/>
          </listRelation>
        </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="institution" xml:id="struct-413289" status="VALID">
          <idno type="IdRef">157040569</idno>
          <idno type="IdUnivLorraine">[UL]100--</idno>
          <idno type="ROR">https://ror.org/04vfs2w97</idno>
          <orgName>Université de Lorraine</orgName>
          <orgName type="acronym">UL</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lorraine.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-303623" status="VALID">
          <idno type="IdRef">026388278</idno>
          <idno type="ROR">https://ror.org/02vjkv261</idno>
          <orgName>Institut National de la Santé et de la Recherche Médicale</orgName>
          <orgName type="acronym">INSERM</orgName>
          <desc>
            <address>
              <addrLine>101, rue de Tolbiac, 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inserm.fr</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-42001" status="VALID">
          <idno type="anr">ANR-15-CE23-0028</idno>
          <idno type="program">Interactions humain-machine, objets connectés, contenus numériques, données massives et connaissance</idno>
          <orgName>PractiKPharma</orgName>
          <desc>Confrontation entre connaissances de l'état de l'art et connaissances extraites de dossiers patients en pharmacogénomique</desc>
          <date type="start">2015</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>