<?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-00734329</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="2026-05-24T02:29:38+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Functional classification of genes using semantic distance and fuzzy clustering approach: Evaluation with reference sets and overlap analysis</title>
            <author role="aut">
              <persName>
                <forename type="first">Marie-Dominique</forename>
                <surname>Devignes</surname>
              </persName>
              <email type="md5">4efdcc3bd197db60205e265b65c0db0f</email>
              <email type="domain">loria.fr</email>
              <idno type="idhal" notation="string">mddevignes</idno>
              <idno type="idhal" notation="numeric">742369</idno>
              <idno type="halauthorid" notation="string">42325-742369</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0399-8713</idno>
              <idno type="IDREF">https://www.idref.fr/134215001</idno>
              <affiliation ref="#struct-205125"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Benabderrahmane</forename>
                <surname>Sidahmed</surname>
              </persName>
              <idno type="halauthorid">660395-0</idno>
              <affiliation ref="#struct-205125"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Malika</forename>
                <surname>Smail-Tabbone</surname>
              </persName>
              <email type="md5">61e7a15bc47488f97f791589b2ce650b</email>
              <email type="domain">loria.fr</email>
              <idno type="idhal" notation="string">malika-smail-tabbone</idno>
              <idno type="idhal" notation="numeric">2054</idno>
              <idno type="halauthorid" notation="string">364128-2054</idno>
              <idno type="IDREF">https://www.idref.fr/190929065</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-8119-2117</idno>
              <affiliation ref="#struct-205125"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Amedeo</forename>
                <surname>Napoli</surname>
              </persName>
              <email type="md5">a9f4e75c5c51e89472d4cad3a9a5cf0b</email>
              <email type="domain">loria.fr</email>
              <idno type="idhal" notation="string">amedeo-napoli</idno>
              <idno type="idhal" notation="numeric">743383</idno>
              <idno type="halauthorid" notation="string">23717-743383</idno>
              <idno type="IDREF">https://www.idref.fr/034282297</idno>
              <affiliation ref="#struct-205125"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Poch</forename>
                <surname>Olivier</surname>
              </persName>
              <email type="md5">4fe991807fd84ba9fb805b8b7419fce1</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">olivier-poch</idno>
              <idno type="idhal" notation="numeric">181632</idno>
              <idno type="halauthorid" notation="string">660396-181632</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7134-3217</idno>
              <idno type="IDREF">https://www.idref.fr/070441553</idno>
              <affiliation ref="#struct-93800"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Malika</forename>
                <surname>Smail-Tabbone</surname>
              </persName>
              <email type="md5">61e7a15bc47488f97f791589b2ce650b</email>
              <email type="domain">loria.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2012-09-21 14:32:16</date>
              <date type="whenModified">2025-11-04 12:03:21</date>
              <date type="whenReleased">2012-09-21 14:32:16</date>
              <date type="whenProduced">2012</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="103146">
                <persName>
                  <forename>Malika</forename>
                  <surname>Smail-Tabbone</surname>
                </persName>
                <email type="md5">61e7a15bc47488f97f791589b2ce650b</email>
                <email type="domain">loria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00734329</idno>
            <idno type="halUri">https://inria.hal.science/hal-00734329</idno>
            <idno type="halBibtex">devignes:hal-00734329</idno>
            <idno type="halRefHtml">&lt;i&gt;International journal of computational biology and drug design&lt;/i&gt;, 2012, 5 (3/4), pp.245-260</idno>
            <idno type="halRef">International journal of computational biology and drug design, 2012, 5 (3/4), pp.245-260</idno>
            <availability status="restricted"/>
          </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="IGBMC" corresp="INSERM">Institut Génétique de Biologie Moléculaire et Cellulaire</idno>
            <idno type="stamp" n="UNIV-STRASBG">Université de Strasbourg</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="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="SITE-ALSACE">Archive ouverte du site Alsace</idno>
            <idno type="stamp" n="UNIVOAK">UNIVOAK</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="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Functional classification of genes using semantic distance and fuzzy clustering approach: Evaluation with reference sets and overlap analysis</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Marie-Dominique</forename>
                    <surname>Devignes</surname>
                  </persName>
                  <email type="md5">4efdcc3bd197db60205e265b65c0db0f</email>
                  <email type="domain">loria.fr</email>
                  <idno type="idhal" notation="string">mddevignes</idno>
                  <idno type="idhal" notation="numeric">742369</idno>
                  <idno type="halauthorid" notation="string">42325-742369</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0399-8713</idno>
                  <idno type="IDREF">https://www.idref.fr/134215001</idno>
                  <affiliation ref="#struct-205125"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Benabderrahmane</forename>
                    <surname>Sidahmed</surname>
                  </persName>
                  <idno type="halauthorid">660395-0</idno>
                  <affiliation ref="#struct-205125"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Malika</forename>
                    <surname>Smail-Tabbone</surname>
                  </persName>
                  <email type="md5">61e7a15bc47488f97f791589b2ce650b</email>
                  <email type="domain">loria.fr</email>
                  <idno type="idhal" notation="string">malika-smail-tabbone</idno>
                  <idno type="idhal" notation="numeric">2054</idno>
                  <idno type="halauthorid" notation="string">364128-2054</idno>
                  <idno type="IDREF">https://www.idref.fr/190929065</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-8119-2117</idno>
                  <affiliation ref="#struct-205125"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Amedeo</forename>
                    <surname>Napoli</surname>
                  </persName>
                  <email type="md5">a9f4e75c5c51e89472d4cad3a9a5cf0b</email>
                  <email type="domain">loria.fr</email>
                  <idno type="idhal" notation="string">amedeo-napoli</idno>
                  <idno type="idhal" notation="numeric">743383</idno>
                  <idno type="halauthorid" notation="string">23717-743383</idno>
                  <idno type="IDREF">https://www.idref.fr/034282297</idno>
                  <affiliation ref="#struct-205125"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Poch</forename>
                    <surname>Olivier</surname>
                  </persName>
                  <email type="md5">4fe991807fd84ba9fb805b8b7419fce1</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">olivier-poch</idno>
                  <idno type="idhal" notation="numeric">181632</idno>
                  <idno type="halauthorid" notation="string">660396-181632</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7134-3217</idno>
                  <idno type="IDREF">https://www.idref.fr/070441553</idno>
                  <affiliation ref="#struct-93800"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">112066</idno>
                <idno type="issn">1756-0756</idno>
                <idno type="eissn">1756-0764</idno>
                <title level="j">International journal of computational biology and drug design</title>
                <imprint>
                  <publisher>Inderscience Enterprise</publisher>
                  <biblScope unit="volume">5</biblScope>
                  <biblScope unit="issue">3/4</biblScope>
                  <biblScope unit="pp">245-260</biblScope>
                  <date type="datePub">2012</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">overlap analysis</term>
                <term xml:lang="en">fuzzy clustering</term>
                <term xml:lang="en">hierarchical clustering</term>
                <term xml:lang="en">gene functional classification</term>
                <term xml:lang="en">gene ontology</term>
                <term xml:lang="en">semantic similarity measure</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
              <classCode scheme="halDomain" n="info.info-bi">Computer Science [cs]/Bioinformatics [q-bio.QM]</classCode>
              <classCode scheme="halDomain" n="sdv.bibs">Life Sciences [q-bio]/Quantitative Methods [q-bio.QM]</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>Functional classification aims at grouping genes according to their molecular function or the biological process they participate in. Evaluating the validity of such unsupervised gene classification remains a challenge given the variety of distance measures and classification algorithms that can be used. We evaluate here functional classification of genes with the help of reference sets: KEGG (Kyoto Encyclopaedia of Genes and Genomes) pathways and Pfam clans. These sets represent ground truth for any distance based on GO (Gene Ontology) biological process and molecular function annotations respectively. Overlaps between clusters and reference sets are estimated by the F-score method. We test our previously described IntelliGO semantic distance with hierarchical and fuzzy C-means clustering and we compare results with the state-of-the-art DAVID (Database for Annotation Visualisation and Integrated Discovery) functional classification method. Finally, study of best matching clusters to reference sets leads us to propose a set-difference method for discovering missing information.</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-93800" status="VALID">
          <idno type="IdRef">155263749</idno>
          <idno type="ISNI">0000 0004 0638 2716</idno>
          <idno type="RNSR">200112491C</idno>
          <idno type="ROR">https://ror.org/0015ws592</idno>
          <idno type="Wikidata">Q3152004</idno>
          <orgName>Institut de Génétique et de Biologie Moléculaire et Cellulaire</orgName>
          <orgName type="acronym">IGBMC</orgName>
          <date type="start">2009-01-01</date>
          <desc>
            <address>
              <addrLine>Parc D'Innovation 1 Rue Laurent Fries - BP 10142 67404 Illkirch Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.igbmc.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMRS964" active="#struct-199013" type="direct"/>
            <relation name="U1258" active="#struct-303623" type="direct"/>
            <relation name="UMR7104" active="#struct-441569" 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-199013" status="VALID">
          <idno type="IdRef">131056549</idno>
          <idno type="ROR">https://ror.org/00pg6eq24</idno>
          <orgName>Université de Strasbourg</orgName>
          <orgName type="acronym">UNISTRA</orgName>
          <desc>
            <address>
              <addrLine>4 rue Blaise Pascal - CS 90032 - 67081 Strasbourg cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.unistra.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>
    </back>
  </text>
</TEI>