<?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 inria-00543910</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="2026-05-23T00:25:09+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">IntelliGO: a new vector-based semantic similarity measure including annotation origin</title>
            <author role="crp">
              <persName>
                <forename type="first">Sidahmed</forename>
                <surname>Benabderrahmane</surname>
              </persName>
              <email type="md5">a981507ca9b20f698496f069ec63d226</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="numeric">917540</idno>
              <idno type="halauthorid" notation="string">399643-917540</idno>
              <affiliation ref="#struct-2358"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Malika</forename>
                <surname>Smaïl-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">677-2054</idno>
              <idno type="IDREF">https://www.idref.fr/190929065</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-8119-2117</idno>
              <affiliation ref="#struct-2358"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Olivier</forename>
                <surname>Poch</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">13685-181632</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>
            <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-2358"/>
            </author>
            <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-2358"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Sidahmed</forename>
                <surname>Benabderrahmane</surname>
              </persName>
              <email type="md5">a981507ca9b20f698496f069ec63d226</email>
              <email type="domain">gmail.com</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2010-12-07 16:29:33</date>
              <date type="whenModified">2025-11-04 12:01:57</date>
              <date type="whenReleased">2010-12-09 11:33:28</date>
              <date type="whenProduced">2010-12-01</date>
              <date type="whenEndEmbargoed">2010-12-07</date>
              <ref type="file" target="https://inria.hal.science/inria-00543910v1/document">
                <date notBefore="2010-12-07"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://inria.hal.science/inria-00543910v1/file/IntelliGO_a_new_vector-based_semantic_similarity_measure_including_annotation_origin.pdf" id="file-543910-465820">
                <date notBefore="2010-12-07"/>
              </ref>
              <ref type="externalLink" target="https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/1471-2105-11-588"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="141812">
                <persName>
                  <forename>Sidahmed</forename>
                  <surname>Benabderrahmane</surname>
                </persName>
                <email type="md5">a981507ca9b20f698496f069ec63d226</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">inria-00543910</idno>
            <idno type="halUri">https://inria.hal.science/inria-00543910</idno>
            <idno type="halBibtex">benabderrahmane:inria-00543910</idno>
            <idno type="halRefHtml">&lt;i&gt;BMC Bioinformatics&lt;/i&gt;, 2010, 11, 11 (1), pp.588. &lt;a target="_blank" href="https://dx.doi.org/10.1186/1471-2105-11-588"&gt;&amp;#x27E8;10.1186/1471-2105-11-588&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">BMC Bioinformatics, 2010, 11, 11 (1), pp.588. &amp;#x27E8;10.1186/1471-2105-11-588&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-543910-465820"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="INSERM">INSERM - Institut national de la santé et de la recherche médicale</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="IGBMC" corresp="INSERM">Institut Génétique de Biologie Moléculaire et Cellulaire</idno>
            <idno type="stamp" n="INPL">Institut National Polytechnique de Lorraine</idno>
            <idno type="stamp" n="UNIV-STRASBG">Université de Strasbourg</idno>
            <idno type="stamp" n="INRIA-LORRAINE">INRIA Nancy - Grand Est</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="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">IntelliGO: a new vector-based semantic similarity measure including annotation origin</title>
                <author role="crp">
                  <persName>
                    <forename type="first">Sidahmed</forename>
                    <surname>Benabderrahmane</surname>
                  </persName>
                  <email type="md5">a981507ca9b20f698496f069ec63d226</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="numeric">917540</idno>
                  <idno type="halauthorid" notation="string">399643-917540</idno>
                  <affiliation ref="#struct-2358"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Malika</forename>
                    <surname>Smaïl-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">677-2054</idno>
                  <idno type="IDREF">https://www.idref.fr/190929065</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-8119-2117</idno>
                  <affiliation ref="#struct-2358"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Olivier</forename>
                    <surname>Poch</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">13685-181632</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>
                <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-2358"/>
                </author>
                <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-2358"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">312</idno>
                <idno type="issn">1471-2105</idno>
                <title level="j">BMC Bioinformatics</title>
                <imprint>
                  <publisher>BioMed Central</publisher>
                  <biblScope unit="serie">11</biblScope>
                  <biblScope unit="volume">11</biblScope>
                  <biblScope unit="issue">1</biblScope>
                  <biblScope unit="pp">588</biblScope>
                  <date type="datePub">2010-12-01</date>
                  <date type="dateEpub">2010-12-01</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1186/1471-2105-11-588</idno>
              <idno type="pubmed">21122125</idno>
              <ref target="http://www.ncbi.nlm.nih.gov/pubmed/21122125?dopt=Abstract" type="seeAlso"/>
              <ref type="publisher">http://www.biomedcentral.com/1471-2105/11/588/abstract</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Semantic similarity measure</term>
                <term xml:lang="en">Gene Ontology</term>
                <term xml:lang="en">Gene functional clustering</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ir">Computer Science [cs]/Information Retrieval [cs.IR]</classCode>
              <classCode scheme="halDomain" n="sdv.bibs">Life Sciences [q-bio]/Quantitative Methods [q-bio.QM]</classCode>
              <classCode scheme="halDomain" n="info.info-bi">Computer Science [cs]/Bioinformatics [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>The Gene Ontology (GO) is a well known controlled vocabulary describing the biological process, molecular function and cellular component aspects of gene annotation. It has become a widely used knowledge source in bioinformatics for annotating genes and measuring their semantic similarity. These measures generally involve the GO graph structure, the information content of GO aspects, or a combination of both. However, only a few of the semantic similarity measures described so far can handle GO annotations differently according to their origin (i.e. their evidence codes). RESULTS: We present here a new semantic similarity measure called IntelliGO which integrates several complementary properties in a novel vector space model. The coefficients associated with each GO term that annotates a given gene or protein include its information content as well as a customized value for each type of GO evidence code. The generalized cosine similarity measure, used for calculating the dot product between two vectors, has been rigorously adapted to the context of the GO graph. The IntelliGO similarity measure is tested on two benchmark datasets consisting of KEGG pathways and Pfam domains grouped as clans, considering the GO biological process and molecular function terms, respectively, for a total of 683 yeast and human genes and involving more than 67,900 pair-wise comparisons. The ability of the IntelliGO similarity measure to express the biological cohesion of sets of genes compares favourably to four existing similarity measures. For inter-set comparison, it consistently discriminates between distinct sets of genes. Furthermore, the IntelliGO similarity measure allows the influence of weights assigned to evidence codes to be checked. Finally, the results obtained with a complementary reference technique give intermediate but correct correlation values with the sequence similarity, Pfam, and Enzyme classifications when compared to previously published measures. CONCLUSIONS: The IntelliGO similarity measure provides a customizable and comprehensive method for quantifying gene similarity based on GO annotations. It also displays a robust set-discriminating power which suggests it will be useful for functional clustering. AVAILABILITY: An on-line version of the IntelliGO similarity measure is available at: http://bioinfo.loria.fr/Members/benabdsi/intelligo_project/</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-2358" status="OLD">
          <idno type="RNSR">200818291B</idno>
          <orgName>Knowledge  representation, reasonning</orgName>
          <orgName type="acronym">ORPAILLEUR</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/orpailleur</ref>
          </desc>
          <listRelation>
            <relation active="#struct-2496" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-466633" type="direct"/>
            <relation active="#struct-300291" type="indirect"/>
            <relation active="#struct-300292" type="indirect"/>
            <relation active="#struct-300293" 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-2496" status="OLD">
          <orgName>INRIA 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/centre-de-recherche-inria/nancy-grand-est</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-466633" status="OLD">
          <orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
          <orgName type="acronym">LORIA</orgName>
          <date type="start">1997-01-01</date>
          <date type="end">2011-12-31</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-300291" type="direct"/>
            <relation active="#struct-300292" type="direct"/>
            <relation active="#struct-300293" type="direct"/>
            <relation name="UMR7503" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300291" status="OLD">
          <orgName>Université Henri Poincaré - Nancy 1</orgName>
          <orgName type="acronym">UHP</orgName>
          <date type="end">2011-12-31</date>
          <desc>
            <address>
              <addrLine>24-30 rue Lionnois, BP 60120, 54 003 NANCY cedex, France</addrLine>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300292" status="OLD">
          <orgName>Université Nancy 2</orgName>
          <date type="end">2011-12-31</date>
          <desc>
            <address>
              <addrLine>91 avenue de la Libération, BP 454, 54001 Nancy cedex</addrLine>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300293" status="OLD">
          <orgName>Institut National Polytechnique de Lorraine</orgName>
          <orgName type="acronym">INPL</orgName>
          <date type="end">2011-12-31</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </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>