<?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-01819547</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="2026-05-03T11:15:10+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Feature extraction in protein sequences classification: a new stability measure</title>
            <author role="aut">
              <persName>
                <forename type="first">Saidi</forename>
                <surname>Rabie</surname>
              </persName>
              <idno type="halauthorid">825622-0</idno>
              <affiliation ref="#struct-182329"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Sabeur</forename>
                <surname>Aridhi</surname>
              </persName>
              <email type="md5">c49523893800b47fac47ee4fe2ec605b</email>
              <email type="domain">loria.fr</email>
              <idno type="idhal" notation="string">sabeur-aridhi</idno>
              <idno type="idhal" notation="numeric">16269</idno>
              <idno type="halauthorid" notation="string">36350-16269</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-3657-3762</idno>
              <idno type="IDREF">https://www.idref.fr/17650513X</idno>
              <affiliation ref="#struct-420402"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Engelbert</forename>
                <surname>Mephu Nguifo</surname>
              </persName>
              <email type="md5">340c79834e003602a20cf2cd078c78de</email>
              <email type="domain">isima.fr</email>
              <idno type="idhal" notation="string">engelbert-mephu-nguifo</idno>
              <idno type="idhal" notation="numeric">15514</idno>
              <idno type="halauthorid" notation="string">36031-15514</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-9119-678X</idno>
              <idno type="IDREF">https://www.idref.fr/087624257</idno>
              <idno type="ARXIV">https://arxiv.org/a/mephunguifo_e_1</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/A-4769-2019</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/A-4769-2019</idno>
              <affiliation ref="#struct-490706"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mondher</forename>
                <surname>Maddouri</surname>
              </persName>
              <email type="md5">67c3471173e0ab2739423a36f6454f7f</email>
              <email type="domain">yahoo.fr</email>
              <idno type="idhal" notation="numeric">963050</idno>
              <idno type="halauthorid" notation="string">881519-963050</idno>
              <affiliation ref="#struct-253756"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Sabeur</forename>
                <surname>Aridhi</surname>
              </persName>
              <email type="md5">c49523893800b47fac47ee4fe2ec605b</email>
              <email type="domain">loria.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2018-06-20 15:41:37</date>
              <date type="whenModified">2026-02-25 12:00:02</date>
              <date type="whenReleased">2018-06-20 15:41:37</date>
              <date type="whenProduced">2012-10-07</date>
              <ref type="externalLink" target="http://arxiv.org/pdf/1206.4822"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="177606">
                <persName>
                  <forename>Sabeur</forename>
                  <surname>Aridhi</surname>
                </persName>
                <email type="md5">c49523893800b47fac47ee4fe2ec605b</email>
                <email type="domain">loria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01819547</idno>
            <idno type="halUri">https://inria.hal.science/hal-01819547</idno>
            <idno type="halBibtex">rabie:hal-01819547</idno>
            <idno type="halRefHtml">&lt;i&gt;ACM BCB 2012 - Conference on Bioinformatics, Computational Biology and Biomedicine&lt;/i&gt;, Oct 2012, Orlando, United States. &lt;a target="_blank" href="https://dx.doi.org/10.1145/2382936.2383060"&gt;&amp;#x27E8;10.1145/2382936.2383060&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">ACM BCB 2012 - Conference on Bioinformatics, Computational Biology and Biomedicine, Oct 2012, Orlando, United States. &amp;#x27E8;10.1145/2382936.2383060&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="PRES_CLERMONT">Université de Clermont</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="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="LIMOS" corresp="PRES_CLERMONT">Laboratoire d'Informatique, de Modélisation et d'optimisation des Systèmes</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-AIS" corresp="LORIA">Department of Complex Systems, Artificial Intelligence  &amp; Robotics</idno>
            <idno type="stamp" n="CLERMONT-AUVERGNE-INP">Clermont Auvergne INP</idno>
            <idno type="stamp" n="TEST3-HALCNRS">TEST3-HALCNRS</idno>
            <idno type="stamp" n="INRIA-ROYAUMEUNI">INRIA-ROYAUMEUNI</idno>
            <idno type="stamp" n="INRIA-ALLEMAGNE">INRIA-ALLEMAGNE</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="1">Yes</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">Feature extraction in protein sequences classification: a new stability measure</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Saidi</forename>
                    <surname>Rabie</surname>
                  </persName>
                  <idno type="halauthorid">825622-0</idno>
                  <affiliation ref="#struct-182329"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Sabeur</forename>
                    <surname>Aridhi</surname>
                  </persName>
                  <email type="md5">c49523893800b47fac47ee4fe2ec605b</email>
                  <email type="domain">loria.fr</email>
                  <idno type="idhal" notation="string">sabeur-aridhi</idno>
                  <idno type="idhal" notation="numeric">16269</idno>
                  <idno type="halauthorid" notation="string">36350-16269</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-3657-3762</idno>
                  <idno type="IDREF">https://www.idref.fr/17650513X</idno>
                  <affiliation ref="#struct-420402"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Engelbert</forename>
                    <surname>Mephu Nguifo</surname>
                  </persName>
                  <email type="md5">340c79834e003602a20cf2cd078c78de</email>
                  <email type="domain">isima.fr</email>
                  <idno type="idhal" notation="string">engelbert-mephu-nguifo</idno>
                  <idno type="idhal" notation="numeric">15514</idno>
                  <idno type="halauthorid" notation="string">36031-15514</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-9119-678X</idno>
                  <idno type="IDREF">https://www.idref.fr/087624257</idno>
                  <idno type="ARXIV">https://arxiv.org/a/mephunguifo_e_1</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/A-4769-2019</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/A-4769-2019</idno>
                  <affiliation ref="#struct-490706"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mondher</forename>
                    <surname>Maddouri</surname>
                  </persName>
                  <email type="md5">67c3471173e0ab2739423a36f6454f7f</email>
                  <email type="domain">yahoo.fr</email>
                  <idno type="idhal" notation="numeric">963050</idno>
                  <idno type="halauthorid" notation="string">881519-963050</idno>
                  <affiliation ref="#struct-253756"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>ACM BCB 2012 - Conference on Bioinformatics, Computational Biology and Biomedicine</title>
                  <date type="start">2012-10-07</date>
                  <date type="end">2012-10-10</date>
                  <settlement>Orlando</settlement>
                  <country key="US">United States</country>
                </meeting>
                <imprint>
                  <publisher>ACM Press</publisher>
                </imprint>
              </monogr>
              <idno type="arxiv">1206.4822</idno>
              <idno type="doi">10.1145/2382936.2383060</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-db">Computer Science [cs]/Databases [cs.DB]</classCode>
              <classCode scheme="halDomain" n="info.info-bi">Computer Science [cs]/Bioinformatics [q-bio.QM]</classCode>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
              <classCode scheme="halDomain" n="info.info-dc">Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC]</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>Feature extraction is an unavoidable task, especially in the critical step of preprocessing biological sequences. This step consists for example in transforming the biological sequences into vectors of motifs where each motif is a subsequence that can be seen as a property (or attribute) characterizing the sequence. Hence, we obtain an object-property table where objects are sequences and properties are motifs extracted from sequences. This output can be used to apply standard machine learning tools to perform data mining tasks such as classification. Several previous works have described feature extraction methods for bio-sequence classification, but none of them discussed the robustness of these methods when perturbing the input data. In this work, we introduce the notion of stability of the generated motifs in order to study the robustness of motif extraction methods. We express this robustness in terms of the ability of the method to reveal any change occurring in the input data and also its ability to target the interesting motifs. We use these criteria to evaluate and experimentally compare four existing extraction methods for biological sequences.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-182329" status="VALID">
          <orgName>European Bioinformatics Institute [Hinxton]</orgName>
          <orgName type="acronym">EMBL-EBI</orgName>
          <desc>
            <address>
              <addrLine>EMBL-EBI, Wellcome Trust Genome Campus, Hinxton, Cambridgeshire, CB10 1SD, UK</addrLine>
              <country key="GB"/>
            </address>
            <ref type="url">http://www.ebi.ac.uk/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-307014" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-420402" status="VALID">
          <idno type="RNSR">201521171B</idno>
          <idno type="ROR">https://ror.org/02m9pkf41</idno>
          <orgName>Computational Algorithms for Protein Structures and Interactions</orgName>
          <orgName type="acronym">CAPSID</orgName>
          <date type="start">2015-07-01</date>
          <date type="end">2025-11-30</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/capsid</ref>
          </desc>
          <listRelation>
            <relation active="#struct-129671" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-423090" 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-490706" status="OLD">
          <idno type="IdRef">155645919</idno>
          <idno type="RNSR">200212221E</idno>
          <orgName>Laboratoire d'Informatique, de Modélisation et d'Optimisation des Systèmes</orgName>
          <orgName type="acronym">LIMOS</orgName>
          <date type="start">2017-01-01</date>
          <date type="end">2020-12-31</date>
          <desc>
            <address>
              <addrLine>Campus Universitaire des Cézeaux, 1 rue de la Chebarde, TSA 60125 / CS 60026, 63178 Aubière Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://limos.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR6158" active="#struct-359750" type="direct"/>
            <relation name="UMR6158" active="#struct-422708" type="direct"/>
            <relation name="UMR6158" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-253756" status="VALID">
          <idno type="ROR">https://ror.org/01xv1nn60</idno>
          <orgName>Taibah University</orgName>
          <desc>
            <address>
              <addrLine>Janadah Bin Umayyah Road, Tayba، Tayba, Medina 42353</addrLine>
              <country key="SA"/>
            </address>
            <ref type="url">https://www.taibahu.edu.sa/Pages/EN/Home.aspx</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-307014" status="VALID">
          <orgName>EMBL Heidelberg</orgName>
          <desc>
            <address>
              <addrLine>Meyerhofstraße 1 69117 Heidelberg</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">http://www.embl.de/</ref>
          </desc>
        </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-423090" status="VALID">
          <orgName>Department of Complex Systems, Artificial Intelligence &amp; Robotics</orgName>
          <orgName type="acronym">LORIA - AIS</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr/en/research/departments/complex-systems-artificial-intelligence-and-robotics/</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-359750" status="VALID">
          <idno type="IdRef">028028694</idno>
          <orgName>Ecole Nationale Supérieure des Mines de St Etienne</orgName>
          <orgName type="acronym">ENSM ST-ETIENNE</orgName>
          <date type="start">1816-01-01</date>
          <desc>
            <address>
              <addrLine>158 Cour Fauriel, 42100 Saint-Étienne</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.mines-stetienne.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-422708" status="OLD">
          <idno type="IdRef">196200032</idno>
          <idno type="ROR">https://ror.org/01a8ajp46</idno>
          <orgName>Université Clermont Auvergne [2017-2020]</orgName>
          <orgName type="acronym">UCA  [2017-2020]</orgName>
          <date type="start">2017-01-01</date>
          <date type="end">2020-12-31</date>
          <desc>
            <address>
              <addrLine>49, bd François-Mitterrand / CS 60032 / 63001 Clermont-Ferrand Cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.uca.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>