<?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-04975216</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="2026-05-16T00:27:23+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">PREDICTING BACTERIAL SECRETION SYSTEM PROTEINS USING POSITIVE AND UNLABELED MACHINE LEARNING</title>
            <title xml:lang="fr">PRÉDIRE LES PROTÉINES DU SYSTÈME DE SÉCRÉTION BACTÉRIEN À L'AIDE DE L'APPRENTISSAGE AUTOMATIQUE POSITIVE AND UNLABELED</title>
            <author role="aut">
              <persName>
                <forename type="first">Sandy</forename>
                <surname>Frank</surname>
              </persName>
              <idno type="halauthorid">3435784-0</idno>
              <affiliation ref="#struct-1069752"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Kwamou</forename>
                <surname>Ngaha</surname>
              </persName>
              <idno type="halauthorid">3435785-0</idno>
              <affiliation ref="#struct-1069752"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Renato</forename>
                <forename type="middle">Augusto</forename>
                <surname>Antoniassi Battistin</surname>
              </persName>
              <idno type="halauthorid">3435786-0</idno>
              <affiliation ref="#struct-1069752"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Sophie</forename>
                <surname>Abby</surname>
              </persName>
              <idno type="halauthorid">2779204-0</idno>
              <affiliation ref="#struct-1069752"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Nelle</forename>
                <surname>Varoquaux</surname>
              </persName>
              <idno type="halauthorid">24098-0</idno>
              <affiliation ref="#struct-1069752"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Sandy Frank</forename>
                <surname>KWAMOU NGAHA</surname>
              </persName>
              <email type="md5">374f58c7b7f46c7efc1305e2c1c7e786</email>
              <email type="domain">aims-cameroon.org</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-03-04 09:20:33</date>
              <date type="whenModified">2025-09-27 18:38:26</date>
              <date type="whenReleased">2025-03-04 09:43:55</date>
              <date type="whenProduced">2024-06-25</date>
              <date type="whenEndEmbargoed">2025-03-04</date>
              <ref type="file" target="https://hal.science/hal-04975216v1/document">
                <date notBefore="2025-03-04"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-04975216v1/file/JOBIM_poster_2024-4.pdf" id="file-4975216-4312745">
                <date notBefore="2025-03-04"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1534527">
                <persName>
                  <forename>Sandy Frank</forename>
                  <surname>KWAMOU NGAHA</surname>
                </persName>
                <email type="md5">374f58c7b7f46c7efc1305e2c1c7e786</email>
                <email type="domain">aims-cameroon.org</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04975216</idno>
            <idno type="halUri">https://hal.science/hal-04975216</idno>
            <idno type="halBibtex">frank:hal-04975216</idno>
            <idno type="halRefHtml">&lt;i&gt;JOBIM 2024&lt;/i&gt;, Jun 2024, Toulouse, France</idno>
            <idno type="halRef">JOBIM 2024, Jun 2024, Toulouse, France</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-4975216-4312745"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UGA">HAL Grenoble Alpes</idno>
            <idno type="stamp" n="IMAG">IMAG</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INPG">Institut polytechnique de Grenoble</idno>
            <idno type="stamp" n="TIMC-IMAG">TIMC</idno>
            <idno type="stamp" n="UNIV-LYON">Université de Lyon</idno>
            <idno type="stamp" n="UGA-EPE">Université Grenoble Alpes [2020-*]</idno>
            <idno type="stamp" n="TIMC-TREE" corresp="TIMC-IMAG">TrEE : Translational microbial Evolution and Engineering</idno>
            <idno type="stamp" n="TEST-UGA">TEST-UGA</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="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">PREDICTING BACTERIAL SECRETION SYSTEM PROTEINS USING POSITIVE AND UNLABELED MACHINE LEARNING</title>
                <title xml:lang="fr">PRÉDIRE LES PROTÉINES DU SYSTÈME DE SÉCRÉTION BACTÉRIEN À L'AIDE DE L'APPRENTISSAGE AUTOMATIQUE POSITIVE AND UNLABELED</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Sandy</forename>
                    <surname>Frank</surname>
                  </persName>
                  <idno type="halauthorid">3435784-0</idno>
                  <affiliation ref="#struct-1069752"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Kwamou</forename>
                    <surname>Ngaha</surname>
                  </persName>
                  <idno type="halauthorid">3435785-0</idno>
                  <affiliation ref="#struct-1069752"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Renato</forename>
                    <forename type="middle">Augusto</forename>
                    <surname>Antoniassi Battistin</surname>
                  </persName>
                  <idno type="halauthorid">3435786-0</idno>
                  <affiliation ref="#struct-1069752"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Sophie</forename>
                    <surname>Abby</surname>
                  </persName>
                  <idno type="halauthorid">2779204-0</idno>
                  <affiliation ref="#struct-1069752"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Nelle</forename>
                    <surname>Varoquaux</surname>
                  </persName>
                  <idno type="halauthorid">24098-0</idno>
                  <affiliation ref="#struct-1069752"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>JOBIM 2024</title>
                  <date type="start">2024-06-25</date>
                  <date type="end">2024-06-28</date>
                  <settlement>Toulouse</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Secretion systems</term>
                <term xml:lang="en">PU Learning</term>
              </keywords>
              <classCode scheme="halDomain" n="sdv.bc">Life Sciences [q-bio]/Cellular Biology</classCode>
              <classCode scheme="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</classCode>
              <classCode scheme="halTypology" n="POSTER">Poster communications</classCode>
              <classCode scheme="halOldTypology" n="POSTER">Poster communications</classCode>
              <classCode scheme="halTreeTypology" n="POSTER">Poster communications</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Proteins are biological molecules made of amino acids that group into hundreds of thousands of different families, involved in functions ranging from structural to chemical roles.They often partner up to fulfil cellular functions and assemble into macro-molecular systems such as secretion systems. The known 12 types of secretion systems play vital roles in prokaryotic organisms as they are used by the organism to interact with their environment for nutrient acquisition, defense, and toxin delivery etc.Current methods for assessing a system's distribution use comparative approaches, analysing protein sequence similarities and genomics organisation. However, given that proteins with different sequences can perform the same function, sequence comparison has limitations that can be overcome by machine learning approaches.We have trained Positive-Unlabeled machine learning classifier to predict whether a given bacterial protein is part of a secretion system and developed a cross validation strategy that avoids the biased performance due to evolutionary similar organisms.</p>
            </abstract>
            <abstract xml:lang="fr">
              <p>Les protéines sont des molécules biologiques composées d'acides aminés qui se regroupent en centaines de milliers de familles différentes, dont les fonctions vont de la structure à la chimie.Elles s'associent souvent pour remplir des fonctions cellulaires et s'assemblent en systèmes macromoléculaires tels que les systèmes de sécrétion. Les 12 types connus de systèmes de sécrétion jouent un rôle vital dans les organismes procaryotes, car ils sont utilisés par l'organisme pour interagir avec son environnement en vue de l'acquisition de nutriments, de la défense, de l'administration de toxines, etc.Les méthodes actuelles d'évaluation de la distribution d'un système utilisent des approches comparatives, analysant les similitudes de séquences protéiques et l'organisation génomique. Cependant, étant donné que des protéines ayant des séquences différentes peuvent remplir la même fonction, la comparaison des séquences présente des limites qui peuvent être surmontées par des approches d'apprentissage automatique.Nous avons entraîné un classifieur PU pour prédire si une protéine bactérienne donnée fait partie d'un système de sécrétion et nous avons développé une stratégie de validation croisée qui évite les performances biaisées dues à des organismes similaires du point de vue de l'évolution.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-1069752" status="VALID">
          <orgName>Translational microbial Evolution and Engineering</orgName>
          <orgName type="acronym">TIMC-TrEE</orgName>
          <date type="start">2021-01-01</date>
          <desc>
            <address>
              <addrLine>Faculté de médecine de Grenoble, bâtiment Jean Roget, 38706 La Tronche</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.timc.fr/TrEE</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1043049" type="direct"/>
            <relation active="#struct-301767" type="indirect"/>
            <relation name="UMR5525" active="#struct-441569" type="indirect"/>
            <relation active="#struct-1042703" type="indirect"/>
            <relation active="#struct-1043329" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1043049" status="VALID">
          <idno type="IdRef">14728936X</idno>
          <idno type="ISNI">0000 0004 4687 1979</idno>
          <idno type="RNSR">199511969L</idno>
          <idno type="ROR">https://ror.org/03985kf35</idno>
          <orgName>Translational Innovation in Medicine and Complexity / Recherche Translationnelle et Innovation en Médecine et Complexité - UMR 5525</orgName>
          <orgName type="acronym">TIMC</orgName>
          <date type="start">2021-01-01</date>
          <desc>
            <address>
              <addrLine>Domaine de la Merci, 38706 La Tronche, France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.timc.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301767" type="direct"/>
            <relation name="UMR5525" active="#struct-441569" type="direct"/>
            <relation active="#struct-1042703" type="direct"/>
            <relation active="#struct-1043329" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-301767" status="VALID">
          <idno type="ROR">https://ror.org/01c7wz417</idno>
          <orgName>VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement</orgName>
          <orgName type="acronym">VAS</orgName>
          <date type="start">2010-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Lyon, VetAgro Sup, 69280 Marcy l'Etoile (campus vétérinaire); Université de Clermont, VetAgro Sup, 63370 Lempdes (campus agronomique)</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.vetagro-sup.fr/</ref>
          </desc>
        </org>
        <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="regroupinstitution" xml:id="struct-1042703" status="VALID">
          <idno type="IdRef">240648315</idno>
          <idno type="ROR">https://ror.org/02rx3b187</idno>
          <orgName>Université Grenoble Alpes</orgName>
          <orgName type="acronym">UGA</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Adresse CS 40700 - 38058 Grenoble cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-grenoble-alpes.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-1043329" status="VALID">
          <idno type="IdRef">026388804</idno>
          <idno type="ROR">https://ror.org/05sbt2524</idno>
          <orgName>Institut polytechnique de Grenoble - Grenoble Institute of Technology</orgName>
          <orgName type="acronym">Grenoble INP</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>46 avenue Félix Viallet 38031 Grenoble Cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.grenoble-inp.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1042703" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>