<?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-00514107</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="2026-05-15T19:25:00+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Over-optimism in bioinformatics: an illustration</title>
            <author role="aut">
              <persName>
                <forename type="first">Monika</forename>
                <surname>Jelizarow</surname>
              </persName>
              <idno type="halauthorid">488428-0</idno>
              <affiliation ref="#struct-562203"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Vincent</forename>
                <surname>Guillemot</surname>
              </persName>
              <email type="md5">a855b5d8d5bec670b0654c989ec20761</email>
              <email type="domain">pasteur.fr</email>
              <idno type="idhal" notation="string">vguillemot</idno>
              <idno type="idhal" notation="numeric">1042725</idno>
              <idno type="halauthorid" notation="string">301584-1042725</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7421-0655</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=VMpMbg0AAAAJ</idno>
              <affiliation ref="#struct-40525"/>
              <affiliation ref="#struct-123689"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Arthur</forename>
                <surname>Tenenhaus</surname>
              </persName>
              <email type="md5">c5e660f5db08d56a213a6d155a3ca7e8</email>
              <email type="domain">centralesupelec.fr</email>
              <idno type="idhal" notation="string">arthur-tenenhaus</idno>
              <idno type="idhal" notation="numeric">736979</idno>
              <idno type="halauthorid" notation="string">4562-736979</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-3459-1518</idno>
              <idno type="IDREF">https://www.idref.fr/115337822</idno>
              <affiliation ref="#struct-123689"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">K.</forename>
                <surname>Strimmer</surname>
              </persName>
              <idno type="halauthorid">488429-0</idno>
              <affiliation ref="#struct-562203"/>
            </author>
            <author role="crp">
              <persName>
                <forename type="first">Anne-Laure</forename>
                <surname>Boulesteix</surname>
              </persName>
              <email type="md5">442ca921cf6f72494fa81d80bb68744e</email>
              <email type="domain">ibe.med-uni-muenchen.de</email>
              <idno type="idhal" notation="numeric">878067</idno>
              <idno type="halauthorid" notation="string">488430-878067</idno>
              <affiliation ref="#struct-562203"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Karine</forename>
                <surname>El Rassi</surname>
              </persName>
              <email type="md5">b5af2e40320c07d2829a887885512ee0</email>
              <email type="domain">supelec.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2010-09-01 11:35:26</date>
              <date type="whenModified">2024-08-02 03:22:15</date>
              <date type="whenReleased">2010-09-02 11:08:47</date>
              <date type="whenProduced">2010-06</date>
              <date type="whenEndEmbargoed">2010-09-01</date>
              <ref type="file" target="https://centralesupelec.hal.science/hal-00514107v1/document">
                <date notBefore="2010-09-01"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://centralesupelec.hal.science/hal-00514107v1/file/Jelizarow2010.pdf" id="file-514107-242827">
                <date notBefore="2010-09-01"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="124033">
                <persName>
                  <forename>Karine</forename>
                  <surname>El Rassi</surname>
                </persName>
                <email type="md5">b5af2e40320c07d2829a887885512ee0</email>
                <email type="domain">supelec.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00514107</idno>
            <idno type="halUri">https://centralesupelec.hal.science/hal-00514107</idno>
            <idno type="halBibtex">jelizarow:hal-00514107</idno>
            <idno type="halRefHtml">&lt;i&gt;Bioinformatics&lt;/i&gt;, 2010, 26, pp.1990-1998</idno>
            <idno type="halRef">Bioinformatics, 2010, 26, pp.1990-1998</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-514107-242827"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CEA">CEA - Commissariat à l'énergie atomique</idno>
            <idno type="stamp" n="SUPELEC">SUPELEC</idno>
            <idno type="stamp" n="UNIV-PARIS7" corresp="UNIV-PARIS">Université Denis Diderot - Paris VII</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="UNIV-PARIS">Université Paris Cité</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="1">Not set</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Over-optimism in bioinformatics: an illustration</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Monika</forename>
                    <surname>Jelizarow</surname>
                  </persName>
                  <idno type="halauthorid">488428-0</idno>
                  <affiliation ref="#struct-562203"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Vincent</forename>
                    <surname>Guillemot</surname>
                  </persName>
                  <email type="md5">a855b5d8d5bec670b0654c989ec20761</email>
                  <email type="domain">pasteur.fr</email>
                  <idno type="idhal" notation="string">vguillemot</idno>
                  <idno type="idhal" notation="numeric">1042725</idno>
                  <idno type="halauthorid" notation="string">301584-1042725</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7421-0655</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=VMpMbg0AAAAJ</idno>
                  <affiliation ref="#struct-40525"/>
                  <affiliation ref="#struct-123689"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Arthur</forename>
                    <surname>Tenenhaus</surname>
                  </persName>
                  <email type="md5">c5e660f5db08d56a213a6d155a3ca7e8</email>
                  <email type="domain">centralesupelec.fr</email>
                  <idno type="idhal" notation="string">arthur-tenenhaus</idno>
                  <idno type="idhal" notation="numeric">736979</idno>
                  <idno type="halauthorid" notation="string">4562-736979</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-3459-1518</idno>
                  <idno type="IDREF">https://www.idref.fr/115337822</idno>
                  <affiliation ref="#struct-123689"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">K.</forename>
                    <surname>Strimmer</surname>
                  </persName>
                  <idno type="halauthorid">488429-0</idno>
                  <affiliation ref="#struct-562203"/>
                </author>
                <author role="crp">
                  <persName>
                    <forename type="first">Anne-Laure</forename>
                    <surname>Boulesteix</surname>
                  </persName>
                  <email type="md5">442ca921cf6f72494fa81d80bb68744e</email>
                  <email type="domain">ibe.med-uni-muenchen.de</email>
                  <idno type="idhal" notation="numeric">878067</idno>
                  <idno type="halauthorid" notation="string">488430-878067</idno>
                  <affiliation ref="#struct-562203"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">3436</idno>
                <idno type="issn">1367-4803</idno>
                <idno type="eissn">1367-4811</idno>
                <title level="j">Bioinformatics</title>
                <imprint>
                  <publisher>Oxford University Press (OUP)</publisher>
                  <biblScope unit="volume">26</biblScope>
                  <biblScope unit="pp">1990-1998</biblScope>
                  <date type="datePub">2010-06</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Validation</term>
                <term xml:lang="en">fishing for significance</term>
                <term xml:lang="en">meta-methodology</term>
                <term xml:lang="en">KEGG</term>
                <term xml:lang="en">discriminant analysis</term>
                <term xml:lang="en">shrinkage covariance estimator</term>
              </keywords>
              <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="halDomain" n="stat.me">Statistics [stat]/Methodology [stat.ME]</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>In statistical bioinformatics research, different optimization mechanisms potentially lead to “over-optimism” in published papers. The present empirical study illustrates these mechanisms through a concrete example from an active research field. The investigated sources of over-optimism include the optimization of the data sets, of the settings, of the competing methods and, most importantly, of the method's characteristics. We consider a “promising” new classification algorithm that turns out to yield disappointing results in terms of error rate, namely linear discriminant analysis incorporating prior knowledge on gene functional groups through an appropriate shrinkage of the within-group covariance matrix. We quantitatively demonstrate that this disappointing method can artificially seem superior to existing approaches if we “fish for significance”. We conclude that, if the improvement of a quantitative criterion such as the error rate is the main contribution of a paper, the superiority of new algorithms should be validated using “fresh” validation data sets. The R codes and preprocessed versions of the data sets as well as additional files can be downloaded from http://www.ibe.med.uni-muenchen.de/organisation/mitarbeiter/020−professuren/boulesteix/overoptimism/,such that the study is completely reproducible.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-562203" status="VALID">
          <idno type="ROR">https://ror.org/03s7gtk40</idno>
          <orgName>Leipzig University / Universität Leipzig</orgName>
          <desc>
            <address>
              <addrLine>Augustusplatz 10, 04109 Leipzig, Allemagne</addrLine>
              <country key="DE"/>
            </address>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-40525" status="OLD">
          <orgName>Laboratoire d'Exploration Fonctionnelle des Génomes</orgName>
          <orgName type="acronym">LEFG</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>2, rue Gaston Crémieux 91000 EVRY</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation name="DSV/IRCM/SCSR/LEFG" active="#struct-300016" type="direct"/>
            <relation active="#struct-300301" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-123689" status="OLD">
          <orgName>Supélec Sciences des Systèmes</orgName>
          <orgName type="acronym">E3S</orgName>
          <desc>
            <address>
              <addrLine>Plateau du Moulon - 3 rue Joliot-Curie  -  91192 GIF-SUR-YVETTE CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.supelec.fr/342_p_14975/e3s-equipe.html</ref>
          </desc>
          <listRelation>
            <relation name="EA4454" active="#struct-303397" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300016" status="VALID">
          <idno type="IdRef">026372061</idno>
          <idno type="ISNI">0000000122998025</idno>
          <idno type="ROR">https://ror.org/00jjx8s55</idno>
          <idno type="Wikidata">Q868550</idno>
          <orgName>Commissariat à l'énergie atomique et aux énergies alternatives</orgName>
          <orgName type="acronym">CEA</orgName>
          <desc>
            <address>
              <addrLine>Centre de SaclayCentre de GrenobleCentre de Cadaracheetc</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.cea.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300301" status="OLD">
          <idno type="IdRef">027542084</idno>
          <idno type="ISNI">0000000121514068</idno>
          <idno type="ROR">https://ror.org/02n7qrg46</idno>
          <orgName>Université Paris Diderot - Paris 7</orgName>
          <orgName type="acronym">UPD7</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>5 rue Thomas-Mann - 75205 Paris cedex 13</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-paris-diderot.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-303397" status="VALID">
          <orgName>Ecole Supérieure d'Electricité - SUPELEC (FRANCE)</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>