<?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 inserm-00143374</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="2026-05-19T08:00:07+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Extension of a local backbone description using a structural alphabet: a new approach to the sequence-structure relationship.</title>
            <author role="crp">
              <persName>
                <forename type="first">Alexandre</forename>
                <surname>de Brevern</surname>
              </persName>
              <email type="md5">c2e597903b2aaf81d12042928a5c3d3c</email>
              <email type="domain">univ-paris-diderot.fr</email>
              <idno type="idhal" notation="string">alexandre-de-brevern</idno>
              <idno type="idhal" notation="numeric">9903</idno>
              <idno type="halauthorid" notation="string">20254-9903</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/B-4788-2009</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-7112-5626</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=NB4OJhoAAAAJ&amp;hl=fr</idno>
              <idno type="IDREF">https://www.idref.fr/135431697</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/B-4788-2009</idno>
              <affiliation ref="#struct-3084"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Hélène</forename>
                <surname>Valadié</surname>
              </persName>
              <idno type="halauthorid">194931-0</idno>
              <affiliation ref="#struct-3084"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Serge</forename>
                <forename type="middle">A.</forename>
                <surname>Hazout</surname>
              </persName>
              <idno type="halauthorid">139262-0</idno>
              <affiliation ref="#struct-3084"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Catherine</forename>
                <surname>Etchebest</surname>
              </persName>
              <idno type="halauthorid">194866-0</idno>
              <affiliation ref="#struct-3084"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Alexandre G.</forename>
                <surname>de Brevern</surname>
              </persName>
              <email type="md5">c2e597903b2aaf81d12042928a5c3d3c</email>
              <email type="domain">univ-paris-diderot.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2007-04-25 15:40:44</date>
              <date type="whenModified">2025-08-18 13:28:06</date>
              <date type="whenReleased">2007-04-25 15:39:24</date>
              <date type="whenProduced">2002-12</date>
              <date type="whenEndEmbargoed">2007-04-25</date>
              <ref type="file" target="https://inserm.hal.science/inserm-00143374v1/document">
                <date notBefore="2007-04-25"/>
              </ref>
              <ref type="file" n="1" target="https://inserm.hal.science/inserm-00143374v1/file/de_Brevern_Protein_Science_2002.pdf" id="file-143374-370202">
                <date notBefore="2007-04-25"/>
              </ref>
              <ref type="annex" subtype="other" n="0" target="https://inserm.hal.science/inserm-00143374v1/file/deBrevern_suppl_11_12.xls" id="file-143374-370201">
                <date notBefore="2007-04-25"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="110036">
                <persName>
                  <forename>Alexandre G.</forename>
                  <surname>de Brevern</surname>
                </persName>
                <email type="md5">c2e597903b2aaf81d12042928a5c3d3c</email>
                <email type="domain">univ-paris-diderot.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">inserm-00143374</idno>
            <idno type="halUri">https://inserm.hal.science/inserm-00143374</idno>
            <idno type="halBibtex">debrevern:inserm-00143374</idno>
            <idno type="halRefHtml">&lt;i&gt;Protein Science&lt;/i&gt;, 2002, 11 (12), pp.2871-86</idno>
            <idno type="halRef">Protein Science, 2002, 11 (12), pp.2871-86</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-143374-370202"/><ref corresp="#file-143374-370201"/></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="UNIV-PARIS7" corresp="UNIV-PARIS">Université Denis Diderot - Paris VII</idno>
            <idno type="stamp" n="UNIV-PARIS">Université Paris Cité</idno>
          </seriesStmt>
          <notesStmt>
            <note type="commentary">FREE FULL TEXT http://www.proteinscience.org/cgi/content/full/11/12/2871</note>
            <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">Extension of a local backbone description using a structural alphabet: a new approach to the sequence-structure relationship.</title>
                <author role="crp">
                  <persName>
                    <forename type="first">Alexandre</forename>
                    <surname>de Brevern</surname>
                  </persName>
                  <email type="md5">c2e597903b2aaf81d12042928a5c3d3c</email>
                  <email type="domain">univ-paris-diderot.fr</email>
                  <idno type="idhal" notation="string">alexandre-de-brevern</idno>
                  <idno type="idhal" notation="numeric">9903</idno>
                  <idno type="halauthorid" notation="string">20254-9903</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/B-4788-2009</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-7112-5626</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=NB4OJhoAAAAJ&amp;hl=fr</idno>
                  <idno type="IDREF">https://www.idref.fr/135431697</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/B-4788-2009</idno>
                  <affiliation ref="#struct-3084"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Hélène</forename>
                    <surname>Valadié</surname>
                  </persName>
                  <idno type="halauthorid">194931-0</idno>
                  <affiliation ref="#struct-3084"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Serge</forename>
                    <forename type="middle">A.</forename>
                    <surname>Hazout</surname>
                  </persName>
                  <idno type="halauthorid">139262-0</idno>
                  <affiliation ref="#struct-3084"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Catherine</forename>
                    <surname>Etchebest</surname>
                  </persName>
                  <idno type="halauthorid">194866-0</idno>
                  <affiliation ref="#struct-3084"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">18303</idno>
                <idno type="issn">0961-8368</idno>
                <idno type="eissn">1469-896X</idno>
                <title level="j">Protein Science</title>
                <imprint>
                  <publisher>Wiley</publisher>
                  <biblScope unit="volume">11</biblScope>
                  <biblScope unit="issue">12</biblScope>
                  <biblScope unit="pp">2871-86</biblScope>
                  <date type="datePub">2002-12</date>
                </imprint>
              </monogr>
              <idno type="pubmed">12441385</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="mesh">Amino Acid Sequence</classCode>
              <classCode scheme="mesh">Bayes Theorem</classCode>
              <classCode scheme="mesh">Thermodynamics</classCode>
              <classCode scheme="mesh">Thermus thermophilus</classCode>
              <classCode scheme="mesh">Computational Biology</classCode>
              <classCode scheme="mesh">Computer Simulation</classCode>
              <classCode scheme="mesh">Databases, Protein</classCode>
              <classCode scheme="mesh">Methionine-tRNA Ligase</classCode>
              <classCode scheme="mesh">Models, Molecular</classCode>
              <classCode scheme="mesh">Molecular Sequence Data</classCode>
              <classCode scheme="mesh">Peptide Fragments</classCode>
              <classCode scheme="mesh">Protein Conformation</classCode>
              <classCode scheme="halDomain" n="sdv.bbm">Life Sciences [q-bio]/Biochemistry, Molecular Biology</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>Protein Blocks (PBs) comprise a structural alphabet of 16 protein fragments, each 5 Calpha long. They make it possible to approximate and correctly predict local protein three-dimensional (3D) structures. We have selected the 72 most frequent sequences of five PBs, which we call Structural Words (SWs). Analysis of four different protein data banks shows that SWs cover 92% of the amino acids in them and provide a good structural approximation for residues (i.e., sequences) 9 Calpha long. We present most of them in a simple network that describes 90% of the overall residues and, interestingly, includes more than 80% of the amino acids present in coils. Analysis of the network shows the specificity and quality of the 3D descriptions as well as a new type of relation between local folds and amino acid distribution. The results show that the 3D structure of these protein data banks can be easily described by a combination of subgraphs included in the network. Finally, a Bayesian probabilistic approach improved the prediction rate by 4%.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-3084" status="OLD">
          <orgName>Bioinformatique génomique et moléculaire</orgName>
          <orgName type="acronym">(U 726)</orgName>
          <desc>
            <address>
              <addrLine>2, Place Jussieu 75251 PARIS CEDEX 05</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-300301" type="direct"/>
            <relation name="U726" active="#struct-303623" type="direct"/>
          </listRelation>
        </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-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>