<?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-00143564</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="2026-05-19T08:00:06+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A structural alphabet for local protein structures: improved prediction methods.</title>
            <author role="aut">
              <persName>
                <forename type="first">Catherine</forename>
                <surname>Etchebest</surname>
              </persName>
              <idno type="halauthorid">194866-0</idno>
              <affiliation ref="#struct-3084"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Cristina</forename>
                <surname>Benros</surname>
              </persName>
              <idno type="halauthorid">177247-0</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="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>
            <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>
            <funder>Ministère de la Recherche Action Bioinformatique inter EPST; Grant Number: 4B005F, 2003-2004 (Outil informatique intégré en Génomique Structurale; Vers une prédiction de la structure tridimensionnelle d'une protéine à partir de sa séquence) Fondation de la Recherche Médicale Ministère de la Recherche</funder>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2007-04-26 09:24:20</date>
              <date type="whenModified">2022-06-25 20:46:44</date>
              <date type="whenReleased">2007-04-26 10:00:10</date>
              <date type="whenProduced">2005-06-01</date>
              <date type="whenEndEmbargoed">9999-12-31</date>
              <ref type="file" target="https://inserm.hal.science/inserm-00143564v1/document">
                <date notBefore="9999-12-31"/>
              </ref>
              <ref type="file" n="1" target="https://inserm.hal.science/inserm-00143564v1/file/Etchebest_Proteins_2005.pdf" id="file-143564-371715">
                <date notBefore="9999-12-31"/>
              </ref>
              <ref type="annex" subtype="other" n="0" target="https://inserm.hal.science/inserm-00143564v1/file/sup_data_1.pdf" id="file-143564-371714">
                <date notBefore="9999-12-31"/>
              </ref>
              <ref type="annex" subtype="other" n="0" target="https://inserm.hal.science/inserm-00143564v1/file/sup_data_2.pdf" id="file-143564-371713">
                <date notBefore="9999-12-31"/>
              </ref>
              <ref type="annex" subtype="other" n="0" target="https://inserm.hal.science/inserm-00143564v1/file/sup_data_3.pdf" id="file-143564-371711">
                <date notBefore="9999-12-31"/>
              </ref>
              <ref type="annex" subtype="other" n="0" target="https://inserm.hal.science/inserm-00143564v1/file/sup_data_4.pdf" id="file-143564-371712">
                <date notBefore="9999-12-31"/>
              </ref>
              <ref type="externalLink" target="https://api.istex.fr/document/9C650CD66E82073C0D8E9287525F5C80590C496B/fulltext/pdf?sid=hal"/>
            </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-00143564</idno>
            <idno type="halUri">https://inserm.hal.science/inserm-00143564</idno>
            <idno type="halBibtex">etchebest:inserm-00143564</idno>
            <idno type="halRefHtml">&lt;i&gt;Proteins - Structure, Function and Bioinformatics&lt;/i&gt;, 2005, 59 (4), pp.810-27. &lt;a target="_blank" href="https://dx.doi.org/10.1002/prot.20458"&gt;&amp;#x27E8;10.1002/prot.20458&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Proteins - Structure, Function and Bioinformatics, 2005, 59 (4), pp.810-27. &amp;#x27E8;10.1002/prot.20458&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-143564-371715"/><ref corresp="#file-143564-371714"/><ref corresp="#file-143564-371713"/><ref corresp="#file-143564-371711"/><ref corresp="#file-143564-371712"/></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="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">A structural alphabet for local protein structures: improved prediction methods.</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Catherine</forename>
                    <surname>Etchebest</surname>
                  </persName>
                  <idno type="halauthorid">194866-0</idno>
                  <affiliation ref="#struct-3084"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Cristina</forename>
                    <surname>Benros</surname>
                  </persName>
                  <idno type="halauthorid">177247-0</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="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>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">18304</idno>
                <idno type="issn">0887-3585</idno>
                <idno type="eissn">1097-0134</idno>
                <title level="j">Proteins - Structure, Function and Bioinformatics</title>
                <imprint>
                  <publisher>Wiley</publisher>
                  <biblScope unit="volume">59</biblScope>
                  <biblScope unit="issue">4</biblScope>
                  <biblScope unit="pp">810-27</biblScope>
                  <date type="datePub">2005-06-01</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1002/prot.20458</idno>
              <idno type="pubmed">15822101</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">Databases, Protein</classCode>
              <classCode scheme="mesh">Peptide Fragments</classCode>
              <classCode scheme="mesh">Probability</classCode>
              <classCode scheme="mesh">Protein Conformation</classCode>
              <classCode scheme="mesh">Protein Structure, Secondary</classCode>
              <classCode scheme="mesh">Proteins</classCode>
              <classCode scheme="mesh">Reproducibility of Results</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>Three-dimensional protein structures can be described with a library of 3D fragments that define a structural alphabet. We have previously proposed such an alphabet, composed of 16 patterns of five consecutive amino acids, called Protein Blocks (PBs). These PBs have been used to describe protein backbones and to predict local structures from protein sequences. The Q16 prediction rate reaches 40.7% with an optimization procedure. This article examines two aspects of PBs. First, we determine the effect of the enlargement of databanks on their definition. The results show that the geometrical features of the different PBs are preserved (local RMSD value equal to 0.41 A on average) and sequence-structure specificities reinforced when databanks are enlarged. Second, we improve the methods for optimizing PB predictions from sequences, revisiting the optimization procedure and exploring different local prediction strategies. Use of a statistical optimization procedure for the sequence-local structure relation improves prediction accuracy by 8% (Q16 = 48.7%). Better recognition of repetitive structures occurs without losing the prediction efficiency of the other local folds. Adding secondary structure prediction improved the accuracy of Q16 by only 1%. An entropy index (Neq), strongly related to the RMSD value of the difference between predicted PBs and true local structures, is proposed to estimate prediction quality. The Neq is linearly correlated with the Q16 prediction rate distributions, computed for a large set of proteins. An "expected" prediction rate QE16 is deduced with a mean error of 5%.</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>