<?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-01667295</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="2026-05-19T23:33:20+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">High-dimensional compositional microbiota data: state-of-the-art of methods and software implementations</title>
            <author role="aut">
              <persName>
                <forename type="first">Perrine</forename>
                <surname>Soret</surname>
              </persName>
              <email type="md5">1612a6430972c115eb9cfdabb4013c03</email>
              <email type="domain">isped.fr</email>
              <idno type="idhal" notation="numeric">993300</idno>
              <idno type="halauthorid" notation="string">879094-993300</idno>
              <affiliation ref="#struct-259761"/>
              <affiliation ref="#struct-219689"/>
              <affiliation ref="#struct-476572"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Marta</forename>
                <forename type="middle">Fernandez</forename>
                <surname>Avalos</surname>
              </persName>
              <email type="md5">b0aa5ee8534aebae414dde1071350275</email>
              <email type="domain">u-bordeaux.fr</email>
              <idno type="idhal" notation="string">mavalosf</idno>
              <idno type="idhal" notation="numeric">742122</idno>
              <idno type="halauthorid" notation="string">979621-742122</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-5471-2615</idno>
              <idno type="IDREF">https://www.idref.fr/153689293</idno>
              <affiliation ref="#struct-259761"/>
              <affiliation ref="#struct-219689"/>
              <affiliation ref="#struct-476572"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Soon</forename>
                <surname>Cheng</surname>
              </persName>
              <idno type="halauthorid">1281520-0</idno>
              <affiliation ref="#struct-487586"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Rodolphe</forename>
                <surname>Thiebaut</surname>
              </persName>
              <email type="md5">242f217052cdd1b15e9288ab507c175b</email>
              <email type="domain">u-bordeaux.fr</email>
              <idno type="idhal" notation="string">rodolphe-thiebaut</idno>
              <idno type="idhal" notation="numeric">175125</idno>
              <idno type="halauthorid" notation="string">883533-175125</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-5235-3962</idno>
              <idno type="IDREF">https://www.idref.fr/071580735</idno>
              <orgName ref="#struct-219689"/>
              <affiliation ref="#struct-259761"/>
              <affiliation ref="#struct-219689"/>
              <affiliation ref="#struct-476572"/>
              <affiliation ref="#struct-408207"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Marta</forename>
                <surname>Avalos</surname>
              </persName>
              <email type="md5">b0aa5ee8534aebae414dde1071350275</email>
              <email type="domain">u-bordeaux.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2017-12-19 11:52:32</date>
              <date type="whenModified">2025-03-17 19:25:31</date>
              <date type="whenReleased">2017-12-19 12:46:55</date>
              <date type="whenProduced">2017-10-05</date>
              <date type="whenEndEmbargoed">2017-12-19</date>
              <ref type="file" target="https://inria.hal.science/hal-01667295v1/document">
                <date notBefore="2017-12-19"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-01667295v1/file/SORET_GdR_Stat%26Sant%C3%A9_2017.pdf" id="file-1667295-1709048">
                <date notBefore="2017-12-19"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="118669">
                <persName>
                  <forename>Marta</forename>
                  <surname>Avalos</surname>
                </persName>
                <email type="md5">b0aa5ee8534aebae414dde1071350275</email>
                <email type="domain">u-bordeaux.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01667295</idno>
            <idno type="halUri">https://inria.hal.science/hal-01667295</idno>
            <idno type="halBibtex">soret:hal-01667295</idno>
            <idno type="halRefHtml">&lt;i&gt;2017 - GDR « Statistiques et santé »&lt;/i&gt;, Oct 2017, Bordeaux, France</idno>
            <idno type="halRef">2017 - GDR « Statistiques et santé », Oct 2017, Bordeaux, France</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1667295-1709048"/></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="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INRIA-BORDEAUX">INRIA Bordeaux - Sud-Ouest</idno>
            <idno type="stamp" n="SANTE_PUB_INSERM" corresp="INSERM">Santé Publique à l'Inserm</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="INRIA2017">INRIA2017</idno>
            <idno type="stamp" n="U1219" corresp="INSERM">Bordeaux Population Health</idno>
            <idno type="stamp" n="INRIA-AUSTRALIE">Copublications Inria-Australie</idno>
            <idno type="stamp" n="UNIVERSITE-BORDEAUX">Université de Bordeaux</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="3">National</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">High-dimensional compositional microbiota data: state-of-the-art of methods and software implementations</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Perrine</forename>
                    <surname>Soret</surname>
                  </persName>
                  <email type="md5">1612a6430972c115eb9cfdabb4013c03</email>
                  <email type="domain">isped.fr</email>
                  <idno type="idhal" notation="numeric">993300</idno>
                  <idno type="halauthorid" notation="string">879094-993300</idno>
                  <affiliation ref="#struct-259761"/>
                  <affiliation ref="#struct-219689"/>
                  <affiliation ref="#struct-476572"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Marta</forename>
                    <forename type="middle">Fernandez</forename>
                    <surname>Avalos</surname>
                  </persName>
                  <email type="md5">b0aa5ee8534aebae414dde1071350275</email>
                  <email type="domain">u-bordeaux.fr</email>
                  <idno type="idhal" notation="string">mavalosf</idno>
                  <idno type="idhal" notation="numeric">742122</idno>
                  <idno type="halauthorid" notation="string">979621-742122</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-5471-2615</idno>
                  <idno type="IDREF">https://www.idref.fr/153689293</idno>
                  <affiliation ref="#struct-259761"/>
                  <affiliation ref="#struct-219689"/>
                  <affiliation ref="#struct-476572"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Soon</forename>
                    <surname>Cheng</surname>
                  </persName>
                  <idno type="halauthorid">1281520-0</idno>
                  <affiliation ref="#struct-487586"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Rodolphe</forename>
                    <surname>Thiebaut</surname>
                  </persName>
                  <email type="md5">242f217052cdd1b15e9288ab507c175b</email>
                  <email type="domain">u-bordeaux.fr</email>
                  <idno type="idhal" notation="string">rodolphe-thiebaut</idno>
                  <idno type="idhal" notation="numeric">175125</idno>
                  <idno type="halauthorid" notation="string">883533-175125</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-5235-3962</idno>
                  <idno type="IDREF">https://www.idref.fr/071580735</idno>
                  <orgName ref="#struct-219689"/>
                  <affiliation ref="#struct-259761"/>
                  <affiliation ref="#struct-219689"/>
                  <affiliation ref="#struct-476572"/>
                  <affiliation ref="#struct-408207"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>2017 - GDR « Statistiques et santé »</title>
                  <date type="start">2017-10-05</date>
                  <date type="end">2017-10-06</date>
                  <settlement>Bordeaux</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint>
                  <date type="datePub">2017</date>
                </imprint>
              </monogr>
              <ref type="publisher">http://gdr-stat-sante.math.cnrs.fr/spip/spip.php?rubrique20</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</classCode>
              <classCode scheme="halDomain" n="stat.me">Statistics [stat]/Methodology [stat.ME]</classCode>
              <classCode scheme="halDomain" n="stat.ap">Statistics [stat]/Applications [stat.AP]</classCode>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
              <classCode scheme="halDomain" n="sdv.spee">Life Sciences [q-bio]/Santé publique et épidémiologie</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>Compositional data (CoDa) consist of a collection of nonnegative measurements that sum to a constant value, typically, proportions that sum to 1. Because knowing the sum, one component can be determined from the sum of the remainder, the parts that make up the composition are mathematically and statistically dependent. This distinct structure complicates analysis and does not allow standard statistical analyses. Aitchison (JRSS-B, 1982) and Egozcue and colleagues (Math. Geol., 2003), among others, provided a framework to analyze CoDa by mapping data from the constrained simplex space to the Euclidian space using nonlinear transforms such as the log-odds or the isometric log-ratio transforms. The increasing quality/reducing cost of high-throughput sequencing technology, in particular, 16S rRNA gene sequencing of the bacterial component of the human microbial community (microbiota), has enabled researchers to investigate human diseases. Subsequently, microbiota has been associated with numerous diseases, including inflammatory bowel disease, diabetes, cancer and cystic fibrosis. Because of the compositional structure and the high-dimensional data generated by microbiota sequencing, there is also a parallel development of specific statistical analysis methods and computational tools. Microbiota are usually measured as relative abundance of species and analyzed as CoDa. The objectives of this work are the following: - First, to review theory and usage of CoDa analysis in the microbiota setting, with particular emphasis on recent proposals adapted to high-dimensional problems (e.g. supervised –constrained Lasso, hierarchical Lasso, kernel methods, sPLS, or unsupervised – PCoA, PCA, Sparse inverse covariance estimation).- Second, to investigate the current state-of-the-art software implementations (basically, R packages: compositions, vegan, ALDex2, PERMANOVA, MiRKAT, MixMC . . . )- Third, using toy examples and publicly available data (the 16S data from the Koren and colleagues’ study in March 2011’s PNAS, available in the MixMC R package), to implement and evaluate those methods with publicly available codes. Evaluation criteria are mainly based oncomputational and practical aspects.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-259761" status="VALID">
          <idno type="IdRef">175206562</idno>
          <idno type="ROR">https://ror.org/057qpr032</idno>
          <orgName>Université de Bordeaux</orgName>
          <orgName type="acronym">UB</orgName>
          <desc>
            <address>
              <addrLine>35, place Pey Berland - 33076 Bordeaux</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.u-bordeaux.fr/</ref>
          </desc>
        </org>
        <org type="researchteam" xml:id="struct-219689" status="VALID">
          <idno type="RNSR">201321095C</idno>
          <idno type="ROR">https://ror.org/026t7px13</idno>
          <orgName>Statistics In System biology and Translational Medicine</orgName>
          <orgName type="acronym">SISTM</orgName>
          <date type="start">2016-01-01</date>
          <date type="end">2027-12-31</date>
          <desc>
            <address>
              <addrLine>200, avenue de la Vieille Tour 33405 Talence cedex 146 Rue Léo Saignat33076 Bordeaux cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/sistm</ref>
          </desc>
          <listRelation>
            <relation active="#struct-104751" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-476572" type="direct"/>
            <relation active="#struct-259761" type="indirect"/>
            <relation active="#struct-302259" type="indirect"/>
            <relation name="U1219" active="#struct-303623" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-476572" status="VALID">
          <idno type="IdRef">197398162</idno>
          <idno type="RNSR">201622170H</idno>
          <idno type="ROR">https://ror.org/00xzzba89</idno>
          <orgName>Bordeaux population health</orgName>
          <orgName type="acronym">BPH</orgName>
          <desc>
            <address>
              <addrLine>Université de Bordeaux - Case 11 - 146 rue Léo Saignat  33076 Bordeaux cedex</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-259761" type="direct"/>
            <relation active="#struct-302259" type="direct"/>
            <relation name="U1219" active="#struct-303623" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-487586" status="VALID">
          <orgName>Data61 [Canberra]</orgName>
          <orgName type="acronym">CSIRO</orgName>
          <desc>
            <address>
              <addrLine>GPO Box 1700Canberra ACT 2601</addrLine>
              <country key="AU"/>
            </address>
            <ref type="url">https://www.data61.csiro.au/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-74662" type="direct"/>
            <relation active="#struct-300095" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-408207" status="VALID">
          <idno type="ROR">https://ror.org/01hq89f96</idno>
          <orgName>CHU de Bordeaux Pellegrin [Bordeaux]</orgName>
          <desc>
            <address>
              <addrLine>Place Amélie Raba-Léon, 33000 Bordeaux</addrLine>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-104751" status="VALID">
          <idno type="RNSR">200818243Z</idno>
          <idno type="ROR">https://ror.org/03tjcj052</idno>
          <orgName>Centre Inria de l'Université de Bordeaux</orgName>
          <desc>
            <address>
              <addrLine>200, avenue de la Vieille Tour, 33405 Talence</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/bordeaux/</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="institution" xml:id="struct-302259" status="VALID">
          <orgName>Institut de Santé Publique, d'Épidémiologie et de Développement (ISPED)</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </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>
        <org type="institution" xml:id="struct-74662" status="VALID">
          <idno type="IdRef">026470942</idno>
          <idno type="ROR">https://ror.org/019wvm592</idno>
          <orgName>Australian National University</orgName>
          <orgName type="acronym">ANU</orgName>
          <desc>
            <address>
              <addrLine>The Australian National University Canberra ACT 0200 Australia</addrLine>
              <country key="AU"/>
            </address>
            <ref type="url">http://www.anu.edu.au/index.php</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300095" status="VALID">
          <idno type="ROR">https://ror.org/03qn8fb07</idno>
          <orgName>Commonwealth Scientific and Industrial Research Organisation [Australia]</orgName>
          <orgName type="acronym">CSIRO</orgName>
          <date type="start">1916-01-01</date>
          <desc>
            <address>
              <addrLine>GPO Box 1700, Canberra ACT 2600</addrLine>
              <country key="AU"/>
            </address>
            <ref type="url">http://www.csiro.au/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>