<?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-05484807</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="2026-05-25T22:56:16+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A Robust Computational Framework to Characterize the Genetic Diversity Across 3,570 Strains in Saccharomyces cerevisiae</title>
            <author role="aut">
              <persName>
                <forename type="first">Louis</forename>
                <surname>Ollivier</surname>
              </persName>
              <email type="md5">b9d50330ba0362c64738332bd507de3a</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">louis-xiv-bis</idno>
              <idno type="idhal" notation="numeric">1299800</idno>
              <idno type="halauthorid" notation="string">763973-1299800</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1177-6202</idno>
              <affiliation ref="#struct-1062146"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gilles</forename>
                <surname>Fischer</surname>
              </persName>
              <email type="md5">824473d59798a6a904bf902dbca34bb2</email>
              <email type="domain">sorbonne-universite.fr</email>
              <idno type="idhal" notation="string">gilles-fischer</idno>
              <idno type="idhal" notation="numeric">740227</idno>
              <idno type="halauthorid" notation="string">23674-740227</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-5732-2682</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=0v9nlVMAAAAJ&amp;hl=fr</idno>
              <idno type="IDREF">https://www.idref.fr/139512624</idno>
              <affiliation ref="#struct-542183"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Fanny</forename>
                <surname>Pouyet</surname>
              </persName>
              <email type="md5">0b42940796da31435b2552dd17766dfd</email>
              <email type="domain">universite-paris-saclay.fr</email>
              <idno type="idhal" notation="string">fannypouyet</idno>
              <idno type="idhal" notation="numeric">754819</idno>
              <idno type="halauthorid" notation="string">55232-754819</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-5614-6998</idno>
              <idno type="IDREF">https://www.idref.fr/196943892</idno>
              <idno type="VIAF">https://viaf.org/viaf/408148389451710711409</idno>
              <affiliation ref="#struct-1061259"/>
              <affiliation ref="#struct-1062146"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Louis</forename>
                <surname>Ollivier</surname>
              </persName>
              <email type="md5">b9d50330ba0362c64738332bd507de3a</email>
              <email type="domain">gmail.com</email>
            </editor>
            <funder ref="#projanr-52540"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2026-01-30 08:36:42</date>
              <date type="whenModified">2026-02-08 03:13:57</date>
              <date type="whenReleased">2026-02-05 09:02:37</date>
              <date type="whenProduced">2025-07-21</date>
              <date type="whenEndEmbargoed">2026-01-30</date>
              <ref type="file" target="https://hal.science/hal-05484807v1/document">
                <date notBefore="2026-01-30"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-05484807v1/file/Poster_Yeast_2025.pdf" id="file-5484807-4694520">
                <date notBefore="2026-01-30"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1468445">
                <persName>
                  <forename>Louis</forename>
                  <surname>Ollivier</surname>
                </persName>
                <email type="md5">b9d50330ba0362c64738332bd507de3a</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05484807</idno>
            <idno type="halUri">https://hal.science/hal-05484807</idno>
            <idno type="halBibtex">ollivier:hal-05484807</idno>
            <idno type="halRefHtml">&lt;i&gt;Yeast 2025&lt;/i&gt;, Jul 2025, Paris, France</idno>
            <idno type="halRef">Yeast 2025, Jul 2025, Paris, France</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-5484807-4694520"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="LCQB" corresp="IBPS">Biologie Computationnelle et Quantitative</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="IBPS" corresp="SORBONNE-UNIVERSITE">Institut de Biologie Paris Seine</idno>
            <idno type="stamp" n="SORBONNE-UNIVERSITE">Sorbonne Université</idno>
            <idno type="stamp" n="SORBONNE-UNIV" corresp="SORBONNE-UNIVERSITE">Sorbonne Université 01/01/2018</idno>
            <idno type="stamp" n="SU-SCIENCES" corresp="SORBONNE-UNIVERSITE">Faculté des Sciences de Sorbonne Université</idno>
            <idno type="stamp" n="UNIVERSITE-PARIS-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="SU-TI">Sorbonne Université - Texte Intégral</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="LISN">Laboratoire Interdisciplinaire des Sciences du Numérique</idno>
            <idno type="stamp" n="GS-COMPUTER-SCIENCE">Graduate School Computer Science</idno>
            <idno type="stamp" n="LISN-BIOINFO" corresp="LISN">BioInformatique </idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
            <idno type="stamp" n="SUPRA_BIOLOGIE">Biologie hors MNHN &amp; stations</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">A Robust Computational Framework to Characterize the Genetic Diversity Across 3,570 Strains in Saccharomyces cerevisiae</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Louis</forename>
                    <surname>Ollivier</surname>
                  </persName>
                  <email type="md5">b9d50330ba0362c64738332bd507de3a</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">louis-xiv-bis</idno>
                  <idno type="idhal" notation="numeric">1299800</idno>
                  <idno type="halauthorid" notation="string">763973-1299800</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1177-6202</idno>
                  <affiliation ref="#struct-1062146"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gilles</forename>
                    <surname>Fischer</surname>
                  </persName>
                  <email type="md5">824473d59798a6a904bf902dbca34bb2</email>
                  <email type="domain">sorbonne-universite.fr</email>
                  <idno type="idhal" notation="string">gilles-fischer</idno>
                  <idno type="idhal" notation="numeric">740227</idno>
                  <idno type="halauthorid" notation="string">23674-740227</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-5732-2682</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=0v9nlVMAAAAJ&amp;hl=fr</idno>
                  <idno type="IDREF">https://www.idref.fr/139512624</idno>
                  <affiliation ref="#struct-542183"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Fanny</forename>
                    <surname>Pouyet</surname>
                  </persName>
                  <email type="md5">0b42940796da31435b2552dd17766dfd</email>
                  <email type="domain">universite-paris-saclay.fr</email>
                  <idno type="idhal" notation="string">fannypouyet</idno>
                  <idno type="idhal" notation="numeric">754819</idno>
                  <idno type="halauthorid" notation="string">55232-754819</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-5614-6998</idno>
                  <idno type="IDREF">https://www.idref.fr/196943892</idno>
                  <idno type="VIAF">https://viaf.org/viaf/408148389451710711409</idno>
                  <affiliation ref="#struct-1061259"/>
                  <affiliation ref="#struct-1062146"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Yeast 2025</title>
                  <date type="start">2025-07-21</date>
                  <date type="end">2025-07-24</date>
                  <settlement>Paris</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-bi">Computer Science [cs]/Bioinformatics [q-bio.QM]</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>Saccharomyces cerevisiae exhibits remarkable genetic diversity, with many strains sampled from diverse ecological and geographical origins. Over the years, thousands of genome sequences have been released across numerous studies, and this dataset continues to grow. This evergrowing genomic dataset calls for a scalable, and robust computational framework to systematically explore the species' genetic diversity, providing an objective and homogeneous view at the population level. To investigate these mechanisms, we developed an integrated computational framework to systematically analyze the genetic diversity of Saccharomyces cerevisiae. This framework consists of: (1) a scalable and HPC-optimized Snakemake pipeline for variant calling, using the GATK toolkit and designed to run efficiently on high-performance computing clusters (via SLURM), (2) an objective and reproducible classification scheme allowing to define populations based on the inference of their genetic ancestries using the sNMF method, (3) a general ploidy and aneuploidy prediction method leveraging allele balance ratios, offering a more straightforward and faster alternative to existing techniques, and (4) a robust framework to quantify heterozygosity without relying on arbitrary thresholds. This framework is designed to be both accessible and scalable, enabling researchers to generate VCF files from ENA IDs and conduct population structure, ploidy, and heterozygosity analyses with minimal bioinformatics expertise.This framework was applied to a dataset of 3,570 genome sequences, representing an unprecedented effort to compile and standardize Saccharomyces cerevisiae genomic diversity. A key component of this effort is a standardized metadata table compiling key ecological, geographical, and sequencing information from 3,570 strains. While our analyses on population structure, admixture, ploidy, and heterozygosity are still ongoing, preliminary results suggest that we are approaching a near-complete representation of the species' genetic diversity, as indicated by rarefaction curve analyses. This dataset, combined with our integrated computational approach, provides a robust foundation for future investigations into the evolutionary forces shaping yeast population structure, adaptation, and genome dynamics.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-1062146" status="VALID">
          <orgName>BioInformatique - LISN</orgName>
          <orgName type="acronym">BioInfo</orgName>
          <date type="start">2021-01-01</date>
          <desc>
            <address>
              <addrLine>Université Paris-Saclay, Bâtiment 650, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-1061259" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-419361" type="indirect"/>
            <relation name="UMR9015" active="#struct-441569" type="indirect"/>
            <relation active="#struct-1065371" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-542183" status="VALID">
          <idno type="IdRef">24301161X</idno>
          <idno type="ISNI">0000000404593739</idno>
          <idno type="RNSR">201119726Y</idno>
          <idno type="ROR">https://ror.org/00pcqj134</idno>
          <idno type="Wikidata">Q51780569</idno>
          <orgName>Biologie Computationnelle, Quantitative et Synthétique [Paris] (ex LCQB)</orgName>
          <orgName type="acronym">CQSB</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>Institut de Biologie Paris Seine [IBPS], Campus Pierre et Marie Curie - 7-9 quai Saint Bernard - 75005 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.ibps.sorbonne-universite.fr/fr/Recherche/umr-7238</ref>
          </desc>
          <listRelation>
            <relation name="U1284" active="#struct-303623" type="direct"/>
            <relation active="#struct-413221" type="direct"/>
            <relation name="UMR7238" active="#struct-441569" type="direct"/>
            <relation active="#struct-542120" type="direct"/>
            <relation active="#struct-303623" type="direct"/>
            <relation name="UAR3631 / FR3631" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1061259" status="VALID">
          <idno type="IdRef">253160316</idno>
          <idno type="RNSR">202123711L</idno>
          <idno type="ROR">https://ror.org/00rd81916</idno>
          <idno type="Wikidata">Q109620676</idno>
          <orgName>Laboratoire Interdisciplinaire des Sciences du Numérique</orgName>
          <orgName type="acronym">LISN</orgName>
          <date type="start">2021-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Universitaire bât 507Rue du Belvédère91405 Orsay cedexet Campus Universitaire bât 6401 rue Raimond Castaing91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.lisn.upsaclay.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation active="#struct-419361" type="direct"/>
            <relation name="UMR9015" active="#struct-441569" 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-411575" status="VALID">
          <idno type="IdRef">184443237</idno>
          <idno type="ROR">https://ror.org/019tcpt25</idno>
          <orgName>CentraleSupélec</orgName>
          <desc>
            <address>
              <addrLine>3, rue Joliot Curie,Plateau de Moulon,91192 GIF-SUR-YVETTE Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.centralesupelec.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-419361" status="VALID">
          <idno type="IdRef">241345251</idno>
          <idno type="ROR">https://ror.org/03xjwb503</idno>
          <orgName>Université Paris-Saclay</orgName>
          <desc>
            <address>
              <addrLine>Bâtiment Bréguet, 3 Rue Joliot Curie 2e ét, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-paris-saclay.fr/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="department" xml:id="struct-1065371" status="VALID">
          <orgName>Science des Données</orgName>
          <orgName type="acronym">SDD</orgName>
          <date type="start">2021-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-1061259" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-419361" type="indirect"/>
            <relation name="UMR9015" active="#struct-441569" type="indirect"/>
          </listRelation>
        </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="regroupinstitution" xml:id="struct-413221" status="VALID">
          <idno type="IdRef">221333754</idno>
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Sorbonne Université</orgName>
          <orgName type="acronym">SU</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>21 rue de l’École de médecine - 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sorbonne-universite.fr/</ref>
          </desc>
        </org>
        <org type="regrouplaboratory" xml:id="struct-542120" status="VALID">
          <idno type="IdRef">245153268</idno>
          <idno type="RNSR">201420879N</idno>
          <idno type="ROR">https://ror.org/01c2cjg59</idno>
          <orgName>Institut de Biologie Paris Seine</orgName>
          <orgName type="acronym">IBPS</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>Quai Saint-Bernard75252 PARIS CEDEX 05</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ibps.upmc.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-303623" type="direct"/>
            <relation active="#struct-413221" type="direct"/>
            <relation name="UAR3631 / FR3631" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-52540" status="VALID">
          <idno type="anr">ANR-20-CE12-0020</idno>
          <orgName>BuddY</orgName>
          <desc>Revisiter le cycle de vie de la levure bourgeonnante</desc>
          <date type="start">2020</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>