<?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-05195584</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="2026-05-15T05:00:45+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">In Silico Generation of Gene Expression profiles using Diffusion Models</title>
            <author role="aut">
              <persName>
                <forename type="first">Alice</forename>
                <surname>Lacan</surname>
              </persName>
              <email type="md5">b78c137b359d383990c8db0498a1692a</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="numeric">1304237</idno>
              <idno type="halauthorid" notation="string">2386520-1304237</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-8006-8440</idno>
              <idno type="IDREF">https://www.idref.fr/28377679X</idno>
              <affiliation ref="#struct-1042359"/>
              <affiliation ref="#struct-1066529"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Romain</forename>
                <surname>André</surname>
              </persName>
              <idno type="idhal" notation="numeric">1568819</idno>
              <idno type="halauthorid" notation="string">2094980-1568819</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4631-3198</idno>
              <affiliation ref="#struct-305057"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Michèle</forename>
                <surname>Sébag</surname>
              </persName>
              <email type="md5">561bde41be5c447102107c78e945b69c</email>
              <email type="domain">lri.fr</email>
              <idno type="idhal" notation="numeric">1568820</idno>
              <idno type="halauthorid" notation="string">3754625-1568820</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-8291-7706</idno>
              <idno type="IDREF">https://www.idref.fr/052538745</idno>
              <idno type="VIAF">https://viaf.org/viaf/272442549</idno>
              <idno type="ISNI">http://isni.org/isni/0000000383886590</idno>
              <affiliation ref="#struct-1066529"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Blaise</forename>
                <surname>Hanczar</surname>
              </persName>
              <email type="md5">c2ddbd976fd02037b13611c4886ee563</email>
              <email type="domain">parisdescartes.fr</email>
              <idno type="idhal" notation="string">blaisehanczar</idno>
              <idno type="idhal" notation="numeric">963426</idno>
              <idno type="halauthorid" notation="string">668098-963426</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-5606-8296</idno>
              <idno type="IDREF">https://www.idref.fr/110750411</idno>
              <idno type="VIAF">https://viaf.org/viaf/197966315</idno>
              <idno type="ISNI">http://isni.org/isni/0000000139241088</idno>
              <affiliation ref="#struct-1042359"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Roxanne</forename>
                <surname>HABLOT</surname>
              </persName>
              <email type="md5">15a85b6da9e1a60257ca84c13c75da37</email>
              <email type="domain">inist.fr</email>
            </editor>
            <funder ref="#projanr-51238"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-11-14 13:11:37</date>
              <date type="whenWritten">2024-04-13</date>
              <date type="whenModified">2025-11-14 13:13:17</date>
              <date type="whenReleased">2025-11-14 13:13:17</date>
              <date type="whenProduced">2024-04-13</date>
              <date type="whenEndEmbargoed">2025-11-14</date>
              <ref type="file" target="https://univ-evry.hal.science/hal-05195584v1/document">
                <date notBefore="2025-11-14"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://univ-evry.hal.science/hal-05195584v1/file/2024.04.10.588825v1.full.pdf" id="file-5365239-4589726">
                <date notBefore="2025-11-14"/>
              </ref>
              <ref type="externalLink" target="https://www.biorxiv.org/content/biorxiv/early/2024/04/13/2024.04.10.588825.full.pdf"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1074726">
                <persName>
                  <forename>Roxanne</forename>
                  <surname>HABLOT</surname>
                </persName>
                <email type="md5">15a85b6da9e1a60257ca84c13c75da37</email>
                <email type="domain">inist.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05195584</idno>
            <idno type="halUri">https://univ-evry.hal.science/hal-05195584</idno>
            <idno type="halBibtex">lacan:hal-05195584</idno>
            <idno type="halRefHtml">2024</idno>
            <idno type="halRef">2024</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by-nc-nd/4.0/">CC BY-NC-ND 4.0 - Attribution - Non-commercial use - No Derivative Works<ref corresp="#file-5365239-4589726"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="UNIV-EVRY">Université d'Evry-Val d'Essonne</idno>
            <idno type="stamp" n="INRIA-SACLAY" corresp="INRIA">INRIA Saclay - Ile de France</idno>
            <idno type="stamp" n="IBISC" corresp="UNIV-EVRY">Informatique, Biologie Intégrative et Systèmes Complexes</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="IBISC-AROBAS" corresp="IBISC">Algorithmique, Recherche Opérationnelle, Bioinformatique et Apprentissage Statistique</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="UNIV-EVRY-SACLAY" corresp="UNIV-PARIS-SACLAY">UNIV-EVRY-SACLAY</idno>
            <idno type="stamp" n="UNIVERSITE-PARIS-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris-Saclay</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="GS-LIFE-SCIENCES-HEALTH" corresp="UNIVERSITE-PARIS-SACLAY">Graduate School Life Sciences and Health</idno>
            <idno type="stamp" n="GS-SPORT-HUMAN-MOVEMENT">Graduate School Sport, Mouvement, Facteurs Humains</idno>
            <idno type="stamp" n="LISN-AO" corresp="LISN">A&amp;O (Apprentissage et Optimisation)</idno>
            <idno type="stamp" n="PSACLAY-TEST">Université Paris-Saclay - Collection pour tests</idno>
            <idno type="stamp" n="ANR-IA-20" corresp="ANR-IA">ANR-IA-20</idno>
            <idno type="stamp" n="ANR-IA">ANR-IA</idno>
          </seriesStmt>
          <notesStmt/>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">In Silico Generation of Gene Expression profiles using Diffusion Models</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Alice</forename>
                    <surname>Lacan</surname>
                  </persName>
                  <email type="md5">b78c137b359d383990c8db0498a1692a</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="numeric">1304237</idno>
                  <idno type="halauthorid" notation="string">2386520-1304237</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-8006-8440</idno>
                  <idno type="IDREF">https://www.idref.fr/28377679X</idno>
                  <affiliation ref="#struct-1042359"/>
                  <affiliation ref="#struct-1066529"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Romain</forename>
                    <surname>André</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1568819</idno>
                  <idno type="halauthorid" notation="string">2094980-1568819</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4631-3198</idno>
                  <affiliation ref="#struct-305057"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Michèle</forename>
                    <surname>Sébag</surname>
                  </persName>
                  <email type="md5">561bde41be5c447102107c78e945b69c</email>
                  <email type="domain">lri.fr</email>
                  <idno type="idhal" notation="numeric">1568820</idno>
                  <idno type="halauthorid" notation="string">3754625-1568820</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-8291-7706</idno>
                  <idno type="IDREF">https://www.idref.fr/052538745</idno>
                  <idno type="VIAF">https://viaf.org/viaf/272442549</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000383886590</idno>
                  <affiliation ref="#struct-1066529"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Blaise</forename>
                    <surname>Hanczar</surname>
                  </persName>
                  <email type="md5">c2ddbd976fd02037b13611c4886ee563</email>
                  <email type="domain">parisdescartes.fr</email>
                  <idno type="idhal" notation="string">blaisehanczar</idno>
                  <idno type="idhal" notation="numeric">963426</idno>
                  <idno type="halauthorid" notation="string">668098-963426</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-5606-8296</idno>
                  <idno type="IDREF">https://www.idref.fr/110750411</idno>
                  <idno type="VIAF">https://viaf.org/viaf/197966315</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000139241088</idno>
                  <affiliation ref="#struct-1042359"/>
                </author>
              </analytic>
              <monogr>
                <imprint>
                  <date type="datePub">2024-04-13</date>
                </imprint>
              </monogr>
              <idno type="biorxiv">2024.04.10.588825</idno>
              <idno type="doi">10.1101/2024.04.10.588825</idno>
            </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="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halOldTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halTreeTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Motivation. RNA-seq data is used for precision medicine (e.g., cancer predictions), which benefits from deep learning approaches to analyze complex gene expression data. However, transcriptomics datasets often have few samples compared to deep learning standards. Synthetic data generation is thus being explored to address this data scarcity. So far, only deep generative models such as Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) have been used for this aim. Considering the recent success of diffusion models (DM) in image generation, we propose the first generation pipeline that leverages the power of said diffusion models. Results. This paper presents two state-of-the-art diffusion models (DDPM and DDIM) and achieves their adaptation in the transcriptomics field. DM-generated data of L1000 landmark genes show better predictive performance over TCGA and GTEx datasets. We also compare linear and nonlinear reconstruction methods to recover the complete transcriptome. Results show that such reconstruction methods can boost the performances of diffusion models, as well as VAEs and GANs. Overall, the extensive comparison of various generative models using data quality indicators shows that diffusion models perform best and second-best, making them promising synthetic transcriptomics generators. Availability and implementation.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1042359" status="VALID">
          <idno type="IdRef">201055902</idno>
          <idno type="RNSR">201019077X</idno>
          <idno type="ROR">https://ror.org/01aqxgr98</idno>
          <idno type="Wikidata">Q51781503</idno>
          <orgName>Informatique, BioInformatique, Systèmes Complexes</orgName>
          <orgName type="acronym">IBISC</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>40,rue du pelvoux, Courcouronnes 91020 EVRY CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ibisc.univ-evry.fr/</ref>
          </desc>
          <listRelation>
            <relation name="EA4526" active="#struct-300306" type="direct"/>
            <relation active="#struct-419361" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-1066529" status="VALID">
          <idno type="RNSR">201622258D</idno>
          <idno type="ROR">https://ror.org/031y5kf09</idno>
          <orgName>TAckling the Underspecified</orgName>
          <orgName type="acronym">TAU</orgName>
          <date type="start">2021-01-01</date>
          <date type="end">2027-12-31</date>
          <desc>
            <address>
              <addrLine>Université Paris SaclayBâtiment 660 - Shannon ; 91405 Orsay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.inria.fr/equipes/tau</ref>
          </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-1225627" type="direct"/>
            <relation active="#struct-118511" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-305057" status="VALID">
          <idno type="ROR">https://ror.org/05wg1m734</idno>
          <orgName>Radboud University Medical Center [Nijmegen]</orgName>
          <orgName type="acronym">RadboudUMC</orgName>
          <desc>
            <address>
              <addrLine>PO Box 9101, 6500 HB Nijmegen, The Netherlands</addrLine>
              <country key="NL"/>
            </address>
            <ref type="url">https://www.radboudumc.nl/EN</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300306" status="VALID">
          <idno type="IdRef">030820529</idno>
          <idno type="ISNI">0000000121805818</idno>
          <idno type="ROR">https://ror.org/00e96v939</idno>
          <idno type="Wikidata">Q1531014</idno>
          <orgName>Université d'Évry-Val-d'Essonne</orgName>
          <orgName type="acronym">UEVE</orgName>
          <date type="start">1991-07-22</date>
          <desc>
            <address>
              <addrLine>Boulevard François Mitterrand 91025 Evry Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-evry.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="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="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-1225627" status="VALID">
          <idno type="ROR">https://ror.org/040753f36</idno>
          <orgName>Centre Inria de l'Université Paris-Saclay</orgName>
          <date type="start">2022-11-01</date>
          <desc>
            <address>
              <addrLine>9 Rue Joliot Curie, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-118511" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-118511" status="VALID">
          <idno type="RNSR">200818248E</idno>
          <idno type="ROR">https://ror.org/0315e5x55</idno>
          <orgName>Centre Inria de Saclay</orgName>
          <desc>
            <address>
              <addrLine>1 rue Honoré d'Estienne d'OrvesBâtiment Alan TuringCampus de l'École Polytechnique91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/saclay</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-51238" status="VALID">
          <idno type="anr">ANR-20-THIA-0013</idno>
          <orgName>UDOPIA</orgName>
          <desc>Programme Doctoral en Intelligence Artificielle de l'Université Paris-Saclay</desc>
          <date type="start">2020</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>