<?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-03375900</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="2026-05-16T14:15:59+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Inference of genome 3D architecture by modeling overdispersion of Hi-C data</title>
            <author role="aut">
              <persName>
                <forename type="first">Nelle</forename>
                <surname>Varoquaux</surname>
              </persName>
              <email type="md5">18f719a71cd957dc6f79655448cacad1</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">nelle-varoquaux</idno>
              <idno type="idhal" notation="numeric">15044</idno>
              <idno type="halauthorid" notation="string">24098-15044</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-8748-6546</idno>
              <idno type="IDREF">https://www.idref.fr/192799991</idno>
              <affiliation ref="#struct-1069752"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">William</forename>
                <surname>Noble</surname>
              </persName>
              <idno type="idhal" notation="numeric">811208</idno>
              <idno type="halauthorid" notation="string">174289-811208</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-7283-4715</idno>
              <affiliation ref="#struct-22573"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jean-Philippe</forename>
                <surname>Vert</surname>
              </persName>
              <email type="md5">2fc098cd12d42d1e76510329e12b2a93</email>
              <email type="domain">mines.org</email>
              <idno type="idhal" notation="string">jean-philippe-vert</idno>
              <idno type="idhal" notation="numeric">10276</idno>
              <idno type="halauthorid" notation="string">30643-10276</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-9510-8441</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=pqpxh7IAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/122407385</idno>
              <affiliation ref="#struct-1062878"/>
              <affiliation ref="#struct-46211"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Nelle</forename>
                <surname>Varoquaux</surname>
              </persName>
              <email type="md5">18f719a71cd957dc6f79655448cacad1</email>
              <email type="domain">gmail.com</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2021-10-13 10:29:30</date>
              <date type="whenModified">2026-01-09 09:40:01</date>
              <date type="whenReleased">2021-10-13 10:29:30</date>
              <date type="whenProduced">2021-10-13</date>
              <ref type="externalLink" target="https://www.biorxiv.org/content/biorxiv/early/2021/02/05/2021.02.04.429864.full.pdf"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="94771">
                <persName>
                  <forename>Nelle</forename>
                  <surname>Varoquaux</surname>
                </persName>
                <email type="md5">18f719a71cd957dc6f79655448cacad1</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03375900</idno>
            <idno type="halUri">https://hal.science/hal-03375900</idno>
            <idno type="halBibtex">varoquaux:hal-03375900</idno>
            <idno type="halRefHtml">2021</idno>
            <idno type="halRef">2021</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="INSERM">INSERM - Institut national de la santé et de la recherche médicale</idno>
            <idno type="stamp" n="ENSMP" corresp="PARISTECH">MINES ParisTech</idno>
            <idno type="stamp" n="UGA">HAL Grenoble Alpes</idno>
            <idno type="stamp" n="IMAG">IMAG</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INPG">Institut polytechnique de Grenoble</idno>
            <idno type="stamp" n="ENSMP_CBIO" corresp="ENSMP">Bio-informatique (CBIO)</idno>
            <idno type="stamp" n="PARISTECH">ParisTech</idno>
            <idno type="stamp" n="FNCLCC" corresp="INSERM">UNICANCER</idno>
            <idno type="stamp" n="CURIE" corresp="INSERM">Institut Curie</idno>
            <idno type="stamp" n="TIMC-IMAG">TIMC</idno>
            <idno type="stamp" n="PSL">Université Paris sciences et lettres</idno>
            <idno type="stamp" n="ENSMP_DEP_MS">Département Mathématiques et systèmes</idno>
            <idno type="stamp" n="UNIV-LYON">Université de Lyon</idno>
            <idno type="stamp" n="TEST-HALCNRS">Collection test HAL CNRS</idno>
            <idno type="stamp" n="ENSMP-PSL" corresp="PSL">MINES ParisTech - École nationale supérieure des mines de Paris - PSL</idno>
            <idno type="stamp" n="INSTITUT-CURIE-PSL" corresp="PSL">Institut Curie - PSL</idno>
            <idno type="stamp" n="UGA-EPE">Université Grenoble Alpes [2020-*]</idno>
            <idno type="stamp" n="TIMC-TREE" corresp="TIMC-IMAG">TrEE : Translational microbial Evolution and Engineering</idno>
            <idno type="stamp" n="TEST3-HALCNRS">TEST3-HALCNRS</idno>
            <idno type="stamp" n="TEST-UGA">TEST-UGA</idno>
          </seriesStmt>
          <notesStmt/>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Inference of genome 3D architecture by modeling overdispersion of Hi-C data</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Nelle</forename>
                    <surname>Varoquaux</surname>
                  </persName>
                  <email type="md5">18f719a71cd957dc6f79655448cacad1</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">nelle-varoquaux</idno>
                  <idno type="idhal" notation="numeric">15044</idno>
                  <idno type="halauthorid" notation="string">24098-15044</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-8748-6546</idno>
                  <idno type="IDREF">https://www.idref.fr/192799991</idno>
                  <affiliation ref="#struct-1069752"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">William</forename>
                    <surname>Noble</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">811208</idno>
                  <idno type="halauthorid" notation="string">174289-811208</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-7283-4715</idno>
                  <affiliation ref="#struct-22573"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jean-Philippe</forename>
                    <surname>Vert</surname>
                  </persName>
                  <email type="md5">2fc098cd12d42d1e76510329e12b2a93</email>
                  <email type="domain">mines.org</email>
                  <idno type="idhal" notation="string">jean-philippe-vert</idno>
                  <idno type="idhal" notation="numeric">10276</idno>
                  <idno type="halauthorid" notation="string">30643-10276</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-9510-8441</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=pqpxh7IAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/122407385</idno>
                  <affiliation ref="#struct-1062878"/>
                  <affiliation ref="#struct-46211"/>
                </author>
              </analytic>
              <monogr>
                <imprint/>
              </monogr>
              <idno type="biorxiv">2021.02.04.429864</idno>
              <idno type="doi">10.1101/2021.02.04.429864</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="sdv">Life Sciences [q-bio]</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>We address the challenge of inferring a consensus 3D model of genome architecture from Hi-C data. Existing approaches most often rely on a two step algorithm: first convert the contact counts into distances, then optimize an objective function akin to multidimensional scaling (MDS) to infer a 3D model. Other approaches use a maximum likelihood approach, modeling the contact counts between two loci as a Poisson random variable whose intensity is a decreasing function of the distance between them. However, a Poisson model of contact counts implies that the variance of the data is equal to the mean, a relationship that is often too restrictive to properly model count data. We first confirm the presence of overdispersion in several real Hi-C data sets, and we show that the overdispersion arises even in simulated data sets. We then propose a new model, called Pastis-NB, where we replace the Poisson model of contact counts by a negative binomial one, which is parametrized by a mean and a separate dispersion parameter. The dispersion parameter allows the variance to be adjusted independently from the mean, thus better modeling overdispersed data. We compare the results of Pastis-NB to those of several previously published algorithms: three MDS-based methods (ShRec3D, ChromSDE, and Pastis-MDS) and a statistical methods based on a Poisson model of the data (Pastis-PM). We show that the negative binomial inference yields more accurate structures on simulated data, and more robust structures than other models across real Hi-C replicates and across different resolutions. A Python implementation of Pastis-NB is available at https://github.com/hiclib/pastis under the BSD license Supplementary information is available at https://nellev.github.io/pastisnb/</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-1069752" status="VALID">
          <orgName>Translational microbial Evolution and Engineering</orgName>
          <orgName type="acronym">TIMC-TrEE</orgName>
          <date type="start">2021-01-01</date>
          <desc>
            <address>
              <addrLine>Faculté de médecine de Grenoble, bâtiment Jean Roget, 38706 La Tronche</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.timc.fr/TrEE</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1043049" type="direct"/>
            <relation active="#struct-301767" type="indirect"/>
            <relation name="UMR5525" active="#struct-441569" type="indirect"/>
            <relation active="#struct-1042703" type="indirect"/>
            <relation active="#struct-1043329" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-22573" status="VALID">
          <orgName>Department of Genome Sciences [Seattle]</orgName>
          <orgName type="acronym">GS</orgName>
          <desc>
            <address>
              <addrLine>1705 NE Pacific St #K-357 / Box 357730 Seattle WA 98195-7730</addrLine>
              <country key="US"/>
            </address>
            <ref type="url">http://gs.washington.edu/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300433" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1062878" status="VALID">
          <orgName>Google Research [Paris]</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-46211" status="VALID">
          <idno type="ROR">https://ror.org/0095dt357</idno>
          <orgName>Cancer et génome: Bioinformatique, biostatistiques et épidémiologie d'un système complexe</orgName>
          <desc>
            <address>
              <addrLine>26 rue d'Ulm - 75248 Paris cedex 05</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://science.curie.fr/recherche/biologie-interactive-des-tumeurs-immunologie-environnement/c/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301492" type="direct"/>
            <relation active="#struct-564132" type="indirect"/>
            <relation active="#struct-301888" type="direct"/>
            <relation name="U900" active="#struct-303623" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1043049" status="VALID">
          <idno type="IdRef">14728936X</idno>
          <idno type="ISNI">0000 0004 4687 1979</idno>
          <idno type="RNSR">199511969L</idno>
          <idno type="ROR">https://ror.org/03985kf35</idno>
          <orgName>Translational Innovation in Medicine and Complexity / Recherche Translationnelle et Innovation en Médecine et Complexité - UMR 5525</orgName>
          <orgName type="acronym">TIMC</orgName>
          <date type="start">2021-01-01</date>
          <desc>
            <address>
              <addrLine>Domaine de la Merci, 38706 La Tronche, France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.timc.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301767" type="direct"/>
            <relation name="UMR5525" active="#struct-441569" type="direct"/>
            <relation active="#struct-1042703" type="direct"/>
            <relation active="#struct-1043329" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-301767" status="VALID">
          <idno type="ROR">https://ror.org/01c7wz417</idno>
          <orgName>VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement</orgName>
          <orgName type="acronym">VAS</orgName>
          <date type="start">2010-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Lyon, VetAgro Sup, 69280 Marcy l'Etoile (campus vétérinaire); Université de Clermont, VetAgro Sup, 63370 Lempdes (campus agronomique)</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.vetagro-sup.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="regroupinstitution" xml:id="struct-1042703" status="VALID">
          <idno type="IdRef">240648315</idno>
          <idno type="ROR">https://ror.org/02rx3b187</idno>
          <orgName>Université Grenoble Alpes</orgName>
          <orgName type="acronym">UGA</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Adresse CS 40700 - 38058 Grenoble cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-grenoble-alpes.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-1043329" status="VALID">
          <idno type="IdRef">026388804</idno>
          <idno type="ROR">https://ror.org/05sbt2524</idno>
          <orgName>Institut polytechnique de Grenoble - Grenoble Institute of Technology</orgName>
          <orgName type="acronym">Grenoble INP</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>46 avenue Félix Viallet 38031 Grenoble Cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.grenoble-inp.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1042703" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300433" status="VALID">
          <idno type="ROR">https://ror.org/00cvxb145</idno>
          <orgName>University of Washington [Seattle]</orgName>
          <desc>
            <address>
              <addrLine>Seattle, Washington 98105</addrLine>
              <country key="US"/>
            </address>
            <ref type="url">http://www.washington.edu/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-301492" status="VALID">
          <idno type="IdRef">026375249</idno>
          <idno type="ROR">https://ror.org/04y8cs423</idno>
          <orgName>Mines Paris - PSL (École nationale supérieure des mines de Paris)</orgName>
          <date type="start">1783-01-01</date>
          <desc>
            <address>
              <addrLine>60, boulevard Saint-Michel 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.minesparis.psl.eu/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-564132" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-564132" status="VALID">
          <idno type="IdRef">241597595</idno>
          <idno type="ISNI">0000 0004 1784 3645</idno>
          <idno type="ROR">https://ror.org/013cjyk83</idno>
          <orgName>Université Paris Sciences et Lettres</orgName>
          <orgName type="acronym">PSL</orgName>
          <desc>
            <address>
              <addrLine>60 rue Mazarine 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.psl.eu/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-301888" status="VALID">
          <idno type="ISNI">0000 0004 0639 6384</idno>
          <idno type="ROR">https://ror.org/04t0gwh46</idno>
          <orgName>Institut Curie [Paris]</orgName>
          <desc>
            <address>
              <addrLine>26 rue d'Ulm - 75248 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://science.curie.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>