<?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-04121819</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="2026-05-22T15:00:20+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Toward Optimal Fingerprint Indexing for Large Scale Genomics</title>
            <author role="aut">
              <persName>
                <forename type="first">Clément</forename>
                <surname>Agret</surname>
              </persName>
              <email type="md5">6ae57246ee27ff2ed4fff3d53e070d2e</email>
              <email type="domain">lirmm.fr</email>
              <idno type="idhal" notation="numeric">1211256</idno>
              <idno type="halauthorid" notation="string">1865818-1211256</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7404-7253</idno>
              <idno type="IDREF">https://www.idref.fr/250366339</idno>
              <affiliation ref="#struct-1100627"/>
              <affiliation ref="#struct-410272"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Bastien</forename>
                <surname>Cazaux</surname>
              </persName>
              <email type="md5">9801dd5f380a8ef2148c88eb68f25fc8</email>
              <email type="domain">lirmm.fr</email>
              <idno type="idhal" notation="string">cazaux-bastien</idno>
              <idno type="idhal" notation="numeric">3129</idno>
              <idno type="halauthorid" notation="string">23494-3129</idno>
              <idno type="IDREF">https://www.idref.fr/226877523</idno>
              <affiliation ref="#struct-410272"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Antoine</forename>
                <surname>Limasset</surname>
              </persName>
              <email type="md5">6de70c50e6f0b920c15c07d64a6b83f3</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">antoine-limasset</idno>
              <idno type="idhal" notation="numeric">180632</idno>
              <idno type="halauthorid" notation="string">30639-180632</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0669-4141</idno>
              <idno type="IDREF">https://www.idref.fr/223503908</idno>
              <affiliation ref="#struct-441569"/>
              <affiliation ref="#struct-410272"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Isabelle</forename>
                <surname>Gouat</surname>
              </persName>
              <email type="md5">01a8910ec35817770bca127295d8d38a</email>
              <email type="domain">lirmm.fr</email>
            </editor>
            <funder ref="#projanr-55832"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-06-08 11:02:30</date>
              <date type="whenModified">2025-12-02 03:18:12</date>
              <date type="whenReleased">2023-06-08 13:56:01</date>
              <date type="whenProduced">2022-09-05</date>
              <date type="whenEndEmbargoed">2023-06-08</date>
              <ref type="file" target="https://hal.science/hal-04121819v1/document">
                <date notBefore="2023-06-08"/>
              </ref>
              <ref type="file" subtype="publisherPaid" n="1" target="https://hal.science/hal-04121819v1/file/LIPIcs-WABI-2022-25.pdf" id="file-4121930-3588235">
                <date notBefore="2023-06-08"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="102079">
                <persName>
                  <forename>Isabelle</forename>
                  <surname>Gouat</surname>
                </persName>
                <email type="md5">01a8910ec35817770bca127295d8d38a</email>
                <email type="domain">lirmm.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04121819</idno>
            <idno type="halUri">https://hal.science/hal-04121819</idno>
            <idno type="halBibtex">agret:hal-04121819</idno>
            <idno type="halRefHtml">&lt;i&gt;WABI 2022 - 22nd International Workshop on Algorithms in Bioinformatics&lt;/i&gt;, Sep 2022, Postdam, Germany. pp.25:1-25:15, &lt;a target="_blank" href="https://dx.doi.org/10.4230/LIPIcs.WABI.2022.25"&gt;&amp;#x27E8;10.4230/LIPIcs.WABI.2022.25&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">WABI 2022 - 22nd International Workshop on Algorithms in Bioinformatics, Sep 2022, Postdam, Germany. pp.25:1-25:15, &amp;#x27E8;10.4230/LIPIcs.WABI.2022.25&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-4121930-3588235"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-MONTP3">Université de Montpellier Paul-Valéry</idno>
            <idno type="stamp" n="UNIV-PERP">Université Perpignan Via Domitia</idno>
            <idno type="stamp" n="MAB" corresp="LIRMM">Méthodes et Algorithmes pour la Bioinformatique</idno>
            <idno type="stamp" n="LIRMM">Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier</idno>
            <idno type="stamp" n="CRISTAL">Centre de Recherche en Informatique, Signal et Automatique de Lille (CRISTAL)</idno>
            <idno type="stamp" n="CRISTAL-BONSAI" corresp="CRISTAL">CRISTAL-BONSAI</idno>
            <idno type="stamp" n="UNIV-MONTPELLIER">Université de Montpellier</idno>
            <idno type="stamp" n="UNIV-LILLE">Université de Lille</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="UPVM-TI" corresp="UNIV-MONTP3">Publications UPVM texte intégral</idno>
            <idno type="stamp" n="UM-2015-2021" corresp="UNIV-MONTPELLIER">Université de Montpellier (2015-2021)</idno>
            <idno type="stamp" n="UM-EPE" corresp="UNIV-MONTPELLIER">Université de Montpellier - EPE</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="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Toward Optimal Fingerprint Indexing for Large Scale Genomics</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Clément</forename>
                    <surname>Agret</surname>
                  </persName>
                  <email type="md5">6ae57246ee27ff2ed4fff3d53e070d2e</email>
                  <email type="domain">lirmm.fr</email>
                  <idno type="idhal" notation="numeric">1211256</idno>
                  <idno type="halauthorid" notation="string">1865818-1211256</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7404-7253</idno>
                  <idno type="IDREF">https://www.idref.fr/250366339</idno>
                  <affiliation ref="#struct-1100627"/>
                  <affiliation ref="#struct-410272"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Bastien</forename>
                    <surname>Cazaux</surname>
                  </persName>
                  <email type="md5">9801dd5f380a8ef2148c88eb68f25fc8</email>
                  <email type="domain">lirmm.fr</email>
                  <idno type="idhal" notation="string">cazaux-bastien</idno>
                  <idno type="idhal" notation="numeric">3129</idno>
                  <idno type="halauthorid" notation="string">23494-3129</idno>
                  <idno type="IDREF">https://www.idref.fr/226877523</idno>
                  <affiliation ref="#struct-410272"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Antoine</forename>
                    <surname>Limasset</surname>
                  </persName>
                  <email type="md5">6de70c50e6f0b920c15c07d64a6b83f3</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">antoine-limasset</idno>
                  <idno type="idhal" notation="numeric">180632</idno>
                  <idno type="halauthorid" notation="string">30639-180632</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0669-4141</idno>
                  <idno type="IDREF">https://www.idref.fr/223503908</idno>
                  <affiliation ref="#struct-441569"/>
                  <affiliation ref="#struct-410272"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>WABI 2022 - 22nd International Workshop on Algorithms in Bioinformatics</title>
                  <date type="start">2022-09-05</date>
                  <date type="end">2022-09-07</date>
                  <settlement>Postdam</settlement>
                  <country key="DE">Germany</country>
                </meeting>
                <imprint>
                  <biblScope unit="serie">Leibniz International Proceedings in Informatics (LIPIcs)</biblScope>
                  <biblScope unit="volume">242</biblScope>
                  <biblScope unit="issue">25</biblScope>
                  <biblScope unit="pp">25:1–25:15</biblScope>
                  <date type="datePub">2022-08-26</date>
                </imprint>
              </monogr>
              <idno type="doi">10.4230/LIPIcs.WABI.2022.25</idno>
              <ref target="https://github.com/Malfoy/NIQKI" type="seeAlso"/>
              <ref target="https://hal-lirmm.ccsd.cnrs.fr/lirmm-04121986v1" type="seeAlso"/>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Data Structure</term>
                <term xml:lang="en">Indexation</term>
                <term xml:lang="en">Local Sensitive Hashing</term>
                <term xml:lang="en">Genomes</term>
                <term xml:lang="en">Databases</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-bi">Computer Science [cs]/Bioinformatics [q-bio.QM]</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>Motivation. To keep up with the scale of genomic databases, several methods rely on local sensitive hashing methods to efficiently find potential matches within large genome collections. Existing solutions rely on Minhash or Hyperloglog fingerprints and require reading the whole index to perform a query. Such solutions can not be considered scalable with the growing amount of documents to index. Results. We present NIQKI, a novel structure with well-designed fingerprints that lead to theoretical and practical query time improvements, outperforming state-of-the-art by orders of magnitude. Our contribution is threefold. First, we generalize the concept of Hyperminhash fingerprints in (h,m)-HMH fingerprints that can be tuned to present the lowest false positive rate given the expected sub-sampling applied. Second, we provide a structure able to index any kind of fingerprints based on inverted indexes that provide optimal queries, namely linear with the size of the output. Third, we implemented these approaches in a tool dubbed NIQKI that can index and calculate pairwise distances for over one million bacterial genomes from GenBank in a few days on a small cluster. We show that our approach can be orders of magnitude faster than state-of-the-art with comparable precision. We believe this approach can lead to tremendous improvements, allowing fast queries and scaling on extensive genomic databases.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-1100627" status="VALID">
          <orgName>Méthodes et Algorithmes pour la Bioinformatique</orgName>
          <orgName type="acronym">LIRMM | MAB</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <addrLine>LIRMM, 161 rue Ada, 34000 Montpellier</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.lirmm.fr/equipes/MAB/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1100620" type="direct"/>
            <relation active="#struct-101475" type="indirect"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation name="UMR5506" active="#struct-441569" type="indirect"/>
            <relation name="UMR5506" active="#struct-1100589" type="indirect"/>
            <relation active="#struct-1219853" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-410272" status="VALID">
          <idno type="IdRef">18388695X</idno>
          <idno type="RNSR">201521249L</idno>
          <idno type="ROR">https://ror.org/05vrs3189</idno>
          <idno type="Wikidata">Q116959497</idno>
          <orgName>Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189</orgName>
          <orgName type="acronym">CRIStAL</orgName>
          <date type="start">2015-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Lille - Campus scientifique - Bâtiment ESPRIT - Avenue Henri Poincaré - 59655 Villeneuve d’Ascq</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cristal.univ-lille.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR9189" active="#struct-120930" type="direct"/>
            <relation name="UMR9189" active="#struct-374570" type="direct"/>
            <relation name="UMR9189" active="#struct-441569" type="direct"/>
          </listRelation>
        </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="laboratory" xml:id="struct-1100620" status="VALID">
          <idno type="IdRef">139590827</idno>
          <idno type="ISNI">0000000405990488</idno>
          <idno type="RNSR">199111950H</idno>
          <idno type="ROR">https://ror.org/013yean28</idno>
          <orgName>Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier</orgName>
          <orgName type="acronym">LIRMM</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <addrLine>161 rue Ada - 34095 Montpellier</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.lirmm.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-101475" type="direct"/>
            <relation active="#struct-300009" type="direct"/>
            <relation name="UMR5506" active="#struct-441569" type="direct"/>
            <relation name="UMR5506" active="#struct-1100589" type="direct"/>
            <relation active="#struct-1219853" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-101475" status="VALID">
          <idno type="ROR">https://ror.org/03am2jy38</idno>
          <orgName>Université de Perpignan Via Domitia</orgName>
          <orgName type="acronym">UPVD</orgName>
          <desc>
            <address>
              <addrLine>52 avenue Paul Alduy - 66860 Perpignan Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-perp.fr/</ref>
          </desc>
        </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="regroupinstitution" xml:id="struct-1100589" status="VALID">
          <idno type="ROR">https://ror.org/051escj72</idno>
          <orgName>Université de Montpellier</orgName>
          <orgName type="acronym">UM</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <addrLine>163 rue Auguste Broussonnet - 34090 Montpellier</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.umontpellier.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-1219853" status="VALID">
          <idno type="IdRef">282217916</idno>
          <orgName>Université de Montpellier Paul-Valéry</orgName>
          <orgName type="acronym">UMPV</orgName>
          <date type="start">2025-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Montpellier Paul-Valéry Route de Mende 34199 Montpellier Cedex 5</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-montp3.fr/fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-120930" status="VALID">
          <idno type="IdRef">256304629</idno>
          <idno type="ISNI">0000000122034461</idno>
          <idno type="ROR">https://ror.org/01x441g73</idno>
          <orgName>Centrale Lille</orgName>
          <desc>
            <address>
              <addrLine>École Centrale de Lille - Cité Scientifique - CS 20048 59651 Villeneuve d'Ascq Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://centralelille.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-374570" status="VALID">
          <idno type="IdRef">223446556</idno>
          <idno type="ISNI">0000 0001 2242 6780</idno>
          <idno type="ROR">https://ror.org/02kzqn938</idno>
          <idno type="Wikidata">Q3551621</idno>
          <orgName>Université de Lille</orgName>
          <desc>
            <address>
              <addrLine>EPE Université de Lille. -- 42 rue Paul Duez, 59000 Lille</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-lille.fr/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-55832" status="VALID">
          <idno type="anr">ANR-21-CE45-0012</idno>
          <orgName>Agate</orgName>
          <desc>Structures de graphe adaptées pour l'exploration de données de séquençage de troisième génération</desc>
          <date type="start">2021</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>