<?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-03591864</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="2026-05-22T20:16:22+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Systematic processing of ribosomal RNA gene amplicon sequencing data</title>
            <author role="aut">
              <persName>
                <forename type="first">Julien</forename>
                <surname>Tremblay</surname>
              </persName>
              <email type="md5">84554c215f3a23704f0f4b5b910cd754</email>
              <email type="domain">inra.fr</email>
              <idno type="idhal" notation="numeric">1297736</idno>
              <idno type="halauthorid" notation="string">516961-1297736</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-6085-3481</idno>
              <affiliation ref="#struct-303485"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Etienne</forename>
                <surname>Yergeau</surname>
              </persName>
              <email type="md5">1373c39f58fd4f16b44024fda85fbbc3</email>
              <email type="domain">iaf.inrs.ca</email>
              <idno type="idhal" notation="numeric">1297737</idno>
              <idno type="halauthorid" notation="string">500045-1297737</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7112-3425</idno>
              <affiliation ref="#struct-54664"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Michel</forename>
                <surname>Courcelles</surname>
              </persName>
              <email type="md5">235ee71abfb5f3fb19e1b204192e01ee</email>
              <email type="domain">iaf.inrs.ca</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2022-02-28 20:28:50</date>
              <date type="whenModified">2024-12-19 11:12:04</date>
              <date type="whenReleased">2022-02-28 20:28:50</date>
              <date type="whenProduced">2019-12-01</date>
              <ref type="externalLink" target="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6901069"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="157387">
                <persName>
                  <forename>Michel</forename>
                  <surname>Courcelles</surname>
                </persName>
                <email type="md5">235ee71abfb5f3fb19e1b204192e01ee</email>
                <email type="domain">iaf.inrs.ca</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03591864</idno>
            <idno type="halUri">https://hal.science/hal-03591864</idno>
            <idno type="halBibtex">tremblay:hal-03591864</idno>
            <idno type="halRefHtml">&lt;i&gt;GigaScience&lt;/i&gt;, 2019, 8 (12), &lt;a target="_blank" href="https://dx.doi.org/10.1093/gigascience/giz146"&gt;&amp;#x27E8;10.1093/gigascience/giz146&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">GigaScience, 2019, 8 (12), &amp;#x27E8;10.1093/gigascience/giz146&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="RIIP">Pasteur Network</idno>
            <idno type="stamp" n="INRS-IAF" corresp="RIIP">Institut Armand Frappier</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Systematic processing of ribosomal RNA gene amplicon sequencing data</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Julien</forename>
                    <surname>Tremblay</surname>
                  </persName>
                  <email type="md5">84554c215f3a23704f0f4b5b910cd754</email>
                  <email type="domain">inra.fr</email>
                  <idno type="idhal" notation="numeric">1297736</idno>
                  <idno type="halauthorid" notation="string">516961-1297736</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-6085-3481</idno>
                  <affiliation ref="#struct-303485"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Etienne</forename>
                    <surname>Yergeau</surname>
                  </persName>
                  <email type="md5">1373c39f58fd4f16b44024fda85fbbc3</email>
                  <email type="domain">iaf.inrs.ca</email>
                  <idno type="idhal" notation="numeric">1297737</idno>
                  <idno type="halauthorid" notation="string">500045-1297737</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7112-3425</idno>
                  <affiliation ref="#struct-54664"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">69034</idno>
                <idno type="eissn">2047-217X</idno>
                <title level="j">GigaScience</title>
                <imprint>
                  <publisher>Oxford Univ Press</publisher>
                  <biblScope unit="volume">8</biblScope>
                  <biblScope unit="issue">12</biblScope>
                  <date type="datePub">2019-12-01</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1093/gigascience/giz146</idno>
              <idno type="pubmed">31816087</idno>
              <idno type="pubmedcentral">PMC6901069</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">rRNA gene amplicons</term>
                <term xml:lang="en">metagenomics</term>
                <term xml:lang="en">bioinformatics</term>
                <term xml:lang="en">High Performance Computing</term>
              </keywords>
              <classCode scheme="mesh">Computational Biology</classCode>
              <classCode scheme="mesh">Genes, rRNA</classCode>
              <classCode scheme="mesh">High-Throughput Nucleotide Sequencing</classCode>
              <classCode scheme="mesh">Metagenomics</classCode>
              <classCode scheme="mesh">Phylogeny</classCode>
              <classCode scheme="mesh">Sequence Analysis, DNA</classCode>
              <classCode scheme="mesh">Software</classCode>
              <classCode scheme="halDomain" n="sdv">Life Sciences [q-bio]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Background: With the advent of high-throughput sequencing, microbiology is becoming increasingly data-intensive. Because of its low cost, robust databases, and established bioinformatic workflows, sequencing of 16S/18S/ITS ribosomal RNA (rRNA) gene amplicons, which provides a marker of choice for phylogenetic studies, has become ubiquitous. Many established end-to-end bioinformatic pipelines are available to perform short amplicon sequence data analysis. These pipelines suit a general audience, but few options exist for more specialized users who are experienced in code scripting, Linux-based systems, and high-performance computing (HPC) environments. For such an audience, existing pipelines can be limiting to fully leverage modern HPC capabilities and perform tweaking and optimization operations. Moreover, a wealth of stand-alone software packages that perform specific targeted bioinformatic tasks are increasingly accessible, and finding a way to easily integrate these applications in a pipeline is critical to the evolution of bioinformatic methodologies.Results: Here we describe AmpliconTagger, a short rRNA marker gene amplicon pipeline coded in a Python framework that enables fine tuning and integration of virtually any potential rRNA gene amplicon bioinformatic procedure. It is designed to work within an HPC environment, supporting a complex network of job dependencies with a smart-restart mechanism in case of job failure or parameter modifications. As proof of concept, we present end results obtained with AmpliconTagger using 16S, 18S, ITS rRNA short gene amplicons and Pacific Biosciences long-read amplicon data types as input.Conclusions: Using a selection of published algorithms for generating operational taxonomic units and amplicon sequence variants and for computing downstream taxonomic summaries and diversity metrics, we demonstrate the performance and versatility of our pipeline for systematic analyses of amplicon sequence data.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-303485" status="VALID">
          <idno type="IdRef">028328361</idno>
          <idno type="ROR">https://ror.org/04mte1k06</idno>
          <orgName>National Research Council of Canada</orgName>
          <orgName type="acronym">NRC</orgName>
          <desc>
            <address>
              <addrLine>1200 Montreal Road, Building M-58, Ottawa, Ontario K1A 0R6</addrLine>
              <country key="CA"/>
            </address>
            <ref type="url">http://www.nrc-cnrc.gc.ca/eng/index.html#</ref>
          </desc>
        </org>
        <org type="regrouplaboratory" xml:id="struct-54664" status="VALID">
          <orgName>Armand-Frappier Santé Biotechnologie Research Centre</orgName>
          <orgName type="acronym">INRS-AFSB</orgName>
          <date type="start">1938-01-01</date>
          <desc>
            <address>
              <addrLine>531 boul. des Prairies Laval (Québec) H7V 1B7</addrLine>
              <country key="CA"/>
            </address>
            <ref type="url">https://inrs.ca/en/inrs/research-centres/armand-frappier-sante-biotechnologie-research-centre/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-92448" type="direct"/>
            <relation active="#struct-301247" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-92448" status="VALID">
          <idno type="ROR">https://ror.org/04td37d32</idno>
          <orgName>Institut National de la Recherche Scientifique [Québec]</orgName>
          <orgName type="acronym">INRS</orgName>
          <desc>
            <address>
              <addrLine>490 rue de la Couronne, Québec, QC G1K 9A9</addrLine>
              <country key="CA"/>
            </address>
            <ref type="url">http://www.inrs.ca/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-301247" status="VALID">
          <orgName>Pasteur Network (Réseau International des Instituts Pasteur)</orgName>
          <desc>
            <address>
              <addrLine>25, rue du Dr Roux 75724 Paris Cedex 15</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://pasteur-network.org/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>