<ddi:DDIInstance xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="ddi:instance:3_3 http://ddialliance.org/Specification/DDI-Lifecycle/3.3/XMLSchema/instance.xsd" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:ddi="ddi:instance:3_3" xmlns:r="ddi:reusable:3_3" xmlns:s="ddi:studyunit:3_3" xmlns:d="ddi:datacollection:3_3" xmlns:a="ddi:archive:3_3" xmlns:c="ddi:conceptualcomponent:3_3" xmlns:cm="ddi:comparative:3_3" xmlns:g="ddi:group:3_3" xmlns:l="ddi:logicalproduct:3_3" xmlns:p="ddi:physicaldataproduct:3_3" xmlns:pi="ddi:physicalinstance:3_3" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:xhtml="http://www.w3.org/1999/xhtml" xmlns:xml="http://www.w3.org/XML/1998/namespace" isMaintainable="true" scopeOfUniqueness="Agency">
  <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7642343:0</r:URN>
  <r:Agency>SND</r:Agency>
  <r:ID>doi-10-17045-sthlmuni-7642343</r:ID>
  <r:Version>0</r:Version>
  <g:ResourcePackage>
    <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7642343.ResourcePackage:2.0</r:URN>
    <r:OtherMaterialScheme>
      <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7642343.OtherMaterialScheme:2.0</r:URN>
    </r:OtherMaterialScheme>
    <a:OrganizationScheme>
      <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7642343.OrganizationScheme-0:2.0</r:URN>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7642343.Individual-0:2.0</r:URN>
        <a:IndividualIdentification>
          <a:IndividualName>
            <a:FullName>
              <r:String>Daniel Lundin</r:String>
            </a:FullName>
          </a:IndividualName>
          <a:ResearcherID>
            <a:TypeOfID>ORCID</a:TypeOfID>
            <a:ResearcherIdentification>0000-0002-8779-6464</a:ResearcherIdentification>
          </a:ResearcherID>
        </a:IndividualIdentification>
      </a:Individual>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7642343.Individual-0:2.0</r:URN>
        <a:IndividualIdentification>
          <a:IndividualName>
            <a:FullName>
              <r:String>Christoph Loderer</r:String>
            </a:FullName>
          </a:IndividualName>
        </a:IndividualIdentification>
      </a:Individual>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7642343.Individual-0:2.0</r:URN>
        <a:IndividualIdentification>
          <a:IndividualName>
            <a:FullName>
              <r:String>Karin Holmfeldt</r:String>
            </a:FullName>
          </a:IndividualName>
        </a:IndividualIdentification>
      </a:Individual>
    </a:OrganizationScheme>
  </g:ResourcePackage>
  <s:StudyUnit>
    <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7642343.StudyUnit:2.0</r:URN>
    <r:UserID typeOfUserID="datasetIdentifier">doi-10-17045-sthlmuni-7642343</r:UserID>
    <r:Citation>
      <r:Title>
        <r:String xml:lang="en">Metagenomic NrdJm5 sequences placed in full phylogeny</r:String>
      </r:Title>
      <r:Creator>
        <r:CreatorReference>
          <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7642343.Individual-0:2.0</r:URN>
          <r:TypeOfObject>Individual</r:TypeOfObject>
        </r:CreatorReference>
      </r:Creator>
      <r:Publisher>
        <r:PublisherName>
          <r:String xml:lang="sv">Stockholms universitet</r:String>
          <r:String xml:lang="en">Stockholm University</r:String>
        </r:PublisherName>
      </r:Publisher>
      <r:Publisher>
        <r:PublisherName>
          <r:String xml:lang="sv">Stockholms universitet</r:String>
          <r:String xml:lang="en">Stockholm University</r:String>
        </r:PublisherName>
      </r:Publisher>
      <r:PublicationDate>
        <r:SimpleDate>2019-01-29</r:SimpleDate>
      </r:PublicationDate>
      <r:InternationalIdentifier>
        <r:IdentifierContent>10.17045/STHLMUNI.7642343</r:IdentifierContent>
        <r:ManagingAgency controlledVocabularyAgencyName="DOI">DOI</r:ManagingAgency>
      </r:InternationalIdentifier>
    </r:Citation>
    <r:Abstract>
      <r:Content xml:lang="en">To search for sequences from metagenomics projects, we downloaded all TARA Ocean ORFs (Eren 2017, https://doi.org/10.6084/m9.figshare.4902917.v1 ; Delmont 2018, https://doi.org/10.1038/s41564-018-0176-9), all ORFs from the Human Microbiome Project (2019-01-09; HMP 2012a, https://doi.org/10.1038/nature11234 ; HMP 2012b, https://doi.org/10.1038/nature11209 ) the majority of bacterial MAGs and SAGs from IMG/MER (4910 MAGs, 2230 SAGs) plus 53 aquatic and soil metagenomes, in particular those with project names containing “virus”, “phage”, “therm” or “hot“ (see img_sags.tsv, img_metag_samples.tsv and img_mags.tsv) (Markowitz 2008, https://doi.org/10.1093/nar/gkm869). Together, we downloaded a total of 250,881,638 ORFs. We used hmm profiles designed for each clan in the phylogeny to search the sequences. We found 181 sequences with a best match to the profile designed from the TV clan. These were aligned to the original alignment using Clustal Omega in profile mode (all.NrdJm5.co.profile.wa.masked.alnfaa ; Sievers 2014, https://doi.org/10.1038/msb.2011.75) and phylogenetically placed in the phylogeny from https://doi.org/10.17045/sthlmuni.7117430.v2  with RAxML (Stamatakis 2014, https://doi.org/10.1093/bioinformatics/btu033). The resulting tree can be viewed with Dendroscope (Huson et al. 2007, https://doi.org/10.1186/1471-2105-8-460); placed sequences have "QUERY" prepended to their names.</r:Content>
    </r:Abstract>
    <r:Coverage>
      <r:TopicalCoverage>
        <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7642343.TopicalCoverage:2.0</r:URN>
        <r:Subject xml:lang="en" controlledVocabularyID="10615" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Evolutionary Biology</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="10615" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Evolutionsbiologi</r:Subject>
        <r:Subject xml:lang="en" controlledVocabularyID="10203" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Bioinformatics (Computational Biology)</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="10203" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Bioinformatik (beräkningsbiologi)</r:Subject>
        <r:Subject xml:lang="en" controlledVocabularyID="10610" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Bioinformatics and Computational Biology</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="10610" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Bioinformatik och beräkningsbiologi</r:Subject>
      </r:TopicalCoverage>
      <r:SpatialCoverage />
    </r:Coverage>
    <a:Archive>
      <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7642343.Archive:2.0</r:URN>
      <a:ArchiveSpecific>
        <a:Item>
          <a:Access>
            <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7642343.Archive-ArchiveSpecificType-AccessType:2.0</r:URN>
            <a:TypeOfAccess controlledVocabularyName="info:eu-repo-Access-Terms vocabulary"></a:TypeOfAccess>
          </a:Access>
          <a:DataFileQuantity>0</a:DataFileQuantity>
        </a:Item>
      </a:ArchiveSpecific>
    </a:Archive>
  </s:StudyUnit>
</ddi:DDIInstance>