<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-7886641:0</r:URN>
  <r:Agency>SND</r:Agency>
  <r:ID>doi-10-17045-sthlmuni-7886641</r:ID>
  <r:Version>0</r:Version>
  <g:ResourcePackage>
    <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7886641.ResourcePackage:2.0</r:URN>
    <r:OtherMaterialScheme>
      <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7886641.OtherMaterialScheme:2.0</r:URN>
    </r:OtherMaterialScheme>
    <a:OrganizationScheme>
      <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7886641.OrganizationScheme-0:2.0</r:URN>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7886641.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:OrganizationScheme>
  </g:ResourcePackage>
  <s:StudyUnit>
    <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7886641.StudyUnit:2.0</r:URN>
    <r:UserID typeOfUserID="datasetIdentifier">doi-10-17045-sthlmuni-7886641</r:UserID>
    <r:Citation>
      <r:Title>
        <r:String xml:lang="en">ATP-cone sequence clusters</r:String>
      </r:Title>
      <r:Creator>
        <r:CreatorReference>
          <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7886641.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>2019-03-25</r:SimpleDate>
      </r:PublicationDate>
      <r:InternationalIdentifier>
        <r:IdentifierContent>10.17045/STHLMUNI.7886641</r:IdentifierContent>
        <r:ManagingAgency controlledVocabularyAgencyName="DOI">DOI</r:ManagingAgency>
      </r:InternationalIdentifier>
    </r:Citation>
    <r:Abstract>
      <r:Content xml:lang="en">The NCBI RefSeq database (2019-03-19; Haft et al. 2018 https://doi.org/10.1093/nar/gkx1068) was searched with Pfam's ATP-cone profile (accno: PF03477; Finn et al. 2010 https://doi.org/10.1093/nar/gkp985) returning 44367 NCBI accessions. Ribonucleotide reductase proteins were identified using HMMER (Eddy 2011 https://doi.org/10.1371/journal.pcbi.1002195) profiles from the RNRdb database (http://rnrdb.pfitmap.org). Subsequently, sequences were clustered with UCLUST (Edgar 2010 https://doi.org/10.1093/bioinformatics/btq461) at identity to remove sequence duplicates (24477 sequences remaning).
All sequences were pairwise aligned to each other using LAST (Kiełbasa et al. 2011 https://doi.org/10.1101/gr.113985.110) and a bitscore matrix was constructed. The bitscore matrix was clustered with MCL (Enright, Dongen &amp; Ouzounis 2002 https://doi.org/10.1093/nar/30.7.1575) using the Cluster Maker 2 (Morris et al. 2011 https://doi.org/10.1186/1471-2105-12-436) Cytoscape (Shannon et al. 2003 https://doi.org/10.1101/gr.1239303) app. Bitscores &lt; 200 were not included in the initial network and an inflation parameter of 2.5 was used.
The file "atp-cone_mcl_clustering.tsv" contains all information necessary to recreate the clustering as well as the assigned cluster numbers to each sequence. 

Column names: SUID: Cytoscape's id, accno: NCBI's accession number, mcl2.0ewc200-mcl3.0: cluster assignments with inflation parameters and bitscore cutoff (ewc; when used), name: sequence identifier composed of accno plus cone number, outer_inner: "inner", "middle" or "outer" when more than one cone present in full sequence, pclass and psubclass: RNR class and subclass, ptype: protein type, taxon, tdomain: taxonomic domain, title: NCBI's description of the sequence.
The "precluster_assignments.tsv" file contains the results of the preclustering with USEARCH, i.e. which usearch cluster (first column) each accession number (second column) belong to.</r:Content>
    </r:Abstract>
    <r:Coverage>
      <r:TopicalCoverage>
        <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7886641.TopicalCoverage:2.0</r:URN>
        <r:Subject xml:lang="en" controlledVocabularyID="10408" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Biochemistry</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="10408" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Biokemi</r:Subject>
      </r:TopicalCoverage>
      <r:SpatialCoverage />
    </r:Coverage>
    <a:Archive>
      <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7886641.Archive:2.0</r:URN>
      <a:ArchiveSpecific>
        <a:Item>
          <a:Access>
            <r:URN>urn:ddi:se.researchdata:doi-10-17045-sthlmuni-7886641.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>