<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-10-17044-scilifelab-28380476:0</r:URN>
  <r:Agency>SND</r:Agency>
  <r:ID>doi-10-17044-scilifelab-28380476</r:ID>
  <r:Version>0</r:Version>
  <g:ResourcePackage>
    <r:URN>urn:ddi:se.researchdata:doi-10-17044-scilifelab-28380476.ResourcePackage:2.0</r:URN>
    <r:OtherMaterialScheme>
      <r:URN>urn:ddi:se.researchdata:doi-10-17044-scilifelab-28380476.OtherMaterialScheme:2.0</r:URN>
    </r:OtherMaterialScheme>
    <a:OrganizationScheme>
      <r:URN>urn:ddi:se.researchdata:doi-10-17044-scilifelab-28380476.OrganizationScheme-0:2.0</r:URN>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:doi-10-17044-scilifelab-28380476.Individual-0:2.0</r:URN>
        <r:UserAttributePair>
          <r:AttributeKey>affiliation</r:AttributeKey>
          <r:AttributeValue>Science for Life Laboratory</r:AttributeValue>
        </r:UserAttributePair>
        <a:IndividualIdentification>
          <a:IndividualName>
            <a:FirstGiven>Nikolay</a:FirstGiven>
            <a:LastFamily>Oskolkov</a:LastFamily>
            <a:FullName>
              <r:String>Nikolay Oskolkov</r:String>
            </a:FullName>
          </a:IndividualName>
          <a:ResearcherID>
            <a:TypeOfID>ORCID</a:TypeOfID>
            <a:ResearcherIdentification>0000-0001-5326-8893</a:ResearcherIdentification>
          </a:ResearcherID>
        </a:IndividualIdentification>
      </a:Individual>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:doi-10-17044-scilifelab-28380476.Individual-0:2.0</r:URN>
        <a:IndividualIdentification>
          <a:IndividualName>
            <a:FirstGiven>Tom</a:FirstGiven>
            <a:LastFamily>van der Valk</a:LastFamily>
            <a:FullName>
              <r:String>Tom van der Valk</r:String>
            </a:FullName>
          </a:IndividualName>
        </a:IndividualIdentification>
      </a:Individual>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:doi-10-17044-scilifelab-28380476.Individual-0:2.0</r:URN>
        <r:UserAttributePair>
          <r:AttributeKey>affiliation</r:AttributeKey>
          <r:AttributeValue>Science for Life Laboratory</r:AttributeValue>
        </r:UserAttributePair>
        <a:IndividualIdentification>
          <a:IndividualName>
            <a:FirstGiven>Samantha</a:FirstGiven>
            <a:LastFamily>Lopez Clinton</a:LastFamily>
            <a:FullName>
              <r:String>Samantha Lopez Clinton</r:String>
            </a:FullName>
          </a:IndividualName>
        </a:IndividualIdentification>
      </a:Individual>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:doi-10-17044-scilifelab-28380476.Individual-0:2.0</r:URN>
        <a:IndividualIdentification>
          <a:IndividualName>
            <a:FirstGiven>Chenyu</a:FirstGiven>
            <a:LastFamily>Jin</a:LastFamily>
            <a:FullName>
              <r:String>Chenyu Jin</r:String>
            </a:FullName>
          </a:IndividualName>
        </a:IndividualIdentification>
      </a:Individual>
    </a:OrganizationScheme>
  </g:ResourcePackage>
  <s:StudyUnit>
    <r:URN>urn:ddi:se.researchdata:doi-10-17044-scilifelab-28380476.StudyUnit:2.0</r:URN>
    <r:UserID typeOfUserID="datasetIdentifier">doi-10-17044-scilifelab-28380476</r:UserID>
    <r:Citation>
      <r:Title>
        <r:String xml:lang="en">Coordinates of microbial contamination in eukaryotic reference genomes</r:String>
      </r:Title>
      <r:Creator>
        <r:CreatorReference>
          <r:URN>urn:ddi:se.researchdata:doi-10-17044-scilifelab-28380476.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>2025-03-27</r:SimpleDate>
      </r:PublicationDate>
      <r:InternationalIdentifier>
        <r:IdentifierContent>10.17044/SCILIFELAB.28380476</r:IdentifierContent>
        <r:ManagingAgency controlledVocabularyAgencyName="DOI">DOI</r:ManagingAgency>
      </r:InternationalIdentifier>
    </r:Citation>
    <r:Abstract>
      <r:Content xml:lang="en">This dataset contains coordinates of microbial contamination in eukaryotic chromosome-level reference genomes of 96 plant, 114 invertebrate and 162 non-mammalian vertebrate species, 566 chromosome- and scaffold-level mammalian reference assemblies from the National Center for Biotechnology Information Reference Sequence Database (NCBI RefSeq), https://ftp.ncbi.nlm.nih.gov/refseq/release/, and a custom arthropod dataset comprising 2088 reference genomes, and 1323 nordic plant contig-level assemblies from the PhyloNorway project, DataverseNO V1, https://dataverse.no/dataset.xhtml;jsessionid=dfe334bbadc5fb9c5eab4332d568?persistentId=doi:10.18710/3CVQAG&amp;version=DRAFT.

Each group of organisms has two coordinate (bed-) files: simple and comprehensive, the "full"-version corresponds to the comprehensive bed-file with microbial annotation for each region of microbial contamination.

The dataset was produced by Nikolay Oskolkov, Lund University, Sweden, within the NBIS SciLifeLab long-term support project, PI Tom van der Valk, Centre for Palaeogenetics, Stockholm, Sweden.

If you use the dataset for your research, please cite our manuscript:

Nikolay Oskolkov, Chenyu Jin, Samantha López Clinton, Flore Wijnands, Ernst Johnson, Benjamin Guinet, Verena Kutschera, Cormac Kinsella, Peter D. Heintzman and Tom van der Valk, Disinfecting eukaryotic reference genomes to improve taxonomic inference from environmental ancient metagenomic data, https://www.biorxiv.org/content/10.1101/2025.03.19.644176v1, https://doi.org/10.1101/2025.03.19.644176

Questions regarding the dataset should be sent to nikolay.oskolkov@scilifelab.se</r:Content>
    </r:Abstract>
    <r:Coverage>
      <r:TopicalCoverage>
        <r:URN>urn:ddi:se.researchdata:doi-10-17044-scilifelab-28380476.TopicalCoverage:2.0</r:URN>
        <r:Subject xml:lang="en" controlledVocabularyID="3" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Medical and Health Sciences</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="3" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Medicin och hälsovetenskap</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:TopicalCoverage>
      <r:SpatialCoverage />
    </r:Coverage>
    <a:Archive>
      <r:URN>urn:ddi:se.researchdata:doi-10-17044-scilifelab-28380476.Archive:2.0</r:URN>
      <a:ArchiveSpecific>
        <a:Item>
          <a:Access>
            <r:URN>urn:ddi:se.researchdata:doi-10-17044-scilifelab-28380476.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>