<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:2024-129:1</r:URN>
  <r:Agency>SND</r:Agency>
  <r:ID>2024-129</r:ID>
  <r:Version>1</r:Version>
  <g:ResourcePackage>
    <r:URN>urn:ddi:se.researchdata:2024-129.ResourcePackage:2.0</r:URN>
    <r:OtherMaterialScheme>
      <r:URN>urn:ddi:se.researchdata:2024-129.OtherMaterialScheme:2.0</r:URN>
    </r:OtherMaterialScheme>
    <a:OrganizationScheme>
      <r:URN>urn:ddi:se.researchdata:2024-129.OrganizationScheme-0:2.0</r:URN>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:2024-129.Individual-0:2.0</r:URN>
        <r:UserAttributePair>
          <r:AttributeKey>affiliation</r:AttributeKey>
          <r:AttributeValue>Department of Medicine, Huddinge / Center for Hematology and Regenerative Medicine (HERM), Karolinska Institutet</r:AttributeValue>
        </r:UserAttributePair>
        <a:IndividualIdentification>
          <a:IndividualName>
            <a:FirstGiven>Tetsuichi</a:FirstGiven>
            <a:LastFamily>Yoshizato</a:LastFamily>
            <a:FullName>
              <r:String>Tetsuichi Yoshizato</r:String>
            </a:FullName>
          </a:IndividualName>
          <a:ResearcherID>
            <a:TypeOfID>ORCID</a:TypeOfID>
            <a:ResearcherIdentification>0000-0003-4283-2983</a:ResearcherIdentification>
          </a:ResearcherID>
        </a:IndividualIdentification>
      </a:Individual>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:2024-129.Individual-0:2.0</r:URN>
        <r:UserAttributePair>
          <r:AttributeKey>affiliation</r:AttributeKey>
          <r:AttributeValue>Department of Medicine, Huddinge / Center for Hematology and Regenerative Medicine (HERM), Karolinska Institutet</r:AttributeValue>
        </r:UserAttributePair>
        <a:IndividualIdentification>
          <a:IndividualName>
            <a:FirstGiven>Sten Eirik</a:FirstGiven>
            <a:LastFamily>Jacobsen</a:LastFamily>
            <a:FullName>
              <r:String>Sten Eirik Jacobsen</r:String>
            </a:FullName>
          </a:IndividualName>
          <a:ResearcherID>
            <a:TypeOfID>ORCID</a:TypeOfID>
            <a:ResearcherIdentification>0000-0002-1362-3659</a:ResearcherIdentification>
          </a:ResearcherID>
        </a:IndividualIdentification>
      </a:Individual>
    </a:OrganizationScheme>
  </g:ResourcePackage>
  <s:StudyUnit>
    <r:URN>urn:ddi:se.researchdata:2024-129.StudyUnit:2.0</r:URN>
    <r:UserID typeOfUserID="datasetIdentifier">2024-129</r:UserID>
    <r:Citation>
      <r:Title>
        <r:String xml:lang="sv">DNA-sekvenseringsdata för "Stabilt klonalt bidrag från härstamningsbegränsade stamceller till mänsklig hematopoies"</r:String>
        <r:String xml:lang="en">DNA sequencing data for "Stable clonal contribution of lineage-restricted stem cells to human hematopoiesis"</r:String>
      </r:Title>
      <r:Creator>
        <r:CreatorReference>
          <r:URN>urn:ddi:se.researchdata:2024-129.Individual-0:2.0</r:URN>
          <r:TypeOfObject>Individual</r:TypeOfObject>
        </r:CreatorReference>
      </r:Creator>
      <r:Publisher>
        <r:PublisherName>
          <r:String xml:lang="sv">Karolinska Institutet</r:String>
          <r:String xml:lang="en">Karolinska Institutet</r:String>
        </r:PublisherName>
      </r:Publisher>
      <r:Publisher>
        <r:PublisherName>
          <r:String xml:lang="sv">Karolinska Institutet</r:String>
          <r:String xml:lang="en">Karolinska Institutet</r:String>
        </r:PublisherName>
      </r:Publisher>
      <r:PublicationDate>
        <r:SimpleDate>2025-10-03</r:SimpleDate>
      </r:PublicationDate>
      <r:InternationalIdentifier>
        <r:IdentifierContent>10.48723/313d-dd68</r:IdentifierContent>
        <r:ManagingAgency controlledVocabularyAgencyName="DOI">DOI</r:ManagingAgency>
      </r:InternationalIdentifier>
    </r:Citation>
    <r:Abstract>
      <r:Content xml:lang="sv">Detta dataset innehåller tre typer av DNA-sekvenseringsdata.
-Error-corrected DNA capture sequencing (ECTS)
-Bulk whole-exome sequencing (WES)
-Single-colony whole-genome sequencing (WGS)
All sekvensering utfördes på en Illumina NovaSeq 6000 vid National Genomics Infrastructure i Stockholm, med hjälp av "paired-end sequencing mode".

ECTS
Mononukleära benmärgsceller isolerade från alla 93 friska donatorer utsattes för ECTS för identifiering av somatiska mutationer riktade mot 23 gener som omfattar de mest återkommande muterade generna som rapporterats i klonal hematopoes.

WES
BM MNC-DNA isolerat från det första besöket från 20 friska donatorer över 71 år utsattes för WES i bulk. Parat buckalt swab-DNA användes för normala kontroller.

Enkelkoloni WGS
DNA extraherat från 333 genotypade enskilda kolonier och 10 kontroll-buckala pinnprover från 10 donatorer genomgick WGS.

Datasetet består av tre mappar:
scWGS innehåller 343 filer i format CRAM totalt cirka 16.3 TiB (17.9 TB).
WES innehåller 40 filer i format CRAM totalt cirka 650 GiB (710 GB).
ECTS innehåller 117 filer i format CRAM totalt cirka 18 GiB (20 GB).</r:Content>
      <r:Content xml:lang="en">This dataset contains three types of DNA sequencing data.
-Error-corrected DNA capture sequencing (ECTS)
-Bulk whole-exome sequencing (WES)
-Single-colony whole-genome sequencing (WGS)
All sequencing was performed on an Illumina NovaSeq 6000 at the National Genomics Infrastructure in
Stockholm, using paired-end sequencing mode.

ECTS
Bone marrow mononuclear cells isolated from all 93 healthy donors were subjected to ECTS for identification of somatic mutations targeted to 23 genes encompassing the most recurrently mutated genes reported in clonal hematopoiesis.

WES
BM MNC DNA isolated from the first visit from 20 healthy donors above 71 years was subjected bulk WES. Paired buccal swab DNA was used for normal controls.

Single colony WGS
DNA extracted from 333 genotyped single colonies and 10 control buccal swabs from 10 donors was subjected to WGS.

The dataset consists of three folders:
scWGS contains 343 files in CRAM format, totaling approximately 16.3 TiB (17.9 TB).
WES contains 40 files in CRAM format, totaling approximately 650 GiB (710 GB).
ECTS contains 117 files in CRAM format, totaling approximately 18 GiB (20 GB).</r:Content>
    </r:Abstract>
    <r:Coverage>
      <r:TopicalCoverage>
        <r:URN>urn:ddi:se.researchdata:2024-129.TopicalCoverage:2.0</r:URN>
        <r:Subject xml:lang="en" controlledVocabularyID="30107" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Medical Genetics and Genomics</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="30107" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Medicinsk genetik och genomik</r:Subject>
        <r:Subject xml:lang="en" controlledVocabularyID="30108" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Cell and Molecular Biology</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="30108" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Cell- och molekylärbiologi</r:Subject>
        <r:Subject xml:lang="en" controlledVocabularyID="30202" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Hematology</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="30202" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Hematologi</r:Subject>
        <r:Keyword xml:lang="en" controlledVocabularyID="D006412" controlledVocabularyName="MeSH">Hematopoietic Stem Cells</r:Keyword>
        <r:Keyword xml:lang="sv" controlledVocabularyID="D006412" controlledVocabularyName="MeSH">Blodstamceller</r:Keyword>
        <r:Keyword xml:lang="en" controlledVocabularyID="D017422" controlledVocabularyName="MeSH">Sequence Analysis, DNA</r:Keyword>
        <r:Keyword xml:lang="sv" controlledVocabularyID="D017422" controlledVocabularyName="MeSH">DNA-sekvensanalys</r:Keyword>
        <r:Keyword xml:lang="en" controlledVocabularyID="D758D" controlledVocabularyName="ICD-10">Klonal hematopoes av obestämd potential (CHIP)</r:Keyword>
        <r:Keyword xml:lang="sv" controlledVocabularyID="D758D" controlledVocabularyName="ICD-10">Klonal hematopoes av obestämd potential (CHIP) (Fördjupningskod)</r:Keyword>
      </r:TopicalCoverage>
      <r:SpatialCoverage>
        <r:URN>urn:ddi:se.researchdata:2024-129.SpatialCoverage:2.0</r:URN>
        <r:CountryCode>SE</r:CountryCode>
      </r:SpatialCoverage>
      <r:TemporalCoverage>
        <r:URN>urn:ddi:se.researchdata:2024-129.TemporalCoverage:2.0</r:URN>
        <r:ReferenceDate>
          <r:StartDate>2018</r:StartDate>
          <r:EndDate>2024</r:EndDate>
        </r:ReferenceDate>
      </r:TemporalCoverage>
    </r:Coverage>
    <a:Archive>
      <r:URN>urn:ddi:se.researchdata:2024-129.Archive:2.0</r:URN>
      <a:ArchiveSpecific>
        <a:Item>
          <a:Access>
            <r:URN>urn:ddi:se.researchdata:2024-129.Archive-ArchiveSpecificType-AccessType:2.0</r:URN>
            <a:TypeOfAccess controlledVocabularyName="info:eu-repo-Access-Terms vocabulary">restrictedAccess</a:TypeOfAccess>
          </a:Access>
          <a:DataFileQuantity>5</a:DataFileQuantity>
        </a:Item>
      </a:ArchiveSpecific>
    </a:Archive>
  </s:StudyUnit>
</ddi:DDIInstance>