<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:2023-121-1:1</r:URN>
  <r:Agency>SND</r:Agency>
  <r:ID>2023-121-1</r:ID>
  <r:Version>1</r:Version>
  <g:ResourcePackage>
    <r:URN>urn:ddi:se.researchdata:2023-121-1.ResourcePackage:2.0</r:URN>
    <r:OtherMaterialScheme>
      <r:URN>urn:ddi:se.researchdata:2023-121-1.OtherMaterialScheme:2.0</r:URN>
    </r:OtherMaterialScheme>
    <a:OrganizationScheme>
      <r:URN>urn:ddi:se.researchdata:2023-121-1.OrganizationScheme-0:2.0</r:URN>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:2023-121-1.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>Pedro Luis</a:FirstGiven>
            <a:LastFamily>Moura</a:LastFamily>
            <a:FullName>
              <r:String>Pedro Luis Moura</r:String>
            </a:FullName>
          </a:IndividualName>
          <a:ResearcherID>
            <a:TypeOfID>ORCID</a:TypeOfID>
            <a:ResearcherIdentification>0000-0002-0493-5394</a:ResearcherIdentification>
          </a:ResearcherID>
        </a:IndividualIdentification>
      </a:Individual>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:2023-121-1.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>Eva</a:FirstGiven>
            <a:LastFamily>Hellström-Lindberg</a:LastFamily>
            <a:FullName>
              <r:String>Eva Hellström-Lindberg</r:String>
            </a:FullName>
          </a:IndividualName>
          <a:ResearcherID>
            <a:TypeOfID>ORCID</a:TypeOfID>
            <a:ResearcherIdentification>0000-0002-7839-3743</a:ResearcherIdentification>
          </a:ResearcherID>
        </a:IndividualIdentification>
      </a:Individual>
    </a:OrganizationScheme>
  </g:ResourcePackage>
  <s:StudyUnit>
    <r:URN>urn:ddi:se.researchdata:2023-121-1.StudyUnit:2.0</r:URN>
    <r:UserID typeOfUserID="datasetIdentifier">2023-121-1</r:UserID>
    <r:Citation>
      <r:Title>
        <r:String xml:lang="sv">10X singel-cell RNA sekvensering av benmärgsceller från MDS-RS patienter och friska donatorer</r:String>
        <r:String xml:lang="en">10X single-cell RNA sequencing of bone marrow cells from MDS-RS patients and healthy donors</r:String>
      </r:Title>
      <r:Creator>
        <r:CreatorReference>
          <r:URN>urn:ddi:se.researchdata:2023-121-1.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>2023-10-19</r:SimpleDate>
      </r:PublicationDate>
      <r:InternationalIdentifier>
        <r:IdentifierContent>10.48723/nq2a-1e03</r:IdentifierContent>
        <r:ManagingAgency controlledVocabularyAgencyName="DOI">DOI</r:ManagingAgency>
      </r:InternationalIdentifier>
    </r:Citation>
    <r:Abstract>
      <r:Content xml:lang="sv">Syftet med denna datainsamling var att bedöma flera parametrar om hur benmärgen hos MDS-RS-patienter skiljer sig från den hos friska donatorer. Denna datauppsättning består av singel-cell RNA sekvensering av benmärgsceller från MDS-RS patienter och friska donatorer. Se den engelska beskrivningen för mer information.

Datasetet består av två mappar:
- Processed_Count_Matrices
- Raw_FASTQ

och en xlsx-fil:
- Sample_key.xlsx

Mappen Processed_Count_Matrices innehåller 1 rds-fil, 1 tsv-fil, 9 mtx-filer och 18 txt-filer.
Mappen Raw_FASTQ innehåller 27 GNU-zippade fastq-filer och 5 txt-filer.

Dokumentationsfilen File_list_10x.txt innehåller en lista över datasetets alla filer.

Datasetets totala storlek är ungefär 21 GB.</r:Content>
      <r:Content xml:lang="en">This dataset consists of single-cell RNA sequencing data of bone marrow cells (CD34+ stem cells, GPA+ erythroblasts, ring sideroblasts and mononuclear cells) obtained from multiple healthy bone marrow donors and MDS-RS patients. The objective of this data collection was to assess several parameters on how the bone marrow of MDS-RS patients differs from that of healthy donors.

This dataset includes raw sequencing data in .fastq format, processed count matrices and associated pseudonymized metadata.
 
Processing: All samples were loaded onto Chromium Single Cell Chips (10x Genomics, CA, USA) at a target capture rate of 10,000 cells per sample. Single cell libraries were prepared using Chromium Next GEM Single Cell 3ʹ Kits v3.1 (10x Genomics) as per the manufacturer’s instructions, except 1µl additive ADT primers were added to the initial cDNA PCR amplification buffer and ADT libraries prepared as described in the Total-Seq B protocol (BioLegend) from the initial cDNA SPRI clean up. Libraries were pooled and sequenced on an Illumina NovaSeq 6000 (Illumina). Read pseudoalignment was performed against the GRCh38.p13 human genome assembly through kallisto v0.46.1 and bustools v0.40.0 was used for barcode and UMI counting.

The dataset consists of 2 folders: 
- Processed_Count_Matrices
- Raw_FASTQ

And one xlsx file:
- Sample_key.xlsx

The folder Processed_Count_Matrices contains 1 rds file, 1 tsv file, 9 mtx files, and 18 txt files.
The folder Raw_FASTQ contains 27 GNU zipped fastq files, and 5 txt files.

The documentation file File_list_10x.txt contains a full list of the files in the dataset.

The total size of the dataset is approximately 21 GB.</r:Content>
    </r:Abstract>
    <r:Coverage>
      <r:TopicalCoverage>
        <r:URN>urn:ddi:se.researchdata:2023-121-1.TopicalCoverage:2.0</r:URN>
        <r:Subject xml:lang="en" controlledVocabularyID="1" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Natural Sciences</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="1" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Naturvetenskap</r:Subject>
        <r:Subject xml:lang="en" controlledVocabularyID="106" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Biological Sciences</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="106" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Biologi</r:Subject>
        <r:Subject xml:lang="en" controlledVocabularyID="10604" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Cell Biology</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="10604" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Cellbiologi</r:Subject>
        <r:Subject xml:lang="en" controlledVocabularyID="10609" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Genetics and Genomics</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="10609" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Genetik och genomik</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: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:Subject xml:lang="en" controlledVocabularyID="30112" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Basic Cancer Research</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="30112" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Basal cancerforskning</r:Subject>
      </r:TopicalCoverage>
      <r:SpatialCoverage />
    </r:Coverage>
    <r:AnalysisUnit controlledVocabularyID="AnalysisUnit" controlledVocabularyAgencyName="DDI Alliance">snd.a01</r:AnalysisUnit>
    <r:AnalysisUnitsCovered>
      <r:String xml:lang="en">Cells</r:String>
      <r:String xml:lang="sv">Celler</r:String>
    </r:AnalysisUnitsCovered>
    <a:Archive>
      <r:URN>urn:ddi:se.researchdata:2023-121-1.Archive:2.0</r:URN>
      <a:ArchiveSpecific>
        <a:Item>
          <a:Access>
            <r:URN>urn:ddi:se.researchdata:2023-121-1.Archive-ArchiveSpecificType-AccessType:2.0</r:URN>
            <a:TypeOfAccess controlledVocabularyName="info:eu-repo-Access-Terms vocabulary">restrictedAccess</a:TypeOfAccess>
          </a:Access>
          <a:DataFileQuantity>2</a:DataFileQuantity>
        </a:Item>
      </a:ArchiveSpecific>
    </a:Archive>
  </s:StudyUnit>
</ddi:DDIInstance>