<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:2023-120-1:1</r:URN>
  <r:Agency>SND</r:Agency>
  <r:ID>2023-120-1</r:ID>
  <r:Version>1</r:Version>
  <g:ResourcePackage>
    <r:URN>urn:ddi:se.researchdata:2023-120-1.ResourcePackage:2.0</r:URN>
    <r:OtherMaterialScheme>
      <r:URN>urn:ddi:se.researchdata:2023-120-1.OtherMaterialScheme:2.0</r:URN>
    </r:OtherMaterialScheme>
    <a:OrganizationScheme>
      <r:URN>urn:ddi:se.researchdata:2023-120-1.OrganizationScheme-0:2.0</r:URN>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:2023-120-1.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:2023-120-1.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:2023-120-1.StudyUnit:2.0</r:URN>
    <r:UserID typeOfUserID="datasetIdentifier">2023-120-1</r:UserID>
    <r:Citation>
      <r:Title>
        <r:String xml:lang="sv">RNA sekvensering av benmärgsceller från MDS-RS patienter och friska donatorer</r:String>
        <r:String xml:lang="en">Bulk 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:2023-120-1.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>10.48723/41wa-yv42</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 RNA sekvensering av benmärgsceller från MDS-RS patienter och friska donatorer. Se den engelska beskrivningen för mer information.

Datasetet består av två mappar: 
- Bulk_Main
- Minibulk_Cycloheximide

Mappen Bulk_Main innehåller 67 GNU zippade fastq-filer, 1 tsv-fil och 1 txt-fil.
Mappen Minibulk_Cycloheximide innehåller 2 GNU zippade fastq-filer och 4 txt-filer.

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

Datasetets totala storlek är ungefär 360 GB.</r:Content>
      <r:Content xml:lang="en">This dataset consists of bulk RNA sequencing data of MACS-separated bone marrow cells (CD34+ stem cells, GPA+ erythroblasts, CD71+ reticulocytes, ring sideroblasts and siderocytes) obtained from multiple healthy bone marrow donors and MDS-RS patients. A second minibulk dataset is included, where CD34+ and GPA+ cells were treated with cycloheximide or left untreated. 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: 
Bulk: 
CD34+ HSPC samples, mixed GPA+ erythroblast samples and CD71+ PB reticulocyte samples (RetPB) were isolated through MACS. RS and siderocytes were obtained through MACS+FACS. Cells were lysed in RLT (Qiagen) + 40 mM dithiothreitol (Sigma-Aldrich) and RNA extraction was performed with RNeasy Micro Kit (Qiagen) with RNase-free DNase treatment according to the manufacturer’s protocol. RNA integrity numbers (RIN) were estimated using Agilent RNA 6000 Pico Kits (Agilent Technologies, CA, USA). A minimum RIN value of 6.5 was considered adequate. 

Minibulk: 
Minibulk RNAseq was performed for assessment of cycloheximide treatment effects in CD34+ and GPA+ cell populations. The library preparation procedure was performed using the Xpress Genomics bulk RNA-seq kit v1, automated on a SP960 liquid handler (MGI Tech). In short, the library preparation procedure denatures RNA samples in presence of oligo-dT primer, which is followed by reverse transcription of RNA with a template-switching procedure and pre-amplification of full-length cDNA for 10 PCR cycles. cDNA was subsequently tagmented using Tn5 (TDE1 Tagment DNA Enzyme; Illumina) and reactions quenched after 10 min at 55 °C by addition of 0.2 % SDS (Sigma-Aldrich). Tagmented DNA was indexed using custom dual-unique Nextera index primers in a 12 cycle PCR reaction. Indexed libraries were cleaned up using SPRI beads in 22% PEG8000 buffer and eluted in 12 µL H2O.

The dataset consists of 2 folders: 
- Bulk_Main
- Minibulk_Cycloheximide

The folder Bulk_Main contains 67 GNU zipped fastq files, 1 tsv file, and 1 txt file.
The folder Minibulk_Cycloheximide contains 2 GNU zipped fastq files, and 4 txt files.

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

The total size of the dataset is approximately 360 GB.</r:Content>
    </r:Abstract>
    <r:Coverage>
      <r:TopicalCoverage>
        <r:URN>urn:ddi:se.researchdata:2023-120-1.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:Keyword xml:lang="en" controlledVocabularyID="D054437" controlledVocabularyName="MeSH">Myelodysplastic-Myeloproliferative Diseases</r:Keyword>
        <r:Keyword xml:lang="sv" controlledVocabularyID="D054437" controlledVocabularyName="MeSH">Myelodysplastiska-myeloproliferativa syndrom</r:Keyword>
      </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:2023-120-1.Archive:2.0</r:URN>
      <a:ArchiveSpecific>
        <a:Item>
          <a:Access>
            <r:URN>urn:ddi:se.researchdata:2023-120-1.Archive-ArchiveSpecificType-AccessType:2.0</r:URN>
            <a:TypeOfAccess controlledVocabularyName="info:eu-repo-Access-Terms vocabulary">restrictedAccess</a:TypeOfAccess>
          </a:Access>
          <a:DataFileQuantity>3</a:DataFileQuantity>
        </a:Item>
      </a:ArchiveSpecific>
    </a:Archive>
  </s:StudyUnit>
</ddi:DDIInstance>