<codeBook xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xsi:schemaLocation="ddi:codebook:2_5 http://www.ddialliance.org/Specification/DDI-Codebook/2.5/XMLSchema/codebook.xsd" xmlns="ddi:codebook:2_5">
  <docDscr>
    <citation>
      <titlStmt>
        <titl xml:lang="sv">RNA sekvensering av benmärgsceller från MDS-RS patienter och friska donatorer</titl>
        <parTitl xml:lang="en">Bulk RNA sequencing of bone marrow cells from MDS-RS patients and healthy donors</parTitl>
        <IDNo agency="SND">2023-120-1-1</IDNo>
        <IDNo agency="DOI">https://doi.org/10.48723/41wa-yv42</IDNo>
      </titlStmt>
      <prodStmt>
        <producer xml:lang="en" abbr="SND">Swedish National Data Service</producer>
        <producer xml:lang="sv" abbr="SND">Svensk nationell datatjänst</producer>
      </prodStmt>
      <holdings URI="https://doi.org/10.48723/41wa-yv42">Landing page</holdings>
    </citation>
  </docDscr>
  <stdyDscr>
    <citation>
      <titlStmt>
        <titl xml:lang="sv">RNA sekvensering av benmärgsceller från MDS-RS patienter och friska donatorer</titl>
        <parTitl xml:lang="en">Bulk RNA sequencing of bone marrow cells from MDS-RS patients and healthy donors</parTitl>
        <IDNo agency="SND">2023-120-1-1</IDNo>
        <IDNo agency="DOI">https://doi.org/10.48723/41wa-yv42</IDNo>
        <IDNo agency="DOI">10.1158/0008-5472.CAN-23-3038</IDNo>
      </titlStmt>
      <rspStmt>
        <AuthEnty xml:lang="en" affiliation="Department of Medicine, Huddinge / Center for Hematology and Regenerative Medicine (HERM), Karolinska Institutet">Moura, Pedro Luis</AuthEnty>
        <AuthEnty xml:lang="sv" affiliation="Institutionen för medicin, Huddinge / Centrum för hematologi och regenerativ medicin (HERM), Karolinska Institutet">Moura, Pedro Luis</AuthEnty>
        <AuthEnty xml:lang="en" affiliation="Department of Medicine, Huddinge / Center for Hematology and Regenerative Medicine (HERM), Karolinska Institutet">Hellström-Lindberg, Eva</AuthEnty>
        <AuthEnty xml:lang="sv" affiliation="Institutionen för medicin, Huddinge / Centrum för hematologi och regenerativ medicin (HERM), Karolinska Institutet">Hellström-Lindberg, Eva</AuthEnty>
      </rspStmt>
      <prodStmt>
        <grantNo xml:lang="en" agency="Swedish Cancer Society">21 0340</grantNo>
        <grantNo xml:lang="sv" agency="Cancerfonden">21 0340</grantNo>
        <grantNo xml:lang="en" agency="Knut and Alice Wallenberg Foundation">2017.0359</grantNo>
        <grantNo xml:lang="sv" agency="Knut och Alice Wallenbergs stiftelse">2017.0359</grantNo>
        <grantNo xml:lang="en" agency="Swedish Cancer Society">19 0200</grantNo>
        <grantNo xml:lang="sv" agency="Cancerfonden">19 0200</grantNo>
        <grantNo xml:lang="en" agency="Swedish Research Council">2021-01404_VR</grantNo>
        <grantNo xml:lang="sv" agency="Vetenskapsrådet">2021-01404_VR</grantNo>
      </prodStmt>
      <distStmt>
        <distrbtr xml:lang="en" abbr="SND" URI="https://snd.se">Swedish National Data Service</distrbtr>
        <distrbtr xml:lang="sv" abbr="SND" URI="https://snd.se">Svensk nationell datatjänst</distrbtr>
        <distDate xml:lang="en" date="2023-10-19" />
      </distStmt>
      <verStmt>
        <version elementVersion="1" elementVersionDate="2023-10-19" />
      </verStmt>
      <holdings URI="https://doi.org/10.48723/41wa-yv42">Landing page</holdings>
    </citation>
    <stdyInfo>
      <subject>
        <keyword xml:lang="en" vocab="MeSH" vocabURI="http://id.nlm.nih.gov/mesh/D054437">Myelodysplastic-Myeloproliferative Diseases</keyword>
        <keyword xml:lang="sv" vocab="MeSH" vocabURI="http://id.nlm.nih.gov/mesh/D054437">Myelodysplastiska-myeloproliferativa syndrom</keyword>
      </subject>
      <abstract xml:lang="en" contentType="abstract">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.</abstract>
      <abstract xml:lang="sv" contentType="abstract">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.</abstract>
      <sumDscr>
        <anlyUnit xml:lang="en" unit="Cells">Cells<concept vocab="DDI Analysis Unit" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/AnalysisUnit/2.1.3?languageVersion=en-2.1.3">Cells</concept></anlyUnit>
        <anlyUnit xml:lang="sv" unit="Celler">Celler<concept vocab="DDI Analysis Unit" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/AnalysisUnit/2.1.3?languageVersion=sv-2.1.3">Celler</concept></anlyUnit>
        <universe xml:lang="en">Patients with Myelodysplastic neoplasms with ring sideroblasts (MDS-RS) and healthy donors</universe>
        <universe xml:lang="sv">Patienter med myelodysplastisk syndrom med ringsideroblaster (MDS-RS) samt friska donatorer</universe>
        <dataKind xml:lang="en">Numeric</dataKind>
        <dataKind xml:lang="en">Other</dataKind>
      </sumDscr>
    </stdyInfo>
    <method>
      <dataColl>
        <sampProc xml:lang="en">Bone marrow (BM) and/or peripheral blood (PB) samples were collected from 36 MDS-RS and 3 MDS non-RS patients evaluated at Karolinska University Hospital, Huddinge, Sweden. Diagnostic procedures were performed according to the European LeukemiaNet recommendation and WHO classification for myeloid neoplasms. As the specific purpose was to dissect the pathobiology of SF3B1-mutant MDS-RS, all MDS-RS patients belonged to the SF3B1α category in the IPSS-M risk classification. RS presence was quantified according to standard clinical practice. Additional samples were collected from a total of 40 healthy normal bone marrow (NBM) donors for control purposes. Please note that a deidentified donor and experiment index is provided in the companion publication for this dataset, including clinical and mutational status. All source material was provided with written informed consent for research use, given in accordance with the Declaration of Helsinki.<concept vocab="DDI Sampling Procedure" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/SamplingProcedure/2.0.1?languageVersion=en-2.0.1">Bone marrow (BM) and/or peripheral blood (PB) samples were collected from 36 MDS-RS and 3 MDS non-RS patients evaluated at Karolinska University Hospital, Huddinge, Sweden. Diagnostic procedures were performed according to the European LeukemiaNet recommendation and WHO classification for myeloid neoplasms. As the specific purpose was to dissect the pathobiology of SF3B1-mutant MDS-RS, all MDS-RS patients belonged to the SF3B1α category in the IPSS-M risk classification. RS presence was quantified according to standard clinical practice. Additional samples were collected from a total of 40 healthy normal bone marrow (NBM) donors for control purposes. Please note that a deidentified donor and experiment index is provided in the companion publication for this dataset, including clinical and mutational status. All source material was provided with written informed consent for research use, given in accordance with the Declaration of Helsinki.</concept></sampProc>
        <sampProc xml:lang="en">Probability: Simple random<concept vocab="DDI Sampling Procedure" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/SamplingProcedure/2.0.1?languageVersion=en-2.0.1">Probability: Simple random</concept></sampProc>
        <sampProc xml:lang="sv">Sannolikhetsurval: obundet slumpmässigt urval<concept vocab="DDI Sampling Procedure" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/SamplingProcedure/2.0.1?languageVersion=sv-2.0.1">Sannolikhetsurval: obundet slumpmässigt urval</concept></sampProc>
        <sampProc xml:lang="en">Non-probability: Availability<concept vocab="DDI Sampling Procedure" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/SamplingProcedure/2.0.1?languageVersion=en-2.0.1">Non-probability: Availability</concept></sampProc>
        <sampProc xml:lang="sv">Icke-sannolikhetsurval: tillgänglighetsurval<concept vocab="DDI Sampling Procedure" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/SamplingProcedure/2.0.1?languageVersion=sv-2.0.1">Icke-sannolikhetsurval: tillgänglighetsurval</concept></sampProc>
        <sampProc xml:lang="en">Mixed probability and non-probability<concept vocab="DDI Sampling Procedure" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/SamplingProcedure/2.0.1?languageVersion=en-2.0.1">Mixed probability and non-probability</concept></sampProc>
        <sampProc xml:lang="sv">Blandat sannolikhets- och icke-sannolikhetsurval<concept vocab="DDI Sampling Procedure" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/SamplingProcedure/2.0.1?languageVersion=sv-2.0.1">Blandat sannolikhets- och icke-sannolikhetsurval</concept></sampProc>
      </dataColl>
    </method>
    <dataAccs>
      <useStmt>
        <restrctn xml:lang="en">Access to data through SND. Access to data is restricted.</restrctn>
        <restrctn xml:lang="sv">Åtkomst till data via SND. Tillgång till data är begränsad.</restrctn>
        <conditions elementVersion="info:eu-repo-Access-Terms vocabulary">restrictedAccess</conditions>
      </useStmt>
    </dataAccs>
    <othrStdyMat>
      <relPubl>
        <citation>
          <titlStmt>
            <titl xml:lang="sv">Moura PL, Mortera Blanco T, Hofman IJ, Todisco G, Kretzschmar WW, Björklund AC, Creignou M, Hagemann-Jensen M, Ziegenhain C, Cabrerizo Granados D, Barbosa I, Walldin G, Jansson M, Ashley N, Mead AJ, Lundin V, Dimitriou M, Yoshizato T, Woll PS, Ogawa S, Sandberg R, Jacobsen SW, Hellström-Lindberg E. Erythroid differentiation enhances RNA mis-splicing in SF3B1-mutant myelodysplastic syndromes with ring sideroblasts. Cancer Res. 2023 Nov 3. doi: 10.1158/0008-5472.CAN-23-3038.</titl>
            <parTitl xml:lang="en">Moura PL, Mortera Blanco T, Hofman IJ, Todisco G, Kretzschmar WW, Björklund AC, Creignou M, Hagemann-Jensen M, Ziegenhain C, Cabrerizo Granados D, Barbosa I, Walldin G, Jansson M, Ashley N, Mead AJ, Lundin V, Dimitriou M, Yoshizato T, Woll PS, Ogawa S, Sandberg R, Jacobsen SW, Hellström-Lindberg E. Erythroid differentiation enhances RNA mis-splicing in SF3B1-mutant myelodysplastic syndromes with ring sideroblasts. Cancer Res. 2023 Nov 3. doi: 10.1158/0008-5472.CAN-23-3038.</parTitl>
            <IDNo agency="DOI">10.1158/0008-5472.CAN-23-3038</IDNo>
          </titlStmt>
          <distStmt>
            <distDate date="2023">2023</distDate>
          </distStmt>
        </citation>
      </relPubl>
    </othrStdyMat>
  </stdyDscr>
</codeBook>