<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 erytroblaster från inducerade pluripotenta stamcellslinjer (iPSC) med vildtyp och muterad SF3B1</titl>
        <parTitl xml:lang="en">Bulk RNA sequencing of erythroblasts from a pair of SF3B1-mutated and SF3B1-wildtype induced pluripotent stem cell (iPSC) lines</parTitl>
        <IDNo agency="SND">2024-128-1</IDNo>
        <IDNo agency="DOI">https://doi.org/10.48723/3hs1-0v44</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/10.48723/3hs1-0v44">Landing page</holdings>
    </citation>
  </docDscr>
  <stdyDscr>
    <citation>
      <titlStmt>
        <titl xml:lang="sv">RNA sekvensering av erytroblaster från inducerade pluripotenta stamcellslinjer (iPSC) med vildtyp och muterad SF3B1</titl>
        <parTitl xml:lang="en">Bulk RNA sequencing of erythroblasts from a pair of SF3B1-mutated and SF3B1-wildtype induced pluripotent stem cell (iPSC) lines</parTitl>
        <IDNo agency="SND">2024-128-1</IDNo>
        <IDNo agency="DOI">https://doi.org/10.48723/3hs1-0v44</IDNo>
        <IDNo agency="DOI">10.1038/s41375-025-02740-1</IDNo>
      </titlStmt>
      <rspStmt>
        <AuthEnty xml:lang="en" affiliation="Department of Medicine, Huddinge / Center for Hematology and Regenerative Medicine (HERM), Karolinska Institutet">Thier, Jonas</AuthEnty>
        <AuthEnty xml:lang="sv" affiliation="Institutionen för medicin, Huddinge / Centrum för hematologi och regenerativ medicin (HERM), Karolinska Institutet">Thier, Jonas</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>
        <AuthEnty xml:lang="en" affiliation="Department of Medicine, Huddinge / Center for Hematology and Regenerative Medicine (HERM), Karolinska Institutet">Moura, Pedro</AuthEnty>
        <AuthEnty xml:lang="sv" affiliation="Institutionen för medicin, Huddinge / Centrum för hematologi och regenerativ medicin (HERM), Karolinska Institutet">Moura, Pedro</AuthEnty>
        <AuthEnty xml:lang="en" affiliation="Department of Medicine, Huddinge / Center for Hematology and Regenerative Medicine (HERM), Karolinska Institutet">Lundin, Vanessa</AuthEnty>
        <AuthEnty xml:lang="sv" affiliation="Institutionen för medicin, Huddinge / Centrum för hematologi och regenerativ medicin (HERM), Karolinska Institutet">Lundin, Vanessa</AuthEnty>
      </rspStmt>
      <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="2025-08-12" />
      </distStmt>
      <verStmt>
        <version elementVersion="1" elementVersionDate="2025-08-12" />
      </verStmt>
      <holdings URI="https://doi.org/10.48723/3hs1-0v44">Landing page</holdings>
    </citation>
    <stdyInfo>
      <subject>
        <keyword xml:lang="en" vocab="MeSH" vocabURI="http://id.nlm.nih.gov/mesh/D009190">Myelodysplastic Syndromes</keyword>
        <keyword xml:lang="sv" vocab="MeSH" vocabURI="http://id.nlm.nih.gov/mesh/D009190">Myelodysplastiskt syndrom</keyword>
        <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>
        <keyword xml:lang="en" vocab="MeSH" vocabURI="http://id.nlm.nih.gov/mesh/D057026">Induced Pluripotent Stem Cells</keyword>
        <keyword xml:lang="sv" vocab="MeSH" vocabURI="http://id.nlm.nih.gov/mesh/D057026">Inducerade pluripotenta stamceller</keyword>
      </subject>
      <abstract xml:lang="en" contentType="abstract">This dataset consists of bulk RNA sequencing data of MACS-separated GPA+ erythroblasts obtained from a pair of induced pluripotent stem cell (iPSC) lines with and without SF3B1-mutation, generated from an MDS patient (Asimomitis G et al. 2022, Blood Advances). The objective of this data collection was to assess how SF3B1 mutation changes the molecular profile of RNA splicing in erythropoiesis.

This dataset includes minimally processed, visualisation-ready .bam format sequencing data for both of the lines.
 
Processing: 
MDS patient iPSC line-derived hematopoietic stem and progenitor cells (HSPC) were cultured for 14 days in erythroid specification media (StemPro-34 SFM [Gibco] + 1% Pen/Strep [Cytiva], 2 mM L-glutamine [Sigma-Aldrich], 3.5 µM 1-Thioglycerol [Sigma-Aldrich], 1% Bovine Albumin Fraction V [Gibco], 150 µg/mL holo-transferrin [Sigma-Aldrich], 2 U/mL erythropoietin [Pfizer], 50 ng/mL Stem Cell Factor [PeproTech] and 50 ng/mL interleukin-3 [PeproTech]).
At Day 14 of culture, mixed glycophorin A-positive (GPA+) erythroblast samples were isolated through MACS. 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. RNA sequencing (RNAseq) libraries were prepared from total RNA using SMARTer Stranded Total RNA-Seq Kits v2 - Pico Input Mammalian (Takara Bio, Japan), including enzymatic ribosomal depletion steps. Libraries were sequenced using an Illumina Novaseq 6000 S4 (Illumina, CA, USA) with paired-end 150bp configuration. Reads were pre-processed with TrimGalore v. 0.6.7 using CutAdapt v. 3.5 and BAM files were generated through via two-pass alignment with STAR v. 2.7.9a against the GRCh38.p13 human genome assembly.

The dataset consists of 13 files: 
- 2 .bam files, one for the SF3B1-mutant sample and one for the wildtype sample;
- 2. bai bam index files, one for each sample to facilitate analysis of the .bam files.
- 8 .fastq raw data files, corresponding to a paired-end run of the two samples in two different lanes (2 x 2 x 2).
- 1 gene-collapsed read count matrix (.txt) summarising read counts for both samples.

The documentation file iPSCEB_FileList.txt contains a full list of the files in the dataset.
The total size of the dataset is approximately 80 GB.</abstract>
      <abstract xml:lang="sv" contentType="abstract">Syftet med denna datainsamling var att bedöma hur SF3B1-mutation förändrar den molekylära profilen för RNA-splitsning vid erytropoes. Denna datauppsättning består av RNA sekvensering av erytroblaster från ett par av SF3B1-muterade och SF3B1-vildtyp inducerade pluripotenta stamcell (iPSC). Se den engelska beskrivningen för mer information.</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">Cell lines from a patient with SF3B1-mutant myelodysplastic neoplasm with ring sideroblasts (MDS-RS)</universe>
        <universe xml:lang="sv">Cellinjer från en patient med SF3B1-muterad myelodysplastisk neoplasi med ringsideroblaster (MDS-RS)</universe>
        <dataKind xml:lang="en">Other</dataKind>
      </sumDscr>
    </stdyInfo>
    <method>
      <dataColl>
        <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>
      </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">Thier, J., Hofmann, S., Kirchhof, K.M. et al. SF3B1-mutant models of RNA mis-splicing uncover UBA1 as a therapeutic target in myelodysplastic neoplasms. Leukemia (2025). https://doi.org/10.1038/s41375-025-02740-1</titl>
            <parTitl xml:lang="en">Thier, J., Hofmann, S., Kirchhof, K.M. et al. SF3B1-mutant models of RNA mis-splicing uncover UBA1 as a therapeutic target in myelodysplastic neoplasms. Leukemia (2025). https://doi.org/10.1038/s41375-025-02740-1</parTitl>
            <IDNo agency="DOI">10.1038/s41375-025-02740-1</IDNo>
          </titlStmt>
          <distStmt>
            <distDate date="2025">2025</distDate>
          </distStmt>
        </citation>
      </relPubl>
    </othrStdyMat>
  </stdyDscr>
</codeBook>