<codeBook xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xsi:schemaLocation="ddi:codebook:2_6 http://www.ddialliance.org/Specification/DDI-Codebook/2.6/XMLSchema/codebook.xsd" xmlns="ddi:codebook:2_6">
  <docDscr>
    <citation>
      <titlStmt>
        <titl xml:lang="sv">Data för: Principles of subclonal gene dosage across human cancers</titl>
        <parTitl xml:lang="en">Data for: Principles of subclonal gene dosage across human cancers</parTitl>
        <IDNo agency="SND">2026-47-1</IDNo>
        <IDNo agency="DOI">https://doi.org/10.48723/gr42-ja30</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/gr42-ja30">Landing page</holdings>
    </citation>
  </docDscr>
  <stdyDscr>
    <citation>
      <titlStmt>
        <titl xml:lang="sv">Data för: Principles of subclonal gene dosage across human cancers</titl>
        <parTitl xml:lang="en">Data for: Principles of subclonal gene dosage across human cancers</parTitl>
        <IDNo agency="SND">2026-47-1</IDNo>
        <IDNo agency="DOI">https://doi.org/10.48723/gr42-ja30</IDNo>
        <IDNo agency="SwePub">oai:swepub.ki.se:1061050</IDNo>
        <IDNo agency="DOI">10.1093/nar/gkaf919</IDNo>
        <IDNo agency="SwePub">oai:swepub.ki.se:467288</IDNo>
        <IDNo agency="DOI">10.1016/j.molcel.2020.09.025</IDNo>
      </titlStmt>
      <rspStmt>
        <AuthEnty xml:lang="en" affiliation="Department of Oncology-Pathology [K7], Karolinska Institutet">Kolbeinsdottir, Solrun</AuthEnty>
        <AuthEnty xml:lang="sv" affiliation="Institutionen för onkologi-patologi, Karolinska Institutet">Kolbeinsdottir, Solrun</AuthEnty>
        <AuthEnty xml:lang="en" affiliation="Department of Oncology-Pathology [K7], Karolinska Institutet">Enge, Martin</AuthEnty>
        <AuthEnty xml:lang="sv" affiliation="Institutionen för onkologi-patologi, Karolinska Institutet">Enge, Martin</AuthEnty>
      </rspStmt>
      <prodStmt>
        <grantNo xml:lang="en" agency="Swedish Research Council">2023-02912</grantNo>
        <grantNo xml:lang="sv" agency="Vetenskapsrådet">2023-02912</grantNo>
        <grantNo xml:lang="en" agency="The Swedish Cancer Society">232839 Pj</grantNo>
        <grantNo xml:lang="sv" agency="Cancerfonden">232839 Pj</grantNo>
        <grantNo xml:lang="en" agency="Swedish Childhood Cancer Foundation">PR2024-0108 and MT2023-0014</grantNo>
        <grantNo xml:lang="sv" agency="Barncancerfonden">PR2024-0108 and MT2023-0014</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="2026-09-30" />
      </distStmt>
      <verStmt>
        <version elementVersion="1" elementVersionDate="2026-09-30" />
      </verStmt>
      <holdings URI="https://doi.org/10.48723/gr42-ja30">Landing page</holdings>
    </citation>
    <stdyInfo>
      <subject>
        <keyword xml:lang="en" vocab="MeSH" vocabURI="http://id.nlm.nih.gov/mesh/D005786">Gene Expression Regulation</keyword>
        <keyword xml:lang="sv" vocab="MeSH" vocabURI="http://id.nlm.nih.gov/mesh/D005786">Genreglering</keyword>
        <keyword xml:lang="en" vocab="MeSH" vocabURI="http://id.nlm.nih.gov/mesh/D009154">Mutation</keyword>
        <keyword xml:lang="sv" vocab="MeSH" vocabURI="http://id.nlm.nih.gov/mesh/D009154">Mutation</keyword>
        <keyword xml:lang="en" vocab="MeSH" vocabURI="http://id.nlm.nih.gov/mesh/D014644">Genetic Variation</keyword>
        <keyword xml:lang="sv" vocab="MeSH" vocabURI="http://id.nlm.nih.gov/mesh/D014644">Genetisk variation</keyword>
        <keyword xml:lang="en" vocab="MeSH" vocabURI="http://id.nlm.nih.gov/mesh/D015870">Gene Expression</keyword>
        <keyword xml:lang="sv" vocab="MeSH" vocabURI="http://id.nlm.nih.gov/mesh/D015870">Genuttryck</keyword>
        <topcClas xml:lang="en" vocab="CESSDA Topic Classification" vocabURI="https://vocabularies.cessda.eu/vocabulary/TopicClassification?code=ScienceAndTechnology.Biotechnology">Biotechnology</topcClas>
        <topcClas xml:lang="sv" vocab="CESSDA Topic Classification" vocabURI="https://vocabularies.cessda.eu/vocabulary/TopicClassification?code=ScienceAndTechnology.Biotechnology">Bioteknik</topcClas>
      </subject>
      <abstract xml:lang="en" contentType="abstract">The data shared here are joint single-cell Whole genome sequencing (WGS) and single-cell mRNA sequencing from primary patient material from different cancer types. Primary samples from pediatric acute lymphoblastic leukemias, acute myeloid leukemias, breast cancers, melanomas and sarcomas were processed using Direct nuclear tagmentation and RNA-sequencing (DNTR-seq). For more information on DNTR-seq, see ‘A Highly Scalable Method for Joint Whole-Genome Sequencing and Gene-Expression Profiling of Single Cells’, DOI:10.1016/j.molcel.2020.09.025.

Data shared here are the fastq files of all single cells sequenced in this study (21826 read 1 and 21826 read 2 files).

The size of the dataset is approximately 2 TB.</abstract>
      <abstract xml:lang="sv" contentType="abstract">De data som delas här är kombinerad single-cell Whole genome sequencing (WGS) och single-cell mRNA-sekvensering från primärt patientmaterial från olika cancertyper. Primära prover från pediatriska akuta lymfoblastiska leukemier, akuta myeloiska leukemier, bröstcancer, melanom och sarkom bearbetades med Direct nuclear tagmentation and RNA-sequencing (DNTR-seq) För mer detaljerad information om DNTR-seq se  ‘A Highly Scalable Method for Joint Whole-Genome Sequencing and Gene-Expression Profiling of Single Cells’, DOI:10.1016/j.molcel.2020.09.025.

Data som delas här är fastq-filerna för alla enskilda celler som sekvenserades i denna studie (21826 read 1 och 21826 read 2 filer).

Datasetet storlek är ca 2 TB.</abstract>
      <sumDscr>
        <nation xml:lang="en" abbr="SE">Sweden</nation>
        <nation xml:lang="sv" abbr="SE">Sverige</nation>
        <universe xml:lang="en">The group of samples come from cancer patients diagnosed in Swedish hospitals. The cancer patients had been diagnosed with pediatric acute lymphoblastic leukemia (n:15), acute myeloid leukemia (n:5), melanoma (n:2), sarcomas (n:11) or breast cancer (n:11).</universe>
        <universe xml:lang="sv">Proverna kommer från cancerpatienter som har varit diagnoserat av svenska sjukhus. Cancerpatienterna hade diagnostiserats med pediatrisk akut lymfatisk leukemi (n=15), akut myeloisk leukemi (n=5), melanom (n=2), sarkom (n=11) eller bröstcancer (n=11).</universe>
        <dataKind xml:lang="en">Other</dataKind>
      </sumDscr>
    </stdyInfo>
    <method>
      <dataColl>
        <timeMeth xml:lang="en">Cross-section<concept vocab="DDI Time Method" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/TimeMethod/1.2.3?languageVersion=en-1.2.3">Cross-section</concept></timeMeth>
        <timeMeth xml:lang="sv">Tvärsnitt<concept vocab="DDI Time Method" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/TimeMethod/1.2.3?languageVersion=sv-1.2.3">Tvärsnitt</concept></timeMeth>
        <sampProc xml:lang="en">We selected different cancer types, known to have different levels and types of CNVs for this study. This included pediatric acute lymphoblastic leukemia (known to have few but large CNVs) acute myeloid leukemia (large CNVs), melanoma (mainly characterized by Single nucleotide variants, SNVs) or breast cancer (multiple small and large CNVs). The leukemia samples originated from bone marrow aspirations taken at diagnosis of the disease. Breast cancer and sarcoma samples originate from surgical resection (without neoadjuvant treatment), following diagnosis. The melanoma samples were metastatic and originated from surgical resections.<concept vocab="DDI Sampling Procedure" vocabURI="https://vocabularies.cessda.eu/v2/vocabularies/SamplingProcedure/2.0.1?languageVersion=en-2.0.1">We selected different cancer types, known to have different levels and types of CNVs for this study. This included pediatric acute lymphoblastic leukemia (known to have few but large CNVs) acute myeloid leukemia (large CNVs), melanoma (mainly characterized by Single nucleotide variants, SNVs) or breast cancer (multiple small and large CNVs). The leukemia samples originated from bone marrow aspirations taken at diagnosis of the disease. Breast cancer and sarcoma samples originate from surgical resection (without neoadjuvant treatment), following diagnosis. The melanoma samples were metastatic and originated from surgical resections.</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">Kolbeinsdottir, S., Zachariadis, V., Sommerauer, C., Lohi, O., Heinaniemi, M., &amp; Enge, M. (2025). Absolute copy number aware CNV calling of sub-megabase segments in ultra-low coverage single-cell DNA sequencing data. In NUCLEIC ACIDS RESEARCH (Vol. 53, Issue 17). https://doi.org/10.1093/nar/gkaf919</titl>
            <parTitl xml:lang="en">Kolbeinsdottir, S., Zachariadis, V., Sommerauer, C., Lohi, O., Heinaniemi, M., &amp; Enge, M. (2025). Absolute copy number aware CNV calling of sub-megabase segments in ultra-low coverage single-cell DNA sequencing data. In NUCLEIC ACIDS RESEARCH (Vol. 53, Issue 17). https://doi.org/10.1093/nar/gkaf919</parTitl>
            <IDNo agency="DOI">10.1093/nar/gkaf919</IDNo>
            <IDNo agency="SWEPUB">oai:swepub.ki.se:1061050</IDNo>
          </titlStmt>
          <distStmt>
            <distDate date="2025">2025</distDate>
          </distStmt>
        </citation>
      </relPubl>
      <relPubl>
        <citation>
          <titlStmt>
            <titl xml:lang="sv">Zachariadis, V., Cheng, H., Andrews, N., &amp; Enge, M. (2020). A Highly Scalable Method for Joint Whole-Genome Sequencing and Gene-Expression Profiling of Single Cells. In MOLECULAR CELL (Vol. 80, Issue 3, pp. 541-553.e5). https://doi.org/10.1016/j.molcel.2020.09.025</titl>
            <parTitl xml:lang="en">Zachariadis, V., Cheng, H., Andrews, N., &amp; Enge, M. (2020). A Highly Scalable Method for Joint Whole-Genome Sequencing and Gene-Expression Profiling of Single Cells. In MOLECULAR CELL (Vol. 80, Issue 3, pp. 541-553.e5). https://doi.org/10.1016/j.molcel.2020.09.025</parTitl>
            <IDNo agency="DOI">10.1016/j.molcel.2020.09.025</IDNo>
            <IDNo agency="SWEPUB">oai:swepub.ki.se:467288</IDNo>
          </titlStmt>
          <distStmt>
            <distDate date="2020">2020</distDate>
          </distStmt>
        </citation>
      </relPubl>
    </othrStdyMat>
  </stdyDscr>
</codeBook>