<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"></titl>
        <parTitl xml:lang="en">Other NS tumors</parTitl>
        <IDNo agency="SND">fega-sweden-egad50000000299-html-0</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>
    </citation>
  </docDscr>
  <stdyDscr>
    <citation>
      <titlStmt>
        <titl xml:lang="sv"></titl>
        <parTitl xml:lang="en">Other NS tumors</parTitl>
        <IDNo agency="SND">fega-sweden-egad50000000299-html-0</IDNo>
      </titlStmt>
      <rspStmt>
        <AuthEnty xml:lang="en" affiliation="">The Swedish Childhood Tumor Biobank</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="2024-02-22" />
      </distStmt>
      <verStmt>
        <version elementVersion="0" elementVersionDate="2024-02-22" />
      </verStmt>
    </citation>
    <stdyInfo>
      <subject />
      <abstract xml:lang="en" contentType="abstract">The dataset represents a total of 18 DNA samples from 6 male and 3 female pediatric patients affected with central or peripheral nervous system tumors not classified as embryonal central nervous system tumors, nor gliomas, glioneuronal, or neuronal tumors. One tumor tissue sample and one peripheral blood sample from each patient were subject to whole genome sequencing (WGS) and were sequenced 2x150 bp paired-end on an Illumina HiSeqX v2.5 instrument. The FASTQ files generated were aligned to the human reference genome sequence GRCh38/hg38 using bwa-mem, with the ALT-aware option turned on. Sorting of reads and marking of PCR duplicates was performed with GATK. Base quality score recalibration and joint realignment of reads around insertions and deletions (indels) were conducted using GATK tools. The dataset consists of 18 files in the CRAM format (lossless compression) with a total file size of ~3,4 TB. Additional genomic and molecular data (FASTQ, BAM, IDAT, and VCF files) and limited clinical data can be requested by ethically approved projects conducting research in the field of pediatric cancer. 

This dataset is 1 of 3 included in the study titled A Combined Omics and Tissue Biobank for Paediatric Cancers, http://identifiers.org/ega.study:EGAS50000000209.</abstract>
      <sumDscr />
    </stdyInfo>
    <method>
      <dataColl />
    </method>
    <dataAccs>
      <useStmt>
        <restrctn xml:lang="en">Access to data through an external actor. </restrctn>
        <restrctn xml:lang="sv">Åtkomst till data via extern aktör. </restrctn>
      </useStmt>
    </dataAccs>
    <othrStdyMat />
  </stdyDscr>
</codeBook>