<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">SweGen whole-genome sequencing from the Northern Sweden Population Health Study</parTitl>
        <IDNo agency="SND">fega-sweden-egad50000001325-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">SweGen whole-genome sequencing from the Northern Sweden Population Health Study</parTitl>
        <IDNo agency="SND">fega-sweden-egad50000001325-html-0</IDNo>
      </titlStmt>
      <rspStmt>
        <AuthEnty xml:lang="en" affiliation="">Uppsala University</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="2025-04-04" />
      </distStmt>
      <verStmt>
        <version elementVersion="0" elementVersionDate="2025-04-04" />
      </verStmt>
    </citation>
    <stdyInfo>
      <subject />
      <abstract xml:lang="en" contentType="abstract">The dataset contains whole-genome sequencing data (aligned read files) in CRAM-format (lossless compression) for a total of 58 DNA samples originating from the Northern Sweden Population Health Study (NSPHS). For each of the 58 individuals, DNA was extracted from a blood sample and subject to whole genome sequencing (WGS). The WGS was performed using 2x150 bp paired-end chemistry on Illumina HiSeq X Ten instrumentation at the SciLifeLab National Genomics Infrastructure (NGI) in Stockholm and Uppsala. FASTQ files generated by WGS were analyzed using the nf-core pipeline Sarek, which includes pre-processing, alignment to the human GRCh38 reference genome, and germline variant calling. The NSPHS study was approved by the local ethics committee at the University of Uppsala (Regionala Etikprövningsnämnden, Uppsala, 2005:325 and 2016-03-09). All participants gave their written informed consent to the study including the examination of environmental and genetic causes of disease in compliance with the Declaration of Helsinki. 

This dataset is 1 of 4 included in the study titled SweGen: a whole-genome data resource of genetic variability in a cross-section of the Swedish population, http://identifiers.org/ega.study:EGAS50000000906.</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>