<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">Mate pair whole genome sequencing of 98 AML samples</parTitl>
        <IDNo agency="SND">fega-sweden-egad50000001574-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">Mate pair whole genome sequencing of 98 AML samples</parTitl>
        <IDNo agency="SND">fega-sweden-egad50000001574-html-0</IDNo>
      </titlStmt>
      <rspStmt>
        <AuthEnty xml:lang="en" affiliation="">Lund 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="2025-06-30" />
      </distStmt>
      <verStmt>
        <version elementVersion="0" elementVersionDate="2025-06-30" />
      </verStmt>
    </citation>
    <stdyInfo>
      <subject />
      <abstract xml:lang="en" contentType="abstract">This dataset contains bam-files from Mate-pair whole genome sequencing of 98 AML samples. DNA was extracted from either bone marow or peripheral blood from primary AML samples. The libraries were prepared using Illumina Nextera mate pair library preparation kit, generating long-insert (2-8 kb) paired end libraries. These were sequenced on an Illumina NextSeq 500 using 2x76bp paired end chemistry. The fastq files generated by sequencing were aligned to the human hg19 reference genome (ucsc.hg19.fasta from the GATK resource bundle) using bwa (0.7.15-r1140) and duplicate reads were identified using samblaster (0.1.24). 

This dataset is 1 of 4 included in the study titled The cellular state space of AML unveils novel NPM1 subtypes with distinct clinical outcomes and immune evasion properties, http://identifiers.org/ega.study:EGAS50000001084.</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>