{
  "dataset": "CRAG open processed-coordinate validation cohort",
  "zenodo_record": "6914806",
  "doi": "10.5281/zenodo.6914806",
  "paper_doi": "10.1186/s13073-022-01141-8",
  "license": "CC BY 4.0 for the Zenodo record",
  "reference_build": "hg19 / GRCh37",
  "coordinate_contract": "liver records are zero-based half-open extended BED8 (name, MAPQ, strand, and two validated mate CIGAR columns); MAPQ is the smaller mate MAPQ according to the authors' README; the separately published BH01 example uses BED6",
  "author_preprocessing": "Adapters trimmed; BWA-MEM to human_g1k_v37; PCR duplicates removed by samblaster; proper unique autosomal pairs retained; fragments outside 50-1000 bp excluded for the paper analysis.",
  "files": [
    {
      "name": "BH01.chr22.frag.bed.gz",
      "bytes": 90413532,
      "md5": "1ea90457d8df8b92ece868624b283466",
      "sha256_local": "4813e74cbd5f51b9518c9bffbccb568284aff445d9f37baf0643169898f03f84",
      "url": "https://zenodo.org/api/records/6914806/files/BH01.chr22.frag.bed.gz/content",
      "status": "downloaded_and_verified"
    },
    {
      "name": "Supplemantary_Materials_1_source_code.zip",
      "bytes": 6092140,
      "md5": "d390561ca0113b36c0a601f78d573768",
      "sha256_local": "e0ff5e2299e6276298d0403c2af871be1e2235b29470dea5d76b25c73cc17034",
      "url": "https://zenodo.org/api/records/6914806/files/Supplemantary_Materials_1_source_code.zip/content",
      "status": "downloaded_and_verified"
    },
    {
      "name": "Supplemantary_Table 2_Hotspots.zip",
      "local_name": "Supplemantary_Table_2_Hotspots.zip",
      "bytes": 44597013,
      "md5": "b5e9bfa7ec8a493af5018df2b6a092cb",
      "sha256_local": "e4eb3f7c87536ad065cf9c1ada5a088aab1347f640e41af8cc2ae6e4e8d95cff",
      "url": "https://zenodo.org/api/records/6914806/files/Supplemantary_Table%202_Hotspots.zip/content",
      "status": "downloaded_and_verified"
    },
    {
      "name": "liver.tar",
      "bytes": 3307939840,
      "md5": "c105ba8975704807aaff669149ffeb8e",
      "url": "https://zenodo.org/api/records/6914806/files/liver.tar/content",
      "status": "downloaded_md5_verified_extracted_and_all_16_gzip_streams_validated_to_eof"
    },
    {
      "name": "CRAG_supplementary_tables.xlsx",
      "bytes": 100669,
      "md5_local": "bf3d08dec2553ff8f6a1dece64e1cf95",
      "sha256_local": "76abc4c1b362f8ec8a155e6308ffa1331f51140235ed746e4ae893e4ba0af09b",
      "url": "https://static-content.springer.com/esm/art%3A10.1186%2Fs13073-022-01141-8/MediaObjects/13073_2022_1141_MOESM1_ESM.xlsx",
      "status": "downloaded; labels parsed from Supplementary Table 2"
    }
  ],
  "analysis_boundary": "Eight early-stage liver cancers and eight independent age/sex-matched noncancer controls are an exploratory matched engineering cohort. They cannot estimate MCED specificity or support a screening claim."
}