{
  "@type": "dcat:Dataset",
  "accessLevel": "public",
  "bureauCode": [
    "006:55"
  ],
  "contactPoint": {
    "fn": "Nathanael David Olson",
    "hasEmail": "mailto:nathanael.olson@nist.gov"
  },
  "description": "CMRG v1.00 of a small variant benchmark and structural variant benchmark focused on 273 challenging medically relevant genes for the Genome in a Bottle (GIAB) sample HG002 (aka Ashkenazi son). These benchmarks were generated from a trio-based hifiasm v0.11 (https://doi.org/10.1038/s41592-020-01056-5) diploid assembly of HG002 using PacBio HiFi reads for HG002 for assembly and partitioning into phased haplotypes using Illumina reads for the parents, HG003 and HG004. This benchmark contains vcfs for small and structural variants along with corresponding benchmark bed files indicating regions that are homozygous reference if they do not have a variant in the vcf. We extensively curated the variant calls, excluding any found to be questionable or errors. This benchmark helps measure performance in important challenging regions, including challenging segmental duplications, regions with complex variants, regions with structural variants, and regions affected by false duplications in GRCh37 or GRCh38. This benchmark is described in https://doi.org/10.1101/2021.06.07.444885.",
  "distribution": [
    {
      "accessURL": "https://doi.org/10.18434/mds2-2475",
      "title": "DOI Access for Challenging Medically-Relevant Genes Benchmark Set"
    },
    {
      "accessURL": "https://ftp-trace.ncbi.nlm.nih.gov/ReferenceSamples/giab/release/AshkenazimTrio/HG002_NA24385_son/CMRG_v1.00/",
      "description": "NCBI Hosted Genome In A Bottle FTP Site",
      "title": "GIAB FTP Site"
    },
    {
      "accessURL": "https://github.com/usnistgov/cmrg-benchmarkset-manuscript",
      "description": "Github repository with code used to generate figures and perform analysis for manuscript.",
      "title": "Code for Manuscript Analysis Repository"
    },
    {
      "accessURL": "https://github.com/usnistgov/giab-cmrg-benchmarkset",
      "description": "Github repository with code used to generate benchmark sets.",
      "title": "Code Repository"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/README.md",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/CHM13v1.0/SmallVariant/HG002_CHM13v1.0_CMRG_smallvar_v1.00_draft.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/CHM13v1.0/SmallVariant/HG002_CHM13v1.0_CMRG_smallvar_v1.00_draft.vcf.gz",
      "mediaType": "application/gzip"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/CHM13v1.0/SmallVariant/HG002_CHM13v1.0_CMRG_smallvar_v1.00_draft.vcf.gz.tbi",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/CHM13v1.0/SupplementaryFiles/HG002_CHM13_CMRG_smallvar_v1.00_GRCh38-equiv-regions_draft.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/CHM13v1.0/SupplementaryFiles/HG002v11-align2-CHM13v1.0/HG002v11-align2-CHM13v1.0.dip.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/CHM13v1.0/SupplementaryFiles/HG002v11-align2-CHM13v1.0/HG002v11-align2-CHM13v1.0.dip.vcf.gz",
      "mediaType": "application/gzip"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/CHM13v1.0/SupplementaryFiles/HG002v11-align2-CHM13v1.0/HG002v11-align2-CHM13v1.0.dip.vcf.gz.tbi",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/CHM13v1.0/SupplementaryFiles/HG002v11-align2-CHM13v1.0/HG002v11-align2-CHM13v1.0.hap1.bam",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/CHM13v1.0/SupplementaryFiles/HG002v11-align2-CHM13v1.0/HG002v11-align2-CHM13v1.0.hap1.bam.bai",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/CHM13v1.0/SupplementaryFiles/HG002v11-align2-CHM13v1.0/HG002v11-align2-CHM13v1.0.hap2.bam",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/CHM13v1.0/SupplementaryFiles/HG002v11-align2-CHM13v1.0/HG002v11-align2-CHM13v1.0.hap2.bam.bai",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh37/SmallVariant/HG002_GRCh37_CMRG_smallvar_v1.00.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh37/SmallVariant/HG002_GRCh37_CMRG_smallvar_v1.00.vcf.gz",
      "mediaType": "application/gzip"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh37/SmallVariant/HG002_GRCh37_CMRG_smallvar_v1.00.vcf.gz.tbi",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh37/StructuralVariant/HG002_GRCh37_CMRG_SV_v1.00.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh37/StructuralVariant/HG002_GRCh37_CMRG_SV_v1.00.vcf.gz",
      "mediaType": "application/gzip"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh37/StructuralVariant/HG002_GRCh37_CMRG_SV_v1.00.vcf.gz.tbi",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh37/SupplementaryFiles/GRCh37_CMRG_benchmark_gene_coordinates.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh37/SupplementaryFiles/HG002v11-align2-GRCh37/HG002v11-align2-GRCh37.dip.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh37/SupplementaryFiles/HG002v11-align2-GRCh37/HG002v11-align2-GRCh37.dip.vcf.gz",
      "mediaType": "application/gzip"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh37/SupplementaryFiles/HG002v11-align2-GRCh37/HG002v11-align2-GRCh37.dip.vcf.gz.tbi",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh37/SupplementaryFiles/HG002v11-align2-GRCh37/HG002v11-align2-GRCh37.hap1.bam",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh37/SupplementaryFiles/HG002v11-align2-GRCh37/HG002v11-align2-GRCh37.hap1.bam.bai",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh37/SupplementaryFiles/HG002v11-align2-GRCh37/HG002v11-align2-GRCh37.hap2.bam",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh37/SupplementaryFiles/HG002v11-align2-GRCh37/HG002v11-align2-GRCh37.hap2.bam.bai",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh38/SmallVariant/HG002_GRCh38_CMRG_smallvar_v1.00.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh38/SmallVariant/HG002_GRCh38_CMRG_smallvar_v1.00.vcf.gz",
      "mediaType": "application/gzip"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh38/SmallVariant/HG002_GRCh38_CMRG_smallvar_v1.00.vcf.gz.tbi",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh38/StructuralVariant/HG002_GRCh38_CMRG_SV_v1.00.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh38/StructuralVariant/HG002_GRCh38_CMRG_SV_v1.00.vcf.gz",
      "mediaType": "application/gzip"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh38/StructuralVariant/HG002_GRCh38_CMRG_SV_v1.00.vcf.gz.tbi",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh38/SupplementaryFiles/GRCh38_CMRG_benchmark_gene_coordinates.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh38/SupplementaryFiles/HG002v11-align2-GRCh38/HG002v11-align2-GRCh38.dip.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh38/SupplementaryFiles/HG002v11-align2-GRCh38/HG002v11-align2-GRCh38.dip.vcf.gz",
      "mediaType": "application/gzip"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh38/SupplementaryFiles/HG002v11-align2-GRCh38/HG002v11-align2-GRCh38.dip.vcf.gz.tbi",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh38/SupplementaryFiles/HG002v11-align2-GRCh38/HG002v11-align2-GRCh38.hap1.bam",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh38/SupplementaryFiles/HG002v11-align2-GRCh38/HG002v11-align2-GRCh38.hap1.bam.bai",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh38/SupplementaryFiles/HG002v11-align2-GRCh38/HG002v11-align2-GRCh38.hap2.bam",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/benchmark_sets/GRCh38/SupplementaryFiles/HG002v11-align2-GRCh38/HG002v11-align2-GRCh38.hap2.bam.bai",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/chksum.md5",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/dependencies/GRCh37_MRG_GAPs.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/dependencies/GRCh37_curation_medicalgene_SV_errorsorunsure.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/dependencies/GRCh37_curation_medicalgene_smallvar_complexrepeat_errorsorunsure_repeatexpanded.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/dependencies/GRCh37_hifiasm_error.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/dependencies/GRCh37_mrg_full_gene.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/dependencies/GRCh38_CD4_gaps.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/dependencies/GRCh38_CD4_gaps_slop50.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/dependencies/GRCh38_MRG_GAPs.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/dependencies/GRCh38_curation_medicalgene_SV_errorsorunsure_repeatexpanded.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/dependencies/GRCh38_curation_medicalgene_smallvar_complexrepeat_errorsorunsure_repeatexpanded.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/dependencies/GRCh38_hifiasm_error.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/dependencies/GRCh38_mrg_full_gene.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/dependencies/HiCanu_2.1_HG002_GRCh37_difficult_medical_gene_smallvar_benchmark_v0.02.03_intersected_FPs_repeatexpanded_slop50.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/dependencies/HiCanu_2.1_HG002_GRCh38_difficult_medical_gene_smallvar_benchmark_v0.02.03_intersected_FPs_repeatexpanded_slop50.bed",
      "mediaType": "application/octet-stream"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/dependencies/HiCanu_2.1_HG002_GRCh38_difficult_medical_gene_smallvar_benchmark_v0.02.03_intersected_subtract_FPs_repeatexpanded_slop50_manual_curation_sites.tsv_manual_curation_sites.txt",
      "mediaType": "text/plain"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/dependencies/combined%20curation%20responses%20from%20benchmarking%20with%20sm%20variant%20v0.02.03%20-%20GRCh37andGRCh38.tsv",
      "mediaType": "text/tab-separated-values"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/hifiasm-assembly/HG002-v0.11.mat.fa.gz",
      "mediaType": "application/gzip"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/hifiasm-assembly/HG002-v0.11.mat.gff.gz",
      "mediaType": "application/gzip"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/hifiasm-assembly/HG002-v0.11.pat.fa.gz",
      "mediaType": "application/gzip"
    },
    {
      "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2475/hifiasm-assembly/HG002-v0.11.pat.gff.gz",
      "mediaType": "application/gzip"
    }
  ],
  "identifier": "ark:/88434/mds2-2475",
  "keyword": [
    "Bioinformatics",
    "Bioinformatics",
    "DNA sequencing",
    "Human genomics",
    "Medical genomics",
    "Reference materials"
  ],
  "landingPage": "https://data.nist.gov/od/id/mds2-2475",
  "language": [
    "en"
  ],
  "license": "https://www.nist.gov/open/license",
  "modified": "2021-09-29 00:00:00",
  "programCode": [
    "006:045"
  ],
  "publisher": {
    "@type": "org:Organization",
    "name": "National Institute of Standards and Technology"
  },
  "references": [
    "https://doi.org/10.1038/s41592-020-01056-5",
    "https://doi.org/10.1101/2021.06.07.444885"
  ],
  "theme": [
    "Bioscience:Genomics"
  ],
  "title": "Challenging Medically-Relevant Genes Benchmark Set"
}