{
  "release": "HGVD v3.1",
  "generated_from": "HGVD_v3.1_Supplementary_Tables.xlsx / Supplementary Tables S2–S5.",
  "footnotes": {
    "a": "For the current sequencing release, #Sample (N_sample) is the number of samples with a non-missing genotype. On autosomes, AN = 2 × N_sample and equals the VCF AN field. For biallelic sites, RR, RA and AA denote Ref/Ref, Ref/Alt and Alt/Alt genotype counts, respectively; N_sample = RR + RA + AA, NR (N_REF) = 2 × RR + RA, and NA (N_ALT) = RA + 2 × AA. Accordingly, AC = NA and AN = NR + NA. At multiallelic sites, AC is reported separately for each ALT allele and equals the VCF AC field.",
    "b": "Missing genotypes (./.) are excluded from both numerator and denominator and are not imputed as homozygous reference. No additional depth or genotype-quality threshold is applied when aggregate counts are generated from the final joint-genotyped VCF; poorer coverage is therefore reflected by a smaller #Sample when genotypes are missing. Successfully genotyped and callable sample counts are equivalent.",
    "c": "Sex-chromosome genotypes are tabulated separately for females and males. N_female and N_male denote the numbers of females and males with non-missing genotypes at the site. Males are treated as haploid and contribute one allele: AN = 2 × N_female + N_male, NR (N_REF) = 2 × Female RR + Female RA + Male RR, and NA (N_ALT) = Female RA + 2 × Female AA + Male AA. Male RR and AA represent hemizygous reference and alternate calls, respectively.",
    "d": "Exome and WGS allele-frequency summaries are available both separately and as combined exome/WGS summaries in the browser and downloadable release."
  },
  "resources": [
    {
      "resource_id": "HGVD-v3.1-01",
      "resource_type": "browser_track",
      "browser_track": "Gene",
      "download_file": "",
      "file_name": "",
      "download_url": "",
      "content": "",
      "source_cohort": "Gene models with NCBI cross-references",
      "processing_stage": "Imported browser annotation",
      "reference_assembly": "GRCh37/hg19, GRCh38/hg38, and T2T-CHM13",
      "filters_applied": "Not applicable",
      "counting_unit": "Not applicable",
      "pipeline_version": "Not applicable (imported annotation)",
      "coordinate_derivation": "Imported assembly-specific annotation",
      "data_provenance": "NCBI Gene annotation",
      "dbsnp_build_for_rsid": "",
      "record_count": "",
      "record_count_unit": "",
      "record_count_detail": "",
      "file_size_bytes": "",
      "md5": "",
      "footnotes": ""
    },
    {
      "resource_id": "HGVD-v3.1-02",
      "resource_type": "browser_track",
      "browser_track": "dbSNP",
      "download_file": "",
      "file_name": "",
      "download_url": "",
      "content": "",
      "source_cohort": "NCBI dbSNP variants",
      "processing_stage": "Imported variant annotation",
      "reference_assembly": "GRCh37/hg19, GRCh38/hg38, and T2T-CHM13",
      "filters_applied": "Not applicable",
      "counting_unit": "Not applicable",
      "pipeline_version": "Not applicable (imported annotation)",
      "coordinate_derivation": "Imported assembly-specific annotation",
      "data_provenance": "NCBI dbSNP annotation",
      "dbsnp_build_for_rsid": "",
      "record_count": "",
      "record_count_unit": "",
      "record_count_detail": "",
      "file_size_bytes": "",
      "md5": "",
      "footnotes": ""
    },
    {
      "resource_id": "HGVD-v3.1-03",
      "resource_type": "browser_track_and_file",
      "browser_track": "Exome; allele frequency, samples covered, and average read depth",
      "download_file": "HGVD Release Version 3.1 (GRCh37/hg19): HGVD-V3_10-dbSNP151.tar.gz",
      "file_name": "HGVD-V3_10-dbSNP151.tar.gz",
      "download_url": "https://www.hgvd.genome.med.kyoto-u.ac.jp/download/HGVD-V3_10-dbSNP151.tar.gz",
      "content": "Autosomes (chr1-chr22)",
      "source_cohort": "Exome dataset (n = 1,209)",
      "processing_stage": "Aggregate browser summaries generated from the final released GRCh37/hg19 exome call set; GRCh38/hg38 and T2T-CHM13 browser views generated by liftOver",
      "reference_assembly": "GRCh37/hg19, GRCh38/hg38, and T2T-CHM13",
      "filters_applied": "Sample and variant QC with VQSR-filtered calls, as described in Methods",
      "counting_unit": "Per-locus genotype, allele, and sample counts (RR, RA, AA, NR, NA and #Sample)",
      "pipeline_version": "Picard/GATK v3.8 Best Practices reprocessing (HaplotypeCaller, joint genotyping, VQSR); see Methods",
      "coordinate_derivation": "GRCh37/hg19 native release coordinates; GRCh38/hg38 and T2T-CHM13 derived by UCSC liftOver from GRCh37/hg19",
      "data_provenance": "HGVD exome aggregate genotype and allele counts",
      "dbsnp_build_for_rsid": "dbSNP Build151",
      "record_count": "",
      "record_count_unit": "",
      "record_count_detail": "",
      "file_size_bytes": 1249129953,
      "md5": "be40bd8c0f4b471c3e9d276f6bc32b8a",
      "footnotes": "a,b,c,d"
    },
    {
      "resource_id": "HGVD-v3.1-04",
      "resource_type": "browser_track_and_file",
      "browser_track": "Exome; allele frequency, samples covered, and average read depth",
      "download_file": "HGVD Release Version 3.1 (GRCh37/hg19): HGVD-V3_10XY-dbSNP151.tar.gz",
      "file_name": "HGVD-V3_10XY-dbSNP151.tar.gz",
      "download_url": "https://www.hgvd.genome.med.kyoto-u.ac.jp/download/HGVD-V3_10XY-dbSNP151.tar.gz",
      "content": "Sex chromosomes (chrX, chrY)",
      "source_cohort": "Exome dataset (n = 1,209)",
      "processing_stage": "Aggregate browser summaries generated from the final released GRCh37/hg19 exome call set; GRCh38/hg38 and T2T-CHM13 browser views generated by liftOver",
      "reference_assembly": "GRCh37/hg19, GRCh38/hg38, and T2T-CHM13",
      "filters_applied": "Sample and variant QC with VQSR-filtered calls, as described in Methods",
      "counting_unit": "Per-locus genotype, allele, and sample counts (RR, RA, AA, NR, NA and #Sample)",
      "pipeline_version": "Picard/GATK v3.8 Best Practices reprocessing (HaplotypeCaller, joint genotyping, VQSR); see Methods",
      "coordinate_derivation": "GRCh37/hg19 native release coordinates; GRCh38/hg38 and T2T-CHM13 derived by UCSC liftOver from GRCh37/hg19",
      "data_provenance": "HGVD exome aggregate genotype and allele counts",
      "dbsnp_build_for_rsid": "dbSNP Build151",
      "record_count": "",
      "record_count_unit": "",
      "record_count_detail": "",
      "file_size_bytes": 49421633,
      "md5": "97234d0a04ff7c4c5591994c3d449f69",
      "footnotes": "a,b,c,d"
    },
    {
      "resource_id": "HGVD-v3.1-05",
      "resource_type": "browser_track_and_file",
      "browser_track": "WGS; allele frequency, samples covered, and average read depth",
      "download_file": "HGVD Release Version 3.1 (GRCh37/hg19): HGVD-V3_10-dbSNP151.tar.gz",
      "file_name": "HGVD-V3_10-dbSNP151.tar.gz",
      "download_url": "https://www.hgvd.genome.med.kyoto-u.ac.jp/download/HGVD-V3_10-dbSNP151.tar.gz",
      "content": "Autosomes (chr1-chr22)",
      "source_cohort": "WGS dataset (n = 3,135)",
      "processing_stage": "Aggregate browser summaries generated from the final released GRCh37/hg19 WGS call set; GRCh38/hg38 and T2T-CHM13 browser views generated by liftOver",
      "reference_assembly": "GRCh37/hg19, GRCh38/hg38, and T2T-CHM13",
      "filters_applied": "Sample and variant QC with VQSR-filtered calls, as described in Methods and reference (4)",
      "counting_unit": "Per-locus genotype, allele, and sample counts (RR, RA, AA, NR, NA and #Sample)",
      "pipeline_version": "BWA-MEM alignment; Picard/GATK v3.8 Best Practices (duplicate marking, base-quality recalibration, HaplotypeCaller, joint genotyping, VQSR)",
      "coordinate_derivation": "GRCh37/hg19 native release coordinates; GRCh38/hg38 and T2T-CHM13 derived by UCSC liftOver from GRCh37/hg19",
      "data_provenance": "HGVD WGS aggregate genotype and allele counts",
      "dbsnp_build_for_rsid": "dbSNP Build151",
      "record_count": "",
      "record_count_unit": "",
      "record_count_detail": "",
      "file_size_bytes": 1249129953,
      "md5": "be40bd8c0f4b471c3e9d276f6bc32b8a",
      "footnotes": "a,b,c,d"
    },
    {
      "resource_id": "HGVD-v3.1-06",
      "resource_type": "browser_track_and_file",
      "browser_track": "WGS; allele frequency, samples covered, and average read depth",
      "download_file": "HGVD Release Version 3.1 (GRCh37/hg19): HGVD-V3_10XY-dbSNP151.tar.gz",
      "file_name": "HGVD-V3_10XY-dbSNP151.tar.gz",
      "download_url": "https://www.hgvd.genome.med.kyoto-u.ac.jp/download/HGVD-V3_10XY-dbSNP151.tar.gz",
      "content": "Sex chromosomes (chrX, chrY)",
      "source_cohort": "WGS dataset (n = 3,135)",
      "processing_stage": "Aggregate browser summaries generated from the final released GRCh37/hg19 WGS call set; GRCh38/hg38 and T2T-CHM13 browser views generated by liftOver",
      "reference_assembly": "GRCh37/hg19, GRCh38/hg38, and T2T-CHM13",
      "filters_applied": "Sample and variant QC with VQSR-filtered calls, as described in Methods and reference (4)",
      "counting_unit": "Per-locus genotype, allele, and sample counts (RR, RA, AA, NR, NA and #Sample)",
      "pipeline_version": "BWA-MEM alignment; Picard/GATK v3.8 Best Practices (duplicate marking, base-quality recalibration, HaplotypeCaller, joint genotyping, VQSR)",
      "coordinate_derivation": "GRCh37/hg19 native release coordinates; GRCh38/hg38 and T2T-CHM13 derived by UCSC liftOver from GRCh37/hg19",
      "data_provenance": "HGVD WGS aggregate genotype and allele counts",
      "dbsnp_build_for_rsid": "dbSNP Build151",
      "record_count": "",
      "record_count_unit": "",
      "record_count_detail": "",
      "file_size_bytes": 49421633,
      "md5": "97234d0a04ff7c4c5591994c3d449f69",
      "footnotes": "a,b,c,d"
    },
    {
      "resource_id": "HGVD-v3.1-07",
      "resource_type": "browser_track",
      "browser_track": "Genotyping; allele frequency and samples covered",
      "download_file": "",
      "file_name": "",
      "download_url": "",
      "content": "",
      "source_cohort": "SNP array dataset (n = 3,248)",
      "processing_stage": "Aggregate browser summaries generated from the final released GRCh37/hg19 SNP-array genotype dataset; GRCh38/hg38 and T2T-CHM13 browser views generated by liftOver",
      "reference_assembly": "GRCh37/hg19, GRCh38/hg38, and T2T-CHM13",
      "filters_applied": "SNP-array marker and sample QC described in references (10, 11)",
      "counting_unit": "Per-locus genotype and allele counts, successfully genotyped sample count, and missing-genotype handling.",
      "pipeline_version": "iScan Control Software (ICS) for scanning and GenomeStudio for genotyping analysis",
      "coordinate_derivation": "GRCh37/hg19 source coordinates; GRCh38/hg38 and T2T-CHM13 browser views derived by liftOver",
      "data_provenance": "Final Report from GenomeStudio",
      "dbsnp_build_for_rsid": "",
      "record_count": "",
      "record_count_unit": "",
      "record_count_detail": "",
      "file_size_bytes": "",
      "md5": "",
      "footnotes": "b,c"
    },
    {
      "resource_id": "HGVD-v3.1-08",
      "resource_type": "browser_track_and_file",
      "browser_track": "eQTL",
      "download_file": "HGVD eQTL Release Version 8.1: HGVDeQTL-V8_1-cis.tar.gz",
      "file_name": "HGVDeQTL-V8_1-cis.tar.gz",
      "download_url": "https://www.hgvd.genome.med.kyoto-u.ac.jp/download/eQTL/version.8.1/HGVDeQTL-V8_1-cis.tar.gz",
      "content": "",
      "source_cohort": "eQTL panel (n = 300)",
      "processing_stage": "Published eQTL association results incorporated into HGVD",
      "reference_assembly": "GRCh37/hg19",
      "filters_applied": "Association-analysis criteria described in reference (9)",
      "counting_unit": "Variant–probe association record; allele-count, genotype-count and callable-sample denominators not reported",
      "pipeline_version": "Published eQTL analysis pipeline (reference 9); incorporated into HGVD without hg38/T2T reprocessing",
      "coordinate_derivation": "Native GRCh37/hg19 coordinates; no hg38/T2T eQTL track",
      "data_provenance": "Published eQTL association statistics (reference 9)",
      "dbsnp_build_for_rsid": "Not applicable",
      "record_count": "",
      "record_count_unit": "",
      "record_count_detail": "",
      "file_size_bytes": 456703313,
      "md5": "4f798100f571418d2fee934391aa12f4",
      "footnotes": ""
    },
    {
      "resource_id": "HGVD-v3.1-09",
      "resource_type": "download_file",
      "browser_track": "Not applicable",
      "download_file": "HGVD Structural Variants Version 1.0 (GRCh37/hg19): HGVD_SV-V1_00.vcf.gz",
      "file_name": "HGVD_SV-V1_00.vcf.gz",
      "download_url": "https://www.hgvd.genome.med.kyoto-u.ac.jp/download/HGVD_SV-V1_00.vcf.gz",
      "content": "",
      "source_cohort": "WGS dataset and Seven Bridges graph-genome source records",
      "processing_stage": "Integrated structural-variant VCF release",
      "reference_assembly": "GRCh37/hg19",
      "filters_applied": "WGS dataset: Manta-based SV calling, cross-sample merging, bcftools normalization, and filtering described in reference (4); Seven Bridges records: source-resource criteria",
      "counting_unit": "VCF record and alternate allele; aggregate AC and AN are provided for records from the WGS dataset",
      "pipeline_version": "Manta-based SV calling; cross-sample merging; bcftools normalization (Methods; reference 4)",
      "coordinate_derivation": "Native GRCh37/hg19 coordinates",
      "data_provenance": "HGVD WGS aggregate AC/AN and source-derived external frequency annotations",
      "dbsnp_build_for_rsid": "Not applicable",
      "record_count": 16112052,
      "record_count_unit": "VCF records",
      "record_count_detail": "Integrated release: 16,112,052 records / 17,491,876 alternate alleles. Of these, 438,056 records are HGVD-derived and carry aggregate AC and AN from the WGS cohort; 15,847,592 records (17,069,591 alternate alleles) are imported from the Seven Bridges graph-genome source and carry no HGVD genotypes. The two counts do not sum to the integrated total because records describing the same structural allele were merged (Table 2).",
      "file_size_bytes": 1058303960,
      "md5": "79051eef01fbb8223efbe347c0413c48",
      "footnotes": ""
    },
    {
      "resource_id": "HGVD-v3.1-10",
      "resource_type": "download_file",
      "browser_track": "Not applicable",
      "download_file": "HGVD Release Version 2.30: HGVD1210-V2_30-dbSNP150.tar.gz",
      "file_name": "HGVD1210-V2_30-dbSNP150.tar.gz",
      "download_url": "https://www.hgvd.genome.med.kyoto-u.ac.jp/download/HGVD1210-V2_30-dbSNP150.tar.gz",
      "content": "Autosomes (chr1-chr22)",
      "source_cohort": "Legacy HGVD exome cohort (n = 1,210)",
      "processing_stage": "Legacy HGVD Release Version 2.30 retained on the Download page",
      "reference_assembly": "GRCh37/hg19",
      "filters_applied": "Centre-specific variant-calling filters described in reference (5); per-locus filter status reported in the downloadable table",
      "counting_unit": "Per-locus genotype, allele, and sample counts (RR, RA, AA, NR, NA and #Sample)",
      "pipeline_version": "Legacy centre-specific exome calling pipelines (reference 5; Version 2.30 release documentation)",
      "coordinate_derivation": "Native GRCh37/hg19 coordinates",
      "data_provenance": "Legacy HGVD exome aggregate genotype and allele counts",
      "dbsnp_build_for_rsid": "dbSNP Build150 (legacy Version 2.30, unchanged)",
      "record_count": "",
      "record_count_unit": "",
      "record_count_detail": "",
      "file_size_bytes": 11761401,
      "md5": "f72ef4099260c832d38c49f0ca60017f",
      "footnotes": "a"
    },
    {
      "resource_id": "HGVD-v3.1-11",
      "resource_type": "download_file",
      "browser_track": "Not applicable",
      "download_file": "HGVD Release Version 2.30: HGVD1210-V2_30XY-dbSNP150.tar.gz",
      "file_name": "HGVD1210-V2_30XY-dbSNP150.tar.gz",
      "download_url": "https://www.hgvd.genome.med.kyoto-u.ac.jp/download/HGVD1210-V2_30XY-dbSNP150.tar.gz",
      "content": "Sex chromosomes (chrX, chrY)",
      "source_cohort": "Legacy HGVD exome cohort (n = 1,210)",
      "processing_stage": "Legacy HGVD Release Version 2.30 retained on the Download page",
      "reference_assembly": "GRCh37/hg19",
      "filters_applied": "Centre-specific variant-calling filters described in reference (5); per-locus filter status reported in the downloadable table",
      "counting_unit": "Per-locus genotype, allele, and sample counts (RR, RA, AA, NR, NA and #Sample)",
      "pipeline_version": "Legacy centre-specific exome calling pipelines (reference 5; Version 2.30 release documentation)",
      "coordinate_derivation": "Native GRCh37/hg19 coordinates",
      "data_provenance": "Legacy HGVD exome aggregate genotype and allele counts",
      "dbsnp_build_for_rsid": "dbSNP Build150 (legacy Version 2.30, unchanged)",
      "record_count": "",
      "record_count_unit": "",
      "record_count_detail": "",
      "file_size_bytes": 313669,
      "md5": "15d1750c7c51fa90697d098956676836",
      "footnotes": "a"
    },
    {
      "resource_id": "HGVD-v3.1-12",
      "resource_type": "download_file",
      "browser_track": "Not applicable",
      "download_file": "HGVD Japanese Reference Sequence Version 1.0 (GRCh37/hg19): JapaneseReferenceV1.0.tar.gz",
      "file_name": "JapaneseReferenceV1.0.tar.gz",
      "download_url": "https://www.hgvd.genome.med.kyoto-u.ac.jp/download/JapaneseReferenceV1.0.tar.gz",
      "content": "",
      "source_cohort": "HGVD Japanese Reference Sequence Version 1.0",
      "processing_stage": "Legacy Japanese Reference Sequence Version 1.0 retained on the Download page",
      "reference_assembly": "GRCh37/hg19",
      "filters_applied": "Not applicable (reference-sequence resource)",
      "counting_unit": "Not applicable",
      "pipeline_version": "Not applicable (reference-sequence resource)",
      "coordinate_derivation": "Native GRCh37/hg19 coordinates",
      "data_provenance": "HGVD Japanese Reference Sequence Version 1.0",
      "dbsnp_build_for_rsid": "Not applicable",
      "record_count": "",
      "record_count_unit": "",
      "record_count_detail": "",
      "file_size_bytes": 937520108,
      "md5": "24c13c1d20efa45c58c8f05f6fa40427",
      "footnotes": ""
    },
    {
      "resource_id": "HGVD-v3.1-13",
      "resource_type": "browser_track_and_file",
      "browser_track": "pathSTR (locus report pages)",
      "download_file": "pathSTR locus reports (HTML, one per locus)",
      "file_name": "",
      "download_url": "https://www.hgvd.genome.med.kyoto-u.ac.jp/pathstr.html",
      "content": "",
      "source_cohort": "1000 Genomes Project Oxford Nanopore dataset (n = 1,019)",
      "processing_stage": "Per-locus tandem-repeat length and motif distributions generated with STRdust and rendered with aSTRonaut",
      "reference_assembly": "T2T-CHM13",
      "filters_applied": "STRdust consensus-read filtering and outlier detection; see Methods and Supplementary Tables S4 and S5",
      "counting_unit": "Repeat-allele length and motif composition per locus; no HGVD allele or genotype counts are reported",
      "pipeline_version": "STRdust v1; aSTRonaut (pathSTR)",
      "coordinate_derivation": "Native T2T-CHM13 coordinates (T2T.STRchive-disease-loci.TRGT.bed)",
      "data_provenance": "Derived from the 1000 Genomes ONT cohort, not from HGVD samples; locus mapping in Supplementary Table S3 and locus-level QC in Supplementary Table S4",
      "dbsnp_build_for_rsid": "Not applicable",
      "record_count": 68,
      "record_count_unit": "Loci",
      "record_count_detail": "68 BED-defined loci (Supplementary Table S3)",
      "file_size_bytes": "",
      "md5": "",
      "footnotes": ""
    }
  ]
}