{
  "generated_at": "2026-07-31T20:00:53.745Z",
  "purpose": "Independent high-coverage WGS SV concordance check for the 150 exome-source sample IDs used by LGASieve.",
  "reference_build": "GRCh38",
  "requested_sample_count": 150,
  "genes": [
    {
      "gene": "BRCA1",
      "transcript": "ENST00000357654",
      "chrom": "chr17",
      "start": 43044295,
      "end": 43125364,
      "exons": [
        [
          43125271,
          43125364
        ],
        [
          43124017,
          43124115
        ],
        [
          43115726,
          43115779
        ],
        [
          43106456,
          43106533
        ],
        [
          43104868,
          43104956
        ],
        [
          43104122,
          43104261
        ],
        [
          43099775,
          43099880
        ],
        [
          43097244,
          43097289
        ],
        [
          43095846,
          43095922
        ],
        [
          43091435,
          43094860
        ],
        [
          43090944,
          43091032
        ],
        [
          43082404,
          43082575
        ],
        [
          43076488,
          43076614
        ],
        [
          43074331,
          43074521
        ],
        [
          43070928,
          43071238
        ],
        [
          43067608,
          43067695
        ],
        [
          43063874,
          43063951
        ],
        [
          43063333,
          43063373
        ],
        [
          43057052,
          43057135
        ],
        [
          43051063,
          43051117
        ],
        [
          43049121,
          43049194
        ],
        [
          43047643,
          43047703
        ],
        [
          43044295,
          43045802
        ]
      ]
    },
    {
      "gene": "BRCA2",
      "transcript": "ENST00000380152",
      "chrom": "chr13",
      "start": 32315508,
      "end": 32400268,
      "exons": [
        [
          32315508,
          32315667
        ],
        [
          32316422,
          32316527
        ],
        [
          32319077,
          32319325
        ],
        [
          32325076,
          32325184
        ],
        [
          32326101,
          32326150
        ],
        [
          32326242,
          32326282
        ],
        [
          32326499,
          32326613
        ],
        [
          32329443,
          32329492
        ],
        [
          32330919,
          32331030
        ],
        [
          32332272,
          32333387
        ],
        [
          32336265,
          32341196
        ],
        [
          32344558,
          32344653
        ],
        [
          32346827,
          32346896
        ],
        [
          32354861,
          32355288
        ],
        [
          32356428,
          32356609
        ],
        [
          32357742,
          32357929
        ],
        [
          32362523,
          32362693
        ],
        [
          32363179,
          32363533
        ],
        [
          32370402,
          32370557
        ],
        [
          32370956,
          32371100
        ],
        [
          32376670,
          32376791
        ],
        [
          32379317,
          32379515
        ],
        [
          32379750,
          32379913
        ],
        [
          32380007,
          32380145
        ],
        [
          32394689,
          32394933
        ],
        [
          32396898,
          32397044
        ],
        [
          32398162,
          32400268
        ]
      ]
    }
  ],
  "callsets": [
    {
      "callset_name": "Illumina ensemble freeze V1",
      "source_vcf_url": "https://ftp.1000genomes.ebi.ac.uk/vol1/ftp/data_collections/1000G_2504_high_coverage/working/20210124.SV_Illumina_Integration/1KGP_3202.Illumina_ensemble_callset.freeze_V1.vcf.gz",
      "source_index_url": "https://ftp.1000genomes.ebi.ac.uk/vol1/ftp/data_collections/1000G_2504_high_coverage/working/20210124.SV_Illumina_Integration/1KGP_3202.Illumina_ensemble_callset.freeze_V1.vcf.gz.tbi",
      "vcf_sample_count": 3202,
      "matched_sample_count": 150,
      "missing_sample_count": 0,
      "missing_samples": [],
      "overlapping_del_dup_cnv_record_count": 4,
      "exon_overlapping_del_dup_cnv_record_count": 2,
      "records_with_at_least_one_carrier_in_150": 1,
      "exon_overlapping_records_with_at_least_one_carrier_in_150": 0,
      "sample_event_pairs": 1,
      "exon_overlapping_sample_event_pairs": 0,
      "events": [
        {
          "gene": "BRCA1",
          "chrom": "chr17",
          "pos": 43045958,
          "end": 43046229,
          "id": "HGSV_62182",
          "svtype": "DEL",
          "alt": "<DEL>",
          "filter": "PASS",
          "allele_frequency": "0.000468",
          "algorithms": null,
          "overlaps_canonical_exon": false,
          "overlapping_exons": [],
          "all_vcf_carrier_count": 3,
          "all_vcf_carriers": [
            {
              "sample_id": "HG01796",
              "gt": "0/1",
              "cn": "2.02272"
            },
            {
              "sample_id": "HG02601",
              "gt": "0/1",
              "cn": "1.07022"
            },
            {
              "sample_id": "HG02602",
              "gt": "0/1",
              "cn": "1.08537"
            }
          ],
          "cohort_carrier_count": 1,
          "carriers": [
            {
              "sample_id": "HG02601",
              "gt": "0/1",
              "cn": "1.07022"
            }
          ]
        },
        {
          "gene": "BRCA1",
          "chrom": "chr17",
          "pos": 43069993,
          "end": 43075601,
          "id": "HGSV_62183",
          "svtype": "DEL",
          "alt": "<DEL>",
          "filter": "PASS",
          "allele_frequency": "0.000156",
          "algorithms": "depth,manta",
          "overlaps_canonical_exon": true,
          "overlapping_exons": [
            {
              "exon": 14,
              "start": 43074331,
              "end": 43074521
            },
            {
              "exon": 15,
              "start": 43070928,
              "end": 43071238
            }
          ],
          "all_vcf_carrier_count": 1,
          "all_vcf_carriers": [
            {
              "sample_id": "NA18949",
              "gt": "0/1",
              "cn": null
            }
          ],
          "cohort_carrier_count": 0,
          "carriers": []
        },
        {
          "gene": "BRCA1",
          "chrom": "chr17",
          "pos": 43071626,
          "end": 43072707,
          "id": "HGSV_62184",
          "svtype": "DEL",
          "alt": "<DEL>",
          "filter": "PASS",
          "allele_frequency": "0.004059",
          "algorithms": "manta,wham",
          "overlaps_canonical_exon": false,
          "overlapping_exons": [],
          "all_vcf_carrier_count": 25,
          "all_vcf_carriers": [
            {
              "sample_id": "HG00637",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG01323",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG01393",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG01395",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG01990",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG02322",
              "gt": "1/1",
              "cn": null
            },
            {
              "sample_id": "HG02481",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG02634",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG03069",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG03172",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG03225",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG03439",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG03455",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19019",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19309",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19324",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19328",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19374",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19399",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19475",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19819",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19901",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA20334",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA20355",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG03456",
              "gt": "0/1",
              "cn": null
            }
          ],
          "cohort_carrier_count": 0,
          "carriers": []
        },
        {
          "gene": "BRCA1",
          "chrom": "chr17",
          "pos": 43102678,
          "end": 43183624,
          "id": "HGSV_62185",
          "svtype": "DEL",
          "alt": "<DEL>",
          "filter": "PASS",
          "allele_frequency": "0.000156",
          "algorithms": "depth,manta",
          "overlaps_canonical_exon": true,
          "overlapping_exons": [
            {
              "exon": 1,
              "start": 43125271,
              "end": 43125364
            },
            {
              "exon": 2,
              "start": 43124017,
              "end": 43124115
            },
            {
              "exon": 3,
              "start": 43115726,
              "end": 43115779
            },
            {
              "exon": 4,
              "start": 43106456,
              "end": 43106533
            },
            {
              "exon": 5,
              "start": 43104868,
              "end": 43104956
            },
            {
              "exon": 6,
              "start": 43104122,
              "end": 43104261
            }
          ],
          "all_vcf_carrier_count": 1,
          "all_vcf_carriers": [
            {
              "sample_id": "HG01528",
              "gt": "0/1",
              "cn": null
            }
          ],
          "cohort_carrier_count": 0,
          "carriers": []
        }
      ]
    },
    {
      "callset_name": "GATK-SV/svtools freeze V3 with AF",
      "source_vcf_url": "https://ftp.1000genomes.ebi.ac.uk/vol1/ftp/data_collections/1000G_2504_high_coverage/working/20210124.SV_Illumina_Integration/1KGP_3202.gatksv_svtools_novelins.freeze_V3.wAF.vcf.gz",
      "source_index_url": "https://ftp.1000genomes.ebi.ac.uk/vol1/ftp/data_collections/1000G_2504_high_coverage/working/20210124.SV_Illumina_Integration/1KGP_3202.gatksv_svtools_novelins.freeze_V3.wAF.vcf.gz.tbi",
      "vcf_sample_count": 3202,
      "matched_sample_count": 150,
      "missing_sample_count": 0,
      "missing_samples": [],
      "overlapping_del_dup_cnv_record_count": 4,
      "exon_overlapping_del_dup_cnv_record_count": 2,
      "records_with_at_least_one_carrier_in_150": 1,
      "exon_overlapping_records_with_at_least_one_carrier_in_150": 0,
      "sample_event_pairs": 1,
      "exon_overlapping_sample_event_pairs": 0,
      "events": [
        {
          "gene": "BRCA1",
          "chrom": "chr17",
          "pos": 43045958,
          "end": 43046229,
          "id": "HGSV_216996",
          "svtype": "DEL",
          "alt": "<DEL>",
          "filter": "PASS",
          "allele_frequency": "0.000468",
          "algorithms": null,
          "overlaps_canonical_exon": false,
          "overlapping_exons": [],
          "all_vcf_carrier_count": 3,
          "all_vcf_carriers": [
            {
              "sample_id": "HG01796",
              "gt": "0/1",
              "cn": "2.02272"
            },
            {
              "sample_id": "HG02601",
              "gt": "0/1",
              "cn": "1.07022"
            },
            {
              "sample_id": "HG02602",
              "gt": "0/1",
              "cn": "1.08537"
            }
          ],
          "cohort_carrier_count": 1,
          "carriers": [
            {
              "sample_id": "HG02601",
              "gt": "0/1",
              "cn": "1.07022"
            }
          ]
        },
        {
          "gene": "BRCA1",
          "chrom": "chr17",
          "pos": 43069993,
          "end": 43075601,
          "id": "HGSV_216997",
          "svtype": "DEL",
          "alt": "<DEL>",
          "filter": "PASS",
          "allele_frequency": "0.000156",
          "algorithms": "depth,manta",
          "overlaps_canonical_exon": true,
          "overlapping_exons": [
            {
              "exon": 14,
              "start": 43074331,
              "end": 43074521
            },
            {
              "exon": 15,
              "start": 43070928,
              "end": 43071238
            }
          ],
          "all_vcf_carrier_count": 1,
          "all_vcf_carriers": [
            {
              "sample_id": "NA18949",
              "gt": "0/1",
              "cn": null
            }
          ],
          "cohort_carrier_count": 0,
          "carriers": []
        },
        {
          "gene": "BRCA1",
          "chrom": "chr17",
          "pos": 43071626,
          "end": 43072707,
          "id": "HGSV_216998",
          "svtype": "DEL",
          "alt": "<DEL>",
          "filter": "PASS",
          "allele_frequency": "0.004059",
          "algorithms": "manta,wham",
          "overlaps_canonical_exon": false,
          "overlapping_exons": [],
          "all_vcf_carrier_count": 25,
          "all_vcf_carriers": [
            {
              "sample_id": "HG00637",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG01323",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG01393",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG01395",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG01990",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG02322",
              "gt": "1/1",
              "cn": null
            },
            {
              "sample_id": "HG02481",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG02634",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG03069",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG03172",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG03225",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG03439",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG03455",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "HG03456",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19019",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19309",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19324",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19328",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19374",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19399",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19475",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19819",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA19901",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA20334",
              "gt": "0/1",
              "cn": null
            },
            {
              "sample_id": "NA20355",
              "gt": "0/1",
              "cn": null
            }
          ],
          "cohort_carrier_count": 0,
          "carriers": []
        },
        {
          "gene": "BRCA1",
          "chrom": "chr17",
          "pos": 43102678,
          "end": 43183624,
          "id": "HGSV_217000",
          "svtype": "DEL",
          "alt": "<DEL>",
          "filter": "PASS",
          "allele_frequency": "0.000156",
          "algorithms": "depth,manta",
          "overlaps_canonical_exon": true,
          "overlapping_exons": [
            {
              "exon": 1,
              "start": 43125271,
              "end": 43125364
            },
            {
              "exon": 2,
              "start": 43124017,
              "end": 43124115
            },
            {
              "exon": 3,
              "start": 43115726,
              "end": 43115779
            },
            {
              "exon": 4,
              "start": 43106456,
              "end": 43106533
            },
            {
              "exon": 5,
              "start": 43104868,
              "end": 43104956
            },
            {
              "exon": 6,
              "start": 43104122,
              "end": 43104261
            }
          ],
          "all_vcf_carrier_count": 1,
          "all_vcf_carriers": [
            {
              "sample_id": "HG01528",
              "gt": "0/1",
              "cn": null
            }
          ],
          "cohort_carrier_count": 0,
          "carriers": []
        }
      ]
    }
  ],
  "interpretation_note": "These high-coverage WGS callsets are stronger external evidence than the legacy low-coverage Phase 3 SV VCF, but they are still not a complete clinical truth set for rare single-exon BRCA CNVs."
}