Files
SimurgArray/docs/validation/P6_gsa36_vs_gtc2vcf.json
T
kemal d625ef23c3 P6 validated against GTCtoVCF too: zero unexplained genotype differences
- GTCtoVCF (Apache-2.0, 36 GSA samples, merged sites): 23.66 M identical calls; every difference named
  (intensity-only probes merged by the oracle, its opposite-strand indel bug EDGE-012, normalisation-based
  grouping, OUT-018 ploidy); indel representations identical, including 144 gtc2vcf cannot resolve
- validate_p6_vcf.py: rule-based categories (--bpm for [I/D]/[D/I] detection)
- docs: validation P6 complete, README status
2026-09-28 13:20:44 +01:00

1160 lines
18 KiB
JSON

{
"oracle": "gtc2vcf",
"samples": 36,
"probes_oracle": 682719,
"probes_ours": 660270,
"probes_in_merged_records": 5000,
"probes_only_in_oracle": 22449,
"only_in_oracle_examples": [
"10:135332149_CNV_CYP2E1",
"10:135332539_CNV_CYP2E1",
"10:135332749_CNV_CYP2E1",
"10:135333169_CNV_CYP2E1",
"10:135333379_CNV_CYP2E1",
"10:135333589_CNV_CYP2E1",
"10:135333799_CNV_CYP2E1",
"10:135334009_CNV_CYP2E1",
"10:135334009_CNV_CYP2E1_ilmndup1",
"10:135334219_CNV_CYP2E1",
"10:135334429_CNV_CYP2E1",
"10:135334639_CNV_CYP2E1",
"10:135334849_CNV_CYP2E1",
"10:135335059_CNV_CYP2E1",
"10:135335569_CNV_CYP2E1",
"10:135335569_CNV_CYP2E1_ilmndup1",
"10:135335869_CNV_CYP2E1",
"10:135335869_CNV_CYP2E1_ilmndup1",
"10:135336079_CNV_CYP2E1",
"10:135336289_CNV_CYP2E1"
],
"categories": {
"grouping_differs": 6424,
"match_called": 23656010,
"match_missing": 102077,
"ours_missing_haploid_Y": 9,
"ours_missing_het_in_haploid": 16,
"representation_diff": 5184
},
"examples": {
"grouping_differs": [
[
"207895980019_R14C03",
"ilmnseq_rs2013249.2_F2BT",
[
"1",
"19287570",
"G",
"T,C",
"0/2"
],
"0/0",
[
"1",
"19287570",
"G",
"T"
]
],
[
"207895980019_R14C03",
"ilmnseq_rs201615754.1_F2BT",
[
"1",
"97515784",
"C",
"A,T",
"0/1"
],
"./.",
[
"1",
"97515784",
"C",
"A"
]
],
[
"207895980019_R14C03",
"ilmnseq_rs201615754.2_F2BT",
[
"1",
"97515784",
"C",
"A,T",
"0/1"
],
"0/0",
[
"1",
"97515784",
"C",
"T"
]
],
[
"207895980019_R14C03",
"rs201615754",
[
"1",
"97515784",
"C",
"A,T",
"0/1"
],
"./.",
[
"1",
"97515784",
"C",
"A"
]
],
[
"207895980019_R14C03",
"ilmnseq_rs168107.1_ilmnrev_F2BT",
[
"1",
"108937356",
"G",
"C,T",
"./."
],
"0/1",
[
"1",
"108937356",
"G",
"C"
]
],
[
"207895980019_R14C03",
"ilmnseq_rs168107.2_ilmnfwd_F2BT",
[
"1",
"108937356",
"G",
"C,T",
"./."
],
"0/1",
[
"1",
"108937356",
"G",
"T"
]
],
[
"207895980019_R14C03",
"ilmnseq_rs168107.2_ilmnrev_F2BT",
[
"1",
"108937356",
"G",
"C,T",
"./."
],
"0/1",
[
"1",
"108937356",
"G",
"T"
]
],
[
"207895980019_R14C03",
"ilmnseq_rs4648276.2_F2BT",
[
"1",
"186676356",
"A",
"C,G",
"./."
],
"1/1",
[
"1",
"186676356",
"A",
"G"
]
],
[
"207895980019_R14C03",
"ilmnseq_rs4648276_ilmnfwd_F2BT",
[
"1",
"186676356",
"A",
"C,G",
"./."
],
"1/1",
[
"1",
"186676356",
"A",
"G"
]
],
[
"207895980019_R14C03",
"rs4648276",
[
"1",
"186676356",
"A",
"C,G",
"./."
],
"1/1",
[
"1",
"186676356",
"A",
"G"
]
],
[
"207895980019_R14C03",
"ilmnseq_rs1819741.1_F2BT",
[
"1",
"192815708",
"T",
"A,C",
"0/2"
],
"0/0",
[
"1",
"192815708",
"T",
"A"
]
],
[
"207895980019_R14C03",
"ilmnseq_rs2777511.1_ilmnfwd_F2BT",
[
"10",
"33785635",
"G",
"A,T",
"./."
],
"0/0",
[
"10",
"33785635",
"G",
"A"
]
],
[
"207895980019_R14C03",
"ilmnseq_rs2777511.1_ilmnrev_F2BT",
[
"10",
"33785635",
"G",
"A,T",
"./."
],
"1/1",
[
"10",
"33785635",
"G",
"A"
]
],
[
"207895980019_R14C03",
"ilmnseq_rs2777511.2_ilmnrev_F2BT",
[
"10",
"33785635",
"G",
"A,T",
"./."
],
"0/0",
[
"10",
"33785635",
"G",
"T"
]
],
[
"207895980019_R14C03",
"ilmnseq_rs11819745.2_F2BT",
[
"10",
"37501484",
"G",
"A,T",
"0/1"
],
"0/0",
[
"10",
"37501484",
"G",
"T"
]
],
[
"207895980019_R14C03",
"ilmnseq_rs7091672.2_F2BT",
[
"10",
"118836909",
"T",
"C,G",
"./."
],
"1/1",
[
"10",
"118836909",
"T",
"C"
]
],
[
"207895980019_R14C03",
"ilmnseq_rs7091672.3_F2BT",
[
"10",
"118836909",
"T",
"C,G",
"./."
],
"0/0",
[
"10",
"118836909",
"T",
"G"
]
],
[
"207895980019_R14C03",
"ilmnseq_rs7091672_ilmnfwd_F2BT",
[
"10",
"118836909",
"T",
"C,G",
"./."
],
"1/1",
[
"10",
"118836909",
"T",
"C"
]
],
[
"207895980019_R14C03",
"rs7091672",
[
"10",
"118836909",
"T",
"C,G",
"./."
],
"1/1",
[
"10",
"118836909",
"T",
"C"
]
],
[
"207895980019_R14C03",
"ilmnseq_rs1219648.2_F2BT",
[
"10",
"121586676",
"A",
"G,T",
"0/1"
],
"0/0",
[
"10",
"121586676",
"A",
"T"
]
]
],
"representation_diff": [
[
"IlmnSeq_rs3215400",
[
"1",
"20589096",
"TC",
"T"
],
[
"1",
"20589098",
"D",
"I"
]
],
[
"ilmnseq_rs3215400_ilmnrev",
[
"1",
"20589096",
"TC",
"T"
],
[
"1",
"20589098",
"D",
"I"
]
],
[
"rs3215400",
[
"1",
"20589096",
"TC",
"T"
],
[
"1",
"20589098",
"D",
"I"
]
],
[
"ilmnseq_rs61697860_ilmnfwd",
[
"1",
"78303099",
"TG",
"T"
],
[
"1",
"78303101",
"D",
"I"
]
],
[
"ilmnseq_rs35219756_ilmnrev_F2BTindel",
[
"1",
"78392093",
"AT",
"A"
],
[
"1",
"78392095",
"I",
"D"
]
],
[
"ilmnseq_rs35081652_ilmnfwd",
[
"1",
"78411336",
"AC",
"A"
],
[
"1",
"78411338",
"D",
"I"
]
],
[
"IlmnSeq_rs72549303_IlmnFWD",
[
"1",
"97450065",
"TG",
"T"
],
[
"1",
"97450067",
"D",
"I"
]
],
[
"IlmnSeq_rs72549303_IlmnREV",
[
"1",
"97450065",
"TG",
"T"
],
[
"1",
"97450067",
"D",
"I"
]
],
[
"ilmnseq_rs72549303",
[
"1",
"97450065",
"TG",
"T"
],
[
"1",
"97450067",
"D",
"I"
]
],
[
"ilmnseq_rs72549303_ilmndup1",
[
"1",
"97450065",
"TG",
"T"
],
[
"1",
"97450067",
"D",
"I"
]
],
[
"ilmnseq_rs72549303_ilmnfwd_deg3a2b0",
[
"1",
"97450065",
"TG",
"T"
],
[
"1",
"97450067",
"D",
"I"
]
],
[
"ilmnseq_rs72549303_ilmnrev_deg3a1b0",
[
"1",
"97450065",
"TG",
"T"
],
[
"1",
"97450067",
"D",
"I"
]
],
[
"ilmnseq_rs1184321568",
[
"1",
"97593250",
"CT",
"C"
],
[
"1",
"97593252",
"I",
"D"
]
],
[
"ilmnseq_rs1184321568_ilmnfwd",
[
"1",
"97593250",
"CT",
"C"
],
[
"1",
"97593252",
"I",
"D"
]
],
[
"ilmnseq_rs1184321568_ilmnfwd_deg3a1b0",
[
"1",
"97593250",
"CT",
"C"
],
[
"1",
"97593252",
"I",
"D"
]
],
[
"ilmnseq_rs1184321568_ilmnrev",
[
"1",
"97593250",
"CT",
"C"
],
[
"1",
"97593252",
"I",
"D"
]
],
[
"ilmnseq_rs1184321568_ilmnrev_deg3a1b0",
[
"1",
"97593250",
"CT",
"C"
],
[
"1",
"97593252",
"I",
"D"
]
],
[
"IlmnSeq_rs72549315_IlmnFWD",
[
"1",
"147208902",
"CT",
"C"
],
[
"1",
"147208904",
"I",
"D"
]
],
[
"ilmnseq_rs72549315_ilmnfwd_ilmndup1",
[
"1",
"147208902",
"CT",
"C"
],
[
"1",
"147208904",
"I",
"D"
]
],
[
"ilmnseq_rs72549315_ilmnfwd_ilmndup2",
[
"1",
"147208902",
"CT",
"C"
],
[
"1",
"147208904",
"I",
"D"
]
]
],
"ours_missing_haploid_Y": [
[
"207895980019_R11C02",
"rs5018209",
[
"Y",
"19428214",
"G",
"C",
"."
],
"0/0",
[
"Y",
"19428214",
"G",
"C"
]
],
[
"207895980035_R10C01",
"rs186564287",
[
"Y",
"14081208",
"A",
"G",
"."
],
"1/1",
[
"Y",
"14081208",
"A",
"G"
]
],
[
"207895980019_R12C01",
"ilmnseq_rs538240449",
[
"Y",
"12030916",
"C",
"T",
"."
],
"0/0",
[
"Y",
"12030916",
"C",
"T"
]
],
[
"207895980019_R12C01",
"ilmnseq_rs537620655",
[
"Y",
"13331090",
"T",
"C",
"."
],
"1/1",
[
"Y",
"13331090",
"T",
"C"
]
],
[
"207895980035_R04C03",
"rs13304158",
[
"Y",
"9957467",
"A",
"T",
"."
],
"0/0",
[
"Y",
"9957467",
"A",
"T"
]
],
[
"207895980035_R04C03",
"exm1667692",
[
"Y",
"12816261",
"A",
"G",
"."
],
"1/1",
[
"Y",
"12816261",
"A",
"G"
]
],
[
"207895980019_R03C01",
"rs373082162",
[
"Y",
"19466559",
"T",
"G",
"."
],
"1/1",
[
"Y",
"19466559",
"T",
"G"
]
],
[
"207895980019_R04C01",
"rs4020596",
[
"Y",
"5680808",
"T",
"G",
"."
],
"1/1",
[
"Y",
"5680808",
"T",
"G"
]
],
[
"207895980019_R03C02",
"JHU_Y.14692226",
[
"Y",
"12580293",
"T",
"C",
"."
],
"0/0",
[
"Y",
"12580293",
"T",
"C"
]
]
],
"ours_missing_het_in_haploid": [
[
"207895980035_R13C03",
"rs5979572",
[
"X",
"7467632",
"A",
"G",
"."
],
"0/1",
[
"X",
"7467632",
"A",
"G"
]
],
[
"207895980035_R13C03",
"rs7887088",
[
"X",
"7478861",
"T",
"C",
"."
],
"0/1",
[
"X",
"7478861",
"T",
"C"
]
],
[
"207895980035_R13C03",
"rs146250304",
[
"X",
"68391913",
"C",
"T",
"."
],
"0/1",
[
"X",
"68391913",
"C",
"T"
]
],
[
"207895980019_R06C01",
"rs138003892",
[
"X",
"33006670",
"T",
"G",
"."
],
"0/1",
[
"X",
"33006670",
"T",
"G"
]
],
[
"207895980035_R09C03",
"rs28602676",
[
"MT",
"2690",
"G",
"A",
"."
],
"0/1",
[
"MT",
"2690",
"G",
"A"
]
],
[
"207895980019_R15C02",
"rs1606778",
[
"X",
"79535086",
"C",
"T",
"."
],
"0/1",
[
"X",
"79535086",
"C",
"T"
]
],
[
"207895980035_R14C01",
"rs104894858",
[
"X",
"120442599",
"C",
"T",
"."
],
"0/1",
[
"X",
"120442599",
"C",
"T"
]
],
[
"207895980035_R03C03",
"JHU_X.22234615",
[
"X",
"22216499",
"A",
"T",
"."
],
"0/1",
[
"X",
"22216499",
"A",
"T"
]
],
[
"207895980019_R09C03",
"rs9786566",
[
"Y",
"7044951",
"G",
"T",
"."
],
"0/1",
[
"Y",
"7044951",
"G",
"T"
]
],
[
"207895980035_R12C03",
"rs148519285",
[
"X",
"20830034",
"A",
"G",
"."
],
"0/1",
[
"X",
"20830034",
"A",
"G"
]
],
[
"207895980035_R11C03",
"ilmnseq_rs111298280",
[
"X",
"91616889",
"G",
"A",
"."
],
"0/1",
[
"X",
"91616889",
"G",
"A"
]
],
[
"207895980035_R11C03",
"ilmnseq_chrX:154532408_ilmnfwd_ilmndup3",
[
"X",
"154532408",
"T",
"C",
"."
],
"0/1",
[
"X",
"154532408",
"T",
"C"
]
],
[
"207895980042_R15C02",
"ilmnseq_rs553518378",
[
"Y",
"15734824",
"C",
"A",
"."
],
"0/1",
[
"Y",
"15734824",
"C",
"A"
]
],
[
"207895980035_R05C03",
"rs12396137",
[
"X",
"7462384",
"A",
"G",
"."
],
"0/1",
[
"X",
"7462384",
"A",
"G"
]
],
[
"207895980035_R05C03",
"rs4830772",
[
"X",
"7475195",
"T",
"C",
"."
],
"0/1",
[
"X",
"7475195",
"T",
"C"
]
],
[
"207895980035_R05C03",
"rs146250304",
[
"X",
"68391913",
"C",
"T",
"."
],
"0/1",
[
"X",
"68391913",
"C",
"T"
]
]
]
},
"unexplained": 0
}