{
  "obelus_witness": "0.2-draft",
  "status": "Assembled by hand on 2026-08-31 from the records it names and checked against them on that date. The Obelus core has not yet produced any step of it.",
  "case": "CFTR-001",
  "recorded": "2026-08-31",
  "claim": {
    "submitted_genomic": "NC_000007.14:g.117559590A>G",
    "submitted_coding": "NM_000492.4:c.1519A>G",
    "claimed_consequence": "NP_000483.3:p.Ile507Val"
  },
  "challenge": {
    "applied": false,
    "alternate_base": "G",
    "submitted_reference_base": "A",
    "transcript_version": "NM_000492.4",
    "protein_claim": "p.Ile507Val",
    "sequence_source": "NCBI NC_000007.14, GRCh38.p14 Primary Assembly"
  },
  "environment": {
    "assembly": "GRCh38.p14",
    "annotation": "UCSC ncbiRefSeqSelect table downloaded 2025-08-13; checked on 2026-08-31 to reproduce NM_000492.4 byte for byte when spliced from NC_000007.14",
    "translation_table": "NCBI standard code (table 1)",
    "coordinate_convention": "HGVS g./n./c. 1-based inclusive; SPDI 0-based interbase"
  },
  "origin_vocabulary": {
    "recorded": "computed outside the core on the recorded date and written into this witness",
    "page": "recomputed by the web page from recorded values when a challenge is applied",
    "derived": "computed by the Obelus core in this run; none yet",
    "retrieved": "read from an external record on the date given"
  },
  "steps": [
    {
      "step": 1,
      "question": "Which chromosome bytes?",
      "derived_from": ["FASTA NC_000007.14, GRCh38.p14 Primary Assembly"],
      "method": "read, uppercase, GA4GH refget: SQ. + base64url(SHA-512[0..24))",
      "value": { "length": 159345973, "refget": "SQ.F-LrLMe1SRpfUZHkQmvkVKFEGaoDeHul" },
      "outcome": "Established",
      "origin": "recorded",
      "note": "digest equals the value published for NC_000007.14 in GA4GH VRS documentation",
      "comparison_record": {
        "other_distribution": "UCSC hg38 chromosomes/chr7.fa.gz",
        "other_refget": "SQ.KZ9qSyP_4fsfj3sWAH9JfhGbo5jeo6Bh",
        "exact_content_identity": "Refuted",
        "local_compatibility_over_g117559464_117559655": "Established",
        "differing_positions": [
          { "pos": 154575459, "ncbi": "R", "ucsc": "N" },
          { "pos": 154578614, "ncbi": "Y", "ucsc": "N" },
          { "pos": 154578615, "ncbi": "S", "ucsc": "N" },
          { "pos": 154578679, "ncbi": "Y", "ucsc": "N" }
        ]
      }
    },
    {
      "step": 2,
      "question": "Is the claimed reference base there?",
      "derived_from": ["g.117,559,579-117,559,601 of step-1 sequence"],
      "method": "sequence[117559590 - 1], 1-based to 0-based",
      "value": { "window": "AAGAAAATATCATCTTTGGTGTT", "base_at_117559590": "A" },
      "outcome": "Established",
      "origin": "recorded"
    },
    {
      "step": 3,
      "question": "Which exon, and where in it?",
      "derived_from": ["NM_000492.4 exon 11: g.117,559,464-117,559,655 <-> n.1,463-1,654"],
      "method": "both intervals 192 bases; offset = 117559590 - 117559464 = 126",
      "value": { "exon": 11, "offset": 126, "invariant": "genomic and transcript exon intervals are the same length (192 = 192)" },
      "outcome": "Established",
      "origin": "recorded"
    },
    {
      "step": 4,
      "question": "Which transcript base?",
      "derived_from": ["exon projection, step 3"],
      "method": "n = 1463 + 126",
      "value": { "n": 1589, "base": "A" },
      "outcome": "Established",
      "origin": "recorded"
    },
    {
      "step": 5,
      "question": "Does it match the coding claim?",
      "derived_from": ["CDS start n.71 (NM_000492.4)"],
      "method": "c = 1589 - 71 + 1",
      "value": { "c": 1519, "claimed": 1519, "agree": true },
      "outcome": "Established",
      "origin": "recorded"
    },
    {
      "step": 6,
      "question": "Which codon?",
      "derived_from": ["c.1519, step 5"],
      "method": "codon = floor((1519 - 1) / 3) + 1; remainder 0 -> first base of codon",
      "value": { "codon": 507, "position_in_codon": 1 },
      "outcome": "Established",
      "origin": "recorded"
    },
    {
      "step": 7,
      "question": "What does the edit do?",
      "derived_from": ["NM_000492.4:n.1589_1591", "NCBI translation table 1"],
      "method": "codon lookup: ATC -> Ile; GTC -> Val",
      "value": { "ref_codon": "ATC", "alt_codon": "GTC", "ref_residue": "Ile", "alt_residue": "Val", "cross_check": "NP_000483.3 residue 507 = Ile" },
      "outcome": "Established",
      "origin": "recorded"
    },
    {
      "step": 8,
      "question": "Does the claimed protein change agree?",
      "derived_from": ["claim NP_000483.3:p.Ile507Val", "step 7"],
      "method": "compare derived consequence to claim",
      "value": { "derived": "NP_000483.3:p.(Ile507Val)", "claimed": "NP_000483.3:p.Ile507Val", "agree": true },
      "outcome": "Established",
      "origin": "recorded",
      "qualification": "parentheses are data: the consequence is predicted from nucleic acid under table 1; no RNA or protein experiment was consulted. Observation: not tested."
    }
  ],
  "imported": {
    "clinvar": {
      "record": "VCV000188863.26",
      "aggregate_germline_classification": "Benign/Likely benign",
      "review_status": "criteria provided, multiple submitters, no conflicts",
      "most_recent_contributing_evaluation": "2025-12-21",
      "scv_count": 6,
      "rcv_count": 2,
      "retrieved": "2026-08-31",
      "note": "a versioned aggregate of human assertions, carried with its source; never recomputed here and never blended into the molecular chain"
    },
    "gnomad_v4_exomes": {
      "id": "7-117559590-A-G",
      "ac": 160,
      "an": 1460592,
      "retrieved": "2026-08-31",
      "note": "allele count and allele number are the recorded values; a frequency is a ratio of them and is derived where it is displayed"
    }
  },
  "replay": "obelus replay i507v.witness.json (planned, not yet implemented)"
}