{
  "status": "Qualified for frozen cross-study transfer only; not matched-protocol or independent base-model validation",
  "source": "https://figshare.com/articles/dataset/26991223",
  "paper": "https://doi.org/10.1186/s13059-023-03144-z",
  "sourceRows": 2230,
  "eligibleRows": 2230,
  "rejectedRows": 0,
  "studies": {
    "FAS": 189,
    "MST1R": 598,
    "POU1F1": 941,
    "WT1": 502
  },
  "referenceChecks": [
    {
      "gene": "FAS",
      "url": "https://api.genome.ucsc.edu/getData/sequence?genome=hg19;chrom=chr10;start=90770509;end=90770572",
      "sha256": "7b2dbfb8b1785a676ee18c70fca67d770e96c00300bb685c7b8204b9f1cb1b31",
      "rows": 189,
      "matches": 189
    },
    {
      "gene": "MST1R",
      "url": "https://api.genome.ucsc.edu/getData/sequence?genome=hg19;chrom=chr3;start=49933352;end=49933584",
      "sha256": "0a292bea7e65f21a47c903e474a85289b751c6b9c9523beb8576e3e8c660f72a",
      "rows": 598,
      "matches": 598
    },
    {
      "gene": "POU1F1",
      "url": "https://api.genome.ucsc.edu/getData/sequence?genome=hg19;chrom=chr3;start=87322396;end=87322725",
      "sha256": "ebdb4470af02eed7f3f516ddb8830d10dfa819d73f732dc438f2a03e1321d044",
      "rows": 941,
      "matches": 941
    },
    {
      "gene": "WT1",
      "url": "https://api.genome.ucsc.edu/getData/sequence?genome=hg19;chrom=chr11;start=32413477;end=32413650",
      "sha256": "db24ac5970485e59bf3c8ad1bf57845de5b916d35261a178543af1a9d2245b0c",
      "rows": 502,
      "matches": 502
    }
  ],
  "publisherMD5Verified": true,
  "externalFileSHA256": "e376bbc302d1b4af4e1bdac384af1132827466be91c9c6969d7500040e8fcf9b",
  "developmentRows": 5801,
  "developmentGroups": 324,
  "developmentExcludedRows": 327,
  "developmentGeneOverlap": [],
  "hg19PositionOverlapIncludingAdjacentBases": 0,
  "overlapScope": "Successful v2 development rows only; same-build coordinate audit conservatively checks original MFASS positions plus/minus one. Gene exclusion applied before training; pretrained network exposure remains unknown.",
  "limitations": [
    "Different assay definitions: MFASS large exon-inclusion loss vs author-defined disruption including alternate isoform gains.",
    "External hg19 MANE/exon-length scoring differs from development hg38 GENCODE44/50nt. Unmasked score columns used for both. Neural scores are published, not rerun.",
    "Only four genes/exons and selected disease-associated loci; whole-gene confidence intervals have limited resolution.",
    "SpliceAI/Pangolin training exposure to external genes was not ruled out. New local calibrators have no external gene or outcome training.",
    "Published study and example rows were inspected for qualification. No external numerical metrics were used to tune models.",
    "M3 v2 depends on Pangolin; this cannot demonstrate a standalone new sequence model is superior to Pangolin.",
    "Not a clinical pathogenicity test or patentability determination."
  ]
}