{
  "date": "2026-10-13",
  "headline": "New M4 lead found; neither endpoint has a qualified fresh holdout yet.",
  "status": "Qualification audit complete for this search; no new accuracy benchmark run",
  "qualifiedFreshHoldouts": 0,
  "benchmarkRun": false,
  "newOutcomeTablesOpened": false,
  "metrics": null,
  "scope": "Metadata and methods search only. Catalogue totals overlap and are not counts of independent eligible studies. Search results are bounded by indexing and public availability; zero qualified datasets does not prove none exist.",
  "catalogues": [
    {
      "name": "NCBI GEO \u00b7 human UPF1 series",
      "count": 101,
      "unit": "series records",
      "query": "UPF1[All Fields] AND \"Homo sapiens\"[Organism] AND gse[Entry Type]",
      "source": "https://www.ncbi.nlm.nih.gov/gds/?term=UPF1+Homo+sapiens"
    },
    {
      "name": "ENA \u00b7 human UPF1 title search",
      "count": 972,
      "unit": "run records across 84 project identifiers",
      "query": "tax_eq(9606) AND (study_title=\"*UPF1*\" OR experiment_title=\"*UPF1*\")",
      "source": "https://www.ebi.ac.uk/ena/browser/text-search?query=UPF1"
    }
  ],
  "cases": [
    {
      "id": "jackson",
      "model": "M4",
      "name": "Jackson-Jones 2021 \u00b7 missing nascent RNA",
      "status": "Not located in the checked public repositories",
      "decision": "unavailable",
      "source": "https://era.ed.ac.uk/handle/1842/37947",
      "evidence": "The thesis repository contains one original attachment: the thesis PDF. Its metadata and file inventory expose no count matrix. Edinburgh DataShare returned no matches for the author/NMD query. The six GEO author-name matches include GSE152435/6/7 and three unrelated mouse studies; the relevant deposit lists total and subcellular RNA, not the missing nascent fraction.",
      "needed": "Nascent and matched total RNA count matrices, sample-to-file map, labeling/normalization metadata and accession lineage. No restricted HeLa genomic variant data are needed."
    },
    {
      "id": "gse276918",
      "model": "M4",
      "name": "GSE276918 \u00b7 newly identified human decay time course",
      "status": "Promising alternative; metadata conflict blocks qualification",
      "decision": "blocked",
      "source": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE276918",
      "evidence": "A separate Yunnan University deposit lists human HCT116 control/UPF1 time courses at 0, 4, 8 and 12 hours with three replicates. Six UPF1 samples have conflicting time labels: 4h titles versus I8 file descriptions, and 8h titles versus I4 descriptions. The series summary names alpha-amanitin, whereas its design names actinomycin D. Exact depletion duration and matched control assignment also need clarification.",
      "needed": "An authoritative corrected sample sheet, inhibitor identity, depletion/control timing and spike-in normalization information. Confirm sample lineage and read identities before qualification. Do not choose a time assignment by whichever gives a better model score."
    },
    {
      "id": "gse143301",
      "model": "M5",
      "name": "GSE143301 \u00b7 UPF1 RNA without UPF1 RPF",
      "status": "Excluded from UPF1 TE-response benchmark",
      "decision": "excluded",
      "source": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE143301",
      "evidence": "All 21 sample metadata records were checked. The 12 RPF entries cover control and ABCE1 depletion; three UPF1-depleted entries are total RNA only. Sequencing lanes are not additional biological replicates.",
      "needed": "A genuinely matched, replicated control/UPF1 RNA-plus-RPF experiment. ABCE1 depletion and ribosomal-RNA depletion (RiboMinus) are not substitutes."
    },
    {
      "id": "nm",
      "model": "M5",
      "name": "PRJEB80386 / E-MTAB-13837_2",
      "status": "Already-used NMDRHT study family",
      "decision": "reused",
      "source": "https://www.ebi.ac.uk/ena/browser/view/PRJEB80386",
      "evidence": "The ENA project record explicitly maps this human UPF1 Ribo-Seq deposit to E-MTAB-13837_2. Its project description and publication lineage identify the Boehm NMDRHT experiments already used in model development. A different archive accession does not make a fresh study.",
      "needed": "A separate study family with eligible RNA/RPF conditions; no recycled NMDRHT accession."
    },
    {
      "id": "tani",
      "model": "M4",
      "name": "PRJDB2542 / DRP000622",
      "status": "Already-used Tani 2012 study family",
      "decision": "reused",
      "source": "https://www.ebi.ac.uk/ena/browser/view/PRJDB2542",
      "evidence": "The project title matches the Tani 2012 BRIC-seq study already used through its reprocessed results. The archive contains 25 runs, including siUPF1 and control time courses. Its later archive release date does not establish a new experiment.",
      "needed": "Independent biological measurements, not another deposit or reanalysis of the same experiment."
    }
  ],
  "timeConflicts": [
    {
      "accession": "GSM8508966",
      "title": "HCT116-UPF1,4h-1",
      "fileDescription": "I8-1_UPF1_1.fq.gz"
    },
    {
      "accession": "GSM8508967",
      "title": "HCT116-UPF1,4h-2",
      "fileDescription": "I8-2_UPF1_1.fq.gz"
    },
    {
      "accession": "GSM8508968",
      "title": "HCT116-UPF1,4h-3",
      "fileDescription": "I8-3_UPF1_1.fq.gz"
    },
    {
      "accession": "GSM8508969",
      "title": "HCT116-UPF1,8h-1",
      "fileDescription": "I4-1_UPF1_1.fq.gz"
    },
    {
      "accession": "GSM8508970",
      "title": "HCT116-UPF1,8h-2",
      "fileDescription": "I4-2_UPF1_1.fq.gz"
    },
    {
      "accession": "GSM8508971",
      "title": "HCT116-UPF1,8h-3",
      "fileDescription": "I4-3_UPF1_1.fq.gz"
    }
  ],
  "benchmarkGate": [
    "Resolve specimen/condition/time labels and normalization before estimating targets.",
    "Verify independent study/sample lineage, eligible human response endpoint and adequate biological replication.",
    "Freeze cohort rules, target estimator and model/preprocessing hashes before opening new numerical outcomes.",
    "Evaluate the fixed candidate, ExtraTrees, ridge and training median on identical rows; report all results, coverage, paired intervals and limitations. No holdout tuning or selection of a winning subgroup."
  ],
  "nextAction": "Obtain the missing Jackson-Jones nascent matrix or corrected GSE276918 sample metadata for M4. M5 still needs a separate replicated human UPF1 RNA/RPF study. The two downloadable requests are prepared but have not been sent.",
  "limitations": [
    "GSE276918 has the relevant assay in principle, but metadata conflicts prevent a defensible decay-rate fit. Its outcome count table remains unopened.",
    "Metadata lineage checks are preliminary; no raw-read identity audit or fresh-test power assessment has been completed for GSE276918.",
    "Public metadata can omit experiments or use unexpected terms. ENA and GEO results overlap; RiboMinus and RIP-seq must not be counted as RPF.",
    "Elicit API access was unavailable for this account. Direct GEO, ENA and Edinburgh repository searches were used instead."
  ],
  "checkpointHashes": {
    "backend/models/m4-reconciled-response-v4/reconciled_v4.joblib": "2031b2026f22bfd6c6dbb2f655c0033955788afecf84d9c435339928866a787a",
    "backend/models/m4-reconciled-response-v4/ExtraTrees.joblib": "de7e31e43298f1276e67c2aa6e19df6413afc108353d84ea1497dda6ab2bea63",
    "backend/models/m4-reconciled-response-v4/ridge.joblib": "8492bd0b1b25112a6a817d8a4c7831d6385e23811c146d093ef76068620eae8f",
    "backend/models/m5-reconciled-response-v4/reconciled_v4.joblib": "8de9d75816d11b17cd03a0988fb4cc1b44cf5958dc01750afa60c05d76db3aee",
    "backend/models/m5-reconciled-response-v4/ExtraTrees.joblib": "48cc22c7316e546c4a294fc016bceac8b643be47a50139b4066292e59cca00fc",
    "backend/models/m5-reconciled-response-v4/ridge.joblib": "65d3ab7c933060c0198ab0388a85915a2dd904f27d56421d35721065b403370e"
  }
}