{
  "schema_version": "1.0",
  "use_cases": [
    {
      "id": "use-case-protein-stability",
      "slug": "protein-variant-stability",
      "title": "Assess methods for protein stability experiments",
      "question": "What evidence supports ranking protein substitutions by folding stability, and what must be validated before choosing a method?",
      "area": "proteins-complexes",
      "contexts": [
        "research",
        "clinical_research"
      ],
      "search_terms": [
        "protein variant",
        "amino acid substitution",
        "folding stability",
        "protein engineering",
        "proteolysis",
        "AMFR",
        "ProteinGym",
        "ESM-2",
        "EVmutation",
        "EVCouplings",
        "pathogenicity"
      ],
      "intended_users": [
        "Experimental researchers selecting variants for protein stability experiments",
        "Computational researchers evaluating sequence-based variant rankings",
        "Translational researchers checking whether stability evidence answers a disease question"
      ],
      "decision": "Inspect the available AMFR assay results as a narrow example, then identify the missing singles-only comparison and validation required for the target protein and endpoint.",
      "inputs": [
        "Wild-type protein sequence and amino acid substitutions",
        "A defined construct and experimental stability endpoint; alignment-derived methods additionally require a traceable alignment and model"
      ],
      "output": "Exact existing AMFR configurations, their assay scope and unresolved comparisons; no universal model ranking or pathogenicity prediction.",
      "setting": "The current evidence is limited to the 47-residue AMFR_HUMAN_Tsuboyama_2023_4G3O construct in ProteinGym v1.3. Its cDNA-display proteolysis assay infers folding stability. Completed evaluations cover 2,972 variants: 820 single and 2,152 double substitutions.",
      "exclusions": [
        "Whole-protein function, cellular activity, organismal fitness and clinical pathogenicity",
        "Generalisation to other proteins, other ESM-2 checkpoints or the full ProteinGym track",
        "Treating the existing mixed cohort as a completed matched single-substitution comparison"
      ],
      "clinical_scope": "Clinical applicability is not established. Stability of this short experimental construct is not evidence of clinical pathogenicity or suitability for diagnosis or treatment.",
      "evidence_gaps": [
        "The existing ESM-2 and fixed-seed random results use separate protocols. They are displayed separately and do not establish a matched cross-protocol winner.",
        "No uncertainty intervals or seed-variability estimates are recorded for these completed evaluations. One random ranking is not a chance-performance interval.",
        "The proposed ESM-2 versus EVCouplings site-independent and EVmutation comparison targets a frozen set of covered single substitutions. It has no completed results.",
        "The planned comparison still needs a separate execution decision, a traceable real evolutionary model, the full-model adapter, resource logging, frozen populations and tested analysis code. Planning resource ceilings are not measured requirements.",
        "The recorded ESM-2 timer excludes checkpoint loading, preparation and metrics; peak memory is unreported. It is not an end-to-end or cross-model speed comparison.",
        "The existing AMFR protocols have no reviewed direct task-membership link. The mappings therefore reference the protocols only and do not infer membership from the ProteinGym suite.",
        "Assay bytes were hashed locally without independent authentication against an upstream published checksum. Training overlap, independent reproduction and human scientific review remain unresolved."
      ],
      "citations": [
        {
          "source_id": "profile-protocol-proteingym-reference-files-dms-substitutions-csv-a8f49801",
          "locator": "DMS_id=AMFR_HUMAN_Tsuboyama_2023_4G3O: seq_len, selection_assay, selection_type, raw_DMS_phenotype_name, DMS_number_single_mutants, DMS_number_multiple_mutants"
        },
        {
          "source_id": "rewire-local-20260920-source-proteingym-esm2",
          "locator": "/coverage; /execution; /provenance; /protocol_results"
        },
        {
          "source_id": "rewire-local-20260921-source-proteingym-random",
          "locator": "/coverage; /model_configuration; /protocol_results"
        },
        {
          "source_id": "use-case-source-amfr-pilot-plan-194a78b",
          "locator": "Status; Question; Task and data; Methods; Gates and execution order; Runtime and cost; Roles and review"
        }
      ],
      "review": {
        "method": "automated_source_review",
        "actor": "Codex research curation",
        "reviewed_at": "2026-09-25T15:43:22Z",
        "note": "Bounded review of pinned assay metadata, completed execution records and the planning artifact. The plan is not a result. No new model execution, human domain review, independent replication or clinical validation. Public planned-work navigation points to the exact reviewed source copy; the original private-repository link remains in source provenance."
      },
      "planned_work": [
        {
          "title": "Matched single-substitution comparison: ESM-2, site-independent model and EVmutation",
          "url": "https://benchmarks.rewire.it/omics/sources/a3208aa4537e8d28c56f68f4559299f31241c50b8d8b2b3776cba5f1718caa43.md",
          "status": "blocked",
          "reason": "Planning is complete; execution is not authorised by that plan. Gates require an execution decision, traceable evolutionary model, full-model adapter, resource logging, frozen populations and tested analysis. No measured comparison or winner is available."
        }
      ]
    },
    {
      "id": "use-case-splicing-follow-up",
      "slug": "splicing-follow-up",
      "title": "Prioritise variants for splicing experiments",
      "question": "Which evaluated configurations can inform selection of human SNVs for follow-up splicing experiments?",
      "area": "dna-genomes",
      "contexts": [
        "research",
        "clinical_research"
      ],
      "search_terms": [
        "splicing",
        "splice disruption",
        "SNV",
        "single nucleotide variant",
        "variant prioritisation",
        "exon recognition",
        "minigene",
        "patient RNA",
        "MFASS",
        "SpliceAI",
        "Pangolin"
      ],
      "intended_users": [
        "Experimental researchers selecting variants for functional follow-up",
        "Computational researchers comparing splice-effect configurations",
        "Clinical researchers investigating the limits of assay evidence"
      ],
      "decision": "Inspect the matched MFASS configurations and their limitations before selecting a method and designing validation in the intended experimental setting.",
      "inputs": [
        "Human single nucleotide variants with alleles, genome assembly and gene/transcript context",
        "The intended experimental endpoint and the number of variants that can be followed up"
      ],
      "output": "A sourced set of exact evaluated configurations and remaining validation needs; no patient-level variant classification or recommendation.",
      "setting": "MFASS measures exon recognition in an artificial minigene reporter. The matched study evaluates genomic-context SpliceAI and Pangolin configurations against this functional endpoint on a fixed held-out population.",
      "exclusions": [
        "Indels and variant types outside the reviewed human SNV protocol",
        "Patient-RNA effects, disease pathogenicity, diagnostic yield and treatment decisions",
        "Pooling the matched annotation study with historical MFASS runs using other annotations or scoring populations"
      ],
      "clinical_scope": "Clinical applicability is not established. Reporter-assay ranking does not demonstrate patient-RNA performance, pathogenicity classification or clinical yield; validation in the intended population and workflow is still needed.",
      "evidence_gaps": [
        "All four conditions scored 8,297 of 8,324 held-out variants. The same 27 exclusions comprise 23 hg19-to-hg38 assembly-orientation mismatches and four canonical-transcript-span exclusions; the latter are not established faulty variants. Missing predictions are not negative predictions.",
        "No top-100 precision difference is established; Pangolin's masked top-100 result is sensitive to the registered tie order. Precision at 100 does not transfer automatically to another follow-up capacity or prevalence.",
        "Individual-condition uncertainty intervals are not recorded. Paired-contrast intervals concern differences between conditions and must not be shown as each condition's uncertainty.",
        "The study is exploratory: prior outcomes were inspected and nine contrast intervals are unadjusted. Matching annotation does not isolate model architecture.",
        "Author confirmation of the assembly-orientation finding is not established. Human scientific review and independent replication remain outstanding.",
        "These mappings do not change the MFASS task's discovered status. A source-reviewed applicability mapping is separate from reviewing the task record."
      ],
      "citations": [
        {
          "source_id": "evidence-expansion-mfass-readme-62a93814",
          "locator": "Dataset; Limits: artificial minigene exon-recognition endpoint, not patient RNA"
        },
        {
          "source_id": "use-case-source-mfass-matched-intake-194a78b",
          "locator": "Opening paragraphs: coverage, exclusion classes, annotation, review and interpretation; Review and validation"
        },
        {
          "source_id": "rewire-mfass-matched-v1-source-report",
          "locator": "/conditions/{S0,S1,P0,P1}/coverage; /conditions/{S0,S1,P0,P1}/ties; /contrasts/{S1-S0,P1-P0,P0-S0}/paired/precision_at_capacity"
        }
      ],
      "review": {
        "method": "automated_source_review",
        "actor": "Codex research curation",
        "reviewed_at": "2026-09-25T15:28:11Z",
        "note": "Bounded review of pinned reports, protocol documentation and intake narrative. No new model execution, human domain review, independent replication or clinical validation."
      },
      "planned_work": []
    }
  ],
  "mappings": [
    {
      "id": "use-case-mapping-protein-stability-amfr-esm2",
      "use_case_id": "use-case-protein-stability",
      "lifecycle": "active",
      "revision": 1,
      "reason": "Initial bounded applicability review of the existing AMFR ESM-2 evaluation.",
      "protocol_id": "rewire-protocol-proteingym-amfr-v13",
      "evaluation_ids": [
        "rewire-local-20260920-evaluation-proteingym-esm2"
      ],
      "endpoint": "Ranking the mixed AMFR assay cohort by proteolysis-inferred folding stability using ESM-2 8M masked marginals.",
      "relevance": "proxy",
      "rationale": "This completed short-construct assay is a narrow example for assessing stability-ranking evidence. Its mixed single/double cohort does not directly answer the planned single-substitution comparison or establish transfer to another protein.",
      "constraints": [
        "One 47-residue AMFR construct and all 2,972 variants, comprising 820 singles and 2,152 doubles; no train/test split.",
        "Exact esm2_t6_8M_UR50D checkpoint, wild-type-context masked marginals summed over substituted sites, CPU, one thread; no assay labels, alignment or structure as scorer inputs.",
        "Protocol-only mapping: a direct reviewed task-membership relationship is not recorded."
      ],
      "limitations": [
        "No interval or seed-variability estimate; training overlap remains unknown and assay bytes have not been independently authenticated against an upstream checksum.",
        "Recorded inference timing excludes loading, preparation and metrics; peak memory is unreported.",
        "The site-independent and full EVmutation methods in the planned singles study have no completed comparison here.",
        "No general whole-protein, ProteinGym-wide or clinical inference; automated source review is not human scientific validation."
      ],
      "citations": [
        {
          "source_id": "rewire-local-20260920-source-proteingym-esm2",
          "locator": "/metrics; /coverage; /execution/adapter_provenance; /execution; /input_information; /provenance; /protocol_results"
        },
        {
          "source_id": "rewire-local-20260920-instructions-proteingym",
          "locator": "Data and method; Reproduce"
        },
        {
          "source_id": "profile-protocol-proteingym-reference-files-dms-substitutions-csv-a8f49801",
          "locator": "AMFR_HUMAN_Tsuboyama_2023_4G3O row: seq_len, selection_assay, raw_DMS_phenotype_name and mutant-count columns"
        },
        {
          "source_id": "use-case-source-amfr-pilot-plan-194a78b",
          "locator": "Question; Task and data; Methods; Gates and execution order; Runtime and cost"
        }
      ],
      "review": {
        "method": "automated_source_review",
        "actor": "Codex research curation",
        "reviewed_at": "2026-09-25T15:28:11Z",
        "note": "Reviewed existing measured evidence separately from the planned singles comparison. No new experiment, human domain review or clinical validation."
      },
      "evidence_sha256": "81883d91b243e8a9c958bca976ad951aa82ba5a130eff9263dc8f3a04707012e"
    },
    {
      "id": "use-case-mapping-protein-stability-amfr-random",
      "use_case_id": "use-case-protein-stability",
      "lifecycle": "active",
      "revision": 1,
      "reason": "Initial review of the separate fixed-seed random control as limited context.",
      "protocol_id": "rewire-protocol-proteingym-amfr-random-v13",
      "evaluation_ids": [
        "rewire-local-20260921-evaluation-proteingym-random"
      ],
      "endpoint": "One fixed-seed random ranking of the mixed AMFR stability cohort.",
      "relevance": "proxy",
      "rationale": "A recorded null control helps inspect the assay and evaluation procedure. It is not a biological prediction method recommendation, a chance-performance interval or a matched comparison with the separately executed ESM-2 protocol.",
      "constraints": [
        "All 2,972 AMFR variants, mixing single and double substitutions; a single fixed seed of 0.",
        "SHA256 ranking of prepared variant IDs; no biological prediction or label fitting.",
        "Protocol-only mapping; keep its evaluation and configuration separate from ESM-2 and the planned singles comparison."
      ],
      "limitations": [
        "One seed does not estimate chance variability or uncertainty. Do not subtract these separate protocol results to assert an evaluated winner.",
        "Local input hashes do not independently authenticate assay bytes against an upstream published checksum.",
        "This control supplies no pathogenicity or clinical suitability evidence; no human scientific review or independent replication is recorded."
      ],
      "citations": [
        {
          "source_id": "rewire-local-20260921-source-proteingym-random",
          "locator": "/metrics; /coverage; /model_configuration; /protocol_configuration; /provenance; /protocol_results"
        },
        {
          "source_id": "rewire-local-20260921-instructions-proteingym-random",
          "locator": "Pinned reproduction instructions and execution scope"
        },
        {
          "source_id": "use-case-source-amfr-pilot-plan-194a78b",
          "locator": "Question; Task and data; Methods (N0); Analysis populations"
        }
      ],
      "review": {
        "method": "automated_source_review",
        "actor": "Codex research curation",
        "reviewed_at": "2026-09-25T15:28:11Z",
        "note": "Reviewed as a separate one-seed control, not clinical evidence or a cross-protocol comparison."
      },
      "evidence_sha256": "2fa413430c25c90a4184be20e096c2200185e566d1690953e29bc40d55c98ddf"
    },
    {
      "id": "use-case-mapping-splicing-mfass-matched-v1",
      "use_case_id": "use-case-splicing-follow-up",
      "lifecycle": "active",
      "revision": 1,
      "reason": "Initial bounded applicability review of the matched MFASS study.",
      "protocol_id": "rewire-mfass-matched-v1-protocol",
      "task_id": "catalog-task-mfass-splice",
      "evaluation_ids": [
        "rewire-mfass-matched-v1-evaluation-s0",
        "rewire-mfass-matched-v1-evaluation-s1",
        "rewire-mfass-matched-v1-evaluation-p0",
        "rewire-mfass-matched-v1-evaluation-p1"
      ],
      "endpoint": "Ranking held-out MFASS SNVs by reporter-assay splice disruption under matched canonical annotation.",
      "relevance": "proxy",
      "rationale": "The recorded endpoint informs assay-oriented prioritisation under its declared conditions. Selecting variants for a different follow-up experiment requires transfer validation; the endpoint is not patient RNA or clinical pathogenicity.",
      "constraints": [
        "Identical scored population: 8,297 of 8,324 held-out variants, 314 scored positives and 460 groups in all four configurations.",
        "Shared GENCODE 44 canonical transcript selection and FASTA; 50-base distance; distinct SpliceAI and Pangolin masking settings.",
        "Keep historical annotation conditions and scoring populations in their existing separate comparison groups."
      ],
      "limitations": [
        "23 assembly-orientation mismatches and four canonical-transcript-span exclusions remain unscored. The latter are protocol exclusions, not established faulty variants; full-population performance is unknown.",
        "No top-100 precision difference is established and masked Pangolin is tie-sensitive. Paired contrast intervals are not individual-condition intervals.",
        "Exploratory source review only; no independent human review, replication or clinical validation. Assembly-issue author confirmation is not established."
      ],
      "citations": [
        {
          "source_id": "rewire-mfass-matched-v1-source-report",
          "locator": "/conditions/{S0,S1,P0,P1}/coverage; /conditions/{S0,S1,P0,P1}/metrics; /conditions/{S0,S1,P0,P1}/ties; /contrasts/{S1-S0,P1-P0,P0-S0}/paired/precision_at_capacity"
        },
        {
          "source_id": "rewire-mfass-matched-v1-source-manifest-v1",
          "locator": "/conditions; /distance; /resources_sha256; /code"
        },
        {
          "source_id": "rewire-mfass-matched-v1-source-exclusion-verification",
          "locator": "/exclusion_counts; /conditions; /checks"
        },
        {
          "source_id": "use-case-source-mfass-matched-intake-194a78b",
          "locator": "Opening coverage, exclusion, annotation and interpretation paragraphs; Review and validation"
        },
        {
          "source_id": "evidence-expansion-mfass-readme-62a93814",
          "locator": "Dataset; Limits"
        }
      ],
      "review": {
        "method": "automated_source_review",
        "actor": "Codex research curation",
        "reviewed_at": "2026-09-25T15:28:11Z",
        "note": "Reviewed exact configuration and population scope against pinned source bytes. Applicability remains proxy evidence; no human domain review or clinical validation."
      },
      "evidence_sha256": "c4cfbe66c30d59308fc8d2226f42720a09a6e54d2f407c7141b08e01e39c0a47"
    }
  ],
  "release_id": "2026-09-25-8af07e960e5f",
  "input_sha256": "d0c76e33f58fe8d4845cdba114d6bb6bea1920fc68c5a5e43922801c7e7ca27b"
}