{
  "registry_schema": "nmd-vcell-source-recovery/1.0",
  "recovery_id": "RECOVERY:GSE293514:IDENTITY_ARTIFACTS:1.0",
  "object_type": "SOURCE_IDENTITY_RECOVERY_PACKAGE",
  "lifecycle_status": "AUTHOR_CONTACT_OR_ARCHIVE_RECOVERY_REQUIRED",
  "resource_release": "v1.2.0-measured-dmd-evidence",
  "evidence_freeze": "2026-08-03",
  "interface_build": "EA-20260817-57",
  "checked_at": "2026-08-09",
  "dataset_id": "GSE293514",
  "accession": "GSE293514",
  "source_url": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE293514",
  "public_source_inventory": {
    "checked_at": "2026-08-09",
    "availability_state": "PUBLIC_MATRIX_AND_METADATA_DOWNLOADABLE_GUIDE_IDENTITY_NOT_PUBLIC",
    "public_files": [
      {
        "filename": "GSE293514_count_matrix.mtx.gz",
        "file_type": "MTX",
        "reported_size": "3.7 GB",
        "official_url": "https://ftp.ncbi.nlm.nih.gov/geo/series/GSE293nnn/GSE293514/suppl/GSE293514_count_matrix.mtx.gz",
        "local_state": "NOT_DOWNLOADED_FULL_MATRIX"
      },
      {
        "filename": "GSE293514_cell_metadata.csv.gz",
        "file_type": "CSV",
        "reported_size": "36.3 MB",
        "official_url": "https://ftp.ncbi.nlm.nih.gov/geo/series/GSE293nnn/GSE293514/suppl/GSE293514_cell_metadata.csv.gz",
        "local_state": "LOCAL_METADATA_PRESENT_GUIDE_FIELDS_ABSENT"
      },
      {
        "filename": "GSE293514_7human_myoblast_tpm.csv.gz",
        "file_type": "CSV",
        "reported_size": "5.1 MB",
        "official_url": "https://ftp.ncbi.nlm.nih.gov/geo/series/GSE293nnn/GSE293514/suppl/GSE293514_7human_myoblast_tpm.csv.gz",
        "local_state": "LOCAL_PARTIAL_EXPORT_PRESENT"
      },
      {
        "filename": "GSE293514_METTL3_count.csv.gz",
        "file_type": "CSV",
        "reported_size": "782.6 KB",
        "official_url": "https://ftp.ncbi.nlm.nih.gov/geo/series/GSE293nnn/GSE293514/suppl/GSE293514_METTL3_count.csv.gz",
        "local_state": "NOT_DOWNLOADED"
      }
    ],
    "source_gap": "Public matrix and 12-column metadata are available, but guide-to-cell identity, author-ordered feature mapping and processing provenance are not supplied by the listed public files."
  },
  "current_state": {
    "deposited_metadata_columns": 12,
    "guide_columns_found": [],
    "matrix_feature_columns": 62711,
    "public_feature_inventory_rows": 62710,
    "feature_identity_reconciled": false,
    "guide_to_cell_identity_reconciled": false,
    "biological_transfer": "BLOCKED",
    "current_deposited_objects": [
      {
        "role": "deposited_cell_metadata",
        "path": "neuromuscular_virtual_cell/data/external/GSE293514/GSE293514_cell_metadata.csv.gz",
        "state": "LOCAL_PARTIAL_OR_SOURCE_MATERIAL",
        "size_bytes": 38055924,
        "sha256": "188876187253170b26a9c73f8bd4bafd710ff9aaccdc901a6a3a815c5e3bad01"
      },
      {
        "role": "partial_expression_export",
        "path": "neuromuscular_virtual_cell/data/external/GSE293514/raw/GSE293514_7human_myoblast_tpm.csv.gz.partial",
        "state": "LOCAL_PARTIAL_OR_SOURCE_MATERIAL",
        "size_bytes": 151601,
        "sha256": "c9d00f8b59bbe3fa33c8366a9a525584c6fe77f1e15c460783a5081edcf5cf69"
      },
      {
        "role": "official_supplementary_workbook_1",
        "path": "neuromuscular_virtual_cell/data/external/GSE293514/raw/Supplementary_Data_1_human_myogenesis_signatures.xlsx",
        "state": "LOCAL_PARTIAL_OR_SOURCE_MATERIAL",
        "size_bytes": 220485,
        "sha256": "e539f9212042cb3cab40a8458dfea2669093d5a5c4b0f64fc550beed2f35dbaa"
      },
      {
        "role": "official_supplementary_workbook_2",
        "path": "neuromuscular_virtual_cell/data/external/GSE293514/raw/Supplementary_Data_2_MyoCRISPR_library.xlsx",
        "state": "LOCAL_PARTIAL_OR_SOURCE_MATERIAL",
        "size_bytes": 988152,
        "sha256": "362806fb11b2798733bb54f8f34b4454f0870aa2de4e487ce7e5aebd20d3ee82"
      },
      {
        "role": "official_supplementary_workbook_3",
        "path": "neuromuscular_virtual_cell/data/external/GSE293514/raw/Supplementary_Data_3_fitness_depletion_hits.xlsx",
        "state": "LOCAL_PARTIAL_OR_SOURCE_MATERIAL",
        "size_bytes": 117046,
        "sha256": "94bf24a63e2740402a56e313c2e8335ddd45b32d8ad0c43fe34d7d95893b1267"
      },
      {
        "role": "official_supplementary_workbook_4",
        "path": "neuromuscular_virtual_cell/data/external/GSE293514/raw/Supplementary_Data_4_fitness_enrichment_hits.xlsx",
        "state": "LOCAL_PARTIAL_OR_SOURCE_MATERIAL",
        "size_bytes": 19628,
        "sha256": "75afb7b025927e1c42bbed8776c13e6a549e792e72a2dc34e2b896c30f12de07"
      },
      {
        "role": "official_supplementary_workbook_5",
        "path": "neuromuscular_virtual_cell/data/external/GSE293514/raw/Supplementary_Data_5_fusion_hits.xlsx",
        "state": "LOCAL_PARTIAL_OR_SOURCE_MATERIAL",
        "size_bytes": 774760,
        "sha256": "b362439cbec443265aa157c4630a9721d553d9d687fee1e7d1a5eed1374467e2"
      },
      {
        "role": "official_supplementary_workbook_6",
        "path": "neuromuscular_virtual_cell/data/external/GSE293514/raw/Supplementary_Data_6_individual_validation.xlsx",
        "state": "LOCAL_PARTIAL_OR_SOURCE_MATERIAL",
        "size_bytes": 15603,
        "sha256": "c3d425e8d577cf4fb7bfdf26591c74a540b98aac005a521624fe56aee4e5fea6"
      },
      {
        "role": "official_supplementary_workbook_7",
        "path": "neuromuscular_virtual_cell/data/external/GSE293514/raw/Supplementary_Data_7_disease_mouse_phenotype_hits.xlsx",
        "state": "LOCAL_PARTIAL_OR_SOURCE_MATERIAL",
        "size_bytes": 27647,
        "sha256": "31b7f8322a8b2a3c2d012ed28b499819f171b414072ace42e06e6e5e7f6dbbe1"
      },
      {
        "role": "official_supplementary_workbook_8",
        "path": "neuromuscular_virtual_cell/data/external/GSE293514/raw/Supplementary_Data_8_cluster_markers.xlsx",
        "state": "LOCAL_PARTIAL_OR_SOURCE_MATERIAL",
        "size_bytes": 16580240,
        "sha256": "e865b1c0dd062381d4e048e42fce1ceed935d2bb8d35dbb7de4ecda4671ce1e6"
      },
      {
        "role": "official_supplementary_workbook_9",
        "path": "neuromuscular_virtual_cell/data/external/GSE293514/raw/Supplementary_Data_9_myogenesis_signature.xlsx",
        "state": "LOCAL_PARTIAL_OR_SOURCE_MATERIAL",
        "size_bytes": 29176,
        "sha256": "f793c02d54d0c5cf24e475d8fc2ac94a8e9cf3b8e027780af0ac6282ea348823"
      }
    ]
  },
  "requested_artifacts": [
    {
      "artifact_id": "all_genes",
      "filename": "all_genes.csv",
      "purpose": "Exact feature row/column order used with count_matrix.mtx",
      "required_fields": [
        "feature_index",
        "ensembl_id",
        "gene_symbol",
        "reference_build",
        "ensembl_release"
      ],
      "acceptance": "Feature count and ordered IDs reconcile exactly with the matrix; any one-column offset fails the gate."
    },
    {
      "artifact_id": "cell_metadata",
      "filename": "cell_metadata_2000_new.csv",
      "purpose": "Exact author-processed cell, sample and guide identity object",
      "required_fields": [
        "barcode",
        "sample_2",
        "guide_infect",
        "guide3",
        "guide4",
        "guide_type",
        "AKAcluster",
        "sig_group",
        "sig_group2",
        "AKAcluster2",
        "human_disease"
      ],
      "acceptance": "All matrix barcodes are conserved and guide fields are populated or explicitly marked non-targeting/unassigned."
    },
    {
      "artifact_id": "guide_reference",
      "filename": "final_guide_reference.csv",
      "purpose": "Guide sequence, target identity and control definitions",
      "required_fields": [
        "guide_id",
        "guide_sequence",
        "target_gene",
        "guide_type",
        "control_class",
        "positive_control_rule"
      ],
      "acceptance": "MYOD/MYMK positive-control rules, non-targeting controls and duplicate-guide rules are explicit."
    },
    {
      "artifact_id": "run_mapping",
      "filename": "cropseq_run_barcode_mapping.csv",
      "purpose": "Mapping between eight guide-only runs, transcriptome sublibraries, Parse barcode keys and final bc_wells IDs",
      "required_fields": [
        "run_id",
        "library_id",
        "parse_barcode_key",
        "bc_wells",
        "cell_barcode",
        "guide_barcode"
      ],
      "acceptance": "Each retained cell has one auditable path from guide run to transcriptome cell identity."
    },
    {
      "artifact_id": "processed_output",
      "filename": "author_processed_fig6_output.h5ad",
      "purpose": "Author-processed AnnData or exact Fig. 6 processing output, if available",
      "required_fields": [
        "obs",
        "var",
        "X",
        "uns.processing_provenance"
      ],
      "acceptance": "Reproduces published Fig. 6 cell/cluster counts within the author-defined filtering contract."
    }
  ],
  "provenance_requirements": [
    "SHA-256 for every returned file",
    "Parse pipeline version, Scanpy version and reference build",
    "Confirmation that files correspond to the GEO GSE293514 archive version dated 2026-01-28",
    "Confirmation that no patient-identifying information is included"
  ],
  "validation_sequence": [
    "Hash-freeze every returned file and record the source/archive date.",
    "Reconcile exact feature count, order, IDs and matrix dimensions.",
    "Reconcile every cell barcode and sample assignment.",
    "Validate guide-to-cell mapping, single-guide assignment rates and unassigned fraction.",
    "Verify non-targeting and MYOD/MYMK positive-control representation.",
    "Reproduce author-defined filtering and Fig. 6 cell/cluster counts.",
    "Only then assess whether any object can support healthy-myoblast context transfer; no DMD claim is implied."
  ],
  "unlocks": [
    "Exact CROP-seq reanalysis decision",
    "Guide-resolved technical reconstruction",
    "A bounded healthy-myoblast muscle-context benchmark if all gates pass"
  ],
  "does_not_unlock": [
    "DMD candidate perturbation truth",
    "Therapeutic efficacy",
    "Clinical prediction"
  ],
  "claim_boundary": "GSE293514 remains a healthy-myoblast screen/context object until feature identity, guide identity and processing provenance are restored. Public accession alone does not authorize expression-level transfer."
}