{
  "record_type": "nnc2215_source_model_validation",
  "schema": "dia-health-one.nnc2215-model-validation.v1",
  "run": {
    "run_id": "DHO-NNC2215-MODEL-VALIDATION-20261018T033024Z",
    "created_at_utc": "2026-10-18T03:30:24.457123+00:00",
    "script": "research/validate_nnc2215_models.py",
    "script_sha256": "e72f4751c9e1e053669017680a106e0c61597772d178f1dad18348b41ac17ad6",
    "python_version": "3.14.4",
    "host_platform": "macOS-26.3-arm64-arm-64bit-Mach-O",
    "nvidia_gpu_used": false
  },
  "source": {
    "dataset_doi": "10.6084/m9.figshare.26526460.v1",
    "dataset_url": "https://springernature.figshare.com/articles/dataset/3D_models_of_NNC2215/26526460",
    "license": {
      "name": "CC BY 4.0",
      "url": "https://creativecommons.org/licenses/by/4.0/"
    },
    "article_doi": "10.1038/s41586-024-08042-3",
    "article_url": "https://www.nature.com/articles/s41586-024-08042-3",
    "chemistry_reference": "The 2024 Nature paper describes the B29 Lys N\u03b5 macrocycle linkage and the B1 Phe N-terminal O1-glucoside modification."
  },
  "expected_insulin_sequence": {
    "A": "GIVEQCCTSICSLYQLENYCN",
    "B": "FVNQHLCGSHLVEALYLVCGERGFFYTPK"
  },
  "models": [
    {
      "state": "active_open",
      "file": "structures/nnc2215-open-model.pdb",
      "sha256": "44c29d45b28ace4ede73a75a8e076dbca62e14b34bd3938a4b495ebd1270267a",
      "coordinate_atom_records": 990,
      "seqres_sequences": {
        "A": {
          "expected": "GIVEQCCTSICSLYQLENYCN",
          "pdb_seqres": "GIVEQCCTSICSLYQLENYCN",
          "matches": true,
          "coordinate_matches": true
        },
        "B": {
          "expected": "FVNQHLCGSHLVEALYLVCGERGFFYTPK",
          "pdb_seqres": "FVNQHLCGSHLVEALYLVCGERGFFYTPK",
          "matches": true,
          "coordinate_matches": true
        }
      },
      "coordinate_sequences": {
        "A": "GIVEQCCTSICSLYQLENYCN",
        "B": "FVNQHLCGSHLVEALYLVCGERGFFYTPK"
      },
      "backbone_atoms_complete": true,
      "missing_backbone_atoms": [],
      "native_disulfide_pairs_match": true,
      "disulfide_records": [
        "SSBOND   1 CYS A    6    CYS A   11                          1555   1555  2.03",
        "SSBOND   2 CYS A    7    CYS B    7                          1555   1555  2.04",
        "SSBOND   3 CYS A   20    CYS B   19                          1555   1555  2.02"
      ],
      "b29_lys_link_present": true,
      "b1_phe_glucoside_link_present": true,
      "macrocycle_roof_link_atom_names": [
        {
          "lyx_attachment_atom": "CD6",
          "macrocycle_attachment_atom": "C31",
          "record": "LINK        C31  MC  C   1                CD6  LYX B  30     1555   1555  1.56"
        }
      ],
      "free_glucose_residue_present": true,
      "open_closed_ligand_state_label_matches": true,
      "record_counts": {
        "ATOM": 767,
        "CONECT": 266,
        "END": 1,
        "HELIX": 3,
        "HETATM": 223,
        "LINK": 3,
        "REMARK": 3,
        "SEQRES": 5,
        "SSBOND": 3,
        "TER": 4,
        "TITLE": 1
      },
      "atom_counts_by_chain": {
        "A": 311,
        "B": 515,
        "C": 140,
        "D": 24
      },
      "nonstandard_residues": [
        {
          "chain": "B",
          "residue_number": 0,
          "insertion_code": "",
          "residue_name": "PHX",
          "atom_count": 35,
          "heavy_atom_count": 18,
          "element_counts": {
            "C": 10,
            "H": 17,
            "O": 8
          }
        },
        {
          "chain": "B",
          "residue_number": 30,
          "insertion_code": "",
          "residue_name": "LYX",
          "atom_count": 22,
          "heavy_atom_count": 13,
          "element_counts": {
            "C": 8,
            "H": 11,
            "N": 3,
            "O": 2
          }
        },
        {
          "chain": "C",
          "residue_number": 1,
          "insertion_code": "",
          "residue_name": "MC",
          "atom_count": 131,
          "heavy_atom_count": 80,
          "element_counts": {
            "C": 56,
            "H": 60,
            "N": 12,
            "O": 12
          }
        },
        {
          "chain": "D",
          "residue_number": 1,
          "insertion_code": "",
          "residue_name": "BGL",
          "atom_count": 24,
          "heavy_atom_count": 12,
          "element_counts": {
            "C": 6,
            "H": 12,
            "O": 6
          }
        }
      ],
      "duplicate_atoms": [
        {
          "residue": [
            "B",
            30,
            "",
            "LYX"
          ],
          "atom": "H2",
          "altloc": ""
        },
        {
          "residue": [
            "B",
            30,
            "",
            "LYX"
          ],
          "atom": "HXT",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H4",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H11",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H12",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H19",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H23",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H26",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H50",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H51",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H60",
          "altloc": ""
        }
      ],
      "invalid_coordinates": [],
      "findings": [
        "Duplicate atom names were found within a residue."
      ],
      "source_model_interpretation": "Publisher-supplied model coordinates; not an experimentally resolved NNC2215 structure."
    },
    {
      "state": "inactive_closed",
      "file": "structures/nnc2215-closed-model.pdb",
      "sha256": "a8287b859e73b274e8403ee56cd83564bc30fd0503d852829fa805fdc777e12d",
      "coordinate_atom_records": 968,
      "seqres_sequences": {
        "A": {
          "expected": "GIVEQCCTSICSLYQLENYCN",
          "pdb_seqres": "GIVEQCCTSICSLYQLENYCN",
          "matches": true,
          "coordinate_matches": true
        },
        "B": {
          "expected": "FVNQHLCGSHLVEALYLVCGERGFFYTPK",
          "pdb_seqres": "FVNQHLCGSHLVEALYLVCGERGFFYTPK",
          "matches": true,
          "coordinate_matches": true
        }
      },
      "coordinate_sequences": {
        "A": "GIVEQCCTSICSLYQLENYCN",
        "B": "FVNQHLCGSHLVEALYLVCGERGFFYTPK"
      },
      "backbone_atoms_complete": true,
      "missing_backbone_atoms": [],
      "native_disulfide_pairs_match": true,
      "disulfide_records": [
        "SSBOND   1 CYS A    6    CYS A   11                          1555   1555  2.07",
        "SSBOND   2 CYS A    7    CYS B    7                          1555   1555  2.04",
        "SSBOND   3 CYS A   20    CYS B   19                          1555   1555  1.97"
      ],
      "b29_lys_link_present": true,
      "b1_phe_glucoside_link_present": true,
      "macrocycle_roof_link_atom_names": [
        {
          "lyx_attachment_atom": "C",
          "macrocycle_attachment_atom": "C31",
          "record": "LINK        C31  MC  C   1                C    LYX B  30     1555   1555  1.55"
        }
      ],
      "free_glucose_residue_present": false,
      "open_closed_ligand_state_label_matches": true,
      "record_counts": {
        "ATOM": 769,
        "CONECT": 226,
        "END": 1,
        "HELIX": 3,
        "HETATM": 199,
        "LINK": 3,
        "REMARK": 3,
        "SEQRES": 5,
        "SSBOND": 3,
        "TER": 3,
        "TITLE": 1
      },
      "atom_counts_by_chain": {
        "A": 312,
        "B": 516,
        "C": 140
      },
      "nonstandard_residues": [
        {
          "chain": "B",
          "residue_number": 0,
          "insertion_code": "",
          "residue_name": "PHX",
          "atom_count": 35,
          "heavy_atom_count": 18,
          "element_counts": {
            "C": 10,
            "H": 18,
            "O": 8
          }
        },
        {
          "chain": "B",
          "residue_number": 30,
          "insertion_code": "",
          "residue_name": "LYX",
          "atom_count": 19,
          "heavy_atom_count": 13,
          "element_counts": {
            "C": 8,
            "H": 10,
            "N": 3,
            "O": 2
          }
        },
        {
          "chain": "C",
          "residue_number": 1,
          "insertion_code": "",
          "residue_name": "MC",
          "atom_count": 131,
          "heavy_atom_count": 80,
          "element_counts": {
            "C": 56,
            "H": 60,
            "N": 12,
            "O": 12
          }
        }
      ],
      "duplicate_atoms": [
        {
          "residue": [
            "B",
            0,
            "",
            "PHX"
          ],
          "atom": "H2",
          "altloc": ""
        },
        {
          "residue": [
            "B",
            30,
            "",
            "LYX"
          ],
          "atom": "HC",
          "altloc": ""
        },
        {
          "residue": [
            "B",
            30,
            "",
            "LYX"
          ],
          "atom": "HC",
          "altloc": ""
        },
        {
          "residue": [
            "B",
            30,
            "",
            "LYX"
          ],
          "atom": "HC",
          "altloc": ""
        },
        {
          "residue": [
            "B",
            30,
            "",
            "LYX"
          ],
          "atom": "HXT",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H4",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H11",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H12",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H19",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H23",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H26",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H50",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H51",
          "altloc": ""
        },
        {
          "residue": [
            "C",
            1,
            "",
            "MC"
          ],
          "atom": "H60",
          "altloc": ""
        }
      ],
      "invalid_coordinates": [],
      "findings": [
        "Duplicate atom names were found within a residue."
      ],
      "source_model_interpretation": "Publisher-supplied model coordinates; not an experimentally resolved NNC2215 structure."
    }
  ],
  "cross_model_comparison": {
    "macrocycle_roof_attachment_atom_names_match": false,
    "open_model_roof_link": [
      {
        "lyx_attachment_atom": "CD6",
        "macrocycle_attachment_atom": "C31",
        "record": "LINK        C31  MC  C   1                CD6  LYX B  30     1555   1555  1.56"
      }
    ],
    "closed_model_roof_link": [
      {
        "lyx_attachment_atom": "C",
        "macrocycle_attachment_atom": "C31",
        "record": "LINK        C31  MC  C   1                C    LYX B  30     1555   1555  1.55"
      }
    ],
    "interpretation": "The open and closed PDBs use different LYX atom names for the linker-to-macrocycle connection. This may be representational, but it must be reconciled to the chemical source before assigning a shared topology."
  },
  "validation_summary": {
    "source_hashes_match_manifest": true,
    "insulin_sequences_match_desB30_human_insulin": true,
    "backbone_atoms_complete": true,
    "three_native_disulfides_match": true,
    "b29_macrocycle_and_b1_glucoside_link_records_present": true,
    "chemical_graph_and_bond_orders_validated": false,
    "protonation_and_partial_charges_validated": false,
    "force_field_parameters_validated": false,
    "insulin_receptor_coordinates_present": false,
    "production_simulation_ready": false
  },
  "readiness_boundary": "Source, sequence, backbone, disulfide, and modification-site records were checked. These are author-supplied model-built NNC2215 conformations, not experimentally resolved NNC2215 coordinates. No receptor coordinates are included. The nonstandard LYX/PHX/MC chemical graphs, bond orders, stereochemistry, protonation, charges, and force-field parameters remain unvalidated; no target simulation is authorized by this record.",
  "models_have_findings": true,
  "cross_model_topology_requires_review": true,
  "clinical_use": false
}