{
  "schema": "dia-health-one.nnc2215-b1-glucoside-atom-map.v1",
  "graph_file": "structures/nnc2215-b1-glucoside-attachment.smi",
  "graph_name": "nnc2215_b1_glucoside_attachment",
  "scope": "Source-supported deprotected B1 glucoside attachment through the PheB1 N boundary atom. The insulin backbone beyond that nitrogen, including its N–Cα peptide continuation, is outside this component graph.",
  "sources": {
    "nature_article": {
      "doi": "10.1038/s41586-024-08042-3",
      "article_url": "https://www.nature.com/articles/s41586-024-08042-3",
      "figure_2a_product_drawing_url": "https://media.springernature.com/full/springer-static/image/art%3A10.1038%2Fs41586-024-08042-3/MediaObjects/41586_2024_8042_Fig2_HTML.png",
      "locations": [
        "Fig. 2a: NNC2215 product drawing, including the B1 glucoside connection.",
        "Chemistry: O1-glucoside is attached through a short linker at the B-chain N-terminal amino group PheB1.",
        "Methods, Synthesis of NNC2215: desB30 insulin is coupled at B1 with the peracetyl glucoside active ester; acetyl groups are removed by gentle saponification."
      ]
    },
    "extended_data_figure_7b": {
      "url": "https://media.springernature.com/original/springer-static/esm/art%3A10.1038%2Fs41586-024-08042-3/MediaObjects/41586_2024_8042_Fig12_ESM.jpg",
      "location": "Extended Data Fig. 7b, beta-carboxymethyl-oxyethyl-O-peracetyl-D-glucoside active ester. The figure labels the glucose carbons C1–C6; linker carbons are not assigned separate numeric source labels."
    },
    "supporting_information": {
      "url": "https://media.springernature.com/original/springer-static/esm/art%3A10.1038%2Fs41586-024-08042-3/MediaObjects/41586_2024_8042_MOESM1_ESM.pdf",
      "section_2": "pp. 2–4: synthesis of beta-carboxymethyl-oxyethyl-O-peracetyl-D-glucoside active ester; H-1 doublet J=7.9 Hz; glucose and linker NMR assignments; peracetylated acid is converted to the active ester.",
      "section_4": "pp. 10–11: active ester coupling to B1 at pH 7.5, isolation of B1-O-peracetyl-glycoside, then saponification at pH 10.5 for 6 hours to the B1 glycoside.",
      "mass_benchmark": "§4, p. 11: following trypsin and TCEP treatment, glucoside is reported on the B1–B22 fragment at measured 1376.6 and calculated 1376.2 [M+2H]2+."
    },
    "patent": {
      "publication": "WO2023144240A1",
      "url": "https://patents.google.com/patent/WO2023144240A1/en",
      "location": "Example 2 (INS2): B1 glycoside active-ester coupling to B29-alkyne insulin at pH 7.5, followed by sodium-carbonate saponification of the O-acetyl esters; see paragraphs describing INS2 and the B1-O-peracetyl-glycoside intermediate."
    }
  },
  "transcription": {
    "protein_to_sugar_sequence": "PheB1 N–C(=O)–CH2–O–CH2–CH2–O–C1(beta-D-glucopyranose)",
    "deprotected_sugar_hydroxyls": ["C2", "C3", "C4", "C6"],
    "source_numbering": "Glucose C1–C6 labels are retained from Extended Data Fig. 7b and SI NMR assignments. The linker is mapped by its depicted OCH2C=O and OCH2CH2O groups; no linker carbon numbering is invented.",
    "linker_orientation": "The glycosidic oxygen on glucose C1 connects to O–CH2–CH2–O–CH2–C(=O); the carbonyl carbon is attached to the PheB1 N endpoint.",
    "stereochemistry": {
      "designation": "beta-D-glucopyranoside",
      "evidence": [
        "Extended Data Fig. 7b depicts the beta-D glucoside and its glucose C1–C6 stereochemical substituent pattern.",
        "SI §2 reports H-1 as a doublet with J=7.9 Hz, consistent with the beta-D-glucopyranoside anomer.",
        "The detached sugar graph matches the beta-D-glucose reference structure (PubChem CID 64689; InChIKey WQZGKKKJIJFFOK-VFUOTHLCSA-N).",
        "RDKit accurate CIP labels are used; RDKit documents its legacy CIP implementation as approximate and known to mislabel some centers."
      ],
      "rdkit_cip_by_source_glucose_carbon": {
        "C1": "R",
        "C2": "R",
        "C3": "S",
        "C4": "S",
        "C5": "R",
        "C6": "not stereogenic (CH2OH)"
      },
      "stereocenter_atom_maps": {"C1": 9, "C2": 11, "C3": 13, "C4": 15, "C5": 17}
    }
  },
  "map_id_legend": {
    "1": {
      "element_in_smiles": "*",
      "role": "Mapped protein-boundary placeholder for PheB1 N; it is joined to the B1 acyl carbonyl.",
      "model_match_element": "N",
      "model_match_identity": "Insulin B-chain PheB1 backbone N; this dummy is not included in substituent formulae or heavy-atom inventory."
    },
    "2": {"element": "C", "source_label": null, "role": "B1 linker carbonyl carbon; amide carbonyl attached to PheB1 N."},
    "3": {"element": "O", "source_label": null, "role": "B1 amide carbonyl oxygen."},
    "4": {"element": "C", "source_label": null, "role": "Methylene alpha to the carbonyl; source NMR group OCH2C=O."},
    "5": {"element": "O", "source_label": null, "role": "Ether oxygen between the carbonyl-alpha methylene and the ethylene linker."},
    "6": {"element": "C", "source_label": null, "role": "First ethylene-linker methylene, adjacent to map 5."},
    "7": {"element": "C", "source_label": null, "role": "Second ethylene-linker methylene, adjacent to the glycosidic-side ether oxygen map 8."},
    "8": {"element": "O", "source_label": null, "role": "Glycosidic-side ether oxygen linking the ethylene linker to glucose C1."},
    "9": {"element": "C", "source_label": "C1", "role": "Anomeric glucose carbon; beta-D glycosidic attachment site."},
    "10": {"element": "O", "source_label": null, "role": "Glucopyranose ring oxygen between glucose C5 and C1."},
    "11": {"element": "C", "source_label": "C2", "role": "Glucose C2 stereocenter bearing a free hydroxyl at map 12."},
    "12": {"element": "O", "source_label": null, "role": "Free hydroxyl oxygen at glucose C2."},
    "13": {"element": "C", "source_label": "C3", "role": "Glucose C3 stereocenter bearing a free hydroxyl at map 14."},
    "14": {"element": "O", "source_label": null, "role": "Free hydroxyl oxygen at glucose C3."},
    "15": {"element": "C", "source_label": "C4", "role": "Glucose C4 stereocenter bearing a free hydroxyl at map 16."},
    "16": {"element": "O", "source_label": null, "role": "Free hydroxyl oxygen at glucose C4."},
    "17": {"element": "C", "source_label": "C5", "role": "Glucose C5 stereocenter; bears the C6 hydroxymethyl substituent and ring oxygen map 10."},
    "18": {"element": "C", "source_label": "C6", "role": "Glucose C6 hydroxymethyl carbon."},
    "19": {"element": "O", "source_label": null, "role": "Free hydroxyl oxygen at glucose C6."}
  },
  "key_connectivity": [
    {"atoms": [1, 2], "bond": "single", "role": "PheB1 N–amide carbonyl C; map 1 is the N boundary placeholder."},
    {"atoms": [2, 3], "bond": "double", "role": "Amide carbonyl."},
    {"atoms": [2, 4], "bond": "single"},
    {"atoms": [4, 5], "bond": "single"},
    {"atoms": [5, 6], "bond": "single"},
    {"atoms": [6, 7], "bond": "single"},
    {"atoms": [7, 8], "bond": "single"},
    {"atoms": [8, 9], "bond": "single", "role": "Glycosidic ether to glucose C1."},
    {"atoms": [9, 11], "bond": "single"},
    {"atoms": [11, 13], "bond": "single"},
    {"atoms": [13, 15], "bond": "single"},
    {"atoms": [15, 17], "bond": "single"},
    {"atoms": [17, 10], "bond": "single"},
    {"atoms": [10, 9], "bond": "single", "role": "Glucopyranose ring closure."},
    {"atoms": [11, 12], "bond": "single", "role": "C2 free hydroxyl."},
    {"atoms": [13, 14], "bond": "single", "role": "C3 free hydroxyl."},
    {"atoms": [15, 16], "bond": "single", "role": "C4 free hydroxyl."},
    {"atoms": [17, 18], "bond": "single"},
    {"atoms": [18, 19], "bond": "single", "role": "C6 free hydroxyl."}
  ],
  "transformations": {
    "requested_graph_path": [
      {
        "from": "beta-carboxymethyl-oxyethyl-O-peracetyl-D-glucoside active ester",
        "to": "deprotected beta-carboxymethyl-oxyethyl-D-glucoside acid representation",
        "operations": [
          "Replace the phenolic active-ester leaving group on the terminal acyl carbon with OH.",
          "Remove the four O-acetyl protecting groups at glucose C2, C3, C4 and C6."
        ],
        "deprotected_acid_formula": "C10H18O9",
        "source_note": "This is the normalized graph intermediate used for the formula and amide mass balance. The published NNC2215 procedure does not isolate this deprotected acid before protein coupling."
      },
      {
        "from": "deprotected beta-carboxymethyl-oxyethyl-D-glucoside acid",
        "to": "PheB1 N amide",
        "operations": ["Form PheB1 N–C(=O) bond; net loss of H2O from the acid plus insulin amino group."],
        "net_attachment_increment": "C10H16O8"
      }
    ],
    "published_procedure": [
      "The peracetylated active ester couples to insulin at B1 to give a peracetylated B1 glycoside amide.",
      "Saponification then removes the four sugar O-acetyl groups to give the deprotected B1 glycoside."
    ],
    "active_ester_to_product_leaving_group": "The active ester aryl-sulfonate group and its Br/CF3/sulfonate atoms are not part of the product graph."
  },
  "composition": {
    "net_attachment_increment_relative_to_unmodified_insulin": "C10H16O8",
    "substituent_heavy_inventory_excluding_map_1_placeholder": {"C": 10, "O": 8},
    "placeholder_heavy_inventory_contribution": 0,
    "inventory_note": "RDKit's mapped-dummy graph formula includes the side chain's 17 implicit hydrogens and a dummy atom. The net protein increment is one hydrogen lower because the PheB1 amino group loses one N–H as the amide bond forms."
  },
  "published_fragment_benchmark": {
    "fragment": "B1–B22 glucoside-bearing insulin B-chain fragment",
    "observed_m_z": 1376.6,
    "calculated_m_z": 1376.2,
    "charge_state": "[M+2H]2+",
    "source": "Nature SI §4, p. 11.",
    "sample_processing": [
      "Trypsin cleaves after ArgB22 to release the B23–B29 fragment from the B1–B22 fragment.",
      "TCEP reduces insulin disulfides to separate A and B chains.",
      "LC–MS assigns the glucoside to B1–B22; the reported 2+ ion is a peptide-fragment composition check, not a standalone mass measurement of the substituent."
    ]
  },
  "rdkit_validation": {
    "rdkit_version": "2026.03.1",
    "smiles_parse_and_sanitize": "pass",
    "mapped_atom_count_including_dummy": 19,
    "atom_map_ids_unique": true,
    "map_id_range": [1, 19],
    "rdkit_graph_formula_including_dummy": "C10H17*O8",
    "rdkit_deprotected_acid_formula": "C10H18O9",
    "formula_balance": "C10H18O9 - H2O = C10H16O8",
    "heavy_inventory_excluding_dummy": {"C": 10, "O": 8},
    "connected_components": 1,
    "cycle_rank_E_minus_V_plus_components": 1,
    "stereocenters_by_map_id": {"9": "R", "11": "R", "13": "S", "15": "S", "17": "R"},
    "stereocenter_count": 5,
    "stereochemistry_note": "All five glucose stereocenters C1–C5 are assigned by RDKit accurate CIP; the detached sugar graph matches the beta-D-glucose reference InChIKey WQZGKKKJIJFFOK-VFUOTHLCSA-N. C6 is achiral CH2OH.",
    "cip_method": "RDKit accurate CIP implementation (useLegacyImplementation=False); legacy CIP is approximate and may misassign labels.",
    "cip_method_reference_url": "https://www.rdkit.org/docs/RDKit_Book.html#assignment-of-absolute-stereochemistry",
    "beta_d_glucose_reference": {"name": "beta-D-glucose", "pubchem_cid": 64689, "url": "https://pubchem.ncbi.nlm.nih.gov/compound/64689", "detached_graph_formula": "C6H12O6", "detached_graph_inchikey": "WQZGKKKJIJFFOK-VFUOTHLCSA-N", "match": true}
  },
  "limitations": [
    "The PheB1 N endpoint is a mapped dummy placeholder whose model-match element is N; the insulin backbone is not included.",
    "The B1–B22 fragment mass supports the modified-fragment assignment and composition but does not independently establish atom-by-atom coordinates.",
    "The graph specifies neutral hydroxyls and an amide connectivity representation; it does not assign physiological protonation, charges, force-field parameters or a full-conjugate topology."
  ]
}