{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://conformome.org/schema/common.schema.json",
  "title": "Shared definitions",
  "$defs": {
    "provenance": {
      "type": "object",
      "description": "Where a record came from. Every record carries one.",
      "required": [
        "source",
        "retrieved",
        "url",
        "licence"
      ],
      "additionalProperties": false,
      "properties": {
        "source": {
          "type": "string",
          "minLength": 1
        },
        "doi": {
          "type": [
            "string",
            "null"
          ]
        },
        "deposit_id": {
          "type": [
            "string",
            "null"
          ],
          "description": "PDB ID, BMRB ID, SASBDB code, PRIDE accession, DOI-less dataset ID, etc."
        },
        "retrieved": {
          "type": "string",
          "format": "date"
        },
        "url": {
          "type": "string",
          "format": "uri"
        },
        "licence": {
          "type": "string",
          "minLength": 1,
          "description": "Licence of the source data, as recorded in docs/SOURCES.md."
        }
      }
    },
    "conditions": {
      "type": "object",
      "description": "Conditions under which the observation or state was measured. Unknown values are null, never omitted.",
      "required": [
        "environment",
        "temperature_c",
        "ph",
        "buffer",
        "salt_mM",
        "ions",
        "ligands",
        "applied_force_pn",
        "notes"
      ],
      "additionalProperties": false,
      "properties": {
        "environment": {
          "enum": [
            "in_vitro",
            "in_cell",
            "in_silico"
          ]
        },
        "temperature_c": {
          "type": [
            "number",
            "null"
          ]
        },
        "ph": {
          "type": [
            "number",
            "null"
          ]
        },
        "buffer": {
          "type": [
            "string",
            "null"
          ]
        },
        "salt_mM": {
          "type": [
            "number",
            "null"
          ]
        },
        "ions": {
          "type": "array",
          "description": "Ions with stated concentrations (Mg2+, K+, Na+ for nucleic acids). salt_mM stays the total monovalent salt when only that is given.",
          "items": {
            "type": "object",
            "required": [
              "ion",
              "concentration_mM"
            ],
            "additionalProperties": false,
            "properties": {
              "ion": {
                "type": "string",
                "minLength": 1,
                "description": "Written with its charge: Mg2+, K+, Na+, Ca2+."
              },
              "concentration_mM": {
                "type": [
                  "number",
                  "null"
                ]
              }
            }
          }
        },
        "ligands": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "applied_force_pn": {
          "type": [
            "number",
            "null"
          ]
        },
        "notes": {
          "type": [
            "string",
            "null"
          ]
        }
      }
    },
    "mapping": {
      "type": "object",
      "description": "One link from an evidence item to a state. Who made it, how sure, and why must always be visible.",
      "required": [
        "state_id",
        "who",
        "confidence",
        "justification"
      ],
      "additionalProperties": false,
      "properties": {
        "state_id": {
          "$ref": "#/$defs/state_id"
        },
        "who": {
          "type": "string",
          "pattern": "^(curator|rule):.+$"
        },
        "confidence": {
          "enum": [
            "high",
            "medium",
            "low"
          ]
        },
        "justification": {
          "type": "string",
          "minLength": 1
        },
        "rule": {
          "type": [
            "string",
            "null"
          ]
        },
        "agreement": {
          "type": [
            "object",
            "null"
          ],
          "description": "For mappings decided by comparing data with a state (a probing profile with a dot-bracket, an smFRET efficiency with an anchor model): the score and the method used.",
          "required": [
            "score",
            "method"
          ],
          "additionalProperties": false,
          "properties": {
            "score": {
              "type": "number"
            },
            "method": {
              "type": "string",
              "minLength": 1
            }
          }
        }
      }
    },
    "basis": {
      "enum": [
        "observed",
        "inferred"
      ],
      "description": "observed: directly resolved (X-ray, cryo-EM, NMR structure). inferred: fitted to indirect constraints."
    },
    "molecule_id": {
      "type": "string",
      "description": "Page key. Protein: UniProtKB accession, with an isoform suffix (P10636-8) when the page is about one isoform. RNA: RNAcentral URS identifier, with a taxon suffix (URS0000000001_9606) when species-specific. DNA without a sequence database entry: DNA- plus the first 12 hex digits of the SHA-256 of the upper-case sequence (see conformome/molecule.py). Complex: a Complex Portal ID (CPX-1234) or CPX- plus a curator-chosen slug.",
      "oneOf": [
        {
          "pattern": "^([OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2})(-[0-9]+)?$"
        },
        {
          "pattern": "^URS[0-9A-F]{10}(_[0-9]+)?$"
        },
        {
          "pattern": "^DNA-[0-9a-f]{12}$"
        },
        {
          "pattern": "^CPX-[A-Za-z0-9_-]+$"
        }
      ]
    },
    "state_id": {
      "type": "string",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9_-]*$"
    },
    "measured": {
      "type": "object",
      "description": "A measured number with its unit and uncertainty.",
      "required": [
        "value",
        "unit",
        "uncertainty"
      ],
      "additionalProperties": false,
      "properties": {
        "value": {
          "type": "number"
        },
        "unit": {
          "type": "string",
          "minLength": 1
        },
        "uncertainty": {
          "type": [
            "number",
            "null"
          ]
        }
      }
    },
    "profile": {
      "type": "object",
      "description": "A per-residue or per-nucleotide series (chemical-probing reactivities, protection factors, Φ-values). values[i] belongs to position start + i; null where not measured. Large profiles may be linked by data_link instead of inlined, with values left empty.",
      "required": [
        "kind",
        "start",
        "values",
        "unit",
        "normalization",
        "data_link"
      ],
      "additionalProperties": false,
      "properties": {
        "kind": {
          "type": "string",
          "pattern": "^[a-z0-9_]+$",
          "description": "For example shape_reactivity, dms_reactivity, protection_factor, phi_value."
        },
        "start": {
          "type": "integer",
          "minimum": 1,
          "description": "Sequence position of values[0] (1-based, in the molecule's own numbering)."
        },
        "values": {
          "type": "array",
          "items": {
            "type": [
              "number",
              "null"
            ]
          }
        },
        "uncertainties": {
          "type": "array",
          "items": {
            "type": [
              "number",
              "null"
            ]
          },
          "description": "Same length as values when given."
        },
        "unit": {
          "type": [
            "string",
            "null"
          ]
        },
        "normalization": {
          "type": [
            "string",
            "null"
          ],
          "description": "How values were normalised (for example 2-8% normalisation, box-plot), as the source states it."
        },
        "data_link": {
          "type": [
            "string",
            "null"
          ],
          "format": "uri"
        }
      }
    },
    "secondary_structure": {
      "type": "object",
      "description": "Base pairing of a nucleic-acid state. Dot-bracket over the full sequence: '.' unpaired, '()' nested pairs, '[]', '{}', '<>' and Aa..Zz (upper opens, lower closes) for pseudoknots. G-quadruplex tetrads use '+' on the guanines that form them.",
      "required": [
        "dot_bracket",
        "source"
      ],
      "additionalProperties": false,
      "properties": {
        "dot_bracket": {
          "type": "string",
          "pattern": "^[.()\\[\\]{}<>A-Za-z+]+$"
        },
        "start": {
          "type": "integer",
          "minimum": 1,
          "description": "Position of the first character, when the state covers part of the molecule. Default 1."
        },
        "source": {
          "type": "string",
          "minLength": 1,
          "description": "Where the pairing comes from: an anchor PDB ID, an Rfam consensus, a probing-guided fold (name the method), or a curator."
        }
      }
    },
    "family_label": {
      "type": "object",
      "description": "A state name from a family vocabulary in taxonomy/state_vocabularies/, so that a term means the same thing across homologs. terms gives one term per axis the state is labelled on, for example {dfg: dfg_in, alpha_c: alpha_c_out}.",
      "required": [
        "vocabulary",
        "terms"
      ],
      "additionalProperties": false,
      "properties": {
        "vocabulary": {
          "type": "string",
          "pattern": "^[a-z0-9_]+$"
        },
        "terms": {
          "type": "object",
          "minProperties": 1,
          "propertyNames": {
            "pattern": "^[a-z0-9_]+$"
          },
          "additionalProperties": {
            "type": "string",
            "pattern": "^[a-z0-9_]+$"
          }
        }
      }
    }
  }
}