ChEMBL Target

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://www.ebi.ac.uk/chembl/schema/target",
  "title": "ChEMBL Target",
  "description": "A biological target in ChEMBL, which can be a single protein, protein complex, organism, cell line, nucleic acid, or other biological entity.",
  "type": "object",
  "properties": {
    "target_chembl_id": {
      "type": "string",
      "pattern": "^CHEMBL[0-9]+$",
      "description": "Unique ChEMBL identifier for the target"
    },
    "pref_name": {
      "type": "string",
      "description": "Preferred name for the target (manually curated)"
    },
    "target_type": {
      "type": "string",
      "enum": [
        "SINGLE PROTEIN",
        "PROTEIN COMPLEX",
        "PROTEIN FAMILY",
        "PROTEIN COMPLEX GROUP",
        "SELECTIVITY GROUP",
        "ORGANISM",
        "TISSUE",
        "CELL-LINE",
        "NUCLEIC-ACID",
        "ADMET",
        "SUBCELLULAR",
        "METAL",
        "CHIMERIC PROTEIN",
        "PROTEIN PROTEIN INTERACTION",
        "UNKNOWN"
      ],
      "description": "Classification of the target type"
    },
    "organism": {
      "type": ["string", "null"],
      "description": "Source organism of the target (e.g., Homo sapiens)"
    },
    "tax_id": {
      "type": ["integer", "null"],
      "description": "NCBI taxonomy ID of the target organism"
    },
    "species_group_flag": {
      "type": ["boolean", "null"],
      "description": "Indicates if the target represents a group of species rather than a single organism"
    },
    "target_components": {
      "type": "array",
      "description": "Protein components (sequences) that make up this target",
      "items": {
        "type": "object",
        "properties": {
          "accession": {
            "type": ["string", "null"],
            "description": "UniProt accession number for the protein component"
          },
          "component_description": {
            "type": ["string", "null"],
            "description": "Description of the component"
          },
          "component_id": {
            "type": "integer"
          },
          "component_type": {
            "type": "string",
            "enum": ["PROTEIN", "DNA", "RNA"],
            "description": "Type of component sequence"
          },
          "relationship": {
            "type": "string",
            "description": "Relationship of this component to the target (e.g., SINGLE PROTEIN, SUBUNIT)"
          },
          "target_component_id": {
            "type": "integer"
          }
        }
      }
    },
    "cross_references": {
      "type": "array",
      "description": "Cross-references to external databases",
      "items": {
        "type": "object",
        "properties": {
          "xref_id": {"type": "string"},
          "xref_name": {"type": ["string", "null"]},
          "xref_src": {"type": "string", "description": "Source database abbreviation (e.g., UniProt, Ensembl, HGNC)"}
        }
      }
    }
  },
  "required": ["target_chembl_id", "pref_name", "target_type"],
  "examples": [
    {
      "target_chembl_id": "CHEMBL301",
      "pref_name": "Cyclooxygenase-2",
      "target_type": "SINGLE PROTEIN",
      "organism": "Homo sapiens",
      "tax_id": 9606,
      "species_group_flag": false,
      "target_components": [
        {
          "accession": "P35354",
          "component_description": "Prostaglandin G/H synthase 2",
          "component_id": 382,
          "component_type": "PROTEIN",
          "relationship": "SINGLE PROTEIN",
          "target_component_id": 382
        }
      ],
      "cross_references": [
        {
          "xref_id": "P35354",
          "xref_name": "PTGS2_HUMAN",
          "xref_src": "UniProt"
        },
        {
          "xref_id": "ENSG00000073756",
          "xref_name": "PTGS2",
          "xref_src": "Ensembl"
        }
      ]
    }
  ]
}