schema.json

{
  "schema_version": "2.0.0",
  "description": "BioHub database entry schema with relationship support",

  "fields": {
    "required": {
      "name": {
        "type": "string",
        "description": "Full name of the database",
        "example": "Gene Expression Omnibus"
      },
      "url": {
        "type": "string",
        "format": "uri",
        "description": "Primary website URL",
        "example": "https://www.ncbi.nlm.nih.gov/geo"
      },
      "description": {
        "type": "string",
        "min_length": 50,
        "max_length": 1000,
        "description": "Clear, concise description (2-3 sentences)",
        "example": "A public repository for high-throughput functional genomics data."
      },
      "category": {
        "type": "string",
        "enum": [
          "genomics",
          "proteomics",
          "pathways",
          "metabolomics",
          "ontologies",
          "literature",
          "model-organisms",
          "clinical-medical",
          "structural-biology",
          "tools-resources"
        ],
        "description": "Primary category for the database"
      },
      "data_types": {
        "type": "array",
        "items": "string",
        "min_items": 1,
        "description": "Types of data available in the database",
        "example": ["gene expression data", "microarray data", "RNA-seq data"]
      }
    },

    "recommended": {
      "abbreviation": {
        "type": "string",
        "description": "Common abbreviation or acronym",
        "example": "GEO"
      },
      "access": {
        "type": "array",
        "items": {
          "enum": ["web", "API", "download", "FTP", "CLI"]
        },
        "description": "Methods available for accessing the database"
      },
      "license": {
        "type": "string",
        "description": "Data license or usage terms",
        "example": "Open access (public domain)"
      },
      "organism": {
        "type": "string",
        "description": "Target organisms (if specific)",
        "example": "All organisms"
      },
      "format": {
        "type": "array",
        "items": "string",
        "description": "Data formats available",
        "example": ["SOFT", "MINiML", "TSV", "FASTQ"]
      },
      "updated": {
        "type": "string",
        "description": "Last major update or maintenance status",
        "example": "Daily updates"
      },
      "documentation": {
        "type": "string",
        "format": "uri",
        "description": "Link to documentation"
      },
      "api_docs": {
        "type": "string",
        "format": "uri",
        "description": "API documentation URL"
      }
    },

    "optional": {
      "subcategories": {
        "type": "array",
        "items": "string",
        "description": "Additional categories this database fits into"
      },
      "references": {
        "type": "array",
        "items": "string",
        "pattern": "^PMID:\\d+$|^DOI:.*$",
        "description": "Key publications (PMID or DOI format)",
        "example": ["PMID:33290552"]
      },
      "funding": {
        "type": "string",
        "description": "Funding sources",
        "example": "NCBI, NLM, NIH"
      },
      "contact": {
        "type": "string",
        "description": "Contact information or support email"
      },
      "tutorials": {
        "type": "array",
        "items": "string",
        "description": "Tutorial or guide URLs"
      },
      "use_cases": {
        "type": "array",
        "items": "string",
        "description": "Example research applications"
      }
    },

    "relationships": {
      "parent": {
        "type": "string",
        "description": "Parent organization or consortium (e.g., INSDC for GenBank)",
        "example": "INSDC"
      },
      "member_of": {
        "type": "array",
        "items": "string",
        "description": "Federations or collaborations this database is part of",
        "example": ["INSDC", "ELIXIR"]
      },
      "curated_from": {
        "type": "array",
        "items": "string",
        "description": "Primary archives this knowledgebase draws from",
        "example": ["GenBank", "ENA", "DDBJ"]
      },
      "integrates": {
        "type": "array",
        "items": "string",
        "description": "Other databases integrated by this meta-database",
        "example": ["Pfam", "PROSITE", "SMART"]
      },
      "mirrors": {
        "type": "array",
        "items": "string",
        "description": "Mirror sites or regional portals",
        "example": ["ENA", "DDBJ"]
      },
      "related_to": {
        "type": "array",
        "items": "string",
        "description": "Related or complementary databases"
      },
      "data_type_analog": {
        "type": "string",
        "description": "Analogous database in different domain (e.g., PRIDE is to proteomics what GEO is to genomics)",
        "example": "GEO"
      }
    }
  },

  "categories": {
    "genomics": {
      "name": "Genomics",
      "description": "Nucleotide sequences, genome annotations, genetic variation, and functional genomics",
      "subcategories": [
        "nucleotide-archives",
        "gene-annotation",
        "genome-browsers",
        "genetic-variation",
        "functional-genomics"
      ]
    },
    "proteomics": {
      "name": "Proteomics",
      "description": "Protein sequences, structures, families, domains, and experimental proteomics data",
      "subcategories": [
        "protein-sequences",
        "protein-families",
        "protein-structures",
        "proteomics-experiments"
      ]
    },
    "pathways": {
      "name": "Pathways & Interactions",
      "description": "Biological pathways and molecular interaction networks",
      "subcategories": [
        "biological-pathways",
        "molecular-interactions"
      ]
    },
    "metabolomics": {
      "name": "Metabolomics & Chemistry",
      "description": "Small molecules, metabolites, drugs, and experimental metabolomics data",
      "subcategories": [
        "chemical-databases",
        "metabolite-databases",
        "drug-databases",
        "metabolomics-experiments"
      ]
    },
    "ontologies": {
      "name": "Ontologies & Vocabularies",
      "description": "Controlled vocabularies and formal definitions for data annotation and integration"
    },
    "literature": {
      "name": "Literature & Publications",
      "description": "Scientific literature databases, citation indexes, and full-text archives"
    },
    "model-organisms": {
      "name": "Model Organism Databases",
      "description": "Organism-specific curated resources (MODs)",
      "note": "To be expanded with SGD, WormBase, FlyBase, etc."
    },
    "clinical-medical": {
      "name": "Clinical & Medical",
      "description": "Disease data, clinical trials, phenotypes, and medical genetics"
    },
    "structural-biology": {
      "name": "Structural Biology",
      "description": "3D structures, molecular interactions, and structural data"
    },
    "tools-resources": {
      "name": "Tools & Resources",
      "description": "Analysis tools, repositories, and general resources"
    }
  },

  "database_types": {
    "primary_archive": {
      "name": "Primary Archive",
      "description": "Repositories for raw, unprocessed, or minimally annotated data submitted directly by researchers",
      "examples": ["GenBank", "GEO", "PRIDE", "MetaboLights"]
    },
    "curated_knowledgebase": {
      "name": "Curated Knowledgebase",
      "description": "Value-added layer with non-redundant, manually reviewed, and richly annotated data",
      "examples": ["RefSeq", "UniProtKB/Swiss-Prot", "Reactome"]
    },
    "integrative_meta_database": {
      "name": "Integrative Meta-Database",
      "description": "Resources that aggregate data from numerous databases to provide unified access",
      "examples": ["InterPro", "STRING"]
    },
    "genome_browser": {
      "name": "Genome Browser",
      "description": "Visualization and integration platforms for genomic data",
      "examples": ["UCSC Genome Browser", "Ensembl"]
    }
  },

  "federations": {
    "INSDC": {
      "name": "International Nucleotide Sequence Database Collaboration",
      "description": "Partnership between GenBank, ENA, and DDBJ for nucleotide sequences",
      "members": ["GenBank", "ENA", "DDBJ"],
      "url": "https://www.insdc.org"
    },
    "wwPDB": {
      "name": "Worldwide Protein Data Bank",
      "description": "Global archive for 3D structural data of biological macromolecules",
      "members": ["RCSB PDB", "PDBe", "PDBj"],
      "url": "https://www.wwpdb.org"
    },
    "UniProt": {
      "name": "Universal Protein Resource",
      "description": "Central hub for protein data",
      "components": ["UniProtKB/Swiss-Prot", "UniProtKB/TrEMBL", "UniParc"],
      "url": "https://www.uniprot.org"
    }
  }
}