{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/scispot/main/json-schema/scispot-sequence-schema.json",
  "title": "Scispot Biological Sequence",
  "description": "A biological sequence (DNA, RNA, protein, or chemical structure) managed in the Scispot platform",
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Unique sequence identifier"
    },
    "name": {
      "type": "string",
      "description": "Sequence name or identifier used in the lab",
      "examples": ["BRCA1-exon10", "pUC19", "Insulin-Human"]
    },
    "type": {
      "type": "string",
      "enum": ["dna", "rna", "protein", "chemical"],
      "description": "Biological sequence type"
    },
    "sequence": {
      "type": "string",
      "description": "Raw sequence string using standard notation (IUPAC for nucleotides, single-letter codes for amino acids)",
      "examples": ["ATGCATGCATGC", "AUGCAUGCAUGC", "MVLSPADKTNVK"]
    },
    "length": {
      "type": "integer",
      "description": "Sequence length in base pairs or amino acid residues",
      "minimum": 1
    },
    "annotations": {
      "type": "array",
      "description": "Sequence features and annotations",
      "items": {
        "$ref": "#/$defs/SequenceAnnotation"
      }
    },
    "metadata": {
      "type": "object",
      "description": "Additional metadata fields as key-value pairs",
      "additionalProperties": true
    },
    "createdAt": {
      "type": "string",
      "format": "date-time"
    },
    "updatedAt": {
      "type": "string",
      "format": "date-time"
    }
  },
  "required": ["id", "name", "type", "sequence"],
  "$defs": {
    "SequenceAnnotation": {
      "type": "object",
      "description": "A feature or annotation on a biological sequence",
      "properties": {
        "name": {
          "type": "string",
          "description": "Feature name (e.g., exon, promoter, CDS)"
        },
        "start": {
          "type": "integer",
          "description": "Start position (1-indexed)",
          "minimum": 1
        },
        "end": {
          "type": "integer",
          "description": "End position (1-indexed)",
          "minimum": 1
        },
        "type": {
          "type": "string",
          "description": "Feature type (e.g., exon, intron, CDS, promoter, protein_binding)"
        },
        "strand": {
          "type": "string",
          "enum": ["forward", "reverse"],
          "description": "Strand orientation (for nucleotide sequences)"
        },
        "color": {
          "type": "string",
          "description": "Display color for visualization"
        }
      },
      "required": ["name", "start", "end", "type"]
    }
  }
}