lineage_schema_1-0-0.yml

# yaml-language-server: $schema=https://json-schema.org/draft/2020-12/schema
type: object
additionalProperties: false
required:
  - name
  - unaliased_name
  - designation_date
  - defining_snps
  - reference_sequences
  - parent
properties:
  name:
    type: string
    description: The name of the lineage, must match file name
  unaliased_name:
    type: string
    description: The unaliased name of the lineage, must be fully unaliased, i.e. start with A
  parent:
    type: string
    description: The name of the parent lineage
  alias:
    type: string
    description: The alias of the lineage, must not contain `.`
  designation_date:
    type: string
    description: The date the lineage was designated in format "2022-07-30"
  defining_snps:
    type: array
    uniqueItems: true
    description: The defining SNPs of the lineage.
    items:
      type: object
      properties:
        pos:
          type: integer
          description: 1-indexed nucleotide positions
        nucleotide:
          enum: [A, C, G, T]
          description: The target nucleotide of the SNP
  reference_sequences:
    type: array
    uniqueItems: true
    description: Reference sequence(s) of the lineage. If there are multiple sequences listed, they stand in for their MRCA.
    items:
      type: object
      required:
        - source
        - accession
      properties:
        source:
          enum:
            - genbank
          description: Source of the reference sequence, e.g. genbank
        accession:
          type: string
          description: The accession of the reference sequence.
        isolate:
          type: string
          description: The isolate (aka strain) name of the reference sequence.