datasets.openapi.yaml

basePath: /datasets/v1alpha
consumes:
- application/json
definitions:
  AssemblyDatasetDescriptorsFilterAssemblyLevel:
    default: chromosome
    enum:
    - chromosome
    - scaffold
    - contig
    - complete_genome
    title: 'The level of the genome assembly: Chromosome, Scaffold, Contig or Complete
      Genome'
    type: string
  AssemblyDatasetDescriptorsFilterAssemblySource:
    default: all
    enum:
    - all
    - refseq
    - genbank
    type: string
  AssemblyDatasetRequestResolution:
    default: FULLY_HYDRATED
    enum:
    - FULLY_HYDRATED
    - DATA_REPORT_ONLY
    type: string
  AssemblyMetadataRequestBioprojects:
    properties:
      accessions:
        items:
          type: string
        type: array
    type: object
  DownloadSummaryDehydrated:
    properties:
      cli_download_command_line:
        type: string
      cli_rehydrate_command_line:
        type: string
      estimated_file_size_mb:
        format: int64
        type: integer
      url:
        type: string
    type: object
  DownloadSummaryHydrated:
    properties:
      cli_download_command_line:
        type: string
      estimated_file_size_mb:
        format: int64
        type: integer
      url:
        type: string
    type: object
  ErrorAssemblyErrorCode:
    default: UNKNOWN_ASSEMBLY_ERROR_CODE
    enum:
    - UNKNOWN_ASSEMBLY_ERROR_CODE
    - INVALID_BIOPROJECT_IDS
    - NO_ASSEMBLIES_FOR_BIOPROJECTS
    - INVALID_TAXON
    type: string
  ErrorGeneErrorCode:
    default: UNKNOWN_GENE_ERROR_CODE
    enum:
    - UNKNOWN_GENE_ERROR_CODE
    - INCOMPLETE_LOOKUP_SYMBOL
    type: string
  ErrorVirusErrorCode:
    default: UNKNOWN_VIRUS_ERROR_CODE
    enum:
    - UNKNOWN_VIRUS_ERROR_CODE
    type: string
  GeneDatasetRequestSort:
    properties:
      direction:
        $ref: '#/definitions/v1alpha1SortDirection'
        description: Select a direction for the sort.
      field:
        $ref: '#/definitions/GeneDatasetRequestSortField'
        description: Select a field to sort on.
    type: object
  GeneDatasetRequestSortField:
    default: SORT_FIELD_UNSPECIFIED
    enum:
    - SORT_FIELD_UNSPECIFIED
    - SORT_FIELD_GENE_ID
    - SORT_FIELD_GENE_TYPE
    - SORT_FIELD_GENE_SYMBOL
    type: string
  GeneDatasetRequestSymbolsForTaxon:
    properties:
      symbols:
        items:
          type: string
        type: array
      taxon:
        type: string
    type: object
  GeneDescriptorGeneType:
    default: UNKNOWN
    enum:
    - UNKNOWN
    - tRNA
    - rRNA
    - snRNA
    - scRNA
    - snoRNA
    - PROTEIN_CODING
    - PSEUDO
    - TRANSPOSON
    - miscRNA
    - ncRNA
    - BIOLOGICAL_REGION
    - OTHER
    type: string
  GeneDescriptorRnaType:
    default: rna_UNKNOWN
    enum:
    - rna_UNKNOWN
    - premsg
    - tmRna
    type: string
  GenomicRegionGenomicRegionType:
    default: UNKNOWN
    enum:
    - UNKNOWN
    - REFSEQ_GENE
    - PSEUDOGENE
    - BIOLOGICAL_REGION
    - OTHER
    type: string
  MicroBiggeDatasetRequestElementFlankConfig:
    properties:
      length:
        format: int64
        type: integer
    title: configuration options for gene file output
    type: object
  OrganismCountByType:
    properties:
      counts:
        $ref: '#/definitions/OrganismCounts'
      type:
        $ref: '#/definitions/OrganismCountType'
    type: object
  OrganismCountType:
    default: COUNT_TYPE_UNSPECIFIED
    enum:
    - COUNT_TYPE_UNSPECIFIED
    - COUNT_TYPE_ASSEMBLY
    - COUNT_TYPE_GENE
    type: string
  OrganismCounts:
    properties:
      node:
        format: int64
        title: The number of assemblies at this node only
        type: integer
      subtree:
        description: The number of assemblies at this node and all children.
        format: int64
        type: integer
    type: object
  OrganismRankType:
    default: NO_RANK
    enum:
    - NO_RANK
    - SUPERKINGDOM
    - KINGDOM
    - SUBKINGDOM
    - SUPERPHYLUM
    - SUBPHYLUM
    - PHYLUM
    - CLADE
    - SUPERCLASS
    - CLASS
    - SUBCLASS
    - INFRACLASS
    - COHORT
    - SUBCOHORT
    - SUPERORDER
    - ORDER
    - SUBORDER
    - INFRAORDER
    - PARVORDER
    - SUPERFAMILY
    - FAMILY
    - SUBFAMILY
    - GENUS
    - SUBGENUS
    - SPECIES_GROUP
    - SPECIES_SUBGROUP
    - SPECIES
    - SUBSPECIES
    - TRIBE
    - SUBTRIBE
    - FORMA
    - VARIETAS
    - STRAIN
    - SECTION
    - SUBSECTION
    - PATHOGROUP
    - SUBVARIETY
    - GENOTYPE
    - SEROTYPE
    - ISOLATE
    - MORPH
    - SERIES
    - FORMA_SPECIALIS
    - SEROGROUP
    - BIOTYPE
    type: string
  ProkaryoteGeneRequestGeneFlankConfig:
    properties:
      length:
        format: int64
        type: integer
    type: object
  SciNameAndIdsSciNameAndId:
    properties:
      sci_name:
        title: Scientific name
        type: string
      tax_id:
        format: uint64
        title: NCBI Taxonomy ID
        type: string
    type: object
  TranscriptTranscriptType:
    default: UNKNOWN
    enum:
    - UNKNOWN
    - PROTEIN_CODING
    - NON_CODING
    - PROTEIN_CODING_MODEL
    - NON_CODING_MODEL
    type: string
  WarningGeneWarningCode:
    default: UNKNOWN_GENE_WARNING_CODE
    enum:
    - UNKNOWN_GENE_WARNING_CODE
    - ACCESSION_VERSION_MISMATCH
    - REPLACED_GENE_ID
    - DISCONTINUED_GENE_ID
    - UNRECOGNIZED_GENE_ID
    - UNRECOGNIZED_GENE_SYMBOL
    - UNRECOGNIZED_ACCESSION
    - UNRECOGNIZED_TAX_TOKEN
    type: string
  WarningReplacedId:
    properties:
      requested:
        type: string
      returned:
        type: string
    type: object
  datasetsv1alpha1Accessions:
    properties:
      accessions:
        items:
          type: string
        type: array
    type: object
  datasetsv1alpha1Annotation:
    properties:
      assemblies_in_scope:
        items:
          $ref: '#/definitions/v1alpha1AnnotatedAssemblies'
        type: array
      release_date:
        type: string
      release_name:
        type: string
    type: object
  protobufAny:
    properties:
      type_url:
        type: string
      value:
        format: byte
        type: string
    type: object
  rpcStatus:
    properties:
      code:
        format: int32
        type: integer
      details:
        items:
          $ref: '#/definitions/protobufAny'
        type: array
      message:
        type: string
    type: object
  v1alpha1AnnotatedAssemblies:
    properties:
      accession:
        type: string
      name:
        type: string
    type: object
  v1alpha1AnnotationForAssembly:
    properties:
      file:
        description: List of annotation files available for this assembly.
        items:
          $ref: '#/definitions/v1alpha1AnnotationForAssemblyFile'
        type: array
      name:
        title: Annotation name
        type: string
      release_date:
        title: The date the annotation was released
        type: string
      release_number:
        description: NCBI Annotation release number, if one exists.
        type: string
      report_url:
        title: NCBI annotation report website
        type: string
      source:
        description: Source of the annotation.  Possibly from a submitter.
        type: string
      stats:
        $ref: '#/definitions/v1alpha1FeatureCounts'
        title: Feature statistics
    type: object
  v1alpha1AnnotationForAssemblyFile:
    properties:
      estimated_size:
        format: uint64
        type: string
      type:
        $ref: '#/definitions/v1alpha1AnnotationForAssemblyType'
    type: object
  v1alpha1AnnotationForAssemblyType:
    default: DEFAULT
    enum:
    - DEFAULT
    - GENOME_GFF
    - GENOME_GBFF
    - GENOME_GB
    - RNA_FASTA
    - PROT_FASTA
    - GENOME_GTF
    type: string
  v1alpha1AnnotationForVirusType:
    default: DEFAULT
    enum:
    - DEFAULT
    - CDS_FASTA
    - PROT_FASTA
    - GENOME_GBFF
    - GENOME_GPFF
    - PDB_FILES
    type: string
  v1alpha1AssemblyDatasetAvailability:
    properties:
      invalid_assemblies:
        items:
          type: string
        type: array
      reason:
        type: string
      valid_assemblies:
        items:
          type: string
        type: array
    type: object
  v1alpha1AssemblyDatasetDescriptor:
    properties:
      annotation_metadata:
        $ref: '#/definitions/v1alpha1AnnotationForAssembly'
        title: Annotation available for this assembly
      assembly_accession:
        title: The GenColl assembly accession (e.g. GCF_000001405.39)
        type: string
      assembly_category:
        description: Category of assembly, like reference.
        type: string
      assembly_level:
        title: The level of the assembly, e.g. Chromosome, Scaffold, Contig or Complete
          Genome
        type: string
      bioproject_lineages:
        items:
          $ref: '#/definitions/v1alpha1BioProjectLineage'
        title: The bioproject(s) associated with this assembly
        type: array
      biosample_accession:
        description: NCBI BioSample Accession for the BioSample from which the sequences
          in the genome assembly were obtained.
        type: string
      chromosomes:
        description: 'Which chromosomes are included in this dataset. NB: Mitochondria
          is encoded as ''MT''.'
        items:
          type: string
        type: array
      contig_n50:
        format: int64
        title: Minimum contig length needed to cover 50% of the genome
        type: integer
      display_name:
        description: The name of the Assembly dataset to be displayed in a user interface.
        type: string
      estimated_size:
        format: uint64
        title: Estimated size of all annotation and sequence files in download
        type: string
      org:
        $ref: '#/definitions/v1alpha1Organism'
        title: Organism information
      seq_length:
        format: uint64
        title: Combined length of all sequence data
        type: string
      submission_date:
        title: Date the assembly was provided to NCBI
        type: string
      submitter:
        title: The submitting consortium or organization. Full submitter information
          is available in the BioProject
        type: string
    type: object
  v1alpha1AssemblyDatasetDescriptors:
    properties:
      datasets:
        description: List of all datasets that match the request, up to the provided
          limit.
        items:
          $ref: '#/definitions/v1alpha1AssemblyDatasetDescriptor'
        type: array
      total_count:
        description: The total count of available datasets (ignoring the cutoff parameter).
        format: int64
        type: integer
    type: object
  v1alpha1AssemblyDatasetDescriptorsFilter:
    properties:
      assembly_level:
        items:
          $ref: '#/definitions/AssemblyDatasetDescriptorsFilterAssemblyLevel'
        title: Only return genome assemblies that have one of the specified assembly
          levels
        type: array
      assembly_source:
        $ref: '#/definitions/AssemblyDatasetDescriptorsFilterAssemblySource'
        title: Return only RefSeq (GCF_) or GenBank (GCA_) genome assemblies
      first_release_date:
        format: date-time
        title: Only return genome assemblies that were released on or after the specified
          date
        type: string
      has_annotation:
        title: Return only annotated genome assemblies
        type: boolean
      last_release_date:
        format: date-time
        title: Only return genome assemblies that were released on or before to the
          specified date
        type: string
      reference_only:
        description: If true, only return reference and representative (GCF_ and GCA_)
          genome assemblies.
        type: boolean
      refseq_only:
        description: If true, only return RefSeq (GCF_) genome assemblies. Deprecated
          - use assembly_type instead.
        type: boolean
      search_text:
        items:
          type: string
        title: Only return results whose fields contain the specified search terms
          in their taxon, infraspecific, assembly name or submitter fields
        type: array
    type: object
  v1alpha1AssemblyDatasetDescriptorsRequestContentType:
    default: COMPLETE
    enum:
    - COMPLETE
    - ASSM_ACC
    - COUNTS
    type: string
  v1alpha1AssemblyDatasetRequest:
    properties:
      accessions:
        items:
          type: string
        title: NCBI genome assembly accessions
        type: array
      assembly_accessions:
        items:
          type: string
        title: NCBI genome assembly accessions
        type: array
      chromosomes:
        description: The default setting is all chromosome. Specify individual chromosome
          by string (1,2,MT or chr1,chr2.chrMT). Unplaced sequences are treated like
          their own chromosome ('Un'). The filter only applies to fasta sequence.
        items:
          type: string
        type: array
      exclude_sequence:
        description: Set to true to omit the genomic sequence.
        type: boolean
      hydrated:
        $ref: '#/definitions/AssemblyDatasetRequestResolution'
        description: Set to DATA_REPORT_ONLY, to only retrieve data-reports.
      include_annotation:
        type: boolean
      include_annotation_type:
        description: Select additional types of annotation to include in the data
          package.  If unset, no annotation is provided.
        items:
          $ref: '#/definitions/v1alpha1AnnotationForAssemblyType'
        type: array
      include_tsv:
        description: Set to true to include a TSV represention of the data-report.
        type: boolean
    type: object
  v1alpha1AssemblyMatch:
    properties:
      assembly:
        $ref: '#/definitions/v1alpha1AssemblyDatasetDescriptor'
      messages:
        items:
          $ref: '#/definitions/v1alpha1Message'
        type: array
    type: object
  v1alpha1AssemblyMetadata:
    properties:
      assemblies:
        items:
          $ref: '#/definitions/v1alpha1AssemblyMatch'
        type: array
      messages:
        items:
          $ref: '#/definitions/v1alpha1Message'
        type: array
      next_page_token:
        description: A token that can be sent as `page_token` to retrieve the next
          page. If this field is omitted, there are no subsequent pages.
        type: string
      total_count:
        description: The total count of available datasets (ignoring the cutoff parameter).
          Only provided for the first page of results (when `page_token` is empty
          in the request).
        format: int64
        type: integer
    type: object
  v1alpha1AssemblyMetadataRequest:
    properties:
      accessions:
        $ref: '#/definitions/datasetsv1alpha1Accessions'
        title: NCBI assembly accession
      bioprojects:
        $ref: '#/definitions/AssemblyMetadataRequestBioprojects'
        title: NCBI bioproject accessions
      filters:
        $ref: '#/definitions/v1alpha1AssemblyDatasetDescriptorsFilter'
      limit:
        title: Deprecated - Limit the number of returned results ("all", "none", otherwise
          an integer value)
        type: string
      page_size:
        description: The maximum number of genome assemblies to return. Default is
          20 and maximum is 1000. If the number of results exceeds the page size,  `page_token`
          can be used to retrieve the remaining results.
        format: int32
        type: integer
      page_token:
        description: A page token is returned from an `AssemblyMetadataRequest` call
          with more than `page_size` results. Use this token, along with the previous  `AssemblyMetadataRequest`
          parameters, to retrieve the next page of results. When `page_token` is empty,
          all results have been retrieved.
        type: string
      returned_content:
        $ref: '#/definitions/v1alpha1AssemblyMetadataRequestContentType'
        title: Return either assembly accessions, or entire assembly-metadata records
      tax_exact_match:
        description: If true, only return assemblies with the given NCBI Taxonomy
          ID, or name. Otherwise, assemblies from taxonomy subtree are included, too.
          Ignored for assembly_accession request.
        type: boolean
      taxon:
        title: NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank
        type: string
    type: object
  v1alpha1AssemblyMetadataRequestContentType:
    default: COMPLETE
    enum:
    - COMPLETE
    - ASSM_ACC
    type: string
  v1alpha1BioProject:
    properties:
      accession:
        type: string
      parent_accession:
        type: string
      parent_accessions:
        items:
          type: string
        type: array
      title:
        type: string
    type: object
  v1alpha1BioProjectLineage:
    properties:
      bioprojects:
        description: In order, from most specific, up to the root.
        items:
          $ref: '#/definitions/v1alpha1BioProject'
        type: array
    type: object
  v1alpha1DownloadSummary:
    properties:
      assembly_count:
        format: int64
        title: For backwards compatability with old VirusDatasetSummary
        type: integer
      dehydrated:
        $ref: '#/definitions/DownloadSummaryDehydrated'
      errors:
        items:
          $ref: '#/definitions/v1alpha1Error'
        type: array
      hydrated:
        $ref: '#/definitions/DownloadSummaryHydrated'
      messages:
        items:
          $ref: '#/definitions/v1alpha1Message'
        type: array
      record_count:
        description: The number of records for the requested filter.
        format: int64
        type: integer
      resource_updated_on:
        description: The latest date on which the resource was updated.
        format: date-time
        type: string
    type: object
  v1alpha1Error:
    properties:
      assembly_error_code:
        $ref: '#/definitions/ErrorAssemblyErrorCode'
      gene_error_code:
        $ref: '#/definitions/ErrorGeneErrorCode'
      invalid_identifiers:
        items:
          type: string
        type: array
      message:
        type: string
      reason:
        type: string
      valid_identifiers:
        items:
          type: string
        type: array
      virus_error_code:
        $ref: '#/definitions/ErrorVirusErrorCode'
    type: object
  v1alpha1Fasta:
    default: FASTA_UNSPECIFIED
    enum:
    - FASTA_UNSPECIFIED
    - FASTA_GENE
    - FASTA_RNA
    - FASTA_PROTEIN
    - FASTA_GENE_FLANK
    type: string
  v1alpha1FeatureCounts:
    properties:
      gene_counts:
        $ref: '#/definitions/v1alpha1GeneCounts'
        title: Counts of gene types
    type: object
  v1alpha1GeneCounts:
    properties:
      protein_coding:
        format: int64
        title: Count of annotated genes that encode a protein
        type: integer
      total:
        format: int64
        title: Total number of annotated genes
        type: integer
    type: object
  v1alpha1GeneDatasetRequest:
    properties:
      accessions:
        description: RNA or Protein accessions.
        items:
          type: string
        type: array
      fasta_filter:
        items:
          type: string
        title: Limit the FASTA sequences in the datasets package to these transcript
          and protein accessions
        type: array
      gene_ids:
        items:
          format: int64
          type: integer
        title: NCBI gene ids
        type: array
      include_annotation_type:
        description: Select additional types of annotation to include in the data
          package.  If unset, no annotation is provided.
        items:
          $ref: '#/definitions/v1alpha1Fasta'
        type: array
      limit:
        title: Limit the number of returned results ("all", "none", otherwise an integer
          value)
        type: string
      returned_content:
        $ref: '#/definitions/v1alpha1GeneDatasetRequestContentType'
        title: Return either gene-ids, or entire gene metadata
      sort_schema:
        $ref: '#/definitions/GeneDatasetRequestSort'
      symbols_for_taxon:
        $ref: '#/definitions/GeneDatasetRequestSymbolsForTaxon'
      taxon:
        title: NCBI Taxonomy ID or name (common or scientific) that the genes are
          annotated at
        type: string
    type: object
  v1alpha1GeneDatasetRequestContentType:
    default: COMPLETE
    enum:
    - COMPLETE
    - IDS_ONLY
    type: string
  v1alpha1GeneDescriptor:
    properties:
      annotations:
        items:
          $ref: '#/definitions/datasetsv1alpha1Annotation'
        type: array
      chromosome:
        title: See chromosomes
        type: string
      chromosomes:
        items:
          type: string
        type: array
      common_name:
        title: Species common-name
        type: string
      description:
        type: string
      ensembl_gene_ids:
        items:
          type: string
        type: array
      gene_id:
        format: uint64
        title: mongo-required
        type: string
      genomic_ranges:
        items:
          $ref: '#/definitions/v1alpha1SeqRangeSet'
        type: array
      genomic_regions:
        items:
          $ref: '#/definitions/v1alpha1GenomicRegion'
        type: array
      nomenclature_authority:
        $ref: '#/definitions/v1alpha1NomenclatureAuthority'
      omim_ids:
        items:
          type: string
        type: array
      orientation:
        $ref: '#/definitions/v1alpha1Orientation'
      proteins:
        items:
          $ref: '#/definitions/v1alpha1Protein'
        type: array
      reference_standards:
        items:
          $ref: '#/definitions/v1alpha1GenomicRegion'
        type: array
      replaced_gene_id:
        format: uint64
        type: string
      rna_type:
        $ref: '#/definitions/GeneDescriptorRnaType'
      swiss_prot_accessions:
        items:
          type: string
        type: array
      symbol:
        type: string
      synonyms:
        items:
          type: string
        type: array
      tax_id:
        format: uint64
        type: string
      taxname:
        type: string
      transcripts:
        items:
          $ref: '#/definitions/v1alpha1Transcript'
        type: array
      type:
        $ref: '#/definitions/GeneDescriptorGeneType'
    title: Summary of NCBI Gene resource
    type: object
  v1alpha1GeneDescriptors:
    properties:
      errors:
        items:
          $ref: '#/definitions/v1alpha1Error'
        type: array
      genes:
        items:
          $ref: '#/definitions/v1alpha1GeneDescriptor'
        type: array
    type: object
  v1alpha1GeneMatch:
    properties:
      errors:
        items:
          $ref: '#/definitions/v1alpha1Error'
        type: array
      gene:
        $ref: '#/definitions/v1alpha1GeneDescriptor'
      messages:
        items:
          $ref: '#/definitions/v1alpha1Message'
        type: array
      query:
        items:
          type: string
        type: array
      warnings:
        items:
          $ref: '#/definitions/v1alpha1Warning'
        type: array
    type: object
  v1alpha1GeneMetadata:
    properties:
      genes:
        items:
          $ref: '#/definitions/v1alpha1GeneMatch'
        type: array
      messages:
        items:
          $ref: '#/definitions/v1alpha1Message'
        type: array
      total_count:
        description: The total count of available datasets (ignoring the cutoff parameter).
        format: int64
        type: integer
    type: object
  v1alpha1GenomicLocation:
    properties:
      exons:
        items:
          $ref: '#/definitions/v1alpha1Range'
        type: array
      genomic_accession_version:
        type: string
      genomic_range:
        $ref: '#/definitions/v1alpha1Range'
      sequence_name:
        type: string
    type: object
  v1alpha1GenomicRegion:
    properties:
      gene_range:
        $ref: '#/definitions/v1alpha1SeqRangeSet'
        description: The range of this Gene record on this genomic region.
      type:
        $ref: '#/definitions/GenomicRegionGenomicRegionType'
    type: object
  v1alpha1MaturePeptide:
    properties:
      accession_version:
        type: string
      length:
        format: int64
        type: integer
      name:
        type: string
    title: Mature peptide
    type: object
  v1alpha1Message:
    properties:
      error:
        $ref: '#/definitions/v1alpha1Error'
      warning:
        $ref: '#/definitions/v1alpha1Warning'
    type: object
  v1alpha1MicroBiggeDatasetRequestFileType:
    default: FILE_TYPE_UNSPECIFIED
    enum:
    - FILE_TYPE_UNSPECIFIED
    - element_fasta
    - element_flank_fasta
    - contig_fasta
    - protein_fasta
    type: string
  v1alpha1NomenclatureAuthority:
    description: The authority and record by which NCBI has named the gene.
    properties:
      authority:
        type: string
      identifier:
        type: string
    type: object
  v1alpha1Organism:
    properties:
      assembly_count:
        description: The number of assemblies at this node, and all children.
        format: uint64
        type: string
      assembly_counts:
        $ref: '#/definitions/OrganismCounts'
        title: assembly_counts will soon be deprecated
      blast_node:
        title: True if a blast nodes
        type: boolean
      breed:
        title: Infraspecies breed
        type: string
      children:
        description: List of all children tax nodes.
        items:
          $ref: '#/definitions/v1alpha1Organism'
        type: array
      common_name:
        title: Common Name of the organism
        type: string
      counts:
        items:
          $ref: '#/definitions/OrganismCountByType'
        type: array
      cultivar:
        title: Infraspecies cultivar
        type: string
      ecotype:
        title: Infraspecies ecotype
        type: string
      icon:
        type: boolean
      isolate:
        title: Infraspecies isolate
        type: string
      key:
        format: uint64
        type: string
      max_ord:
        format: int64
        type: integer
      merged:
        description: List of all merged tax nodes for the pruned taxonomic tree.
        items:
          $ref: '#/definitions/v1alpha1Organism'
        type: array
      merged_tax_ids:
        description: List of merged (now deprecated) Taxonomy IDs for the current
          Organism.
        items:
          format: uint64
          type: string
        type: array
      min_ord:
        format: int64
        title: ordinal values for any node are the full range of the ordinal values
          in the subtree underneath this node, and are used for faster range-based
          lookups
        type: integer
      parent_tax_id:
        format: uint64
        title: The parent taxnode ID
        type: string
      rank:
        $ref: '#/definitions/OrganismRankType'
        description: The rank of the tax node.
      sci_name:
        title: Scientific Name
        type: string
      search_text:
        items:
          type: string
        title: May include names from merged nodes
        type: array
      sex:
        title: Infraspecies sex
        type: string
      strain:
        title: Infraspecies strain
        type: string
      tax_id:
        format: uint64
        title: NCBI Taxonomy ID
        type: string
      title:
        type: string
    type: object
  v1alpha1Orientation:
    default: none
    enum:
    - none
    - plus
    - minus
    type: string
  v1alpha1OrthologRequestContentType:
    default: COMPLETE
    enum:
    - COMPLETE
    - IDS_ONLY
    type: string
  v1alpha1OrthologSet:
    properties:
      genes:
        $ref: '#/definitions/v1alpha1GeneMetadata'
      method:
        type: string
      ortholog_set_id:
        format: int64
        type: integer
    type: object
  v1alpha1ProkaryoteGeneRequest:
    properties:
      accessions:
        items:
          type: string
        title: WP prokaryote protein accession
        type: array
      gene_flank_config:
        $ref: '#/definitions/ProkaryoteGeneRequestGeneFlankConfig'
      include_annotation_type:
        description: Select additional types of annotation to include in the data
          package.  If unset, no annotation is provided.
        items:
          $ref: '#/definitions/v1alpha1Fasta'
        type: array
      taxon:
        title: NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank
          When specified, return data from this taxon and its subtree
        type: string
    type: object
  v1alpha1Protein:
    properties:
      accession_version:
        type: string
      ensembl_protein:
        type: string
      isoform_name:
        type: string
      length:
        format: int64
        type: integer
      mature_peptides:
        items:
          $ref: '#/definitions/v1alpha1MaturePeptide'
        type: array
      name:
        type: string
    title: Protein product of a transcript
    type: object
  v1alpha1Range:
    description: A range on a sequence record.
    properties:
      begin:
        format: uint64
        type: string
      end:
        format: uint64
        type: string
      order:
        description: When an ordering is desired, fill out the order in the range.
        format: int64
        type: integer
      orientation:
        $ref: '#/definitions/v1alpha1Orientation'
      ribosomal_slippage:
        description: When ribosomal slippage is desired, fill out slippage amount
          between this and previous range.
        format: int32
        type: integer
    type: object
  v1alpha1SciNameAndIds:
    properties:
      sci_name_and_ids:
        items:
          $ref: '#/definitions/SciNameAndIdsSciNameAndId'
        type: array
    type: object
  v1alpha1SeqRangeSet:
    properties:
      accession_version:
        title: NCBI Accession.version of the sequence
        type: string
      range:
        items:
          $ref: '#/definitions/v1alpha1Range'
        title: Series of intervals on above accession_version
        type: array
    type: object
  v1alpha1SleepReply:
    properties:
      reply:
        type: string
    type: object
  v1alpha1SortDirection:
    default: SORT_DIRECTION_UNSPECIFIED
    enum:
    - SORT_DIRECTION_UNSPECIFIED
    - SORT_DIRECTION_ASCENDING
    - SORT_DIRECTION_DESCENDING
    type: string
  v1alpha1TableFormat:
    default: tsv
    enum:
    - tsv
    - csv
    - jsonl
    type: string
  v1alpha1TabularOutput:
    properties:
      data:
        type: string
    type: object
  v1alpha1Transcript:
    properties:
      accession_version:
        title: Transcript accession-version
        type: string
      cds:
        $ref: '#/definitions/v1alpha1SeqRangeSet'
      ensembl_transcript:
        type: string
      exons:
        $ref: '#/definitions/v1alpha1SeqRangeSet'
      genomic_locations:
        items:
          $ref: '#/definitions/v1alpha1GenomicLocation'
        type: array
      genomic_range:
        $ref: '#/definitions/v1alpha1SeqRangeSet'
      length:
        format: int64
        type: integer
      name:
        type: string
      protein:
        $ref: '#/definitions/v1alpha1Protein'
        title: Protein, if coding transcript
      type:
        $ref: '#/definitions/TranscriptTranscriptType'
    type: object
  v1alpha1VersionReply:
    properties:
      major_ver:
        format: int64
        type: integer
      minor_ver:
        format: int64
        type: integer
      patch_ver:
        format: int64
        type: integer
      version:
        type: string
    type: object
  v1alpha1VirusTableField:
    default: unspecified
    enum:
    - unspecified
    - nucleotide_accession
    - species_tax_id
    - species_name
    - genus
    - family
    - nucleotide_length
    - isolate_name
    - sequence_type
    - nuc_completeness
    - geo_location
    - us_state
    - host_name
    - host_tax_id
    - collection_date
    - bioproject
    - biosample
    - polyprotein_name
    - protein_name
    - protein_accession
    - protein_synonym
    - cds_span
    type: string
  v1alpha1Warning:
    properties:
      gene_warning_code:
        $ref: '#/definitions/WarningGeneWarningCode'
      message:
        type: string
      reason:
        type: string
      replaced_id:
        $ref: '#/definitions/WarningReplacedId'
      unrecognized_identifier:
        type: string
    type: object
externalDocs:
  description: Interactively explore genome assembly datasets
  url: https://www.ncbi.nlm.nih.gov/datasets/genomes/
host: api.ncbi.nlm.nih.gov
info:
  description: NCBI service to query and download biological sequence data across
    all domains of life from NCBI databases.
  title: NCBI Datasets API
  version: v1alpha
paths:
  /gene:
    post:
      description: Get detailed gene metadata in a JSON output format.
      operationId: gene_metadata_by_post
      parameters:
      - in: body
        name: body
        required: true
        schema:
          $ref: '#/definitions/v1alpha1GeneDatasetRequest'
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1GeneMetadata'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get gene metadata as JSON
      tags:
      - Gene
  /gene/accession/{accessions}:
    get:
      description: Get detailed gene metadata by RefSeq Accession in a JSON output
        format.
      operationId: gene_metadata_by_accession
      parameters:
      - collectionFormat: csv
        description: RNA or Protein accessions.
        in: path
        items:
          type: string
        minItems: 1
        name: accessions
        required: true
        type: array
      - default: COMPLETE
        description: Return either gene-ids, or entire gene metadata.
        enum:
        - COMPLETE
        - IDS_ONLY
        in: query
        name: returned_content
        required: false
        type: string
      - default: SORT_FIELD_UNSPECIFIED
        description: Select a field to sort on.
        enum:
        - SORT_FIELD_UNSPECIFIED
        - SORT_FIELD_GENE_ID
        - SORT_FIELD_GENE_TYPE
        - SORT_FIELD_GENE_SYMBOL
        in: query
        name: sort_schema.field
        required: false
        type: string
      - default: SORT_DIRECTION_UNSPECIFIED
        description: Select a direction for the sort.
        enum:
        - SORT_DIRECTION_UNSPECIFIED
        - SORT_DIRECTION_ASCENDING
        - SORT_DIRECTION_DESCENDING
        in: query
        name: sort_schema.direction
        required: false
        type: string
      - description: Limit the number of returned results ("all", "none", otherwise
          an integer value).
        in: query
        name: limit
        required: false
        type: string
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1GeneMetadata'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get gene metadata by RefSeq Accession
      tags:
      - Gene
  /gene/accession/{accessions}/download_summary:
    get:
      description: Get gene download summary by RefSeq Accession in a JSON output
        format.
      operationId: gene_download_summary_by_accession
      parameters:
      - collectionFormat: csv
        description: RNA or Protein accessions.
        in: path
        items:
          type: string
        minItems: 1
        name: accessions
        required: true
        type: array
      - description: Limit the number of returned results ("all", "none", otherwise
          an integer value).
        in: query
        name: limit
        required: false
        type: string
      - collectionFormat: multi
        description: Limit the FASTA sequences in the datasets package to these transcript
          and protein accessions.
        in: query
        items:
          type: string
        name: fasta_filter
        required: false
        type: array
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1DownloadSummary'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get gene download summary by RefSeq Accession
      tags:
      - Gene
  /gene/download:
    post:
      description: Get a gene dataset including gene, transcript and protein fasta
        sequence, annotation and metadata by POST.
      operationId: download_gene_package_post
      parameters:
      - in: body
        name: body
        required: true
        schema:
          $ref: '#/definitions/v1alpha1GeneDatasetRequest'
      - default: ncbi_dataset.zip
        description: Output file name.
        in: query
        name: filename
        required: false
        type: string
      produces:
      - application/zip
      responses:
        '200':
          description: Download selected gene data as a zip file.
          schema:
            description: Zip compressed stream
            format: binary
            type: string
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get a gene dataset by POST
      tags:
      - Gene
  /gene/download_summary:
    post:
      description: Get gene download summary in a JSON output format.
      operationId: gene_download_summary_by_post
      parameters:
      - in: body
        name: body
        required: true
        schema:
          $ref: '#/definitions/v1alpha1GeneDatasetRequest'
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1DownloadSummary'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get gene download summary
      tags:
      - Gene
  /gene/id/{gene_ids}:
    get:
      description: Get detailed gene metadata by GeneID in a JSON output format.
      operationId: gene_metadata_by_id
      parameters:
      - collectionFormat: csv
        description: NCBI gene ids
        in: path
        items:
          format: int64
          type: integer
        minItems: 1
        name: gene_ids
        required: true
        type: array
      - default: COMPLETE
        description: Return either gene-ids, or entire gene metadata.
        enum:
        - COMPLETE
        - IDS_ONLY
        in: query
        name: returned_content
        required: false
        type: string
      - default: SORT_FIELD_UNSPECIFIED
        description: Select a field to sort on.
        enum:
        - SORT_FIELD_UNSPECIFIED
        - SORT_FIELD_GENE_ID
        - SORT_FIELD_GENE_TYPE
        - SORT_FIELD_GENE_SYMBOL
        in: query
        name: sort_schema.field
        required: false
        type: string
      - default: SORT_DIRECTION_UNSPECIFIED
        description: Select a direction for the sort.
        enum:
        - SORT_DIRECTION_UNSPECIFIED
        - SORT_DIRECTION_ASCENDING
        - SORT_DIRECTION_DESCENDING
        in: query
        name: sort_schema.direction
        required: false
        type: string
      - description: Limit the number of returned results ("all", "none", otherwise
          an integer value).
        in: query
        name: limit
        required: false
        type: string
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1GeneMetadata'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get gene metadata by GeneID
      tags:
      - Gene
  /gene/id/{gene_ids}/download:
    get:
      description: Get a gene dataset including gene, transcript and protein fasta
        sequence, annotation and metadata by gene ID.
      operationId: download_gene_package
      parameters:
      - collectionFormat: csv
        description: NCBI gene ids
        in: path
        items:
          format: int64
          type: integer
        minItems: 1
        name: gene_ids
        required: true
        type: array
      - collectionFormat: multi
        description: Select additional types of annotation to include in the data
          package.  If unset, no annotation is provided.
        in: query
        items:
          enum:
          - FASTA_GENE
          - FASTA_RNA
          - FASTA_PROTEIN
          type: string
        name: include_annotation_type
        required: false
        type: array
      - collectionFormat: multi
        description: Limit the FASTA sequences in the datasets package to these transcript
          and protein accessions.
        in: query
        items:
          type: string
        name: fasta_filter
        required: false
        type: array
      - default: ncbi_dataset.zip
        description: Output file name.
        in: query
        name: filename
        required: false
        type: string
      produces:
      - application/zip
      responses:
        '200':
          description: Download selected gene data as a zip file.
          schema:
            description: Zip compressed stream
            format: binary
            type: string
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get a gene dataset by gene ID
      tags:
      - Gene
  /gene/id/{gene_ids}/download_summary:
    get:
      description: Get a download summary by GeneID in a JSON output format.
      operationId: gene_download_summary_by_id
      parameters:
      - collectionFormat: csv
        description: NCBI gene ids
        in: path
        items:
          format: int64
          type: integer
        minItems: 1
        name: gene_ids
        required: true
        type: array
      - description: Limit the number of returned results ("all", "none", otherwise
          an integer value).
        in: query
        name: limit
        required: false
        type: string
      - collectionFormat: multi
        description: Limit the FASTA sequences in the datasets package to these transcript
          and protein accessions.
        in: query
        items:
          type: string
        name: fasta_filter
        required: false
        type: array
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1DownloadSummary'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get gene download summary by GeneID
      tags:
      - Gene
  /gene/id/{gene_id}/orthologs:
    get:
      description: Get detailed gene metadata for an ortholog set by gene ID in a
        JSON output format.
      operationId: gene_orthologs_by_id
      parameters:
      - format: int64
        in: path
        name: gene_id
        required: true
        type: integer
      - default: COMPLETE
        description: Return either gene-ids, or entire gene metadata.
        enum:
        - COMPLETE
        - IDS_ONLY
        in: query
        name: returned_content
        required: false
        type: string
      - collectionFormat: multi
        description: Filter genes by taxa.
        in: query
        items:
          type: string
        name: taxon_filter
        required: false
        type: array
      produces:
      - application/json
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1OrthologSet'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get gene orthologs by gene ID
      tags:
      - Gene
  /gene/stream:
    post:
      description: Get detailed gene metadata in a streaming, JSON-lines output format.
      operationId: gene_metadata_stream_by_post
      parameters:
      - in: body
        name: body
        required: true
        schema:
          $ref: '#/definitions/v1alpha1GeneDatasetRequest'
      produces:
      - application/x-ndjson
      responses:
        '200':
          description: Successful request, returning a stream of individual JSON Text
            payloads.
          headers:
            Transfer-Encoding:
              description: chunked
              schema:
                type: string
          schema:
            $ref: '#/definitions/v1alpha1GeneMatch'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get gene metadata
      tags:
      - Gene
  /gene/symbol/{symbols}/taxon/{taxon}:
    get:
      description: Get detailed gene metadata by gene symbol in a JSON output format.
      operationId: gene_metadata_by_tax_and_symbol
      parameters:
      - collectionFormat: csv
        in: path
        items:
          type: string
        minItems: 1
        name: symbols
        required: true
        type: array
      - in: path
        name: taxon
        required: true
        type: string
      - default: COMPLETE
        description: Return either gene-ids, or entire gene metadata.
        enum:
        - COMPLETE
        - IDS_ONLY
        in: query
        name: returned_content
        required: false
        type: string
      - default: SORT_FIELD_UNSPECIFIED
        description: Select a field to sort on.
        enum:
        - SORT_FIELD_UNSPECIFIED
        - SORT_FIELD_GENE_ID
        - SORT_FIELD_GENE_TYPE
        - SORT_FIELD_GENE_SYMBOL
        in: query
        name: sort_schema.field
        required: false
        type: string
      - default: SORT_DIRECTION_UNSPECIFIED
        description: Select a direction for the sort.
        enum:
        - SORT_DIRECTION_UNSPECIFIED
        - SORT_DIRECTION_ASCENDING
        - SORT_DIRECTION_DESCENDING
        in: query
        name: sort_schema.direction
        required: false
        type: string
      - description: Limit the number of returned results ("all", "none", otherwise
          an integer value).
        in: query
        name: limit
        required: false
        type: string
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1GeneMetadata'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get gene metadata by gene symbol.
      tags:
      - Gene
  /gene/symbol/{symbols}/taxon/{taxon}/download_summary:
    get:
      description: Get gene download summary by gene symbol in a JSON output format.
      operationId: gene_download_summary_by_tax_and_symbol
      parameters:
      - collectionFormat: csv
        in: path
        items:
          type: string
        minItems: 1
        name: symbols
        required: true
        type: array
      - in: path
        name: taxon
        required: true
        type: string
      - collectionFormat: multi
        description: Limit the FASTA sequences in the datasets package to these transcript
          and protein accessions.
        in: query
        items:
          type: string
        name: fasta_filter
        required: false
        type: array
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1DownloadSummary'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get gene download summary by gene symbol.
      tags:
      - Gene
  /gene/taxon/{taxon}/tree:
    get:
      operationId: gene_tax_tree
      parameters:
      - description: NCBI Taxonomy ID or name (common or scientific) at any taxonomic
          rank
        in: path
        name: taxon
        required: true
        type: string
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1Organism'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Retrieve tax tree
      tags:
      - Gene
  /gene/taxon_suggest/{taxon_query}:
    get:
      description: This endpoint retrieves a list of taxonomy names and IDs found
        in the gene dataset given a partial taxonomic name of any rank.
      operationId: gene_tax_name_query
      parameters:
      - description: NCBI Taxonomy ID or name (common or scientific) at any taxonomic
          rank
        in: path
        name: taxon_query
        required: true
        type: string
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1SciNameAndIds'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get a list of taxonomy names and IDs found in the gene dataset given
        a partial taxonomic name.
      tags:
      - Gene
  /genome:
    post:
      description: Get detailed metadata for assembled genomes by accession in a JSON
        output format.
      operationId: genome_metadata_by_post
      parameters:
      - in: body
        name: body
        required: true
        schema:
          $ref: '#/definitions/v1alpha1AssemblyMetadataRequest'
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1AssemblyMetadata'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get genome metadata by accession
      tags:
      - Genome
  /genome/accession/{accessions}:
    get:
      description: Get detailed metadata for assembled genomes by accession in a JSON
        output format.
      operationId: assembly_descriptors_by_accessions
      parameters:
      - collectionFormat: csv
        in: path
        items:
          type: string
        minItems: 1
        name: accessions
        required: true
        type: array
      - default: False, do not filter
        description: If true, only return reference and representative (GCF_ and GCA_)
          genome assemblies.
        in: query
        name: filters.reference_only
        required: false
        type: boolean
      - default: All, do not filter
        description: Return only RefSeq (GCF_) or GenBank (GCA_) genome assemblies.
        enum:
        - all
        - refseq
        - genbank
        in: query
        name: filters.assembly_source
        required: false
        type: string
      - default: False, do not filter
        description: Return only annotated genome assemblies.
        in: query
        name: filters.has_annotation
        required: false
        type: boolean
      - collectionFormat: multi
        default: Empty, do not filter
        description: Only return genome assemblies that have one of the specified
          assembly levels.
        in: query
        items:
          enum:
          - chromosome
          - scaffold
          - contig
          - complete_genome
          type: string
        name: filters.assembly_level
        required: false
        type: array
      - default: Empty, do not filter
        description: Only return genome assemblies that were released on or after
          the specified date.
        format: date-time
        in: query
        name: filters.first_release_date
        required: false
        type: string
      - default: Empty, do not filter
        description: Only return genome assemblies that were released on or before
          to the specified date.
        format: date-time
        in: query
        name: filters.last_release_date
        required: false
        type: string
      - collectionFormat: multi
        default: Empty, do not filter
        description: Only return results whose fields contain the specified search
          terms in their taxon, infraspecific, assembly name or submitter fields.
        in: query
        items:
          type: string
        name: filters.search_text
        required: false
        type: array
      - default: 20
        description: The maximum number of genome assemblies to return. Default is
          20 and maximum is 1000. If the number of results exceeds the page size,  `page_token`
          can be used to retrieve the remaining results.
        format: int32
        in: query
        name: page_size
        required: false
        type: integer
      - description: A page token is returned from an `AssemblyMetadataRequest` call
          with more than `page_size` results. Use this token, along with the previous  `AssemblyMetadataRequest`
          parameters, to retrieve the next page of results. When `page_token` is empty,
          all results have been retrieved.
        in: query
        name: page_token
        required: false
        type: string
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1AssemblyMetadata'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get genome metadata by accession
      tags:
      - Genome
  /genome/accession/{accessions}/check:
    get:
      description: The 'GET' version of check is limited by the size of the GET URL
        (2KB, which works out to about 140 genomic accessions).  The POST operation
        is provided to allow users to supply a larger number of accessions in a single
        request.
      operationId: check_assembly_availability
      parameters:
      - collectionFormat: csv
        description: NCBI genome assembly accessions
        in: path
        items:
          type: string
        minItems: 1
        name: accessions
        required: true
        type: array
      produces:
      - application/json
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1AssemblyDatasetAvailability'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Check the validity of genome accessions
      tags:
      - Genome
  /genome/accession/{accessions}/download:
    get:
      description: Download a genome dataset including fasta sequence, annotation
        and a detailed data report by accession.
      operationId: download_assembly_package
      parameters:
      - collectionFormat: csv
        description: NCBI genome assembly accessions
        in: path
        items:
          type: string
        minItems: 1
        name: accessions
        required: true
        type: array
      - collectionFormat: multi
        default: Empty, for all chromosomes
        description: The default setting is all chromosome. Specify individual chromosome
          by string (1,2,MT or chr1,chr2.chrMT). Unplaced sequences are treated like
          their own chromosome ('Un'). The filter only applies to fasta sequence.
        in: query
        items:
          type: string
        name: chromosomes
        required: false
        type: array
      - default: False, thus including genomic sequence
        description: Set to true to omit the genomic sequence.
        in: query
        name: exclude_sequence
        required: false
        type: boolean
      - collectionFormat: multi
        description: Select additional types of annotation to include in the data
          package.  If unset, no annotation is provided.
        in: query
        items:
          enum:
          - GENOME_GFF
          - GENOME_GBFF
          - RNA_FASTA
          - PROT_FASTA
          - GENOME_GTF
          type: string
        name: include_annotation_type
        required: false
        type: array
      - default: FULLY_HYDRATED
        description: Set to DATA_REPORT_ONLY, to only retrieve data-reports.
        enum:
        - FULLY_HYDRATED
        - DATA_REPORT_ONLY
        in: query
        name: hydrated
        required: false
        type: string
      - default: ncbi_dataset.zip
        description: Output file name.
        in: query
        name: filename
        required: false
        type: string
      produces:
      - application/zip
      responses:
        '200':
          description: Download selected genome assemblies and associated annotation
            data as a zip file.
          schema:
            description: Zip compressed stream
            format: binary
            type: string
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get a genome dataset by accession
      tags:
      - Genome
  /genome/accession/{accessions}/download_summary:
    get:
      description: Get a download summary by accession in a JSON output format.
      operationId: genome_download_summary
      parameters:
      - collectionFormat: csv
        description: NCBI genome assembly accessions
        in: path
        items:
          type: string
        minItems: 1
        name: accessions
        required: true
        type: array
      - collectionFormat: multi
        default: Empty, for all chromosomes
        description: The default setting is all chromosome. Specify individual chromosome
          by string (1,2,MT or chr1,chr2.chrMT). Unplaced sequences are treated like
          their own chromosome ('Un'). The filter only applies to fasta sequence.
        in: query
        items:
          type: string
        name: chromosomes
        required: false
        type: array
      - default: False, thus including genomic sequence
        description: Set to true to omit the genomic sequence.
        in: query
        name: exclude_sequence
        required: false
        type: boolean
      - collectionFormat: multi
        description: Select additional types of annotation to include in the data
          package.  If unset, no annotation is provided.
        in: query
        items:
          enum:
          - GENOME_GFF
          - GENOME_GBFF
          - RNA_FASTA
          - PROT_FASTA
          - GENOME_GTF
          type: string
        name: include_annotation_type
        required: false
        type: array
      produces:
      - application/json
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1DownloadSummary'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Preview genome dataset download
      tags:
      - Genome
  /genome/bioproject/{accessions}:
    get:
      description: Get detailed metadata for assembled genomes by bioproject accession
        in a JSON output format.
      operationId: assembly_descriptors_by_bioproject
      parameters:
      - collectionFormat: csv
        in: path
        items:
          type: string
        minItems: 1
        name: accessions
        required: true
        type: array
      - default: False, do not filter
        description: If true, only return reference and representative (GCF_ and GCA_)
          genome assemblies.
        in: query
        name: filters.reference_only
        required: false
        type: boolean
      - default: All, do not filter
        description: Return only RefSeq (GCF_) or GenBank (GCA_) genome assemblies.
        enum:
        - all
        - refseq
        - genbank
        in: query
        name: filters.assembly_source
        required: false
        type: string
      - default: False, do not filter
        description: Return only annotated genome assemblies.
        in: query
        name: filters.has_annotation
        required: false
        type: boolean
      - collectionFormat: multi
        default: Empty, do not filter
        description: Only return genome assemblies that have one of the specified
          assembly levels.
        in: query
        items:
          enum:
          - chromosome
          - scaffold
          - contig
          - complete_genome
          type: string
        name: filters.assembly_level
        required: false
        type: array
      - default: Empty, do not filter
        description: Only return genome assemblies that were released on or after
          the specified date.
        format: date-time
        in: query
        name: filters.first_release_date
        required: false
        type: string
      - default: Empty, do not filter
        description: Only return genome assemblies that were released on or before
          to the specified date.
        format: date-time
        in: query
        name: filters.last_release_date
        required: false
        type: string
      - collectionFormat: multi
        default: Empty, do not filter
        description: Only return results whose fields contain the specified search
          terms in their taxon, infraspecific, assembly name or submitter fields.
        in: query
        items:
          type: string
        name: filters.search_text
        required: false
        type: array
      - default: COMPLETE
        description: Return either assembly accessions, or entire assembly-metadata
          records.
        enum:
        - COMPLETE
        - ASSM_ACC
        in: query
        name: returned_content
        required: false
        type: string
      - default: 20
        description: The maximum number of genome assemblies to return. Default is
          20 and maximum is 1000. If the number of results exceeds the page size,  `page_token`
          can be used to retrieve the remaining results.
        format: int32
        in: query
        name: page_size
        required: false
        type: integer
      - description: A page token is returned from an `AssemblyMetadataRequest` call
          with more than `page_size` results. Use this token, along with the previous  `AssemblyMetadataRequest`
          parameters, to retrieve the next page of results. When `page_token` is empty,
          all results have been retrieved.
        in: query
        name: page_token
        required: false
        type: string
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1AssemblyMetadata'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get genome metadata by bioproject accession
      tags:
      - Genome
  /genome/check:
    post:
      description: The 'GET' version of check is limited by the size of the GET URL
        (2KB, which works out to about 140 genomic accessions).  The POST operation
        is provided to allow users to supply a larger number of accessions in a single
        request.
      operationId: check_assembly_availability_post
      parameters:
      - in: body
        name: body
        required: true
        schema:
          $ref: '#/definitions/v1alpha1AssemblyDatasetRequest'
      produces:
      - application/json
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1AssemblyDatasetAvailability'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Check the validity of many genome accessions in a single request
      tags:
      - Genome
  /genome/download:
    post:
      description: The 'GET' version of download is limited by the size of the GET
        URL (2KB, which works out to about 140 genomic accessions).  The POST operation
        is provided to allow users to supply a larger number of accessions in a single
        request.
      operationId: download_assembly_package_post
      parameters:
      - in: body
        name: body
        required: true
        schema:
          $ref: '#/definitions/v1alpha1AssemblyDatasetRequest'
      - default: ncbi_dataset.zip
        description: Output file name.
        in: query
        name: filename
        required: false
        type: string
      produces:
      - application/zip
      responses:
        '200':
          description: Download selected genome assemblies and associated annotation
            data as a zip file.
          schema:
            description: Zip compressed stream
            format: binary
            type: string
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get a genome dataset by post
      tags:
      - Genome
  /genome/download_summary:
    post:
      description: The 'GET' version of download summary is limited by the size of
        the GET URL (2KB, which works out to about 140 genomic accessions).  The POST
        operation is provided to allow users to supply a larger number of accessions
        in a single request.
      operationId: genome_download_summary_by_post
      parameters:
      - in: body
        name: body
        required: true
        schema:
          $ref: '#/definitions/v1alpha1AssemblyDatasetRequest'
      produces:
      - application/json
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1DownloadSummary'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Preview genome dataset download by POST
      tags:
      - Genome
  /genome/taxon/{taxon}:
    get:
      description: Get detailed metadata on all assembled genomes for a specified
        NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank
      operationId: assembly_descriptors_by_taxon
      parameters:
      - description: NCBI Taxonomy ID or name (common or scientific) at any taxonomic
          rank
        in: path
        name: taxon
        required: true
        type: string
      - default: False, do not filter
        description: If true, only return reference and representative (GCF_ and GCA_)
          genome assemblies.
        in: query
        name: filters.reference_only
        required: false
        type: boolean
      - default: All, do not filter
        description: Return only RefSeq (GCF_) or GenBank (GCA_) genome assemblies.
        enum:
        - all
        - refseq
        - genbank
        in: query
        name: filters.assembly_source
        required: false
        type: string
      - default: False, do not filter
        description: Return only annotated genome assemblies.
        in: query
        name: filters.has_annotation
        required: false
        type: boolean
      - collectionFormat: multi
        default: Empty, do not filter
        description: Only return genome assemblies that have one of the specified
          assembly levels.
        in: query
        items:
          enum:
          - chromosome
          - scaffold
          - contig
          - complete_genome
          type: string
        name: filters.assembly_level
        required: false
        type: array
      - default: Empty, do not filter
        description: Only return genome assemblies that were released on or after
          the specified date.
        format: date-time
        in: query
        name: filters.first_release_date
        required: false
        type: string
      - default: Empty, do not filter
        description: Only return genome assemblies that were released on or before
          to the specified date.
        format: date-time
        in: query
        name: filters.last_release_date
        required: false
        type: string
      - collectionFormat: multi
        default: Empty, do not filter
        description: Only return results whose fields contain the specified search
          terms in their taxon, infraspecific, assembly name or submitter fields.
        in: query
        items:
          type: string
        name: filters.search_text
        required: false
        type: array
      - default: False, include all taxonomy children
        description: If true, only return assemblies with the given NCBI Taxonomy
          ID, or name. Otherwise, assemblies from taxonomy subtree are included, too.
          Ignored for assembly_accession request.
        in: query
        name: tax_exact_match
        required: false
        type: boolean
      - default: COMPLETE
        description: Return either assembly accessions, or entire assembly-metadata
          records.
        enum:
        - COMPLETE
        - ASSM_ACC
        in: query
        name: returned_content
        required: false
        type: string
      - default: 20
        description: The maximum number of genome assemblies to return. Default is
          20 and maximum is 1000. If the number of results exceeds the page size,  `page_token`
          can be used to retrieve the remaining results.
        format: int32
        in: query
        name: page_size
        required: false
        type: integer
      - description: A page token is returned from an `AssemblyMetadataRequest` call
          with more than `page_size` results. Use this token, along with the previous  `AssemblyMetadataRequest`
          parameters, to retrieve the next page of results. When `page_token` is empty,
          all results have been retrieved.
        in: query
        name: page_token
        required: false
        type: string
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1AssemblyMetadata'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get genome metadata by taxonomic identifier
      tags:
      - Genome
  /genome/taxon/{taxon}/tree:
    get:
      description: Using a NCBI Taxonomy ID or name (common or scientific) at any
        rank, get a subtree filtered for species with assembled genomes
      operationId: genome_tax_tree
      parameters:
      - description: NCBI Taxonomy ID or name (common or scientific) at any taxonomic
          rank
        in: path
        name: taxon
        required: true
        type: string
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1Organism'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get a taxonomic subtree by taxonomic identifier
      tags:
      - Genome
  /genome/taxon_suggest/{taxon_query}:
    get:
      description: This endpoint retrieves a list of taxonomy names and IDs found
        in the assembly dataset given a partial taxonomic name of any rank.
      operationId: genome_tax_name_query
      parameters:
      - description: NCBI Taxonomy ID or name (common or scientific) at any taxonomic
          rank
        in: path
        name: taxon_query
        required: true
        type: string
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1SciNameAndIds'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get a list of taxonomy names and IDs found in the assembly dataset
        given a partial taxonomic name.
      tags:
      - Genome
  /protein/accession/download:
    post:
      description: Get a prokaryote gene dataset including gene and protein fasta
        sequence, annotation and metadata by prokaryote protein accession by POST.
      operationId: download_prokaryote_gene_package_post
      parameters:
      - in: body
        name: body
        required: true
        schema:
          $ref: '#/definitions/v1alpha1ProkaryoteGeneRequest'
      - default: ncbi_dataset.zip
        description: Output file name.
        in: query
        name: filename
        required: false
        type: string
      produces:
      - application/zip
      responses:
        '200':
          description: Download selected prokaryote gene data as a zip file.
          schema:
            description: Zip compressed stream
            format: binary
            type: string
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get a prokaryote gene dataset by RefSeq protein accession by POST
      tags:
      - Prokaryote
  /protein/accession/{accessions}/download:
    get:
      description: Get a prokaryote gene dataset including gene and protein fasta
        sequence, annotation and metadata by prokaryote protein accession.
      operationId: download_prokaryote_gene_package
      parameters:
      - collectionFormat: csv
        description: WP prokaryote protein accession
        in: path
        items:
          type: string
        minItems: 1
        name: accessions
        required: true
        type: array
      - collectionFormat: multi
        description: Select additional types of annotation to include in the data
          package.  If unset, no annotation is provided.
        in: query
        items:
          enum:
          - FASTA_GENE
          - FASTA_PROTEIN
          - FASTA_GENE_FLANK
          type: string
        name: include_annotation_type
        required: false
        type: array
      - format: int64
        in: query
        name: gene_flank_config.length
        required: false
        type: integer
      - description: NCBI Taxonomy ID or name (common or scientific) at any taxonomic
          rank When specified, return data from this taxon and its subtree.
        in: query
        name: taxon
        required: false
        type: string
      - default: ncbi_dataset.zip
        description: Output file name.
        in: query
        name: filename
        required: false
        type: string
      produces:
      - application/zip
      responses:
        '200':
          description: Download selected prokaryote gene data as a zip file.
          schema:
            description: Zip compressed stream
            format: binary
            type: string
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get a prokaryote gene dataset by RefSeq protein accession
      tags:
      - Prokaryote
  /version:
    get:
      description: Retrieve the latest version of the Datasets services.
      operationId: version
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1VersionReply'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Retrieve service version
      tags:
      - Version
  /virus/taxon/sars2/protein/{proteins}:
    get:
      description: Download a summary of available SARS-CoV-2 protein datasets
      operationId: sars2_protein_summary
      parameters:
      - collectionFormat: csv
        description: Which proteins to retrieve in the data package
        in: path
        items:
          type: string
        minItems: 1
        name: proteins
        required: true
        type: array
      - default: False, do not filter
        description: If true, limit results to RefSeq genomes.
        in: query
        name: refseq_only
        required: false
        type: boolean
      - default: False, do not filter
        description: If true, limit results to annotated genomes.
        in: query
        name: annotated_only
        required: false
        type: boolean
      - default: From the beginning of the archive
        description: 'If set, limit results to viral genomes that have been released
          after a specified date and time. April 1, 2020 midnight UTC should be formatted
          as follows: 2020-04-01T00:00:00.000Z.'
        format: date-time
        in: query
        name: released_since
        required: false
        type: string
      - default: All hosts
        description: If set, limit results to genomes extracted from this host (Taxonomy
          ID or name).
        in: query
        name: host
        required: false
        type: string
      - default: Empty, for no filtering
        description: Assemblies from this location (country and state, or continent).
        in: query
        name: geo_location
        required: false
        type: string
      - default: False, do not filter
        description: only include complete genomes.
        in: query
        name: complete_only
        required: false
        type: boolean
      - collectionFormat: multi
        default: No annotation
        description: Select additional types of annotation to include in the data
          package.  If unset, no annotation is provided.
        in: query
        items:
          enum:
          - CDS_FASTA
          - PROT_FASTA
          - GENOME_GPFF
          - PDB_FILES
          type: string
        name: include_annotation_type
        required: false
        type: array
      produces:
      - application/json
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1DownloadSummary'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Summary of SARS-CoV-2 protein and CDS datasets by protein name
      tags:
      - Virus
  /virus/taxon/sars2/protein/{proteins}/download:
    get:
      description: Download a SARS-CoV-2 protein datasets
      operationId: sars2_protein_download
      parameters:
      - collectionFormat: csv
        description: Which proteins to retrieve in the data package
        in: path
        items:
          type: string
        minItems: 1
        name: proteins
        required: true
        type: array
      - default: False, do not filter
        description: If true, limit results to RefSeq genomes.
        in: query
        name: refseq_only
        required: false
        type: boolean
      - default: False, do not filter
        description: If true, limit results to annotated genomes.
        in: query
        name: annotated_only
        required: false
        type: boolean
      - default: From the beginning of the archive
        description: 'If set, limit results to viral genomes that have been released
          after a specified date and time. April 1, 2020 midnight UTC should be formatted
          as follows: 2020-04-01T00:00:00.000Z.'
        format: date-time
        in: query
        name: released_since
        required: false
        type: string
      - default: All hosts
        description: If set, limit results to genomes extracted from this host (Taxonomy
          ID or name).
        in: query
        name: host
        required: false
        type: string
      - default: Empty, for no filtering
        description: Assemblies from this location (country and state, or continent).
        in: query
        name: geo_location
        required: false
        type: string
      - default: False, do not filter
        description: only include complete genomes.
        in: query
        name: complete_only
        required: false
        type: boolean
      - collectionFormat: multi
        description: Select additional types of annotation to include in the data
          package.  If unset, no annotation is provided.
        in: query
        items:
          enum:
          - CDS_FASTA
          - PROT_FASTA
          - GENOME_GPFF
          - PDB_FILES
          type: string
        name: include_annotation_type
        required: false
        type: array
      - default: ncbi_dataset.zip
        description: Output file name.
        in: query
        name: filename
        required: false
        type: string
      produces:
      - application/zip
      responses:
        '200':
          description: Download selected SARS-CoV-2 proteins and associated annotation
            data as a zip file.
          schema:
            description: Zip compressed stream
            format: binary
            type: string
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Download SARS-CoV-2 protein and CDS datasets by protein name
      tags:
      - Virus
  /virus/taxon/sars2/protein/{proteins}/table:
    get:
      description: Get protein metadata in tabular format for SARS-CoV-2 genomes.
      operationId: sars2_protein_table
      parameters:
      - collectionFormat: csv
        description: Which proteins to retrieve in the data package
        in: path
        items:
          type: string
        minItems: 1
        name: proteins
        required: true
        type: array
      - default: False, do not filter
        description: If true, limit results to RefSeq genomes.
        in: query
        name: refseq_only
        required: false
        type: boolean
      - default: False, do not filter
        description: If true, limit results to annotated genomes.
        in: query
        name: annotated_only
        required: false
        type: boolean
      - default: From the beginning of the archive
        description: 'If set, limit results to viral genomes that have been released
          after a specified date and time. April 1, 2020 midnight UTC should be formatted
          as follows: 2020-04-01T00:00:00.000Z.'
        format: date-time
        in: query
        name: released_since
        required: false
        type: string
      - default: All hosts
        description: If set, limit results to genomes extracted from this host (Taxonomy
          ID or name).
        in: query
        name: host
        required: false
        type: string
      - default: Empty, for no filtering
        description: Assemblies from this location (country and state, or continent).
        in: query
        name: geo_location
        required: false
        type: string
      - default: False, do not filter
        description: only include complete genomes.
        in: query
        name: complete_only
        required: false
        type: boolean
      - collectionFormat: multi
        description: Specify which fields to include in the tabular report.
        in: query
        items:
          enum:
          - nucleotide_accession
          - species_tax_id
          - species_name
          - genus
          - family
          - nucleotide_length
          - isolate_name
          - sequence_type
          - nuc_completeness
          - geo_location
          - us_state
          - host_name
          - host_tax_id
          - collection_date
          - bioproject
          - biosample
          - polyprotein_name
          - protein_name
          - protein_accession
          - protein_synonym
          - cds_span
          type: string
        name: table_fields
        required: false
        type: array
      - default: tsv
        description: Choose download format.
        enum:
        - tsv
        - csv
        - jsonl
        in: query
        name: format
        required: false
        type: string
      produces:
      - application/tsv
      responses:
        '200':
          description: A successful response.(streaming responses)
          schema:
            properties:
              error:
                $ref: '#/definitions/rpcStatus'
              result:
                $ref: '#/definitions/v1alpha1TabularOutput'
            title: Stream result of v1alpha1TabularOutput
            type: object
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get SARS-CoV-2 protein metadata in a tabular format.
      tags:
      - Virus
  /virus/taxon/{taxon}/genome:
    get:
      description: Get summary data and download by command line instructions for
        Coronaviridae genomes by taxon.
      operationId: virus_genome_summary
      parameters:
      - description: NCBI Taxonomy ID or name (common or scientific) at any taxonomic
          rank
        in: path
        name: taxon
        required: true
        type: string
      - default: False, do not filter
        description: If true, limit results to RefSeq genomes.
        in: query
        name: refseq_only
        required: false
        type: boolean
      - default: False, do not filter
        description: If true, limit results to annotated genomes.
        in: query
        name: annotated_only
        required: false
        type: boolean
      - default: From the beginning of the archive
        description: 'If set, limit results to viral genomes that have been released
          after a specified date (and optionally, time). April 1, 2020 midnight UTC
          should be formatted as follows: 2020-04-01T00:00:00.000Z.'
        format: date-time
        in: query
        name: released_since
        required: false
        type: string
      - default: All hosts
        description: If set, limit results to genomes extracted from this host (Taxonomy
          ID or name).
        in: query
        name: host
        required: false
        type: string
      - description: If set, limit results to genomes classified to this lineage by
          the PangoLearn tool.
        in: query
        name: pangolin_classification
        required: false
        type: string
      - default: Empty, for no filtering
        description: Assemblies from this location (country and state, or continent).
        in: query
        name: geo_location
        required: false
        type: string
      - default: False, do not filter
        description: only include complete genomes.
        in: query
        name: complete_only
        required: false
        type: boolean
      - default: False, thus including genomic sequence
        description: Set to true to omit the genomic sequence.
        in: query
        name: exclude_sequence
        required: false
        type: boolean
      - collectionFormat: multi
        default: No annotation
        description: Select additional types of annotation to include in the data
          package.  If unset, no annotation is provided.
        in: query
        items:
          enum:
          - CDS_FASTA
          - PROT_FASTA
          - GENOME_GBFF
          - GENOME_GPFF
          - PDB_FILES
          type: string
        name: include_annotation_type
        required: false
        type: array
      responses:
        '200':
          description: A successful response.
          schema:
            $ref: '#/definitions/v1alpha1DownloadSummary'
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get summary data for Coronaviridae genomes by taxon
      tags:
      - Virus
  /virus/taxon/{taxon}/genome/download:
    get:
      description: Download a Coronavirus genome datasets by taxon
      operationId: virus_genome_download
      parameters:
      - description: NCBI Taxonomy ID or name (common or scientific) at any taxonomic
          rank
        in: path
        name: taxon
        required: true
        type: string
      - default: False, do not filter
        description: If true, limit results to RefSeq genomes.
        in: query
        name: refseq_only
        required: false
        type: boolean
      - default: False, do not filter
        description: If true, limit results to annotated genomes.
        in: query
        name: annotated_only
        required: false
        type: boolean
      - default: From the beginning of the archive
        description: 'If set, limit results to viral genomes that have been released
          after a specified date (and optionally, time). April 1, 2020 midnight UTC
          should be formatted as follows: 2020-04-01T00:00:00.000Z.'
        format: date-time
        in: query
        name: released_since
        required: false
        type: string
      - default: All hosts
        description: If set, limit results to genomes extracted from this host (Taxonomy
          ID or name).
        in: query
        name: host
        required: false
        type: string
      - description: If set, limit results to genomes classified to this lineage by
          the PangoLearn tool.
        in: query
        name: pangolin_classification
        required: false
        type: string
      - default: Empty, for no filtering
        description: Assemblies from this location (country and state, or continent).
        in: query
        name: geo_location
        required: false
        type: string
      - default: False, do not filter
        description: only include complete genomes.
        in: query
        name: complete_only
        required: false
        type: boolean
      - default: False, thus including genomic sequence
        description: Set to true to omit the genomic sequence.
        in: query
        name: exclude_sequence
        required: false
        type: boolean
      - collectionFormat: multi
        default: No annotation
        description: Select additional types of annotation to include in the data
          package.  If unset, no annotation is provided.
        in: query
        items:
          enum:
          - CDS_FASTA
          - PROT_FASTA
          - GENOME_GBFF
          - GENOME_GPFF
          - PDB_FILES
          type: string
        name: include_annotation_type
        required: false
        type: array
      - default: ncbi_dataset.zip
        description: Output file name.
        in: query
        name: filename
        required: false
        type: string
      produces:
      - application/zip
      responses:
        '200':
          description: Download selected viral genome and associated annotation data
            as a zip file.
          schema:
            description: Zip compressed stream
            format: binary
            type: string
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Download Coronavirus genome datasets by taxon
      tags:
      - Virus
  /virus/taxon/{taxon}/genome/table:
    get:
      description: Get viral genomic metadata in tabular format for Coronaviridae
        genomes by taxon.
      operationId: virus_genome_table
      parameters:
      - description: NCBI Taxonomy ID or name (common or scientific) at any taxonomic
          rank
        in: path
        name: taxon
        required: true
        type: string
      - default: False, do not filter
        description: If true, limit results to RefSeq genomes.
        in: query
        name: refseq_only
        required: false
        type: boolean
      - default: False, do not filter
        description: If true, limit results to annotated genomes.
        in: query
        name: annotated_only
        required: false
        type: boolean
      - default: From the beginning of the archive
        description: 'If set, limit results to viral genomes that have been released
          after a specified date (and optionally, time). April 1, 2020 midnight UTC
          should be formatted as follows: 2020-04-01T00:00:00.000Z.'
        format: date-time
        in: query
        name: released_since
        required: false
        type: string
      - default: All hosts
        description: If set, limit results to genomes extracted from this host (Taxonomy
          ID or name).
        in: query
        name: host
        required: false
        type: string
      - description: If set, limit results to genomes classified to this lineage by
          the PangoLearn tool.
        in: query
        name: pangolin_classification
        required: false
        type: string
      - default: Empty, for no filtering
        description: Assemblies from this location (country and state, or continent).
        in: query
        name: geo_location
        required: false
        type: string
      - default: False, do not filter
        description: only include complete genomes.
        in: query
        name: complete_only
        required: false
        type: boolean
      - collectionFormat: multi
        description: Specify which fields to include in the tabular report.
        in: query
        items:
          enum:
          - nucleotide_accession
          - species_tax_id
          - species_name
          - genus
          - family
          - nucleotide_length
          - isolate_name
          - sequence_type
          - nuc_completeness
          - geo_location
          - us_state
          - host_name
          - host_tax_id
          - collection_date
          - bioproject
          - biosample
          - polyprotein_name
          - protein_name
          - protein_accession
          - protein_synonym
          - cds_span
          type: string
        name: table_fields
        required: false
        type: array
      - default: tsv
        description: Choose download format (tsv, csv or jsonl).
        enum:
        - tsv
        - csv
        - jsonl
        in: query
        name: format
        required: false
        type: string
      produces:
      - application/tsv
      responses:
        '200':
          description: A successful response.(streaming responses)
          schema:
            properties:
              error:
                $ref: '#/definitions/rpcStatus'
              result:
                $ref: '#/definitions/v1alpha1TabularOutput'
            title: Stream result of v1alpha1TabularOutput
            type: object
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/rpcStatus'
      summary: Get viral genomic metadata in a tabular format.
      tags:
      - Virus
produces:
- application/json
schemes:
- https
security:
- ApiKeyAuthHeader: []
securityDefinitions:
  ApiKeyAuth:
    in: query
    name: api_key
    type: apiKey
  ApiKeyAuthHeader:
    in: header
    name: api-key
    type: apiKey
swagger: '2.0'
tags:
- description: Options to explore, summarize and download assembled genomes, including
    the associated sequence, metadata and annotation.
  name: Genome
- description: Options to explore, summarize and download sequences and metadata for
    genes and their associated transcripts and proteins.
  name: Gene
- description: Options to explore, summarize and download sequences and metadata for
    prokaryote genes and their associated proteins.
  name: Prokaryote
- description: Options to summarize and download sequences SARS-CoV-2 and coronavirus
    genome and protein sequence, annotation and metadata.
  name: Virus