nih-gov/www.ncbi.nlm.nih.gov/datasets/docs/v2/openapi3/openapi3.docs.yaml/index.html

13611 lines
445 KiB
HTML

openapi: 3.0.1
info:
title: NCBI Datasets API
version: v2
description: '### NCBI Datasets is a resource that lets you easily gather data from
NCBI.
The Datasets version 2 API is still in alpha, and we''re updating it often to add new functionality,
iron out bugs and enhance usability.
For some larger downloads, you may want to download a [dehydrated zip archive](https://www.ncbi.nlm.nih.gov/datasets/docs/v2/how-tos/genomes/large-download/),
and retrieve the individual data files at a later time.
'
contact:
name: NCBI
url: https://www.ncbi.nlm.nih.gov/datasets
email: help@ncbi.nlm.nih.gov
servers:
- url: https://api.ncbi.nlm.nih.gov/datasets/v2
- url: https://dev.ncbi.nlm.nih.gov/datasets/v2
tags:
- name: Genome
description: '#### Options to explore, summarize, and download assembled genomes, including associated
sequences, metadata, and annotations.
These genome services allow you to browse genome assemblies. For genomes of interest,
identified by taxonomic name or ID, Assembly, BioProject, BioSample, WGS or Nucleotide
accession, you can explore metadata, generate summaries, and determine package sizes. You can
download data packages including metadata (in tabular and JSON Lines formats), annotation,
genome, protein, RNA and CDS sequence in FASTA format by Assembly or BioProject
accession.
'
- name: Gene
description: '#### Options to explore, summarize, and download sequences and metadata for genes and gene
ortholog sets, along with their associated transcripts and proteins.
These gene services allow you to explore RefSeq curated gene data. For genes of interest,
identified by GeneID, Gene symbol, or RefSeq sequence accession, you can download data
packages including metadata (in tabular and JSON Lines formats), and gene, transcript and
protein sequences in FASTA format.
'
- name: BioSample
description: '#### Options to explore and download BioSample data by BioSample accession.
These BioSample services allow you to browse metadata for specified BioSample accessions.
'
- name: Prokaryote
description: '#### Options to download sequences and metadata for prokaryotic genes and their associated proteins.
These prokaryote services allow you to download prokaryotic gene data by RefSeq protein
sequence accession (WP_). You can download data packages including gene metadata, genomic
annotations (in JSON Lines format), and gene and protein sequences in FASTA format.
'
- name: Virus
description: '#### Options to explore, summarize, and download virus genome and protein sequences, annotations
and associated metadata.
These virus services allow you to explore virus metadata and annotations curated by NCBI Virus
or download a data package including metadata and annotations (in JSON Lines formats), and
genome, transcript, CDS and protein sequences in FASTA format.
'
- name: Version
description: "#### Retrieve the current version of all services. \nServices follow\
\ [Semantic Versioning 2.0.0 Schema](https://semver.org/spec/v2.0.0.html).\n"
- name: Taxonomy
description: '#### Options to explore and download taxonomic metadata, images, and relationships.
These taxonomy services allow you to explore taxonomic metadata and images, retrieve parent
lineages, and access filtered sets of child nodes for specified taxonomic identifiers.
'
- name: Organelle
description: '#### Options to explore, summarize, and download RefSeq-curated organelle genomes, including associated sequences, metadata, and annotations.
These organelle services allow you to browse organelle metadata by genomic accession or
taxonomic identifiers. You can download data packages including metadata, gene annotation
information in JSON Lines format, and genome and protein sequences in FASTA format.
'
externalDocs:
description: Interactively explore genome assembly datasets
url: https://www.ncbi.nlm.nih.gov/datasets/genomes/
security:
- ApiKeyAuthHeader: []
paths:
/genome/accession/{accessions}/download_summary:
get:
summary: Preview genome dataset download
description: 'Get a download summary by accession in a JSON output format.'
tags:
- Genome
operationId: genome_download_summary
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2DownloadSummary'
parameters:
- name: accessions
description: 'NCBI genome assembly accessions'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- GCF_000001405.40
summary: Human
example-1:
value:
- GCF_000001405.40
- GCF_000001635.27
summary: Human and Mouse
- name: 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
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- "1"
- "2"
- "3"
- X
- Y
- MT
summary: Selected chromosomes #1
example-1:
value:
- X
- Y
summary: Human sex chromosomes
- name: include_annotation_type
description: 'Select additional types of annotation to include in the data package. If unset, no annotation is provided.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2AnnotationForAssemblyType'
examples:
example-0:
value:
- GENOME_FASTA
- PROT_FASTA
- RNA_FASTA
summary: Genomic, Transcript & Protein Sequence
example-1:
value:
- GENOME_GFF
- GENOME_GBFF
- GENOME_GTF
- PROT_FASTA
- RNA_FASTA
- CDS_FASTA
- SEQUENCE_REPORT
summary: All
/genome/download_summary:
post:
summary: Preview genome dataset download by 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.'
tags:
- Genome
operationId: genome_download_summary_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2DownloadSummary'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyDatasetRequest'
examples:
Single GCF accession example:
description: GCF Accession (just one)
value:
accessions:
- GCF_000001405.40
/genome/accession/{accessions}/dataset_report:
get:
summary: Get dataset reports by accessions
description: 'Get dataset reports by accessions. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Genome
operationId: genome_dataset_report
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsAssemblyDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsAssemblyDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: accessions
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- GCF_000001405.40
summary: Human
example-1:
value:
- GCF_000001405.40
- GCF_000001635.27
summary: Human and Mouse
- name: filters.reference_only
description: 'If true, only return reference genome assemblies'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to reference genomes
example-1:
value: false
summary: Include reference and non-reference genomes
- name: filters.assembly_source
description: 'Return only RefSeq (GCF_) or GenBank (GCA_) genome assemblies'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterAssemblySource'
examples:
example-0:
value: refseq
summary: Limit to RefSeq genomes
example-1:
value: genbank
summary: Limit to GenBank genomes
example-2:
value: all
summary: All genomes
- name: filters.has_annotation
description: 'Return only annotated genome assemblies'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated assemblies
example-1:
value: false
summary: Return all assemblies
- name: filters.exclude_paired_reports
description: 'For paired (GCA/GCF) records, only return the primary record'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all assemblies
example-1:
value: true
summary: Only return single record for GCA/GCF pairs
- name: filters.exclude_atypical
description: 'If true, exclude atypical genomes, i.e. genomes that have assembly issues or are otherwise atypical'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones that are atypical
example-1:
value: true
summary: Only return genomes that have not been classified as atypical
- name: filters.assembly_version
description: 'Return all assemblies, including replaced and suppressed, or only current assemblies'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterAssemblyVersion'
examples:
example-0:
value: current
summary: Only return current assemblies
example-1:
value: all_assemblies
summary: Return all assemblies, including suppressed and replaced
- name: filters.assembly_level
description: 'Only return genome assemblies that have one of the specified assembly levels. By default, do not filter.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2reportsAssemblyLevel'
examples:
example-0:
value:
- chromosome
- complete_genome
summary: Chromosome and complete genome
example-1:
value:
- scaffold
- chromosome
- complete_genome
summary: Scaffold and higher
- name: filters.first_release_date
description: 'Only return genome assemblies that were released on or after the specified date By default, do not filter.'
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2015-01-10T00:00:00Z
summary: Jan 10, 2015
- name: filters.last_release_date
description: 'Only return genome assemblies that were released on or before to the specified date By default, do not filter.'
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-01-10T00:00:00Z
summary: Jan 10, 2021
- name: filters.search_text
description: 'Only return results whose fields contain the specified search terms in their taxon, infraspecific, assembly name or submitter fields By default, do not filter'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- Genome Reference Consortium
summary: Genome Reference Consortium
example-1:
value:
- GRCh38
summary: GRCh38
example-2:
value:
- C57BL/6J
summary: C57BL/6J
- name: filters.is_metagenome_derived
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterMetagenomeDerivedFilter'
examples:
example-0:
value: metagenome_derived_exclude
summary: Exclude metagenome derived assemblies
example-1:
value: metagenome_derived_only
summary: Return only metagenome derived assemblies
- name: filters.is_type_material
description: 'If true, include only type materials'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of type materials
example-1:
value: true
summary: Only return genomes that are classified as type materials
- name: filters.is_ictv_exemplar
description: 'If true, include only ICTV Exemplars'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of type ICTV exemplar
example-1:
value: true
summary: Only return genomes that are classified as ICTV exemplar
- name: filters.exclude_multi_isolate
description: 'If true, exclude large multi-isolate projects'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of large multi-isolate projects
example-1:
value: true
summary: Exclude genomes that are classified as large multi-isolate projects
- name: filters.type_material_category
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterTypeMaterialCategory'
examples:
example-0:
value: TYPE_MATERIAL
summary: A Type Material with no classification
example-1:
value: TYPE_MATERIAL_CLADE
summary: A Type Material of the Clade classification
example-2:
value: TYPE_MATERIAL_NEOTYPE
summary: A Type Material of the Neotype classification
- name: 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.'
in: query
required: false
schema:
type: boolean
default: false
- name: table_fields
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- assminfo-accession
- assminfo-name
summary: Genome Accession and Name
example-1:
value:
- assminfo-accession
summary: Just accession
- name: returned_content
description: 'Return either assembly accessions, or complete assembly reports'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetReportsRequestContentType'
- name: page_size
description: 'The maximum number of genome assembly reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: sort.field
in: query
required: false
schema:
type: string
- name: sort.direction
in: query
required: false
schema:
$ref: '#/components/schemas/v2SortDirection'
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
/genome/taxon/{taxons}/dataset_report:
get:
summary: Get dataset reports by taxons
description: 'Get dataset reports by taxons. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Genome
operationId: genome_dataset_reports_by_taxon
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsAssemblyDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsAssemblyDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: taxons
description: 'NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- "9606"
summary: NCBI Taxonomy Identifier
example-1:
value:
- chimpanzee
- eastern gorilla
summary: Common Names
example-2:
value:
- Homo sapiens
summary: Scientific Name
- name: filters.reference_only
description: 'If true, only return reference genome assemblies'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to reference genomes
example-1:
value: false
summary: Include reference and non-reference genomes
- name: filters.assembly_source
description: 'Return only RefSeq (GCF_) or GenBank (GCA_) genome assemblies'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterAssemblySource'
examples:
example-0:
value: refseq
summary: Limit to RefSeq genomes
example-1:
value: genbank
summary: Limit to GenBank genomes
example-2:
value: all
summary: All genomes
- name: filters.has_annotation
description: 'Return only annotated genome assemblies'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated assemblies
example-1:
value: false
summary: Return all assemblies
- name: filters.exclude_paired_reports
description: 'For paired (GCA/GCF) records, only return the primary record'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all assemblies
example-1:
value: true
summary: Only return single record for GCA/GCF pairs
- name: filters.exclude_atypical
description: 'If true, exclude atypical genomes, i.e. genomes that have assembly issues or are otherwise atypical'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones that are atypical
example-1:
value: true
summary: Only return genomes that have not been classified as atypical
- name: filters.assembly_version
description: 'Return all assemblies, including replaced and suppressed, or only current assemblies'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterAssemblyVersion'
examples:
example-0:
value: current
summary: Only return current assemblies
example-1:
value: all_assemblies
summary: Return all assemblies, including suppressed and replaced
- name: filters.assembly_level
description: 'Only return genome assemblies that have one of the specified assembly levels. By default, do not filter.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2reportsAssemblyLevel'
examples:
example-0:
value:
- chromosome
- complete_genome
summary: Chromosome and complete genome
example-1:
value:
- scaffold
- chromosome
- complete_genome
summary: Scaffold and higher
- name: filters.first_release_date
description: 'Only return genome assemblies that were released on or after the specified date By default, do not filter.'
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2015-01-10T00:00:00Z
summary: Jan 10, 2015
- name: filters.last_release_date
description: 'Only return genome assemblies that were released on or before to the specified date By default, do not filter.'
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-01-10T00:00:00Z
summary: Jan 10, 2021
- name: filters.search_text
description: 'Only return results whose fields contain the specified search terms in their taxon, infraspecific, assembly name or submitter fields By default, do not filter'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- Genome Reference Consortium
summary: Genome Reference Consortium
example-1:
value:
- GRCh38
summary: GRCh38
example-2:
value:
- C57BL/6J
summary: C57BL/6J
- name: filters.is_metagenome_derived
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterMetagenomeDerivedFilter'
examples:
example-0:
value: metagenome_derived_exclude
summary: Exclude metagenome derived assemblies
example-1:
value: metagenome_derived_only
summary: Return only metagenome derived assemblies
- name: filters.is_type_material
description: 'If true, include only type materials'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of type materials
example-1:
value: true
summary: Only return genomes that are classified as type materials
- name: filters.is_ictv_exemplar
description: 'If true, include only ICTV Exemplars'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of type ICTV exemplar
example-1:
value: true
summary: Only return genomes that are classified as ICTV exemplar
- name: filters.exclude_multi_isolate
description: 'If true, exclude large multi-isolate projects'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of large multi-isolate projects
example-1:
value: true
summary: Exclude genomes that are classified as large multi-isolate projects
- name: filters.type_material_category
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterTypeMaterialCategory'
examples:
example-0:
value: TYPE_MATERIAL
summary: A Type Material with no classification
example-1:
value: TYPE_MATERIAL_CLADE
summary: A Type Material of the Clade classification
example-2:
value: TYPE_MATERIAL_NEOTYPE
summary: A Type Material of the Neotype classification
- name: 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.'
in: query
required: false
schema:
type: boolean
default: false
- name: table_fields
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- assminfo-accession
- assminfo-name
summary: Genome Accession and Name
example-1:
value:
- assminfo-accession
summary: Just accession
- name: returned_content
description: 'Return either assembly accessions, or complete assembly reports'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetReportsRequestContentType'
- name: page_size
description: 'The maximum number of genome assembly reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: sort.field
in: query
required: false
schema:
type: string
- name: sort.direction
in: query
required: false
schema:
$ref: '#/components/schemas/v2SortDirection'
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
/genome/bioproject/{bioprojects}/dataset_report:
get:
summary: Get dataset reports by bioproject
description: 'Get dataset reports by bioprojects. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Genome
operationId: genome_dataset_reports_by_bioproject
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsAssemblyDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsAssemblyDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: bioprojects
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- PRJNA489243
summary: Vertebrate Genomes Project
example-1:
value:
- PRJNA31257
summary: Human Genome Project
- name: filters.reference_only
description: 'If true, only return reference genome assemblies'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to reference genomes
example-1:
value: false
summary: Include reference and non-reference genomes
- name: filters.assembly_source
description: 'Return only RefSeq (GCF_) or GenBank (GCA_) genome assemblies'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterAssemblySource'
examples:
example-0:
value: refseq
summary: Limit to RefSeq genomes
example-1:
value: genbank
summary: Limit to GenBank genomes
example-2:
value: all
summary: All genomes
- name: filters.has_annotation
description: 'Return only annotated genome assemblies'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated assemblies
example-1:
value: false
summary: Return all assemblies
- name: filters.exclude_paired_reports
description: 'For paired (GCA/GCF) records, only return the primary record'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all assemblies
example-1:
value: true
summary: Only return single record for GCA/GCF pairs
- name: filters.exclude_atypical
description: 'If true, exclude atypical genomes, i.e. genomes that have assembly issues or are otherwise atypical'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones that are atypical
example-1:
value: true
summary: Only return genomes that have not been classified as atypical
- name: filters.assembly_version
description: 'Return all assemblies, including replaced and suppressed, or only current assemblies'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterAssemblyVersion'
examples:
example-0:
value: current
summary: Only return current assemblies
example-1:
value: all_assemblies
summary: Return all assemblies, including suppressed and replaced
- name: filters.assembly_level
description: 'Only return genome assemblies that have one of the specified assembly levels. By default, do not filter.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2reportsAssemblyLevel'
examples:
example-0:
value:
- chromosome
- complete_genome
summary: Chromosome and complete genome
example-1:
value:
- scaffold
- chromosome
- complete_genome
summary: Scaffold and higher
- name: filters.first_release_date
description: 'Only return genome assemblies that were released on or after the specified date By default, do not filter.'
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2015-01-10T00:00:00Z
summary: Jan 10, 2015
- name: filters.last_release_date
description: 'Only return genome assemblies that were released on or before to the specified date By default, do not filter.'
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-01-10T00:00:00Z
summary: Jan 10, 2021
- name: filters.search_text
description: 'Only return results whose fields contain the specified search terms in their taxon, infraspecific, assembly name or submitter fields By default, do not filter'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- Genome Reference Consortium
summary: Genome Reference Consortium
example-1:
value:
- GRCh38
summary: GRCh38
example-2:
value:
- C57BL/6J
summary: C57BL/6J
- name: filters.is_metagenome_derived
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterMetagenomeDerivedFilter'
examples:
example-0:
value: metagenome_derived_exclude
summary: Exclude metagenome derived assemblies
example-1:
value: metagenome_derived_only
summary: Return only metagenome derived assemblies
- name: filters.is_type_material
description: 'If true, include only type materials'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of type materials
example-1:
value: true
summary: Only return genomes that are classified as type materials
- name: filters.is_ictv_exemplar
description: 'If true, include only ICTV Exemplars'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of type ICTV exemplar
example-1:
value: true
summary: Only return genomes that are classified as ICTV exemplar
- name: filters.exclude_multi_isolate
description: 'If true, exclude large multi-isolate projects'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of large multi-isolate projects
example-1:
value: true
summary: Exclude genomes that are classified as large multi-isolate projects
- name: filters.type_material_category
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterTypeMaterialCategory'
examples:
example-0:
value: TYPE_MATERIAL
summary: A Type Material with no classification
example-1:
value: TYPE_MATERIAL_CLADE
summary: A Type Material of the Clade classification
example-2:
value: TYPE_MATERIAL_NEOTYPE
summary: A Type Material of the Neotype classification
- name: 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.'
in: query
required: false
schema:
type: boolean
default: false
- name: table_fields
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- assminfo-accession
- assminfo-name
summary: Genome Accession and Name
example-1:
value:
- assminfo-accession
summary: Just accession
- name: returned_content
description: 'Return either assembly accessions, or complete assembly reports'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetReportsRequestContentType'
- name: page_size
description: 'The maximum number of genome assembly reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: sort.field
in: query
required: false
schema:
type: string
- name: sort.direction
in: query
required: false
schema:
$ref: '#/components/schemas/v2SortDirection'
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
/genome/biosample/{biosample_ids}/dataset_report:
get:
summary: Get dataset reports by biosample id
description: 'Get dataset reports by biosample id. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Genome
operationId: genome_dataset_reports_by_biosample_id
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsAssemblyDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsAssemblyDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: biosample_ids
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- SAMN15960293
summary: BioSample Identifier
- name: filters.reference_only
description: 'If true, only return reference genome assemblies'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to reference genomes
example-1:
value: false
summary: Include reference and non-reference genomes
- name: filters.assembly_source
description: 'Return only RefSeq (GCF_) or GenBank (GCA_) genome assemblies'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterAssemblySource'
examples:
example-0:
value: refseq
summary: Limit to RefSeq genomes
example-1:
value: genbank
summary: Limit to GenBank genomes
example-2:
value: all
summary: All genomes
- name: filters.has_annotation
description: 'Return only annotated genome assemblies'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated assemblies
example-1:
value: false
summary: Return all assemblies
- name: filters.exclude_paired_reports
description: 'For paired (GCA/GCF) records, only return the primary record'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all assemblies
example-1:
value: true
summary: Only return single record for GCA/GCF pairs
- name: filters.exclude_atypical
description: 'If true, exclude atypical genomes, i.e. genomes that have assembly issues or are otherwise atypical'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones that are atypical
example-1:
value: true
summary: Only return genomes that have not been classified as atypical
- name: filters.assembly_version
description: 'Return all assemblies, including replaced and suppressed, or only current assemblies'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterAssemblyVersion'
examples:
example-0:
value: current
summary: Only return current assemblies
example-1:
value: all_assemblies
summary: Return all assemblies, including suppressed and replaced
- name: filters.assembly_level
description: 'Only return genome assemblies that have one of the specified assembly levels. By default, do not filter.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2reportsAssemblyLevel'
examples:
example-0:
value:
- chromosome
- complete_genome
summary: Chromosome and complete genome
example-1:
value:
- scaffold
- chromosome
- complete_genome
summary: Scaffold and higher
- name: filters.first_release_date
description: 'Only return genome assemblies that were released on or after the specified date By default, do not filter.'
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2015-01-10T00:00:00Z
summary: Jan 10, 2015
- name: filters.last_release_date
description: 'Only return genome assemblies that were released on or before to the specified date By default, do not filter.'
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-01-10T00:00:00Z
summary: Jan 10, 2021
- name: filters.search_text
description: 'Only return results whose fields contain the specified search terms in their taxon, infraspecific, assembly name or submitter fields By default, do not filter'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- Genome Reference Consortium
summary: Genome Reference Consortium
example-1:
value:
- GRCh38
summary: GRCh38
example-2:
value:
- C57BL/6J
summary: C57BL/6J
- name: filters.is_metagenome_derived
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterMetagenomeDerivedFilter'
examples:
example-0:
value: metagenome_derived_exclude
summary: Exclude metagenome derived assemblies
example-1:
value: metagenome_derived_only
summary: Return only metagenome derived assemblies
- name: filters.is_type_material
description: 'If true, include only type materials'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of type materials
example-1:
value: true
summary: Only return genomes that are classified as type materials
- name: filters.is_ictv_exemplar
description: 'If true, include only ICTV Exemplars'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of type ICTV exemplar
example-1:
value: true
summary: Only return genomes that are classified as ICTV exemplar
- name: filters.exclude_multi_isolate
description: 'If true, exclude large multi-isolate projects'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of large multi-isolate projects
example-1:
value: true
summary: Exclude genomes that are classified as large multi-isolate projects
- name: filters.type_material_category
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterTypeMaterialCategory'
examples:
example-0:
value: TYPE_MATERIAL
summary: A Type Material with no classification
example-1:
value: TYPE_MATERIAL_CLADE
summary: A Type Material of the Clade classification
example-2:
value: TYPE_MATERIAL_NEOTYPE
summary: A Type Material of the Neotype classification
- name: 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.'
in: query
required: false
schema:
type: boolean
default: false
- name: table_fields
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- assminfo-accession
- assminfo-name
summary: Genome Accession and Name
example-1:
value:
- assminfo-accession
summary: Just accession
- name: returned_content
description: 'Return either assembly accessions, or complete assembly reports'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetReportsRequestContentType'
- name: page_size
description: 'The maximum number of genome assembly reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: sort.field
in: query
required: false
schema:
type: string
- name: sort.direction
in: query
required: false
schema:
$ref: '#/components/schemas/v2SortDirection'
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
/genome/wgs/{wgs_accessions}/dataset_report:
get:
summary: Get dataset reports by wgs accession
description: 'Get dataset reports by wgs accession. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Genome
operationId: genome_dataset_reports_by_wgs
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsAssemblyDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsAssemblyDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: wgs_accessions
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- JAXUCZ01
summary: Norway rat (Rattus norvegicus) wgs accession
example-1:
value:
- JAHLSK02
- JAAKGM02
summary: Human wgs accessions
- name: filters.reference_only
description: 'If true, only return reference genome assemblies'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to reference genomes
example-1:
value: false
summary: Include reference and non-reference genomes
- name: filters.assembly_source
description: 'Return only RefSeq (GCF_) or GenBank (GCA_) genome assemblies'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterAssemblySource'
examples:
example-0:
value: refseq
summary: Limit to RefSeq genomes
example-1:
value: genbank
summary: Limit to GenBank genomes
example-2:
value: all
summary: All genomes
- name: filters.has_annotation
description: 'Return only annotated genome assemblies'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated assemblies
example-1:
value: false
summary: Return all assemblies
- name: filters.exclude_paired_reports
description: 'For paired (GCA/GCF) records, only return the primary record'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all assemblies
example-1:
value: true
summary: Only return single record for GCA/GCF pairs
- name: filters.exclude_atypical
description: 'If true, exclude atypical genomes, i.e. genomes that have assembly issues or are otherwise atypical'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones that are atypical
example-1:
value: true
summary: Only return genomes that have not been classified as atypical
- name: filters.assembly_version
description: 'Return all assemblies, including replaced and suppressed, or only current assemblies'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterAssemblyVersion'
examples:
example-0:
value: current
summary: Only return current assemblies
example-1:
value: all_assemblies
summary: Return all assemblies, including suppressed and replaced
- name: filters.assembly_level
description: 'Only return genome assemblies that have one of the specified assembly levels. By default, do not filter.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2reportsAssemblyLevel'
examples:
example-0:
value:
- chromosome
- complete_genome
summary: Chromosome and complete genome
example-1:
value:
- scaffold
- chromosome
- complete_genome
summary: Scaffold and higher
- name: filters.first_release_date
description: 'Only return genome assemblies that were released on or after the specified date By default, do not filter.'
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2015-01-10T00:00:00Z
summary: Jan 10, 2015
- name: filters.last_release_date
description: 'Only return genome assemblies that were released on or before to the specified date By default, do not filter.'
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-01-10T00:00:00Z
summary: Jan 10, 2021
- name: filters.search_text
description: 'Only return results whose fields contain the specified search terms in their taxon, infraspecific, assembly name or submitter fields By default, do not filter'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- Genome Reference Consortium
summary: Genome Reference Consortium
example-1:
value:
- GRCh38
summary: GRCh38
example-2:
value:
- C57BL/6J
summary: C57BL/6J
- name: filters.is_metagenome_derived
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterMetagenomeDerivedFilter'
examples:
example-0:
value: metagenome_derived_exclude
summary: Exclude metagenome derived assemblies
example-1:
value: metagenome_derived_only
summary: Return only metagenome derived assemblies
- name: filters.is_type_material
description: 'If true, include only type materials'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of type materials
example-1:
value: true
summary: Only return genomes that are classified as type materials
- name: filters.is_ictv_exemplar
description: 'If true, include only ICTV Exemplars'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of type ICTV exemplar
example-1:
value: true
summary: Only return genomes that are classified as ICTV exemplar
- name: filters.exclude_multi_isolate
description: 'If true, exclude large multi-isolate projects'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of large multi-isolate projects
example-1:
value: true
summary: Exclude genomes that are classified as large multi-isolate projects
- name: filters.type_material_category
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterTypeMaterialCategory'
examples:
example-0:
value: TYPE_MATERIAL
summary: A Type Material with no classification
example-1:
value: TYPE_MATERIAL_CLADE
summary: A Type Material of the Clade classification
example-2:
value: TYPE_MATERIAL_NEOTYPE
summary: A Type Material of the Neotype classification
- name: 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.'
in: query
required: false
schema:
type: boolean
default: false
- name: table_fields
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- assminfo-accession
- assminfo-name
summary: Genome Accession and Name
example-1:
value:
- assminfo-accession
summary: Just accession
- name: returned_content
description: 'Return either assembly accessions, or complete assembly reports'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetReportsRequestContentType'
- name: page_size
description: 'The maximum number of genome assembly reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: sort.field
in: query
required: false
schema:
type: string
- name: sort.direction
in: query
required: false
schema:
$ref: '#/components/schemas/v2SortDirection'
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
/genome/assembly_name/{assembly_names}/dataset_report:
get:
summary: Get dataset reports by assembly name (exact)
description: 'Get dataset reports by assembly name (exact). By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Genome
operationId: genome_dataset_reports_by_assembly_name
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsAssemblyDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsAssemblyDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: assembly_names
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- HanXRQr2.0-SUNRISE
summary: Assembly name (exact)
- name: filters.reference_only
description: 'If true, only return reference genome assemblies'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to reference genomes
example-1:
value: false
summary: Include reference and non-reference genomes
- name: filters.assembly_source
description: 'Return only RefSeq (GCF_) or GenBank (GCA_) genome assemblies'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterAssemblySource'
examples:
example-0:
value: refseq
summary: Limit to RefSeq genomes
example-1:
value: genbank
summary: Limit to GenBank genomes
example-2:
value: all
summary: All genomes
- name: filters.has_annotation
description: 'Return only annotated genome assemblies'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated assemblies
example-1:
value: false
summary: Return all assemblies
- name: filters.exclude_paired_reports
description: 'For paired (GCA/GCF) records, only return the primary record'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all assemblies
example-1:
value: true
summary: Only return single record for GCA/GCF pairs
- name: filters.exclude_atypical
description: 'If true, exclude atypical genomes, i.e. genomes that have assembly issues or are otherwise atypical'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones that are atypical
example-1:
value: true
summary: Only return genomes that have not been classified as atypical
- name: filters.assembly_version
description: 'Return all assemblies, including replaced and suppressed, or only current assemblies'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterAssemblyVersion'
examples:
example-0:
value: current
summary: Only return current assemblies
example-1:
value: all_assemblies
summary: Return all assemblies, including suppressed and replaced
- name: filters.assembly_level
description: 'Only return genome assemblies that have one of the specified assembly levels. By default, do not filter.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2reportsAssemblyLevel'
examples:
example-0:
value:
- chromosome
- complete_genome
summary: Chromosome and complete genome
example-1:
value:
- scaffold
- chromosome
- complete_genome
summary: Scaffold and higher
- name: filters.first_release_date
description: 'Only return genome assemblies that were released on or after the specified date By default, do not filter.'
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2015-01-10T00:00:00Z
summary: Jan 10, 2015
- name: filters.last_release_date
description: 'Only return genome assemblies that were released on or before to the specified date By default, do not filter.'
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-01-10T00:00:00Z
summary: Jan 10, 2021
- name: filters.search_text
description: 'Only return results whose fields contain the specified search terms in their taxon, infraspecific, assembly name or submitter fields By default, do not filter'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- Genome Reference Consortium
summary: Genome Reference Consortium
example-1:
value:
- GRCh38
summary: GRCh38
example-2:
value:
- C57BL/6J
summary: C57BL/6J
- name: filters.is_metagenome_derived
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterMetagenomeDerivedFilter'
examples:
example-0:
value: metagenome_derived_exclude
summary: Exclude metagenome derived assemblies
example-1:
value: metagenome_derived_only
summary: Return only metagenome derived assemblies
- name: filters.is_type_material
description: 'If true, include only type materials'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of type materials
example-1:
value: true
summary: Only return genomes that are classified as type materials
- name: filters.is_ictv_exemplar
description: 'If true, include only ICTV Exemplars'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of type ICTV exemplar
example-1:
value: true
summary: Only return genomes that are classified as ICTV exemplar
- name: filters.exclude_multi_isolate
description: 'If true, exclude large multi-isolate projects'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: false
summary: Return all selected genomes, including ones of large multi-isolate projects
example-1:
value: true
summary: Exclude genomes that are classified as large multi-isolate projects
- name: filters.type_material_category
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterTypeMaterialCategory'
examples:
example-0:
value: TYPE_MATERIAL
summary: A Type Material with no classification
example-1:
value: TYPE_MATERIAL_CLADE
summary: A Type Material of the Clade classification
example-2:
value: TYPE_MATERIAL_NEOTYPE
summary: A Type Material of the Neotype classification
- name: 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.'
in: query
required: false
schema:
type: boolean
default: false
- name: table_fields
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- assminfo-accession
- assminfo-name
summary: Genome Accession and Name
example-1:
value:
- assminfo-accession
summary: Just accession
- name: returned_content
description: 'Return either assembly accessions, or complete assembly reports'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetReportsRequestContentType'
- name: page_size
description: 'The maximum number of genome assembly reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: sort.field
in: query
required: false
schema:
type: string
- name: sort.direction
in: query
required: false
schema:
$ref: '#/components/schemas/v2SortDirection'
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
/genome/dataset_report:
post:
summary: Get dataset reports by accessions
description: 'Get a dataset report by accession. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Genome
operationId: genome_dataset_report_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsAssemblyDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsAssemblyDataReportPage'
text/tab-separated-values:
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyDatasetReportsRequest'
examples:
Single GCF accession example:
description: GCF Accessions (just one)
value:
accessions:
- GCF_000001405.40
/genome/accession/{accession}/revision_history:
get:
summary: Get revision history for assembly by accession
description: 'Get revision history for assembly by accession'
tags:
- Genome
operationId: assembly_revision_history_by_get
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyRevisionHistory'
parameters:
- name: accession
in: path
required: true
schema:
type: string
examples:
example-0:
value: GCF_000001405.40
summary: Human
/genome/revision_history:
post:
summary: Get revision history for assembly by accession
description: 'Get revision history for assembly by accession'
tags:
- Genome
operationId: assembly_revision_history_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyRevisionHistory'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyRevisionHistoryRequest'
examples:
Single GCF accession example:
description: GCF Accession (just one)
value:
accession: "GCF_000001405.40"
/genome/sequence_accession/{accession}/sequence_assemblies:
get:
summary: Get assembly accessions for a sequence accession
description: 'Get assembly accessions for a sequence (nucleotide) accession'
tags:
- Genome
operationId: assembly_accessions_for_sequence_accession
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyAccessions'
parameters:
- name: accession
in: path
required: true
schema:
type: string
examples:
example-0:
value: NC_000001.11
summary: Human chromosome accession
/genome/sequence_assemblies:
post:
summary: Get assembly accessions for a sequence accession
description: 'Get assembly accessions for a sequence (nucleotide) accession'
tags:
- Genome
operationId: assembly_accessions_for_sequence_accession_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyAccessions'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2SequenceAccessionRequest'
examples:
Single chromosome accession example:
description: Chromosome nucleotide accession
value:
accession: "NC_000001.11"
/genome/accession/{accession}/sequence_reports:
get:
summary: Get sequence reports by accessions
description: 'Get a sequence report by accession. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Genome
operationId: genome_sequence_report
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2SequenceReportPage'
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet:
schema:
$ref: '#/components/schemas/v2SequenceReportPage'
text/tab-separated-values:
schema:
type: string
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2SequenceReportPage'
parameters:
- name: accession
in: path
required: true
schema:
type: string
examples:
example-0:
value: GCF_000001635.27
summary: Mouse
example-1:
value: GCF_000001405.40
summary: Human
- name: chromosomes
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- "1"
- "2"
- "3"
- X
- Y
- MT
summary: Selected chromosomes #1
example-1:
value:
- X
- Y
summary: Human sex chromosomes
- name: role_filters
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- assembled-molecule
- unlocalized-scaffold
- unplaced-scaffold
summary: All types of sequence
example-1:
value:
- assembled-molecule
summary: Only assembled molecules
- name: table_fields
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- accession
- chr-name
summary: Genome Accession and Chromosome Name
example-1:
value:
- ucsc-style-name
summary: UCSC Name
- name: count_assembly_unplaced
in: query
required: false
schema:
type: boolean
default: false
- name: 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `GetSequenceReports` 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
required: false
schema:
type: string
- name: include_tabular_header
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
/genome/sequence_reports:
post:
summary: Get sequence reports by accessions
description: 'Get a sequence report by accession. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Genome
operationId: genome_sequence_report_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2SequenceReportPage'
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet:
schema:
$ref: '#/components/schemas/v2SequenceReportPage'
text/tab-separated-values:
schema:
type: string
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2SequenceReportPage'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblySequenceReportsRequest'
examples:
Single GCF accession example:
description: GCF Accession (just one)
value:
accession: "GCF_000001405.40"
/genome/accession/{accessions}/links:
get:
summary: Get assembly links by accessions
description: 'Get links to available assembly resources by accessions.'
tags:
- Genome
operationId: genome_links_by_accession
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyLinksReply'
parameters:
- name: accessions
description: 'NCBI genome assembly accessions, limited to 1000'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- GCF_000001405.40
summary: Human
example-1:
value:
- GCF_000001405.40
- GCF_000001635.27
summary: Human and Mouse
/genome/links:
post:
summary: Get assembly links by accessions
description: 'Get links to available assembly resources by accessions.'
tags:
- Genome
operationId: genome_links_by_accession_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyLinksReply'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyLinksRequest'
examples:
Single GCF accession example:
description: GCF Accessions (just one)
value:
accessions:
- GCF_000001405.40
/genome/taxon/{species_taxon}/checkm_histogram:
get:
summary: Get CheckM histogram by species taxon
description: 'Get CheckM histogram by species taxon. CheckM histograms are only available for certain bacterial species.'
tags:
- Genome
operationId: checkm_histogram_by_taxon
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyCheckMHistogramReply'
parameters:
- name: species_taxon
in: path
required: true
schema:
type: string
examples:
example-0:
value: "202956"
summary: Acinetobacter towneri
/genome/checkm_histogram:
post:
summary: Get CheckM histogram by species taxon
description: 'Get CheckM histogram by species taxon. CheckM histograms are only available for certain bacterial species.'
tags:
- Genome
operationId: checkm_histogram_by_taxon_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyCheckMHistogramReply'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyCheckMHistogramRequest'
examples:
Single TaxID example:
description: TaxID example (just one)
value:
species_taxon: "202956"
/biosample/accession/{accessions}/biosample_report:
get:
summary: Get BioSample dataset reports by accession(s)
description: 'Get BioSample dataset reports by accession(s). By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- BioSample
operationId: BioSample_dataset_report
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsBioSampleDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsBioSampleDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: accessions
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- SAMN15960293
summary: BioSample Identifier
/genome/accession/{accessions}/download:
get:
summary: Get a genome dataset by accession
description: 'Download a genome dataset including fasta sequence, annotation and a detailed data report by accession.'
tags:
- Genome
operationId: download_assembly_package
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
parameters:
- name: accessions
description: 'NCBI genome assembly accessions'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- GCF_000001405.40
summary: Human
example-1:
value:
- GCF_000001405.40
- GCF_000001635.27
summary: Human and Mouse
- name: 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
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- "1"
- "2"
- "3"
- X
- Y
- MT
summary: Selected chromosomes #1
example-1:
value:
- X
- Y
summary: Human sex chromosomes
- name: include_annotation_type
description: 'Select additional types of annotation to include in the data package. If unset, no annotation is provided.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2AnnotationForAssemblyType'
examples:
example-0:
value:
- GENOME_FASTA
- PROT_FASTA
- RNA_FASTA
summary: Genomic, Transcript & Protein Sequence
example-1:
value:
- GENOME_GFF
- GENOME_GBFF
- GENOME_GTF
- PROT_FASTA
- RNA_FASTA
- CDS_FASTA
- SEQUENCE_REPORT
summary: All
- name: hydrated
description: 'Set to DATA_REPORT_ONLY, to only retrieve data-reports.'
in: query
required: false
schema:
$ref: '#/components/schemas/v2AssemblyDatasetRequestResolution'
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
/genome/download:
post:
summary: Get a genome dataset by 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.'
tags:
- Genome
operationId: download_assembly_package_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyDatasetRequest'
examples:
Single GCF accession example:
description: GCF Accession (just one)
value:
accessions:
- GCF_000001405.40
parameters:
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
/gene/id/{gene_ids}/download:
get:
summary: Get a gene dataset by gene ID
description: 'Get a gene dataset including gene, transcript and protein fasta sequence, annotation and metadata by gene ID.'
tags:
- Gene
operationId: download_gene_package
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
parameters:
- name: gene_ids
description: 'NCBI gene ids'
in: path
required: true
schema:
type: array
items:
type: integer
examples:
example-0:
value:
- 59067
summary: IL21 GeneID
example-1:
value:
- 59067
- 50615
summary: IL21 & IL21R GeneIDs
- name: include_annotation_type
description: 'Select additional types of annotation to include in the data package. If unset, no annotation is provided.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2Fasta'
- name: fasta_filter
description: 'Limit the FASTA sequences in the datasets package to these transcript and protein accessions (deprecated)'
in: query
required: false
schema:
type: array
items:
type: string
- name: accession_filter
description: 'Limit the FASTA sequences and tabular product report in the datasets package to these transcript and protein accessions'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NM_001408458.1
- NM_001407959.1
summary: Selected transcripts from BRCA1
- name: aux_report
description: 'list additional reports to include with download. Data report is included by default.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GeneDatasetRequestGeneDatasetReportType'
examples:
example-0:
value:
- PRODUCT_REPORT
summary: Select additional report types to include with download. The base data report will always be included.
- name: tabular_reports
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GeneDatasetRequestGeneDatasetReportType'
examples:
example-0:
value:
- DATASET_REPORT
- PRODUCT_REPORT
summary: Select tabular files to include. These tabular files will use the 'summary' templates in dataformat.
- name: table_fields
description: 'Specify which fields to include in the tabular report. This is currently deprecated - use tabular_reports instead.'
in: query
required: false
schema:
type: array
items:
type: string
- name: table_report_type
description: 'Specify the report from which the table fields will be taken. This is currently deprecated - use tabular_reports instead.'
in: query
required: false
schema:
$ref: '#/components/schemas/v2GeneDatasetRequestGeneDatasetReportType'
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
/gene/download:
post:
summary: Get a gene dataset by POST
description: 'Get a gene dataset including gene, transcript and protein fasta sequence, annotation and metadata by POST.'
tags:
- Gene
operationId: download_gene_package_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2GeneDatasetRequest'
examples:
Multiple GeneID examples:
description: GeneIDs (multiple)
value:
gene_ids:
- 59067
- 50615
parameters:
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
/protein/accession/{accessions}/download:
get:
summary: Get a prokaryote gene dataset by RefSeq protein accession
description: 'Get a prokaryote gene dataset including gene and protein fasta sequence, annotation and metadata by prokaryote protein accession.'
tags:
- Prokaryote
operationId: download_prokaryote_gene_package
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
parameters:
- name: accessions
description: 'WP prokaryote protein accession'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- WP_015878339.1
summary: DNA-deoxyinosine glycosylase
example-1:
value:
- WP_001040085.1
summary: type II CRISPR RNA-guided endonuclease Cas9
- name: include_annotation_type
description: 'Select additional types of annotation to include in the data package. If unset, no annotation is provided.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2Fasta'
examples:
example-0:
value:
- FASTA_GENE
summary: Gene range FASTA
example-1:
value:
- FASTA_RNA
- FASTA_PROTEIN
summary: Transcript & protein sequence FASTA
example-2:
value:
- FASTA_GENE
- FASTA_RNA
- FASTA_PROTEIN
summary: All annotation
- name: gene_flank_config.length
in: query
required: false
schema:
type: integer
- name: taxon
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
required: false
schema:
type: string
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
/protein/accession/download:
post:
summary: Get a prokaryote gene dataset by RefSeq protein accession by POST
description: 'Get a prokaryote gene dataset including gene and protein fasta sequence, annotation and metadata by prokaryote protein accession by POST.'
tags:
- Prokaryote
operationId: download_prokaryote_gene_package_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2ProkaryoteGeneRequest'
examples:
Multiple Prokaryote (WP_) accessions example:
description: Prokaryote (WP_) accessions (multiple)
value:
accessions:
- WP_000000001.1
- WP_000000002.1
parameters:
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
/genome/accession/{accession}/annotation_report/download:
get:
summary: Get an annotation report dataset by accession
description: 'Download an annotation report including fasta sequence and a detailed annotation report by genomic accession.'
tags:
- Genome
operationId: download_genome_annotation_package
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
parameters:
- name: accession
in: path
required: true
schema:
type: string
examples:
example-0:
value: GCF_000001635.27
summary: Mouse
- name: annotation_ids
description: 'Limit the reports by internal, unstable annotation ids.'
in: query
required: false
schema:
type: array
items:
type: string
- name: symbols
description: 'Filter parameters'
in: query
required: false
schema:
type: array
items:
type: string
- name: locations
description: 'Locations with a chromosome or accession and optional start-stop range: chromosome|accession[:start-end]'
in: query
required: false
schema:
type: array
items:
type: string
- name: gene_types
description: 'granular gene_types'
in: query
required: false
schema:
type: array
items:
type: string
- name: search_text
in: query
required: false
schema:
type: array
items:
type: string
- name: sort.field
in: query
required: false
schema:
type: string
- name: sort.direction
in: query
required: false
schema:
$ref: '#/components/schemas/v2SortDirection'
- name: include_annotation_type
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GenomeAnnotationRequestAnnotationType'
- name: page_size
description: 'The maximum number of features 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
- name: table_format
description: 'Optional pre-defined template for processing a tabular data request'
in: query
required: false
schema:
$ref: '#/components/schemas/v2GenomeAnnotationRequestGenomeAnnotationTableFormat'
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_token
description: 'A page token is returned from a `GetFeatures` call with more than `page_size` results. Use this token, along with the previous `FeatureRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
/genome/annotation_report/download:
post:
summary: Get an annotation report dataset by accession
description: 'Download an annotation report including fasta sequence and a detailed annotation report by genomic accession.'
tags:
- Genome
operationId: download_genome_annotation_package_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2GenomeAnnotationRequest'
examples:
Single GCF accession example:
description: GCF accession (just one)
value:
accession: "GCF_000001635.27"
parameters:
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
/taxonomy/taxon/{tax_ids}/download:
get:
summary: Get a taxonomy data package by tax ID
description: 'Download a taxonomy report and names data package.'
tags:
- Taxonomy
operationId: download_taxonomy_package
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
parameters:
- name: tax_ids
in: path
required: true
schema:
type: array
items:
type: integer
examples:
example-0:
value:
- 9606
summary: NCBI Taxonomy Identifier
example-1:
value:
- 9606
- 10090
summary: NCBI Taxonomy Identifier
- name: aux_reports
description: 'list additional reports to include with download. TAXONOMY_REPORT is included by default.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2TaxonomyDatasetRequestTaxonomyReportType'
examples:
example-0:
value:
- NAMES_REPORT
- TAXONOMY_SUMMARY
summary: Select additional report types to include with download. The base data report will always be included.
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
/taxonomy/download:
post:
summary: Get a taxonomy data package by tax_id
description: 'Download a taxonomy report and names data package.'
tags:
- Taxonomy
operationId: download_taxonomy_package_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyDatasetRequest'
examples:
Multiple TaxID examples:
description: TaxIDs (multiple)
value:
tax_ids:
- 9606
- 10090
parameters:
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
/genome/accession/{accessions}/check:
get:
summary: Check the validity of genome accessions
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.'
tags:
- Genome
operationId: check_assembly_availability
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyDatasetAvailability'
parameters:
- name: accessions
description: 'NCBI genome assembly accessions'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- GCF_000001405.40
summary: Human
example-1:
value:
- GCF_000001405.40
- GCF_000001635.27
summary: Human and Mouse
/genome/check:
post:
summary: Check the validity of many genome accessions in a single request
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.'
tags:
- Genome
operationId: check_assembly_availability_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyDatasetAvailability'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2AssemblyDatasetRequest'
examples:
Single GCF accession example:
description: GCF Accession (just one)
value:
accessions:
- GCF_000001405.40
/organelle/accession/{accessions}/download:
get:
summary: Get a organelle data package by accesions
description: 'Download a organelle data report and annotation data package.'
tags:
- Organelle
operationId: download_organelle_package
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
parameters:
- name: accessions
description: 'NCBI organelle assembly accessions'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NC_001643.1
summary: Chimpanzee
example-1:
value:
- NC_001643.1
- NC_002082.1
summary: Chimpanzee and Common Gibbon
- name: exclude_sequence
description: 'Set to true to omit the genomic sequence.'
in: query
required: false
schema:
type: boolean
- name: include_annotation_type
description: 'Select additional types of annotation to include in the data package. If unset, no annotation is provided.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2AnnotationForOrganelleType'
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
/organelle/download:
post:
summary: Get a organelle data package by post
description: 'Download a organelle report and annotation data package by post.'
tags:
- Organelle
operationId: download_organelle_package_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2OrganelleDownloadRequest'
examples:
Single organelle accession example:
description: Organelle accession (just one)
value:
accessions:
- NC_001643.1
parameters:
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
/version:
get:
summary: Retrieve service version
description: 'Retrieve the latest version of the Datasets services.'
tags:
- Version
operationId: version
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2VersionReply'
/gene/id/{gene_ids}:
get:
summary: Get gene reports by GeneID
description: 'Get a gene summary by GeneID. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
deprecated: true
tags:
- Gene
operationId: gene_reports_by_id
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: returned_content
description: 'Return either gene-ids, or entire gene metadata'
in: query
required: false
schema:
$ref: '#/components/schemas/v2GeneDatasetReportsRequestContentType'
- name: gene_ids
description: 'NCBI gene ids'
in: path
required: true
schema:
type: array
items:
type: integer
examples:
example-0:
value:
- 59067
summary: IL21 GeneID
example-1:
value:
- 59067
- 50615
summary: IL21 & IL21R GeneIDs
- name: locus_tags
description: 'Gene locus tags'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- b0001
summary: Locus tag for gene
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- gene-id
- gene-type
- description
summary: GeneID, type and description
example-1:
value:
- gene-id
summary: Just GeneID
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_size
description: 'The maximum number of gene reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: accession_filter
description: 'Filter tabular product report to only include the selected accessions'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NM_001408458.1
- NM_001407959.1
summary: Selected transcripts from BRCA1
/gene/accession/{accessions}:
get:
summary: Get gene metadata by RefSeq Accession
description: 'Get a gene summary by RefSeq Accession. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
deprecated: true
tags:
- Gene
operationId: gene_metadata_by_accession
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: returned_content
description: 'Return either gene-ids, or entire gene metadata'
in: query
required: false
schema:
$ref: '#/components/schemas/v2GeneDatasetReportsRequestContentType'
- name: accessions
description: 'RNA or Protein accessions.'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NM_021803.4
summary: RefSeq transcript
example-1:
value:
- NP_068575.1
- NP_851564.1
summary: RefSeq proteins
- name: locus_tags
description: 'Gene locus tags'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- b0001
summary: Locus tag for gene
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- gene-id
- gene-type
- description
summary: GeneID, type and description
example-1:
value:
- gene-id
summary: Just GeneID
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_size
description: 'The maximum number of gene reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: accession_filter
description: 'Filter tabular product report to only include the selected accessions'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NM_001408458.1
- NM_001407959.1
summary: Selected transcripts from BRCA1
/gene/symbol/{symbols}/taxon/{taxon}:
get:
summary: Get gene metadata by gene symbol
description: 'Get a gene summary by by gene symbol. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
deprecated: true
tags:
- Gene
operationId: gene_metadata_by_tax_and_symbol
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: returned_content
description: 'Return either gene-ids, or entire gene metadata'
in: query
required: false
schema:
$ref: '#/components/schemas/v2GeneDatasetReportsRequestContentType'
- name: symbols
description: 'Gene symbol'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- GNAS
summary: GNAS
- name: taxon
description: 'Taxon for provided gene symbol'
in: path
required: true
schema:
type: string
examples:
example-0:
value: "9606"
summary: NCBI Taxonomy Identifier
example-1:
value: human
summary: Common Name
example-2:
value: Homo sapiens
summary: Scientific Name
- name: locus_tags
description: 'Gene locus tags'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- b0001
summary: Locus tag for gene
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- gene-id
- gene-type
- description
summary: GeneID, type and description
example-1:
value:
- gene-id
summary: Just GeneID
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_size
description: 'The maximum number of gene reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: accession_filter
description: 'Filter tabular product report to only include the selected accessions'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NM_001408458.1
- NM_001407959.1
summary: Selected transcripts from BRCA1
/gene/taxon/{taxon}:
get:
summary: Get gene reports by taxonomic identifier
description: 'Get a gene summary for a specified NCBI Taxonomy ID or name (common or scientific). By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
deprecated: true
tags:
- Gene
operationId: gene_reports_by_taxon
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: returned_content
description: 'Return either gene-ids, or entire gene metadata'
in: query
required: false
schema:
$ref: '#/components/schemas/v2GeneDatasetReportsRequestContentType'
- name: taxon
description: 'NCBI Taxonomy ID or name (common or scientific) that the genes are annotated at'
in: path
required: true
schema:
type: string
examples:
example-0:
value: "9606"
summary: NCBI Taxonomy Identifier
example-1:
value: human
summary: Common Name
example-2:
value: Homo sapiens
summary: Scientific Name
- name: locus_tags
description: 'Gene locus tags'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- b0001
summary: Locus tag for gene
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- gene-id
- gene-type
- description
summary: GeneID, type and description
example-1:
value:
- gene-id
summary: Just GeneID
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_size
description: 'The maximum number of gene reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: query
description: 'text search within gene symbol, aliases, name, locus-tag and protein name'
in: query
required: false
schema:
type: string
examples:
example-0:
value: A2M immunoglobulin
summary: Text search for A2M gene by name
- name: types
description: 'Gene types to filter'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GeneType'
examples:
example-0:
value:
- PROTEIN_CODING
summary: Only protein coding genes
- name: accession_filter
description: 'Filter tabular product report to only include the selected accessions'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NM_001408458.1
- NM_001407959.1
summary: Selected transcripts from BRCA1
/gene:
post:
summary: Get gene metadata as JSON
description: 'Get a gene summary. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
deprecated: true
tags:
- Gene
operationId: gene_metadata_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2GeneDatasetReportsRequest'
examples:
Multiple GeneID examples:
description: GeneIDs (multiple)
value:
gene_ids:
- 59067
- 50615
/gene/id/{gene_ids}/dataset_report:
get:
summary: Get dataset reports by gene IDs.
description: 'Get dataset reports by gene IDs. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Gene
operationId: gene_dataset_reports_by_id
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: returned_content
description: 'Return either gene-ids, or entire gene metadata'
in: query
required: false
schema:
$ref: '#/components/schemas/v2GeneDatasetReportsRequestContentType'
- name: gene_ids
description: 'NCBI gene ids'
in: path
required: true
schema:
type: array
items:
type: integer
examples:
example-0:
value:
- 59067
summary: IL21 GeneID
example-1:
value:
- 59067
- 50615
summary: IL21 & IL21R GeneIDs
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- gene-id
- gene-type
- description
summary: GeneID, type and description
example-1:
value:
- gene-id
summary: Just GeneID
- name: table_format
description: 'Optional pre-defined template for processing a tabular data request'
in: query
required: false
schema:
type: string
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_size
description: 'The maximum number of gene reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: query
description: 'text search within gene symbol, aliases, name, locus-tag and protein name'
in: query
required: false
schema:
type: string
examples:
example-0:
value: A2M immunoglobulin
summary: Text search for A2M gene by name
- name: types
description: 'Gene types to filter'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GeneType'
examples:
example-0:
value:
- PROTEIN_CODING
summary: Only protein coding genes
/gene/accession/{accessions}/dataset_report:
get:
summary: Get dataset reports by accession IDs
description: 'Get dataset reports by accession IDs. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Gene
operationId: gene_dataset_report_by_accession
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: returned_content
description: 'Return either gene-ids, or entire gene metadata'
in: query
required: false
schema:
$ref: '#/components/schemas/v2GeneDatasetReportsRequestContentType'
- name: accessions
description: 'RNA or Protein accessions.'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NM_021803.4
summary: RefSeq transcript
example-1:
value:
- NP_068575.1
- NP_851564.1
summary: RefSeq proteins
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- gene-id
- gene-type
- description
summary: GeneID, type and description
example-1:
value:
- gene-id
summary: Just GeneID
- name: table_format
description: 'Optional pre-defined template for processing a tabular data request'
in: query
required: false
schema:
type: string
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_size
description: 'The maximum number of gene reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: query
description: 'text search within gene symbol, aliases, name, locus-tag and protein name'
in: query
required: false
schema:
type: string
examples:
example-0:
value: A2M immunoglobulin
summary: Text search for A2M gene by name
- name: types
description: 'Gene types to filter'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GeneType'
examples:
example-0:
value:
- PROTEIN_CODING
summary: Only protein coding genes
/gene/symbol/{symbols}/taxon/{taxon}/dataset_report:
get:
summary: Get dataset reports by taxons.
description: 'Get dataset reports by taxons. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Gene
operationId: gene_dataset_report_by_tax_and_symbol
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: returned_content
description: 'Return either gene-ids, or entire gene metadata'
in: query
required: false
schema:
$ref: '#/components/schemas/v2GeneDatasetReportsRequestContentType'
- name: symbols
description: 'Gene symbol'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- GNAS
summary: GNAS
- name: taxon
description: 'Taxon for provided gene symbol'
in: path
required: true
schema:
type: string
examples:
example-0:
value: "9606"
summary: NCBI Taxonomy Identifier
example-1:
value: human
summary: Common Name
example-2:
value: Homo sapiens
summary: Scientific Name
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- gene-id
- gene-type
- description
summary: GeneID, type and description
example-1:
value:
- gene-id
summary: Just GeneID
- name: table_format
description: 'Optional pre-defined template for processing a tabular data request'
in: query
required: false
schema:
type: string
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_size
description: 'The maximum number of gene reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: query
description: 'text search within gene symbol, aliases, name, locus-tag and protein name'
in: query
required: false
schema:
type: string
examples:
example-0:
value: A2M immunoglobulin
summary: Text search for A2M gene by name
- name: types
description: 'Gene types to filter'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GeneType'
examples:
example-0:
value:
- PROTEIN_CODING
summary: Only protein coding genes
/gene/taxon/{taxon}/dataset_report:
get:
summary: Get gene dataset reports by taxonomic identifier
description: 'Get a gene summary for a specified NCBI Taxonomy ID or name (common or scientific). By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Gene
operationId: gene_dataset_reports_by_taxon
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: returned_content
description: 'Return either gene-ids, or entire gene metadata'
in: query
required: false
schema:
$ref: '#/components/schemas/v2GeneDatasetReportsRequestContentType'
- name: taxon
description: 'NCBI Taxonomy ID or name (common or scientific) that the genes are annotated at'
in: path
required: true
schema:
type: string
examples:
example-0:
value: "9606"
summary: NCBI Taxonomy Identifier
example-1:
value: human
summary: Common Name
example-2:
value: Homo sapiens
summary: Scientific Name
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- gene-id
- gene-type
- description
summary: GeneID, type and description
example-1:
value:
- gene-id
summary: Just GeneID
- name: table_format
description: 'Optional pre-defined template for processing a tabular data request'
in: query
required: false
schema:
type: string
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_size
description: 'The maximum number of gene reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: query
description: 'text search within gene symbol, aliases, name, locus-tag and protein name'
in: query
required: false
schema:
type: string
examples:
example-0:
value: A2M immunoglobulin
summary: Text search for A2M gene by name
- name: types
description: 'Gene types to filter'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GeneType'
examples:
example-0:
value:
- PROTEIN_CODING
summary: Only protein coding genes
/gene/locus_tag/{locus_tags}/dataset_report:
get:
summary: Get gene dataset reports by locus tag
description: 'Get a gene summary for one or more gene locus tags. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Gene
operationId: gene_dataset_reports_by_locus_tag
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: returned_content
description: 'Return either gene-ids, or entire gene metadata'
in: query
required: false
schema:
$ref: '#/components/schemas/v2GeneDatasetReportsRequestContentType'
- name: locus_tags
description: 'Gene locus tags'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- b0001
summary: Locus tag for gene
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- gene-id
- gene-type
- description
summary: GeneID, type and description
example-1:
value:
- gene-id
summary: Just GeneID
- name: table_format
description: 'Optional pre-defined template for processing a tabular data request'
in: query
required: false
schema:
type: string
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_size
description: 'The maximum number of gene reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: query
description: 'text search within gene symbol, aliases, name, locus-tag and protein name'
in: query
required: false
schema:
type: string
examples:
example-0:
value: A2M immunoglobulin
summary: Text search for A2M gene by name
- name: types
description: 'Gene types to filter'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GeneType'
examples:
example-0:
value:
- PROTEIN_CODING
summary: Only protein coding genes
/gene/dataset_report:
post:
summary: Get gene dataset report as JSON
description: 'Get gene dataset report. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Gene
operationId: gene_dataset_report
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2GeneDatasetReportsRequest'
examples:
Multiple GeneID examples:
description: GeneIDs (multiple)
value:
gene_ids:
- 59067
- 50615
/gene/id/{gene_ids}/product_report:
get:
summary: Get gene product reports by gene IDs.
description: 'Get gene product reports by gene IDs. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Gene
operationId: gene_product_reports_by_id
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: gene_ids
description: 'NCBI gene ids'
in: path
required: true
schema:
type: array
items:
type: integer
examples:
example-0:
value:
- 59067
summary: IL21 GeneID
example-1:
value:
- 59067
- 50615
summary: IL21 & IL21R GeneIDs
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- gene-id
- gene-type
- description
summary: GeneID, type and description
example-1:
value:
- gene-id
summary: Just GeneID
- name: table_format
description: 'Optional pre-defined template for processing a tabular data request'
in: query
required: false
schema:
type: string
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_size
description: 'The maximum number of gene reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: query
description: 'text search within gene symbol, aliases, name, locus-tag and protein name'
in: query
required: false
schema:
type: string
examples:
example-0:
value: A2M immunoglobulin
summary: Text search for A2M gene by name
- name: types
description: 'Gene types to filter'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GeneType'
examples:
example-0:
value:
- PROTEIN_CODING
summary: Only protein coding genes
- name: accession_filter
description: 'Filter tabular product report to only include the selected accessions'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NM_001408458.1
- NM_001407959.1
summary: Selected transcripts from BRCA1
/gene/accession/{accessions}/product_report:
get:
summary: Get gene product reports by accession IDs
description: 'Get gene product reports by accession IDs. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Gene
operationId: gene_product_report_by_accession
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: accessions
description: 'RNA or Protein accessions.'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NM_021803.4
summary: RefSeq transcript
example-1:
value:
- NP_068575.1
- NP_851564.1
summary: RefSeq proteins
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- gene-id
- gene-type
- description
summary: GeneID, type and description
example-1:
value:
- gene-id
summary: Just GeneID
- name: table_format
description: 'Optional pre-defined template for processing a tabular data request'
in: query
required: false
schema:
type: string
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_size
description: 'The maximum number of gene reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: query
description: 'text search within gene symbol, aliases, name, locus-tag and protein name'
in: query
required: false
schema:
type: string
examples:
example-0:
value: A2M immunoglobulin
summary: Text search for A2M gene by name
- name: types
description: 'Gene types to filter'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GeneType'
examples:
example-0:
value:
- PROTEIN_CODING
summary: Only protein coding genes
- name: accession_filter
description: 'Filter tabular product report to only include the selected accessions'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NM_001408458.1
- NM_001407959.1
summary: Selected transcripts from BRCA1
/gene/symbol/{symbols}/taxon/{taxon}/product_report:
get:
summary: Get product reports by taxon.
description: 'Get gene product reports by taxon. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Gene
operationId: gene_product_report_by_tax_and_symbol
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: symbols
description: 'Gene symbol'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- GNAS
summary: GNAS
- name: taxon
description: 'Taxon for provided gene symbol'
in: path
required: true
schema:
type: string
examples:
example-0:
value: "9606"
summary: NCBI Taxonomy Identifier
example-1:
value: human
summary: Common Name
example-2:
value: Homo sapiens
summary: Scientific Name
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- gene-id
- gene-type
- description
summary: GeneID, type and description
example-1:
value:
- gene-id
summary: Just GeneID
- name: table_format
description: 'Optional pre-defined template for processing a tabular data request'
in: query
required: false
schema:
type: string
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_size
description: 'The maximum number of gene reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: query
description: 'text search within gene symbol, aliases, name, locus-tag and protein name'
in: query
required: false
schema:
type: string
examples:
example-0:
value: A2M immunoglobulin
summary: Text search for A2M gene by name
- name: types
description: 'Gene types to filter'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GeneType'
examples:
example-0:
value:
- PROTEIN_CODING
summary: Only protein coding genes
- name: accession_filter
description: 'Filter tabular product report to only include the selected accessions'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NM_001408458.1
- NM_001407959.1
summary: Selected transcripts from BRCA1
/gene/taxon/{taxon}/product_report:
get:
summary: Get gene product reports by taxonomic identifier
description: 'Get gene product reports for a specified NCBI Taxonomy ID or name (common or scientific). By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Gene
operationId: gene_product_reports_by_taxon
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: taxon
description: 'NCBI Taxonomy ID or name (common or scientific) that the genes are annotated at'
in: path
required: true
schema:
type: string
examples:
example-0:
value: "9606"
summary: NCBI Taxonomy Identifier
example-1:
value: human
summary: Common Name
example-2:
value: Homo sapiens
summary: Scientific Name
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- gene-id
- gene-type
- description
summary: GeneID, type and description
example-1:
value:
- gene-id
summary: Just GeneID
- name: table_format
description: 'Optional pre-defined template for processing a tabular data request'
in: query
required: false
schema:
type: string
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_size
description: 'The maximum number of gene reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: query
description: 'text search within gene symbol, aliases, name, locus-tag and protein name'
in: query
required: false
schema:
type: string
examples:
example-0:
value: A2M immunoglobulin
summary: Text search for A2M gene by name
- name: types
description: 'Gene types to filter'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GeneType'
examples:
example-0:
value:
- PROTEIN_CODING
summary: Only protein coding genes
- name: accession_filter
description: 'Filter tabular product report to only include the selected accessions'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NM_001408458.1
- NM_001407959.1
summary: Selected transcripts from BRCA1
/gene/locus_tag/{locus_tags}/product_report:
get:
summary: Get gene product reports by locus tags
description: 'Get gene product reports for one or more gene locus tags. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Gene
operationId: gene_product_reports_by_locus_tags
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: locus_tags
description: 'Gene locus tags'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- b0001
summary: Locus tag for gene
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- gene-id
- gene-type
- description
summary: GeneID, type and description
example-1:
value:
- gene-id
summary: Just GeneID
- name: table_format
description: 'Optional pre-defined template for processing a tabular data request'
in: query
required: false
schema:
type: string
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_size
description: 'The maximum number of gene reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: query
description: 'text search within gene symbol, aliases, name, locus-tag and protein name'
in: query
required: false
schema:
type: string
examples:
example-0:
value: A2M immunoglobulin
summary: Text search for A2M gene by name
- name: types
description: 'Gene types to filter'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GeneType'
examples:
example-0:
value:
- PROTEIN_CODING
summary: Only protein coding genes
- name: accession_filter
description: 'Filter tabular product report to only include the selected accessions'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NM_001408458.1
- NM_001407959.1
summary: Selected transcripts from BRCA1
/gene/product_report:
post:
summary: Get gene product reports as JSON
description: 'Get gene product reports. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Gene
operationId: gene_product_report
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
text/tab-separated-values:
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2GeneDatasetReportsRequest'
examples:
Multiple GeneID examples:
description: GeneIDs (multiple)
value:
gene_ids:
- 59067
- 50615
/gene/id/{gene_ids}/download_summary:
get:
summary: Get gene download summary by GeneID
description: 'Get a download summary by GeneID in a JSON output format.'
tags:
- Gene
operationId: gene_download_summary_by_id
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2DownloadSummary'
parameters:
- name: gene_ids
description: 'NCBI gene ids'
in: path
required: true
schema:
type: array
items:
type: integer
examples:
example-0:
value:
- 59067
summary: IL21 GeneID
example-1:
value:
- 59067
- 50615
summary: IL21 & IL21R GeneIDs
- name: include_annotation_type
description: 'Select additional types of annotation to include in the data package. If unset, no annotation is provided.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2Fasta'
- name: returned_content
description: 'Return either gene-ids, or entire gene metadata'
in: query
required: false
schema:
$ref: '#/components/schemas/v2GeneDatasetRequestContentType'
- name: fasta_filter
description: 'Limit the FASTA sequences in the datasets package to these transcript and protein accessions (deprecated)'
in: query
required: false
schema:
type: array
items:
type: string
- name: accession_filter
description: 'Limit the FASTA sequences and tabular product report in the datasets package to these transcript and protein accessions'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NM_001408458.1
- NM_001407959.1
summary: Selected transcripts from BRCA1
- name: aux_report
description: 'list additional reports to include with download. Data report is included by default.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GeneDatasetRequestGeneDatasetReportType'
examples:
example-0:
value:
- PRODUCT_REPORT
summary: Select additional report types to include with download. The base data report will always be included.
- name: tabular_reports
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GeneDatasetRequestGeneDatasetReportType'
examples:
example-0:
value:
- DATASET_REPORT
- PRODUCT_REPORT
summary: Select tabular files to include. These tabular files will use the 'summary' templates in dataformat.
- name: table_fields
description: 'Specify which fields to include in the tabular report. This is currently deprecated - use tabular_reports instead.'
in: query
required: false
schema:
type: array
items:
type: string
- name: table_report_type
description: 'Specify the report from which the table fields will be taken. This is currently deprecated - use tabular_reports instead.'
in: query
required: false
schema:
$ref: '#/components/schemas/v2GeneDatasetRequestGeneDatasetReportType'
/gene/download_summary:
post:
summary: Get gene download summary
description: 'Get gene download summary in a JSON output format.'
tags:
- Gene
operationId: gene_download_summary_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2DownloadSummary'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2GeneDatasetRequest'
examples:
Multiple GeneID examples:
description: GeneIDs (multiple)
value:
gene_ids:
- 59067
- 50615
/gene/taxon/{taxon}/counts:
get:
summary: Get gene counts by taxonomic identifier
description: 'Get gene counts for a specified NCBI Taxonomy ID or name (common or scientific) in JSON format.'
tags:
- Gene
operationId: gene_counts_for_taxon
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2GeneCountsByTaxonReply'
parameters:
- name: taxon
description: 'Taxon for provided gene symbol'
in: path
required: true
schema:
type: string
examples:
example-0:
value: "9606"
summary: NCBI Taxonomy Identifier
example-1:
value: human
summary: Common Name
example-2:
value: Homo sapiens
summary: Scientific Name
/gene/taxon/counts:
post:
summary: Get gene counts by taxonomic identifier
description: 'Get gene counts for a specified NCBI Taxonomy ID or name (common or scientific) in JSON format.'
tags:
- Gene
operationId: gene_counts_for_taxon_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2GeneCountsByTaxonReply'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2GeneCountsByTaxonRequest'
examples:
Single TaxID example:
description: TaxID (just one)
value:
taxon: "9606"
/gene/id/{gene_id}/orthologs:
get:
summary: Get gene orthologs by gene ID
description: 'Get a gene summary for an ortholog set by gene ID in a JSON output format.'
tags:
- Gene
operationId: gene_orthologs_by_id
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
parameters:
- name: gene_id
in: path
required: true
schema:
type: integer
examples:
example-0:
value: 2778
summary: GNAS
example-1:
value: 2
summary: A2M
- name: returned_content
description: 'Return either gene-ids, or entire gene metadata'
in: query
required: false
schema:
$ref: '#/components/schemas/v2OrthologRequestContentType'
- name: taxon_filter
description: 'Filter genes by taxa'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- "9606"
- "10090"
summary: NCBI Taxonomy Identifier
example-1:
value:
- human
- house mouse
summary: Common Name
example-2:
value:
- homo sapiens
- mus musculus
summary: Scientific Name
- name: page_size
description: 'The maximum number of gene reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from an `OrthologRequest` call with more than `page_size` results. Use this token, along with the previous `OrthologRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
/gene/orthologs:
post:
summary: Get gene orthologs by gene ID
description: 'Get a gene summary for an ortholog set by gene ID in a JSON output format by POST'
tags:
- Gene
operationId: gene_orthologs_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGeneDataReportPage'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2OrthologRequest'
examples:
Single GeneID example:
description: GeneID (just one)
value:
gene_id: 2778
/gene/id/{gene_ids}/links:
get:
summary: Get gene links by gene ID
description: 'Get links to available gene resources by gene ID.'
tags:
- Gene
operationId: gene_links_by_id
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2GeneLinksReply'
parameters:
- name: gene_ids
description: 'NCBI gene ids, limited to 1000 ids'
in: path
required: true
schema:
type: array
items:
type: integer
examples:
example-0:
value:
- 59067
summary: IL21 GeneID
example-1:
value:
- 59067
- 50615
summary: IL21 & IL21R GeneIDs
/gene/links:
post:
summary: Get gene links by gene ID
description: 'Get links to available gene resources by gene ID.'
tags:
- Gene
operationId: gene_links_by_id_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2GeneLinksReply'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2GeneLinksRequest'
examples:
Multiple GeneID examples:
description: GeneIDs (multiple)
value:
gene_ids:
- 59067
- 50615
/gene/taxon/{taxon}/annotation/{annotation_name}/chromosome_summary:
get:
summary: Get summary of chromosomes for a particular taxon's annotation
description: 'Get summary of chromosomes for a particular taxon''s annotation.'
tags:
- Gene
operationId: gene_chromosome_summary
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2GeneChromosomeSummaryReply'
parameters:
- name: taxon
in: path
required: true
schema:
type: string
examples:
example-0:
value: "9117"
summary: NCBI Taxonomy Identifier
example-1:
value: Whooping crane
summary: Common Name
example-2:
value: Grus americana
summary: Scientific Name
- name: annotation_name
in: path
required: true
schema:
type: string
examples:
example-0:
value: GCF_028858705.1-RS_2023_03
summary: Grus americana Annotation Release
/genome/accession/{accession}/annotation_report:
get:
summary: Get genome annotation reports by genome accession
description: 'Get genome annotation reports by genome accession. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Genome
operationId: genome_annotation_report
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGenomeAnnotationReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGenomeAnnotationReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: accession
in: path
required: true
schema:
type: string
examples:
example-0:
value: GCF_000001635.27
summary: Mouse
- name: annotation_ids
description: 'Limit the reports by internal, unstable annotation ids.'
in: query
required: false
schema:
type: array
items:
type: string
- name: symbols
description: 'Filter parameters'
in: query
required: false
schema:
type: array
items:
type: string
- name: locations
description: 'Locations with a chromosome or accession and optional start-stop range: chromosome|accession[:start-end]'
in: query
required: false
schema:
type: array
items:
type: string
- name: gene_types
description: 'granular gene_types'
in: query
required: false
schema:
type: array
items:
type: string
- name: search_text
in: query
required: false
schema:
type: array
items:
type: string
- name: sort.field
in: query
required: false
schema:
type: string
- name: sort.direction
in: query
required: false
schema:
$ref: '#/components/schemas/v2SortDirection'
- name: page_size
description: 'The maximum number of features 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
- name: table_format
description: 'Optional pre-defined template for processing a tabular data request'
in: query
required: false
schema:
$ref: '#/components/schemas/v2GenomeAnnotationRequestGenomeAnnotationTableFormat'
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_token
description: 'A page token is returned from a `GetFeatures` call with more than `page_size` results. Use this token, along with the previous `FeatureRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
/genome/annotation_report:
post:
summary: Get genome annotation reports by genome accession
description: 'Get genome annotation reports by genome accession. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Genome
operationId: genome_annotation_report_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsGenomeAnnotationReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsGenomeAnnotationReportPage'
text/tab-separated-values:
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2GenomeAnnotationRequest'
examples:
Single GCF accession example:
description: GCF accession (just one)
value:
accession: "GCF_000001635.27"
/genome/accession/{accession}/annotation_summary:
get:
summary: Get genome annotation report summary information
description: 'Get genome annotation report summary information by genome accession. The return facets can be used in subsequent queries.'
tags:
- Genome
operationId: annotation_report_facets_by_accession
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2GenomeAnnotationTableSummaryReply'
parameters:
- name: accession
in: path
required: true
schema:
type: string
examples:
example-0:
value: GCF_000001635.27
summary: Mouse
- name: sort.field
in: query
required: false
schema:
type: string
- name: sort.direction
in: query
required: false
schema:
$ref: '#/components/schemas/v2SortDirection'
/genome/annotation_summary:
post:
summary: Get genome annotation report summary information
description: 'Get genome annotation report summary information by genome accession. The return facets can be used in subsequent queries.'
tags:
- Genome
operationId: annotation_report_facets_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2GenomeAnnotationTableSummaryReply'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2GenomeAnnotationRequest'
examples:
Single GCF accession example:
description: GCF accession (just one)
value:
accession: "GCF_000001635.27"
/genome/accession/{accession}/annotation_report/download_summary:
get:
summary: Preview feature dataset download
description: 'Get a download feature summary by accession in a JSON output format.'
tags:
- Genome
operationId: genome_annotation_download_summary
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2DownloadSummary'
parameters:
- name: accession
in: path
required: true
schema:
type: string
examples:
example-0:
value: GCF_000001635.27
summary: Mouse
- name: annotation_ids
description: 'Limit the reports by internal, unstable annotation ids.'
in: query
required: false
schema:
type: array
items:
type: string
- name: symbols
description: 'Filter parameters'
in: query
required: false
schema:
type: array
items:
type: string
- name: locations
description: 'Locations with a chromosome or accession and optional start-stop range: chromosome|accession[:start-end]'
in: query
required: false
schema:
type: array
items:
type: string
- name: gene_types
description: 'granular gene_types'
in: query
required: false
schema:
type: array
items:
type: string
- name: search_text
in: query
required: false
schema:
type: array
items:
type: string
- name: sort.field
in: query
required: false
schema:
type: string
- name: sort.direction
in: query
required: false
schema:
$ref: '#/components/schemas/v2SortDirection'
- name: include_annotation_type
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2GenomeAnnotationRequestAnnotationType'
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
- name: table_format
description: 'Optional pre-defined template for processing a tabular data request'
in: query
required: false
schema:
$ref: '#/components/schemas/v2GenomeAnnotationRequestGenomeAnnotationTableFormat'
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
/genome/annotation_report/download_summary:
post:
summary: Preview feature download by POST
description: 'The ''GET'' version of feature download summary is limited by the size of the GET URL (2KB). The POST operation is provided to allow users to supply a larger number of annotation_ids in a single request.'
tags:
- Genome
operationId: genome_annotation_download_summary_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2DownloadSummary'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2GenomeAnnotationRequest'
examples:
Single GCF accession example:
description: GCF accession (just one)
value:
accession: "GCF_000001635.27"
/organelle/accessions/{accessions}/dataset_report:
get:
summary: Get Organelle dataset report by accession
description: 'Get Organelle dataset report by accession.'
tags:
- Organelle
operationId: organelle_datareport_by_accession
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsOrganelleDataReports'
parameters:
- name: taxons
description: 'NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- "9443"
summary: Primates
example-1:
value:
- "9606"
- "10090"
summary: Human and Mouse
- name: accessions
description: 'NCBI assembly accession'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NC_001643.1
summary: Chimpanzee
example-1:
value:
- NC_001643.1
- NC_002082.1
summary: Chimpanzee and Common Gibbon
- name: organelle_types
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2reportsOrganelleType'
- name: first_release_date
description: 'Only return organelle assemblies that were released on or after the specified date By default, do not filter.'
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2015-01-10T00:00:00Z
summary: Jan 10, 2015
- name: last_release_date
description: 'Only return organelle assemblies that were released on or before to the specified date By default, do not filter.'
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-01-10T00:00:00Z
summary: Jan 10, 2021
- name: 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.'
in: query
required: false
schema:
type: boolean
default: false
- name: sort.field
in: query
required: false
schema:
type: string
- name: sort.direction
in: query
required: false
schema:
$ref: '#/components/schemas/v2SortDirection'
- name: returned_content
description: 'Return either assembly accessions, or entire assembly-metadata records'
in: query
required: false
schema:
$ref: '#/components/schemas/v2OrganelleMetadataRequestContentType'
- name: table_format
description: 'Optional pre-defined template for processing a tabular data request'
in: query
required: false
schema:
$ref: '#/components/schemas/v2OrganelleMetadataRequestOrganelleTableFormat'
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
/organelle/taxon/{taxons}/dataset_report:
get:
summary: Get Organelle dataset report by taxons
description: 'Get Organelle dataset report by taxons.'
tags:
- Organelle
operationId: organelle_datareport_by_taxon
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsOrganelleDataReports'
parameters:
- name: taxons
description: 'NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- "9443"
summary: Primates
example-1:
value:
- "9606"
- "10090"
summary: Human and Mouse
- name: organelle_types
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2reportsOrganelleType'
- name: first_release_date
description: 'Only return organelle assemblies that were released on or after the specified date By default, do not filter.'
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2015-01-10T00:00:00Z
summary: Jan 10, 2015
- name: last_release_date
description: 'Only return organelle assemblies that were released on or before to the specified date By default, do not filter.'
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-01-10T00:00:00Z
summary: Jan 10, 2021
- name: 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.'
in: query
required: false
schema:
type: boolean
default: false
- name: sort.field
in: query
required: false
schema:
type: string
- name: sort.direction
in: query
required: false
schema:
$ref: '#/components/schemas/v2SortDirection'
- name: returned_content
description: 'Return either assembly accessions, or entire assembly-metadata records'
in: query
required: false
schema:
$ref: '#/components/schemas/v2OrganelleMetadataRequestContentType'
- name: page_size
description: 'The maximum number of organelle 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.'
in: query
required: false
schema:
type: integer
- name: page_token
description: 'A page token is returned from an `OrganelleMetadata` call with more than `page_size` results. Use this token, along with the previous `OrganelleMetadata` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: table_format
description: 'Optional pre-defined template for processing a tabular data request'
in: query
required: false
schema:
$ref: '#/components/schemas/v2OrganelleMetadataRequestOrganelleTableFormat'
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
/organelle/dataset_report:
post:
summary: Get Organelle dataset report by http post
description: 'Get Organelle dataset report by http post.'
tags:
- Organelle
operationId: organelle_datareport_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsOrganelleDataReports'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2OrganelleMetadataRequest'
examples:
Single TaxID example:
description: TaxID example (just one)
value:
taxons:
- "9443"
/taxonomy/taxon/{taxons}:
get:
summary: Use taxonomic identifiers to get taxonomic metadata
description: 'Using NCBI Taxonomy IDs or names (common or scientific) at any rank, get metadata about a taxonomic node including taxonomic identifiers, lineage information, child nodes, and gene and genome counts in JSON format.'
tags:
- Taxonomy
operationId: taxonomy_metadata
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyMetadataResponse'
parameters:
- name: taxons
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- "9606"
summary: NCBI Taxonomy Identifier
example-1:
value:
- human
- house mouse
summary: Common Name
example-2:
value:
- Homo sapiens
- Mus musculus
summary: Scientific Name
- name: returned_content
description: 'Return either tax-ids alone, or entire taxononmy-metadata records'
in: query
required: false
schema:
$ref: '#/components/schemas/v2TaxonomyMetadataRequestContentType'
- name: page_size
description: 'The maximum number of taxons 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_token
description: 'A page token is returned from `GetTaxonomyDataReportFor` and `GetTaxonomyNamesDataReportFor` calls with more than `page_size` results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: table_format
in: query
required: false
schema:
$ref: '#/components/schemas/v2TaxonomyMetadataRequestTableFormat'
- name: children
description: 'Flag for tax explosion.'
in: query
required: false
schema:
type: boolean
- name: ranks
description: 'Only include taxons of the provided ranks. If empty, return all ranks.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2reportsRankType'
/taxonomy:
post:
summary: Use taxonomic identifiers to get taxonomic metadata by post
description: 'Using NCBI Taxonomy IDs or names (common or scientific) at any rank, get metadata about a taxonomic node including taxonomic identifiers, lineage information, child nodes, and gene and genome counts in JSON format.'
tags:
- Taxonomy
operationId: taxonomy_metadata_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyMetadataResponse'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyMetadataRequest'
examples:
Multiple TaxID and common name examples:
description: Taxon input (multiple types)
value:
taxons:
- "9606"
- house mouse
/taxonomy/taxon/{taxons}/dataset_report:
get:
summary: Use taxonomic identifiers to get taxonomic data report
description: 'Using NCBI Taxonomy IDs or names (common or scientific) at any rank, get metadata about a taxonomic node including taxonomic identifiers, lineage information, child nodes, and gene and genome counts in JSON format.'
tags:
- Taxonomy
operationId: taxonomy_data_report
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsTaxonomyDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsTaxonomyDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: taxons
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- "9606"
summary: NCBI Taxonomy Identifier
example-1:
value:
- human
- house mouse
summary: Common Name
example-2:
value:
- Homo sapiens
- Mus musculus
summary: Scientific Name
- name: returned_content
description: 'Return either tax-ids alone, or entire taxononmy-metadata records'
in: query
required: false
schema:
$ref: '#/components/schemas/v2TaxonomyMetadataRequestContentType'
- name: page_size
description: 'The maximum number of taxons 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_token
description: 'A page token is returned from `GetTaxonomyDataReportFor` and `GetTaxonomyNamesDataReportFor` calls with more than `page_size` results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: table_format
in: query
required: false
schema:
$ref: '#/components/schemas/v2TaxonomyMetadataRequestTableFormat'
- name: children
description: 'Flag for tax explosion.'
in: query
required: false
schema:
type: boolean
- name: ranks
description: 'Only include taxons of the provided ranks. If empty, return all ranks.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2reportsRankType'
/taxonomy/dataset_report:
post:
summary: Use taxonomic identifiers to get taxonomic names data report by post
description: 'Using NCBI Taxonomy IDs or names (common or scientific) at any rank, get metadata about a taxonomic node including taxonomic identifiers, lineage information, child nodes, and gene and genome counts in JSON format.'
tags:
- Taxonomy
operationId: taxonomy_data_report_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsTaxonomyDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsTaxonomyDataReportPage'
text/tab-separated-values:
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyMetadataRequest'
examples:
Multiple TaxID and common name examples:
description: Taxon input (multiple types)
value:
taxons:
- "9606"
- house mouse
/taxonomy/taxon/{taxons}/name_report:
get:
summary: Use taxonomic identifiers to get taxonomic names data report
description: 'Using NCBI Taxonomy IDs or names (common or scientific) at any rank, get metadata about associated taxonomic names.'
tags:
- Taxonomy
operationId: taxonomy_names
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsTaxonomyNamesDataReportPage'
parameters:
- name: taxons
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- "9606"
summary: NCBI Taxonomy Identifier
example-1:
value:
- human
- house mouse
summary: Common Name
example-2:
value:
- Homo sapiens
- Mus musculus
summary: Scientific Name
- name: returned_content
description: 'Return either tax-ids alone, or entire taxononmy-metadata records'
in: query
required: false
schema:
$ref: '#/components/schemas/v2TaxonomyMetadataRequestContentType'
- name: page_size
description: 'The maximum number of taxons 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: include_tabular_header
description: 'Whether this request for tabular data should include the header row'
in: query
required: false
schema:
$ref: '#/components/schemas/v2IncludeTabularHeader'
- name: page_token
description: 'A page token is returned from `GetTaxonomyDataReportFor` and `GetTaxonomyNamesDataReportFor` calls with more than `page_size` results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
- name: table_format
in: query
required: false
schema:
$ref: '#/components/schemas/v2TaxonomyMetadataRequestTableFormat'
- name: children
description: 'Flag for tax explosion.'
in: query
required: false
schema:
type: boolean
- name: ranks
description: 'Only include taxons of the provided ranks. If empty, return all ranks.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2reportsRankType'
/taxonomy/name_report:
post:
summary: Use taxonomic identifiers to get taxonomic names data report by post
description: 'Using NCBI Taxonomy IDs or names (common or scientific) at any rank, get metadata about associated taxonomic names.'
tags:
- Taxonomy
operationId: taxonomy_names_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsTaxonomyNamesDataReportPage'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyMetadataRequest'
examples:
Multiple TaxID and common name examples:
description: Taxon input (multiple types)
value:
taxons:
- "9606"
- house mouse
/taxonomy/taxon/{tax_id}/related_ids:
get:
summary: Use taxonomic identifier to get related taxonomic identifiers, such as children
description: 'Using a single NCBI Taxonomy ID at any rank, get a list of related taxonomic IDs in JSON format.'
tags:
- Taxonomy
operationId: taxonomy_related_ids
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyTaxIdsPage'
parameters:
- name: tax_id
in: path
required: true
schema:
type: integer
examples:
example-0:
value: 9606
summary: NCBI Taxonomy Identifier
- name: include_lineage
description: 'If true, return reports for all taxonomy nodes in the lineages of the requested tax_id'
in: query
required: false
schema:
type: boolean
default: false
- name: include_subtree
description: 'This field is deprecated because all requests include the subtree, so it has no effect'
in: query
required: false
schema:
type: boolean
default: false
- name: ranks
description: 'Only include taxons of the provided ranks. If empty, return all ranks.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2reportsRankType'
- name: page_size
description: 'The maximum number of taxids 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from a `GetRelatedTaxids` call with more than `page_size` results. Use this token, along with the previous `TaxonomyRelatedIdRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
/taxonomy/related_ids:
post:
summary: Use taxonomic identifier to get related taxonomic identifiers, such as children
description: 'Using a single NCBI Taxonomy ID at any rank, get a list of related taxonomic IDs in JSON format.'
tags:
- Taxonomy
operationId: taxonomy_related_ids_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyTaxIdsPage'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyRelatedIdRequest'
examples:
Single TaxID example:
description: TaxID (just one)
value:
tax_id: 9606
/taxonomy/taxon/{taxons}/filtered_subtree:
get:
summary: Use taxonomic identifiers to get a filtered taxonomic subtree
description: 'Using NCBI Taxonomy IDs or names (common or scientific) at any rank, get a filtered taxonomic subtree that includes the full parent lineage and all immediate children from the selected taxonomic ranks in JSON format.'
tags:
- Taxonomy
operationId: taxonomy_filtered_subtree
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyFilteredSubtreeResponse'
parameters:
- name: taxons
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- "9606"
summary: NCBI Taxonomy Identifier
example-1:
value:
- human
- mouse
summary: Common Name
example-2:
value:
- Homo sapiens
- Mus musculus
summary: Scientific Name
- name: specified_limit
description: 'Limit to specified species'
in: query
required: false
schema:
type: boolean
- name: rank_limits
description: 'Limit to the provided ranks. If empty, accept any rank.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2reportsRankType'
/taxonomy/filtered_subtree:
post:
summary: Use taxonomic identifiers to get a filtered taxonomic subtree by post
description: 'Using NCBI Taxonomy IDs or names (common or scientific) at any rank, get a filtered taxonomic subtree that includes the full parent lineage and all immediate children from the selected taxonomic ranks in JSON format.'
tags:
- Taxonomy
operationId: taxonomy_filtered_subtree_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyFilteredSubtreeResponse'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyFilteredSubtreeRequest'
examples:
Multiple TaxID example:
description: TaxIDs (multiple)
value:
taxons:
- "9606"
- "10090"
/taxonomy/taxon_suggest/{taxon_query}:
get:
summary: Get a list of taxonomy names and IDs given a partial taxonomic name
description: 'This endpoint retrieves a list of taxonomy names and IDs given a possibly partial taxonomic name of any rank.'
tags:
- Taxonomy
operationId: tax_name_query
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2SciNameAndIds'
parameters:
- name: taxon_query
description: 'NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank'
in: path
required: true
schema:
type: string
examples:
example-0:
value: hum
summary: hum
- name: tax_rank_filter
description: 'Set the scope of searched tax ranks when filtering by gene or genome. Not used for ''all'''
in: query
required: false
schema:
$ref: '#/components/schemas/v2OrganismQueryRequestTaxRankFilter'
- name: taxon_resource_filter
description: 'Limit results to those with gene or genome counts (no filter by default)'
in: query
required: false
schema:
$ref: '#/components/schemas/v2OrganismQueryRequestTaxonResourceFilter'
- name: exact_match
description: 'If true, only return results that exactly match the provided name or tax-id'
in: query
required: false
schema:
type: boolean
default: false
/taxonomy/taxon_suggest:
post:
summary: Get a list of taxonomy names and IDs given a partial taxonomic name
description: 'This endpoint retrieves a list of taxonomy names and IDs given a possibly partial taxonomic name of any rank, by post.'
tags:
- Taxonomy
operationId: tax_name_query_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2SciNameAndIds'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2OrganismQueryRequest'
examples:
Incomplete taxon name example:
description: Incomplete taxon name example
value:
taxon_query: "hum"
/taxonomy/taxon/{taxon}/links:
get:
summary: Retrieve external links associated with a taxonomic identifier.
description: 'Using an NCBI Taxonomy ID at any rank, get the external links associated with the taxon.'
tags:
- Taxonomy
operationId: taxonomy_links
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyLinksResponse'
parameters:
- name: taxon
in: path
required: true
schema:
type: string
examples:
example-0:
value: "9606"
summary: NCBI Taxonomy Identifier
/taxonomy/links:
post:
summary: Retrieve external links associated with a taxonomic identifier.
description: 'Using an NCBI Taxonomy ID at any rank, get the external links associated with the taxon.'
tags:
- Taxonomy
operationId: taxonomy_links_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyLinksResponse'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyLinksRequest'
examples:
Single TaxID example:
description: TaxID (just one)
value:
taxon: "9606"
/taxonomy/taxon/{taxon}/image:
get:
summary: Retrieve image associated with a taxonomic identifier
description: 'Using an NCBI Taxonomy ID or a name (common or scientific) at any rank, get the image associated with the taxon.'
tags:
- Taxonomy
operationId: taxonomy_image
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
image/jpeg:
schema:
format: binary
type: string
description: Image stream (jpeg/png/tiff)
image/png:
schema:
format: binary
type: string
description: Image stream (jpeg/png/tiff)
image/gif:
schema:
$ref: '#/components/schemas/v2HttpBody'
image/tiff:
schema:
format: binary
type: string
description: Image stream (jpeg/png/tiff)
image/svg+xml:
schema:
format: binary
type: string
description: SVG Image stream
parameters:
- name: taxon
in: path
required: true
schema:
type: string
examples:
example-0:
value: "9606"
summary: NCBI Taxonomy Identifier
- name: image_size
in: query
required: false
schema:
$ref: '#/components/schemas/v2ImageSize'
/taxonomy/image:
post:
summary: Retrieve image associated with a taxonomic identifier by post
description: 'Using an NCBI Taxonomy ID or a name (common or scientific) at any rank, get the image associated with the taxon.'
tags:
- Taxonomy
operationId: taxonomy_image_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
image/jpeg:
schema:
format: binary
type: string
description: Image stream (jpeg/png/tiff)
image/png:
schema:
format: binary
type: string
description: Image stream (jpeg/png/tiff)
image/tiff:
schema:
format: binary
type: string
description: Image stream (jpeg/png/tiff)
image/svg+xml:
schema:
format: binary
type: string
description: SVG Image stream
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyImageRequest'
examples:
Single TaxID example:
description: TaxID (just one)
value:
taxon: "9606"
/taxonomy/taxon/{taxon}/image/metadata:
get:
summary: Retrieve image metadata associated with a taxonomic identifier
description: 'Using an NCBI Taxonomy ID or a name (common or scientific) at any rank, get the image metadata associated with the taxon.'
tags:
- Taxonomy
operationId: taxonomy_image_metadata
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyImageMetadataResponse'
parameters:
- name: taxon
in: path
required: true
schema:
type: string
examples:
example-0:
value: "9606"
summary: NCBI Taxonomy Identifier
/taxonomy/image/metadata:
post:
summary: Retrieve image metadata associated with a taxonomic identifier by post
description: 'Using an NCBI Taxonomy ID or a name (common or scientific) at any rank, get the image metadata associated with the taxon.'
tags:
- Taxonomy
operationId: taxonomy_image_metadata_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyImageMetadataResponse'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2TaxonomyImageMetadataRequest'
examples:
Single TaxID example:
description: TaxID (just one)
value:
taxon: "9606"
/virus/taxon/{taxon}/genome:
get:
summary: Get summary data for virus genomes by taxon
description: 'Get summary data and download by command line instructions for virus genomes by taxon.'
tags:
- Virus
operationId: virus_genome_summary
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2DownloadSummary'
parameters:
- name: accessions
description: 'genome sequence accessions'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NC_038294.1
summary: Middle East respiratory syndrome-related coronavirus, complete genome
- name: taxon
description: 'NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank'
in: path
required: true
schema:
type: string
examples:
example-0:
value: "1335626"
summary: MERS
example-1:
value: "2697049"
summary: SARS-COV-2
example-2:
value: "11118"
summary: Coronaviridae
- name: refseq_only
description: 'If true, limit results to RefSeq genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to RefSeq genomes
example-1:
value: false
summary: Both GenBank & RefSeq genomes
- name: annotated_only
description: 'If true, limit results to annotated genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated genomes
example-1:
value: false
summary: All genomes
- name: released_since
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 ''2020-04-01T00:00:00.000Z'''
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2020-08-01T00:00:00Z
summary: August 1, 2020
- name: updated_since
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-07-18T00:00:00Z
summary: July 18, 2021
- name: host
description: 'If set, limit results to genomes extracted from this host (Taxonomy ID or name) All hosts by default'
in: query
required: false
schema:
type: string
examples:
example-0:
value: human
summary: human
- name: pangolin_classification
description: 'If set, limit results to genomes classified to this lineage by the PangoLearn tool.'
in: query
required: false
schema:
type: string
- name: geo_location
description: 'Assemblies from this location (country or continent)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: USA
summary: USA
example-1:
value: Asia
summary: Asia
- name: usa_state
description: 'Assemblies from this state (official two letter code only)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: CA
summary: California
example-1:
value: TX
summary: Texas
- name: complete_only
description: 'only include complete genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to complete genomes
example-1:
value: false
summary: All genomes
- name: include_sequence
description: 'specify which sequence files to include in the download'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2ViralSequenceType'
examples:
example-0:
value:
- GENOME
- CDS
- PROTEIN
summary: Select viral sequences to include
- name: aux_report
description: 'list additional reports to include with download. Data report is included by default.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2VirusDatasetReportType'
examples:
example-0:
value:
- ANNOTATION
summary: Select additional report types to include with download. The base data report will always be included.
/virus/genome:
post:
summary: Get summary data for virus genomes by post
description: 'Get summary data and download by command line instructions for virus genomes by taxon.'
tags:
- Virus
operationId: virus_genome_summary_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2DownloadSummary'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2VirusDatasetRequest'
examples:
Single Virus accession example:
description: Virus accession (just one)
value:
accessions:
- NC_038294.1
/virus/taxon/sars2/protein/{proteins}:
get:
summary: Summary of SARS-CoV-2 protein and CDS datasets by protein name
description: 'Download a summary of available SARS-CoV-2 protein datasets'
tags:
- Virus
operationId: sars2_protein_summary
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2DownloadSummary'
parameters:
- name: proteins
description: 'Which proteins to retrieve in the data package'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- spike protein
summary: Spike Protein
example-1:
value:
- spike protein
- envelope protein
- RdRp
summary: SARS-CoV-2 proteins
- name: refseq_only
description: 'If true, limit results to RefSeq genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to RefSeq genomes
example-1:
value: false
summary: Both GenBank & RefSeq genomes
- name: annotated_only
description: 'If true, limit results to annotated genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated genomes
example-1:
value: false
summary: All genomes
- name: released_since
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 ''2020-04-01T00:00:00.000Z'''
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2020-08-01T00:00:00Z
summary: August 1, 2020
- name: updated_since
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-07-18T00:00:00Z
summary: July 18, 2021
- name: host
description: 'If set, limit results to genomes extracted from this host (Taxonomy ID or name) All hosts by default'
in: query
required: false
schema:
type: string
examples:
example-0:
value: human
summary: human
- name: pangolin_classification
description: 'If set, limit results to genomes classified to this lineage by the PangoLearn tool.'
in: query
required: false
schema:
type: string
- name: geo_location
description: 'Assemblies from this location (country or continent)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: USA
summary: USA
example-1:
value: Asia
summary: Asia
- name: usa_state
description: 'Assemblies from this state (official two letter code only)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: CA
summary: California
example-1:
value: TX
summary: Texas
- name: complete_only
description: 'only include complete genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to complete genomes
example-1:
value: false
summary: All genomes
- name: include_sequence
description: 'Specify which sequence files to include in the download'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2ViralSequenceType'
examples:
example-0:
value:
- CDS
- PROTEIN
summary: Select viral sequences to include
- name: aux_report
description: 'List additional reports to include with download. Data report is included by default.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2VirusDatasetReportType'
examples:
example-0:
value:
- ANNOTATION
summary: Select additional report types to include with download. The base data report will always be included.
/virus/taxon/sars2/protein:
post:
summary: Summary of SARS-CoV-2 protein and CDS datasets by protein name
description: 'Download a summary of available SARS-CoV-2 protein datasets'
tags:
- Virus
operationId: sars2_protein_summary_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2DownloadSummary'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2Sars2ProteinDatasetRequest'
examples:
SARS-CoV-2 virus RefSeq protein example:
description: SARS-CoV-2 virus protein (RefSeq)
value:
proteins:
- spike
refseq_only: true
/virus/taxon/{taxon}/genome/table:
get:
summary: Get virus genome metadata in a tabular format.
description: 'Get virus genome metadata in tabular format for virus genomes by taxon.'
tags:
- Virus
operationId: virus_genome_table
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2TabularOutput'
parameters:
- name: accessions
description: 'genome sequence accessions'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NC_038294.1
summary: Middle East respiratory syndrome-related coronavirus, complete genome
- name: taxon
description: 'NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank'
in: path
required: true
schema:
type: string
examples:
example-0:
value: "1335626"
summary: MERS
example-1:
value: "2697049"
summary: SARS-COV-2
example-2:
value: "11118"
summary: Coronaviridae
- name: refseq_only
description: 'If true, limit results to RefSeq genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to RefSeq genomes
example-1:
value: false
summary: Both GenBank & RefSeq genomes
- name: annotated_only
description: 'If true, limit results to annotated genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated genomes
example-1:
value: false
summary: All genomes
- name: released_since
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 ''2020-04-01T00:00:00.000Z'''
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2020-08-01T00:00:00Z
summary: August 1, 2020
- name: updated_since
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-07-18T00:00:00Z
summary: July 18, 2021
- name: host
description: 'If set, limit results to genomes extracted from this host (Taxonomy ID or name) All hosts by default'
in: query
required: false
schema:
type: string
examples:
example-0:
value: human
summary: human
- name: pangolin_classification
description: 'If set, limit results to genomes classified to this lineage by the PangoLearn tool.'
in: query
required: false
schema:
type: string
- name: geo_location
description: 'Assemblies from this location (country or continent)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: USA
summary: USA
example-1:
value: Asia
summary: Asia
- name: usa_state
description: 'Assemblies from this state (official two letter code only)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: CA
summary: California
example-1:
value: TX
summary: Texas
- name: complete_only
description: 'only include complete genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to complete genomes
example-1:
value: false
summary: All genomes
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2VirusTableField'
examples:
example-0:
value:
- nucleotide_accession
- nucleotide_length
- nuc_completeness
summary: Assembly Fields
- name: include_sequence
description: 'specify which sequence files to include in the download'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2ViralSequenceType'
examples:
example-0:
value:
- GENOME
- CDS
- PROTEIN
summary: Select viral sequences to include
- name: aux_report
description: 'list additional reports to include with download. Data report is included by default.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2VirusDatasetReportType'
examples:
example-0:
value:
- ANNOTATION
summary: Select additional report types to include with download. The base data report will always be included.
- name: format
description: 'Choose download format (tsv, csv or jsonl)'
in: query
required: false
schema:
$ref: '#/components/schemas/v2TableFormat'
examples:
example-0:
value: tsv
summary: TSV
example-1:
value: csv
summary: CSV
example-2:
value: jsonl
summary: JSON Lines
/virus/taxon/sars2/protein/{proteins}/table:
get:
summary: Get SARS-CoV-2 protein metadata in a tabular format.
description: 'Get protein metadata in tabular format for SARS-CoV-2 genomes.'
tags:
- Virus
operationId: sars2_protein_table
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2TabularOutput'
parameters:
- name: proteins
description: 'Which proteins to retrieve in the data package'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- spike protein
summary: Spike Protein
example-1:
value:
- spike protein
- envelope protein
- RdRp
summary: SARS-CoV-2 proteins
- name: refseq_only
description: 'If true, limit results to RefSeq genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to RefSeq genomes
example-1:
value: false
summary: Both GenBank & RefSeq genomes
- name: annotated_only
description: 'If true, limit results to annotated genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated genomes
example-1:
value: false
summary: All genomes
- name: released_since
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 ''2020-04-01T00:00:00.000Z'''
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2020-08-01T00:00:00Z
summary: August 1, 2020
- name: updated_since
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-07-18T00:00:00Z
summary: July 18, 2021
- name: host
description: 'If set, limit results to genomes extracted from this host (Taxonomy ID or name) All hosts by default'
in: query
required: false
schema:
type: string
examples:
example-0:
value: human
summary: human
- name: pangolin_classification
description: 'If set, limit results to genomes classified to this lineage by the PangoLearn tool.'
in: query
required: false
schema:
type: string
- name: geo_location
description: 'Assemblies from this location (country or continent)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: USA
summary: USA
example-1:
value: Asia
summary: Asia
- name: usa_state
description: 'Assemblies from this state (official two letter code only)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: CA
summary: California
example-1:
value: TX
summary: Texas
- name: complete_only
description: 'only include complete genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to complete genomes
example-1:
value: false
summary: All genomes
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2VirusTableField'
examples:
example-0:
value:
- nucleotide_accession
- nucleotide_length
- nuc_completeness
summary: Assembly Fields
- name: include_sequence
description: 'Specify which sequence files to include in the download'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2ViralSequenceType'
examples:
example-0:
value:
- CDS
- PROTEIN
summary: Select viral sequences to include
- name: aux_report
description: 'List additional reports to include with download. Data report is included by default.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2VirusDatasetReportType'
examples:
example-0:
value:
- ANNOTATION
summary: Select additional report types to include with download. The base data report will always be included.
- name: format
description: 'Choose download format (tsv, csv or jsonl)'
in: query
required: false
schema:
$ref: '#/components/schemas/v2TableFormat'
examples:
example-0:
value: tsv
summary: TSV
example-1:
value: csv
summary: CSV
example-2:
value: jsonl
summary: JSON Lines
/virus/taxon/{taxon}/dataset_report:
get:
summary: Get virus metadata by taxon
description: 'Get virus metadata by taxon. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Virus
operationId: virus_reports_by_taxon
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsVirusDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsVirusDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: taxon
description: 'NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank'
in: path
required: true
schema:
type: string
examples:
example-0:
value: "1335626"
summary: MERS
example-1:
value: "2697049"
summary: SARS-COV-2
example-2:
value: "11118"
summary: Coronaviridae
- name: filter.refseq_only
description: 'If true, limit results to RefSeq genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to RefSeq genomes
example-1:
value: false
summary: Both GenBank & RefSeq genomes
- name: filter.annotated_only
description: 'If true, limit results to annotated genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated genomes
example-1:
value: false
summary: All genomes
- name: filter.released_since
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 ''2020-04-01T00:00:00.000Z'''
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2020-08-01T00:00:00Z
summary: August 1, 2020
- name: filter.updated_since
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-07-18T00:00:00Z
summary: July 18, 2021
- name: filter.host
description: 'If set, limit results to genomes extracted from this host (Taxonomy ID or name) All hosts by default'
in: query
required: false
schema:
type: string
examples:
example-0:
value: human
summary: human
- name: filter.pangolin_classification
description: 'If set, limit results to genomes classified to this lineage by the PangoLearn tool.'
in: query
required: false
schema:
type: string
- name: filter.geo_location
description: 'Assemblies from this location (country or continent)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: USA
summary: USA
example-1:
value: Asia
summary: Asia
- name: filter.usa_state
description: 'Assemblies from this state (official two letter code only)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: CA
summary: California
example-1:
value: TX
summary: Texas
- name: filter.complete_only
description: 'only include complete genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to complete genomes
example-1:
value: false
summary: All genomes
- name: returned_content
description: 'Return either virus genome accessions, or complete virus metadata'
in: query
required: false
schema:
$ref: '#/components/schemas/v2VirusDataReportRequestContentType'
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- accession
- is-complete
- is-annotated
summary: Virus Data Report Fields
- name: page_size
description: 'The maximum number of virus data reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from a `GetVirusDataReports` call with more than `page_size` results. Use this token, along with the previous `VirusDataReportRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
/virus/accession/{accessions}/dataset_report:
get:
summary: Get virus metadata by accession
description: 'Get virus metadata by accesion. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Virus
operationId: virus_reports_by_acessions
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsVirusDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsVirusDataReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: accessions
description: 'genome sequence accessions'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NC_038294.1
summary: Middle East respiratory syndrome-related coronavirus, complete genome
- name: filter.refseq_only
description: 'If true, limit results to RefSeq genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to RefSeq genomes
example-1:
value: false
summary: Both GenBank & RefSeq genomes
- name: filter.annotated_only
description: 'If true, limit results to annotated genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated genomes
example-1:
value: false
summary: All genomes
- name: filter.released_since
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 ''2020-04-01T00:00:00.000Z'''
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2020-08-01T00:00:00Z
summary: August 1, 2020
- name: filter.updated_since
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-07-18T00:00:00Z
summary: July 18, 2021
- name: filter.host
description: 'If set, limit results to genomes extracted from this host (Taxonomy ID or name) All hosts by default'
in: query
required: false
schema:
type: string
examples:
example-0:
value: human
summary: human
- name: filter.pangolin_classification
description: 'If set, limit results to genomes classified to this lineage by the PangoLearn tool.'
in: query
required: false
schema:
type: string
- name: filter.geo_location
description: 'Assemblies from this location (country or continent)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: USA
summary: USA
example-1:
value: Asia
summary: Asia
- name: filter.usa_state
description: 'Assemblies from this state (official two letter code only)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: CA
summary: California
example-1:
value: TX
summary: Texas
- name: filter.complete_only
description: 'only include complete genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to complete genomes
example-1:
value: false
summary: All genomes
- name: returned_content
description: 'Return either virus genome accessions, or complete virus metadata'
in: query
required: false
schema:
$ref: '#/components/schemas/v2VirusDataReportRequestContentType'
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- accession
- is-complete
- is-annotated
summary: Virus Data Report Fields
- name: page_size
description: 'The maximum number of virus data reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from a `GetVirusDataReports` call with more than `page_size` results. Use this token, along with the previous `VirusDataReportRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
/virus:
post:
summary: Get virus metadata by POST
description: 'Get virus metadata. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Virus
operationId: virus_reports_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsVirusDataReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsVirusDataReportPage'
text/tab-separated-values:
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2VirusDataReportRequest'
examples:
RefSeq Virus TaxID example:
description: Virus TaxID (RefSeq)
value:
taxon: 1335626
refseq_only: true
/virus/taxon/{taxon}/annotation_report:
get:
summary: Get virus annotation report by taxon
description: 'Get virus annotation report by taxon. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Virus
operationId: virus_annotation_reports_by_taxon
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsVirusAnnotationReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsVirusAnnotationReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: taxon
description: 'NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank'
in: path
required: true
schema:
type: string
examples:
example-0:
value: "1335626"
summary: MERS
example-1:
value: "2697049"
summary: SARS-COV-2
example-2:
value: "11118"
summary: Coronaviridae
- name: filter.refseq_only
description: 'If true, limit results to RefSeq genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to RefSeq genomes
example-1:
value: false
summary: Both GenBank & RefSeq genomes
- name: filter.annotated_only
description: 'If true, limit results to annotated genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated genomes
example-1:
value: false
summary: All genomes
- name: filter.released_since
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 ''2020-04-01T00:00:00.000Z'''
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2020-08-01T00:00:00Z
summary: August 1, 2020
- name: filter.updated_since
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-07-18T00:00:00Z
summary: July 18, 2021
- name: filter.host
description: 'If set, limit results to genomes extracted from this host (Taxonomy ID or name) All hosts by default'
in: query
required: false
schema:
type: string
examples:
example-0:
value: human
summary: human
- name: filter.pangolin_classification
description: 'If set, limit results to genomes classified to this lineage by the PangoLearn tool.'
in: query
required: false
schema:
type: string
- name: filter.geo_location
description: 'Assemblies from this location (country or continent)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: USA
summary: USA
example-1:
value: Asia
summary: Asia
- name: filter.usa_state
description: 'Assemblies from this state (official two letter code only)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: CA
summary: California
example-1:
value: TX
summary: Texas
- name: filter.complete_only
description: 'only include complete genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to complete genomes
example-1:
value: false
summary: All genomes
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- accession
- isolate-name
summary: Virus Annotation Report Fields
- name: page_size
description: 'The maximum number of virus data reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from a `GetVirusDataReports` call with more than `page_size` results. Use this token, along with the previous `VirusDataReportRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
/virus/accession/{accessions}/annotation_report:
get:
summary: Get virus annotation report by accession
description: 'Get virus annotation report by accesion. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Virus
operationId: virus_annotation_reports_by_acessions
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsVirusAnnotationReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsVirusAnnotationReportPage'
text/tab-separated-values:
schema:
type: string
parameters:
- name: accessions
description: 'genome sequence accessions'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NC_038294.1
summary: Middle East respiratory syndrome-related coronavirus, complete genome
- name: filter.refseq_only
description: 'If true, limit results to RefSeq genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to RefSeq genomes
example-1:
value: false
summary: Both GenBank & RefSeq genomes
- name: filter.annotated_only
description: 'If true, limit results to annotated genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated genomes
example-1:
value: false
summary: All genomes
- name: filter.released_since
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 ''2020-04-01T00:00:00.000Z'''
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2020-08-01T00:00:00Z
summary: August 1, 2020
- name: filter.updated_since
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-07-18T00:00:00Z
summary: July 18, 2021
- name: filter.host
description: 'If set, limit results to genomes extracted from this host (Taxonomy ID or name) All hosts by default'
in: query
required: false
schema:
type: string
examples:
example-0:
value: human
summary: human
- name: filter.pangolin_classification
description: 'If set, limit results to genomes classified to this lineage by the PangoLearn tool.'
in: query
required: false
schema:
type: string
- name: filter.geo_location
description: 'Assemblies from this location (country or continent)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: USA
summary: USA
example-1:
value: Asia
summary: Asia
- name: filter.usa_state
description: 'Assemblies from this state (official two letter code only)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: CA
summary: California
example-1:
value: TX
summary: Texas
- name: filter.complete_only
description: 'only include complete genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to complete genomes
example-1:
value: false
summary: All genomes
- name: table_fields
description: 'Specify which fields to include in the tabular report'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- accession
- isolate-name
summary: Virus Annotation Report Fields
- name: page_size
description: 'The maximum number of virus data reports 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.'
in: query
required: false
schema:
type: integer
default: 20
- name: page_token
description: 'A page token is returned from a `GetVirusDataReports` call with more than `page_size` results. Use this token, along with the previous `VirusDataReportRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
in: query
required: false
schema:
type: string
/virus/annotation_report:
post:
summary: Get virus annotation report by POST
description: 'Get virus annotation report. By default, in paged JSON format, but also available as tabular (accept: text/tab-separated-values) or json-lines (accept: application/x-ndjson)'
tags:
- Virus
operationId: virus_annotation_reports_by_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2reportsVirusAnnotationReportPage'
application/x-ndjson:
schema:
$ref: '#/components/schemas/v2reportsVirusAnnotationReportPage'
text/tab-separated-values:
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2VirusAnnotationReportRequest'
examples:
RefSeq Virus TaxID example:
description: Virus TaxID (RefSeq)
value:
taxon: 1335626
refseq_only: true
/virus/accession/{accessions}/check:
get:
summary: Check available viruses by accession
description: 'Check available viruses'
tags:
- Virus
operationId: virus_accession_availability
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2VirusAvailability'
parameters:
- name: accessions
description: 'virus accessions'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NC_038294.1
summary: Middle East respiratory syndrome-related coronavirus, complete genome
/virus/check:
post:
summary: Check available viruses by accession
description: 'Check available viruses'
tags:
- Virus
operationId: virus_accession_availability_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/json:
schema:
$ref: '#/components/schemas/v2VirusAvailability'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2VirusAvailabilityRequest'
examples:
Single Virus accession example:
description: Virus accession (just one)
value:
accessions:
- NC_038294.1
/virus/taxon/{taxon}/genome/download:
get:
summary: Download a virus genome dataset by taxon
description: 'Download a virus genome dataset by taxon'
tags:
- Virus
operationId: virus_genome_download
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
parameters:
- name: taxon
description: 'NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank'
in: path
required: true
schema:
type: string
examples:
example-0:
value: "1335626"
summary: MERS
example-1:
value: "2697049"
summary: SARS-COV-2
example-2:
value: "11118"
summary: Coronaviridae
- name: taxons
description: 'NCBI Taxonomy IDs or names (common or scientific) at any taxonomic rank'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- "1335626"
summary: MERS
example-1:
value:
- "2697049"
summary: SARS-COV-2
example-2:
value:
- "11118"
summary: Coronaviridae
- name: refseq_only
description: 'If true, limit results to RefSeq genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to RefSeq genomes
example-1:
value: false
summary: Both GenBank & RefSeq genomes
- name: annotated_only
description: 'If true, limit results to annotated genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated genomes
example-1:
value: false
summary: All genomes
- name: released_since
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 ''2020-04-01T00:00:00.000Z'''
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2020-08-01T00:00:00Z
summary: August 1, 2020
- name: updated_since
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-07-18T00:00:00Z
summary: July 18, 2021
- name: host
description: 'If set, limit results to genomes extracted from this host (Taxonomy ID or name) All hosts by default'
in: query
required: false
schema:
type: string
examples:
example-0:
value: human
summary: human
- name: pangolin_classification
description: 'If set, limit results to genomes classified to this lineage by the PangoLearn tool.'
in: query
required: false
schema:
type: string
- name: geo_location
description: 'Assemblies from this location (country or continent)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: USA
summary: USA
example-1:
value: Asia
summary: Asia
- name: usa_state
description: 'Assemblies from this state (official two letter code only)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: CA
summary: California
example-1:
value: TX
summary: Texas
- name: complete_only
description: 'only include complete genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to complete genomes
example-1:
value: false
summary: All genomes
- name: include_sequence
description: 'specify which sequence files to include in the download'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2ViralSequenceType'
examples:
example-0:
value:
- GENOME
- CDS
- PROTEIN
summary: Select viral sequences to include
- name: aux_report
description: 'list additional reports to include with download. Data report is included by default.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2VirusDatasetReportType'
examples:
example-0:
value:
- ANNOTATION
summary: Select additional report types to include with download. The base data report will always be included.
- name: use_psg
description: 'Experimental approach to retrieving sequence data.'
in: query
required: false
schema:
type: boolean
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
/virus/accession/{accessions}/genome/download:
get:
summary: Download a virus genome dataset by accession
description: 'Download a virus genome dataset by accession'
tags:
- Virus
operationId: virus_genome_download_accession
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
parameters:
- name: accessions
description: 'genome sequence accessions'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- NC_038294.1
summary: Middle East respiratory syndrome-related coronavirus, complete genome
- name: taxons
description: 'NCBI Taxonomy IDs or names (common or scientific) at any taxonomic rank'
in: query
required: false
schema:
type: array
items:
type: string
examples:
example-0:
value:
- "1335626"
summary: MERS
example-1:
value:
- "2697049"
summary: SARS-COV-2
example-2:
value:
- "11118"
summary: Coronaviridae
- name: refseq_only
description: 'If true, limit results to RefSeq genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to RefSeq genomes
example-1:
value: false
summary: Both GenBank & RefSeq genomes
- name: annotated_only
description: 'If true, limit results to annotated genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated genomes
example-1:
value: false
summary: All genomes
- name: released_since
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 ''2020-04-01T00:00:00.000Z'''
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2020-08-01T00:00:00Z
summary: August 1, 2020
- name: updated_since
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-07-18T00:00:00Z
summary: July 18, 2021
- name: host
description: 'If set, limit results to genomes extracted from this host (Taxonomy ID or name) All hosts by default'
in: query
required: false
schema:
type: string
examples:
example-0:
value: human
summary: human
- name: pangolin_classification
description: 'If set, limit results to genomes classified to this lineage by the PangoLearn tool.'
in: query
required: false
schema:
type: string
- name: geo_location
description: 'Assemblies from this location (country or continent)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: USA
summary: USA
example-1:
value: Asia
summary: Asia
- name: usa_state
description: 'Assemblies from this state (official two letter code only)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: CA
summary: California
example-1:
value: TX
summary: Texas
- name: complete_only
description: 'only include complete genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to complete genomes
example-1:
value: false
summary: All genomes
- name: include_sequence
description: 'specify which sequence files to include in the download'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2ViralSequenceType'
examples:
example-0:
value:
- GENOME
- CDS
- PROTEIN
summary: Select viral sequences to include
- name: aux_report
description: 'list additional reports to include with download. Data report is included by default.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2VirusDatasetReportType'
examples:
example-0:
value:
- ANNOTATION
summary: Select additional report types to include with download. The base data report will always be included.
- name: use_psg
description: 'Experimental approach to retrieving sequence data.'
in: query
required: false
schema:
type: boolean
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
/virus/genome/download:
post:
summary: Get a virus genome dataset by 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.'
tags:
- Virus
operationId: virus_genome_download_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2VirusDatasetRequest'
examples:
Single Virus accession example:
description: Virus accession (just one)
value:
accessions:
- NC_038294.1
parameters:
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
/virus/taxon/sars2/protein/{proteins}/download:
get:
summary: Download SARS-CoV-2 protein and CDS datasets by protein name
description: 'Download SARS-CoV-2 protein datasets'
tags:
- Virus
operationId: sars2_protein_download
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
parameters:
- name: proteins
description: 'Which proteins to retrieve in the data package'
in: path
required: true
schema:
type: array
items:
type: string
examples:
example-0:
value:
- spike protein
summary: Spike Protein
example-1:
value:
- spike protein
- envelope protein
- RdRp
summary: SARS-CoV-2 proteins
- name: refseq_only
description: 'If true, limit results to RefSeq genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to RefSeq genomes
example-1:
value: false
summary: Both GenBank & RefSeq genomes
- name: annotated_only
description: 'If true, limit results to annotated genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to annotated genomes
example-1:
value: false
summary: All genomes
- name: released_since
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 ''2020-04-01T00:00:00.000Z'''
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2020-08-01T00:00:00Z
summary: August 1, 2020
- name: updated_since
in: query
required: false
schema:
type: string
format: date-time
examples:
example-0:
value: 2021-07-18T00:00:00Z
summary: July 18, 2021
- name: host
description: 'If set, limit results to genomes extracted from this host (Taxonomy ID or name) All hosts by default'
in: query
required: false
schema:
type: string
examples:
example-0:
value: human
summary: human
- name: pangolin_classification
description: 'If set, limit results to genomes classified to this lineage by the PangoLearn tool.'
in: query
required: false
schema:
type: string
- name: geo_location
description: 'Assemblies from this location (country or continent)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: USA
summary: USA
example-1:
value: Asia
summary: Asia
- name: usa_state
description: 'Assemblies from this state (official two letter code only)'
in: query
required: false
schema:
type: string
examples:
example-0:
value: CA
summary: California
example-1:
value: TX
summary: Texas
- name: complete_only
description: 'only include complete genomes.'
in: query
required: false
schema:
type: boolean
default: false
examples:
example-0:
value: true
summary: Limit to complete genomes
example-1:
value: false
summary: All genomes
- name: include_sequence
description: 'Specify which sequence files to include in the download'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2ViralSequenceType'
examples:
example-0:
value:
- CDS
- PROTEIN
summary: Select viral sequences to include
- name: aux_report
description: 'List additional reports to include with download. Data report is included by default.'
in: query
required: false
schema:
type: array
items:
$ref: '#/components/schemas/v2VirusDatasetReportType'
examples:
example-0:
value:
- ANNOTATION
summary: Select additional report types to include with download. The base data report will always be included.
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
/virus/taxon/sars2/protein/download:
post:
summary: Download SARS-CoV-2 protein and CDS datasets by protein name by POST request
description: 'Download SARS-CoV-2 protein datasets POST request'
tags:
- Virus
operationId: sars2_protein_download_post
responses:
default:
description: An unexpected error response.
content:
text/plain:
schema:
$ref: '#/components/schemas/rpcStatus'
'200':
description: A successful response
content:
application/zip:
schema:
format: binary
type: string
description: Zip compressed stream
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/v2Sars2ProteinDatasetRequest'
examples:
SARS-CoV-2 virus RefSeq protein example:
description: SARS-CoV-2 virus protein (RefSeq)
value:
proteins:
- spike
refseq_only: true
parameters:
- name: filename
description: Output file name.
in: query
required: false
schema:
type: string
default: ncbi_dataset.zip
components:
securitySchemes:
ApiKeyAuth:
type: apiKey
in: query
name: api_key
ApiKeyAuthHeader:
type: apiKey
in: header
name: api-key
schemas:
v2AssemblyAccessions:
type: object
properties:
accessions:
type: array
items:
type: string
v2AssemblyCheckMHistogramReply:
type: object
properties:
species_taxid:
type: integer
histogram_intervals:
type: array
items:
$ref: '#/components/schemas/v2AssemblyCheckMHistogramReplyHistogramInterval'
v2AssemblyCheckMHistogramReplyHistogramInterval:
type: object
properties:
start_pos:
type: number
format: float
title: 'Starting position for this interval'
stop_pos:
type: number
format: float
title: 'ending position for this interval'
count:
type: number
format: float
title: 'number of elements in this interval'
v2AssemblyCheckMHistogramRequest:
type: object
properties:
species_taxon:
type: string
v2AssemblyDatasetAvailability:
type: object
properties:
valid_assemblies:
type: array
items:
type: string
invalid_assemblies:
type: array
items:
type: string
reason:
type: string
v2AssemblyDatasetDescriptorsFilter:
type: object
properties:
reference_only:
type: boolean
title: 'If true, only return reference genome assemblies'
assembly_source:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterAssemblySource'
title: 'Return only RefSeq (GCF_) or GenBank (GCA_) genome assemblies'
has_annotation:
type: boolean
title: 'Return only annotated genome assemblies'
exclude_paired_reports:
type: boolean
title: 'For paired (GCA/GCF) records, only return the primary record'
exclude_atypical:
type: boolean
title: 'If true, exclude atypical genomes, i.e. genomes that have assembly issues or are otherwise atypical'
assembly_version:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterAssemblyVersion'
title: 'Return all assemblies, including replaced and suppressed, or only current assemblies'
assembly_level:
type: array
items:
$ref: '#/components/schemas/v2reportsAssemblyLevel'
first_release_date:
type: string
format: date-time
title: 'Only return genome assemblies that were released on or after the specified date By default, do not filter.'
last_release_date:
type: string
format: date-time
title: 'Only return genome assemblies that were released on or before to the specified date By default, do not filter.'
search_text:
type: array
items:
type: string
is_metagenome_derived:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterMetagenomeDerivedFilter'
is_type_material:
type: boolean
title: 'If true, include only type materials'
is_ictv_exemplar:
type: boolean
title: 'If true, include only ICTV Exemplars'
exclude_multi_isolate:
type: boolean
title: 'If true, exclude large multi-isolate projects'
type_material_category:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilterTypeMaterialCategory'
v2AssemblyDatasetReportsRequest:
type: object
properties:
taxons:
type: array
items:
type: string
bioprojects:
type: array
items:
type: string
biosample_ids:
type: array
items:
type: string
assembly_names:
type: array
items:
type: string
wgs_accessions:
type: array
items:
type: string
accessions:
type: array
items:
type: string
filters:
$ref: '#/components/schemas/v2AssemblyDatasetDescriptorsFilter'
tax_exact_match:
type: boolean
title: 'If true, only return assemblies with the given NCBI Taxonomy ID, or name. Otherwise, assemblies from taxonomy subtree are included, too.'
chromosomes:
type: array
items:
type: string
table_fields:
type: array
items:
type: string
returned_content:
$ref: '#/components/schemas/v2AssemblyDatasetReportsRequestContentType'
title: 'Return either assembly accessions, or complete assembly reports'
page_size:
type: integer
title: 'The maximum number of genome assembly reports 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.'
page_token:
type: string
title: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
sort:
type: array
items:
$ref: '#/components/schemas/v2SortField'
include_tabular_header:
$ref: '#/components/schemas/v2IncludeTabularHeader'
title: 'Whether this request for tabular data should include the header row'
table_format:
type: string
title: 'Optional pre-defined template for processing a tabular data request'
v2AssemblyDatasetRequest:
type: object
properties:
accessions:
type: array
items:
type: string
chromosomes:
type: array
items:
type: string
include_annotation_type:
type: array
items:
$ref: '#/components/schemas/v2AnnotationForAssemblyType'
hydrated:
$ref: '#/components/schemas/v2AssemblyDatasetRequestResolution'
title: 'Set to DATA_REPORT_ONLY, to only retrieve data-reports.'
include_tsv:
type: boolean
title: 'Set to true to include a TSV representation of the data-report.'
v2AssemblyLinksReply:
type: object
properties:
assembly_links:
type: array
items:
$ref: '#/components/schemas/v2AssemblyLinksReplyAssemblyLink'
v2AssemblyLinksReplyAssemblyLink:
type: object
properties:
accession:
type: string
title: 'The matching assembly accession'
assembly_link_type:
$ref: '#/components/schemas/v2AssemblyLinksReplyAssemblyLinkType'
title: 'The type of link'
resource_link:
type: string
title: 'A link to the resource'
linked_identifiers:
type: array
items:
type: string
v2AssemblyLinksRequest:
type: object
properties:
accessions:
type: array
items:
type: string
v2AssemblyRevisionHistory:
type: object
properties:
assembly_revisions:
type: array
items:
$ref: '#/components/schemas/v2reportsAssemblyRevision'
total_count:
type: integer
v2AssemblyRevisionHistoryRequest:
type: object
properties:
accession:
type: string
v2AssemblySequenceReportsRequest:
type: object
properties:
accession:
type: string
chromosomes:
type: array
items:
type: string
role_filters:
type: array
items:
type: string
table_fields:
type: array
items:
type: string
count_assembly_unplaced:
type: boolean
page_size:
type: integer
title: '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.'
page_token:
type: string
title: 'A page token is returned from an `GetSequenceReports` 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.'
include_tabular_header:
$ref: '#/components/schemas/v2IncludeTabularHeader'
table_format:
type: string
title: 'Optional pre-defined template for processing a tabular data request'
v2DatasetRequest:
type: object
properties:
genome_v2:
$ref: '#/components/schemas/v2AssemblyDatasetRequest'
gene_v2:
$ref: '#/components/schemas/v2GeneDatasetRequest'
virus_v2:
$ref: '#/components/schemas/v2VirusDatasetRequest'
v2DownloadSummary:
type: object
properties:
record_count:
type: integer
title: 'The number of records for the requested filter.'
assembly_count:
type: integer
title: 'For backwards compatability with old VirusDatasetSummary'
resource_updated_on:
type: string
format: date-time
title: 'The latest date on which the resource was updated.'
hydrated:
$ref: '#/components/schemas/v2DownloadSummaryHydrated'
dehydrated:
$ref: '#/components/schemas/v2DownloadSummaryDehydrated'
errors:
type: array
items:
$ref: '#/components/schemas/v2reportsError'
messages:
type: array
items:
$ref: '#/components/schemas/v2reportsMessage'
available_files:
$ref: '#/components/schemas/v2DownloadSummaryAvailableFiles'
v2DownloadSummaryAvailableFiles:
type: object
properties:
all_genomic_fasta:
$ref: '#/components/schemas/v2DownloadSummaryFileSummary'
genome_gff:
$ref: '#/components/schemas/v2DownloadSummaryFileSummary'
genome_gbff:
$ref: '#/components/schemas/v2DownloadSummaryFileSummary'
rna_fasta:
$ref: '#/components/schemas/v2DownloadSummaryFileSummary'
prot_fasta:
$ref: '#/components/schemas/v2DownloadSummaryFileSummary'
genome_gtf:
$ref: '#/components/schemas/v2DownloadSummaryFileSummary'
cds_fasta:
$ref: '#/components/schemas/v2DownloadSummaryFileSummary'
sequence_report:
$ref: '#/components/schemas/v2DownloadSummaryFileSummary'
annotation_report:
$ref: '#/components/schemas/v2DownloadSummaryFileSummary'
v2DownloadSummaryDehydrated:
type: object
properties:
estimated_file_size_mb:
type: integer
url:
type: string
cli_download_command_line:
type: string
cli_rehydrate_command_line:
type: string
v2DownloadSummaryFileSummary:
type: object
properties:
file_count:
type: integer
size_mb:
type: number
format: float
v2DownloadSummaryHydrated:
type: object
properties:
estimated_file_size_mb:
type: integer
url:
type: string
cli_download_command_line:
type: string
v2GeneChromosomeSummaryReply:
type: object
properties:
gene_chromosome_summaries:
type: array
items:
$ref: '#/components/schemas/v2GeneChromosomeSummaryReplyGeneChromosomeSummary'
v2GeneChromosomeSummaryReplyGeneChromosomeSummary:
type: object
properties:
name:
type: string
count:
type: integer
accession:
type: string
v2GeneCountsByTaxonReply:
type: object
properties:
report:
type: array
items:
$ref: '#/components/schemas/v2GeneCountsByTaxonReplyGeneTypeAndCount'
v2GeneCountsByTaxonReplyGeneTypeAndCount:
type: object
properties:
gene_type:
type: string
count:
type: integer
v2GeneCountsByTaxonRequest:
type: object
properties:
taxon:
type: string
title: 'Taxon for provided gene symbol'
v2GeneDatasetReportsRequest:
type: object
properties:
returned_content:
$ref: '#/components/schemas/v2GeneDatasetReportsRequestContentType'
title: 'Return either gene-ids, or entire gene metadata'
gene_ids:
type: array
items:
type: integer
accessions:
type: array
items:
type: string
symbols_for_taxon:
$ref: '#/components/schemas/v2GeneDatasetReportsRequestSymbolsForTaxon'
taxon:
type: string
title: 'NCBI Taxonomy ID or name (common or scientific) that the genes are annotated at'
locus_tags:
type: array
items:
type: string
table_fields:
type: array
items:
type: string
table_format:
type: string
title: 'Optional pre-defined template for processing a tabular data request'
include_tabular_header:
$ref: '#/components/schemas/v2IncludeTabularHeader'
title: 'Whether this request for tabular data should include the header row'
page_size:
type: integer
title: 'The maximum number of gene reports 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.'
page_token:
type: string
title: 'A page token is returned from an `AssemblyDatasetReportsRequest` call with more than `page_size` results. Use this token, along with the previous `AssemblyDatasetReportsRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
query:
type: string
title: 'text search within gene symbol, aliases, name, locus-tag and protein name'
types:
type: array
items:
$ref: '#/components/schemas/v2GeneType'
accession_filter:
type: array
items:
type: string
v2GeneDatasetReportsRequestSymbolsForTaxon:
type: object
properties:
symbols:
type: array
items:
type: string
taxon:
type: string
title: 'Taxon for provided gene symbol'
v2GeneDatasetRequest:
type: object
properties:
gene_ids:
type: array
items:
type: integer
include_annotation_type:
type: array
items:
$ref: '#/components/schemas/v2Fasta'
returned_content:
$ref: '#/components/schemas/v2GeneDatasetRequestContentType'
title: 'Return either gene-ids, or entire gene metadata'
fasta_filter:
type: array
items:
type: string
accession_filter:
type: array
items:
type: string
aux_report:
type: array
items:
$ref: '#/components/schemas/v2GeneDatasetRequestGeneDatasetReportType'
tabular_reports:
type: array
items:
$ref: '#/components/schemas/v2GeneDatasetRequestGeneDatasetReportType'
table_fields:
type: array
items:
type: string
table_report_type:
$ref: '#/components/schemas/v2GeneDatasetRequestGeneDatasetReportType'
title: 'Specify the report from which the table fields will be taken. This is currently deprecated - use tabular_reports instead.'
v2GeneLinksReply:
type: object
properties:
gene_links:
type: array
items:
$ref: '#/components/schemas/v2GeneLinksReplyGeneLink'
v2GeneLinksReplyGeneLink:
type: object
properties:
gene_id:
type: integer
title: 'The matching gene id'
gene_link_type:
$ref: '#/components/schemas/v2GeneLinksReplyGeneLinkType'
title: 'The type of link, e.g. gdv link or ortholog set'
resource_link:
type: string
title: 'A link to a gene resource'
resource_id:
type: string
title: 'A resource ID, provided if gene-id is not used for the link, e.g. the ortholog id.'
v2GeneLinksRequest:
type: object
properties:
gene_ids:
type: array
items:
type: integer
v2GenomeAnnotationRequest:
type: object
properties:
accession:
type: string
annotation_ids:
type: array
items:
type: string
symbols:
type: array
items:
type: string
locations:
type: array
items:
type: string
gene_types:
type: array
items:
type: string
search_text:
type: array
items:
type: string
sort:
type: array
items:
$ref: '#/components/schemas/v2SortField'
include_annotation_type:
type: array
items:
$ref: '#/components/schemas/v2GenomeAnnotationRequestAnnotationType'
page_size:
type: integer
title: 'The maximum number of features 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.'
table_fields:
type: array
items:
type: string
table_format:
$ref: '#/components/schemas/v2GenomeAnnotationRequestGenomeAnnotationTableFormat'
title: 'Optional pre-defined template for processing a tabular data request'
include_tabular_header:
$ref: '#/components/schemas/v2IncludeTabularHeader'
title: 'Whether this request for tabular data should include the header row'
page_token:
type: string
title: 'A page token is returned from a `GetFeatures` call with more than `page_size` results. Use this token, along with the previous `FeatureRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
v2GenomeAnnotationTableSummaryReply:
type: object
properties:
accession:
type: string
title: 'Assembly from which available values are taken'
chromosomes:
type: array
items:
type: string
gene_types:
type: array
items:
type: string
empty_columns:
type: array
items:
type: string
v2HttpBody:
type: object
properties:
content_type:
type: string
title: 'The HTTP Content-Type header value specifying the content type of the body.'
data:
type: string
format: byte
title: 'The HTTP request/response body as raw binary.'
v2OrganelleDownloadRequest:
type: object
properties:
accessions:
type: array
items:
type: string
exclude_sequence:
type: boolean
title: 'Set to true to omit the genomic sequence.'
include_annotation_type:
type: array
items:
$ref: '#/components/schemas/v2AnnotationForOrganelleType'
v2OrganelleMetadataRequest:
type: object
properties:
taxons:
type: array
items:
type: string
accessions:
type: array
items:
type: string
organelle_types:
type: array
items:
$ref: '#/components/schemas/v2reportsOrganelleType'
first_release_date:
type: string
format: date-time
title: 'Only return organelle assemblies that were released on or after the specified date By default, do not filter.'
last_release_date:
type: string
format: date-time
title: 'Only return organelle assemblies that were released on or before to the specified date By default, do not filter.'
tax_exact_match:
type: boolean
title: 'If true, only return assemblies with the given NCBI Taxonomy ID, or name. Otherwise, assemblies from taxonomy subtree are included, too.'
sort:
type: array
items:
$ref: '#/components/schemas/v2OrganelleSort'
returned_content:
$ref: '#/components/schemas/v2OrganelleMetadataRequestContentType'
title: 'Return either assembly accessions, or entire assembly-metadata records'
page_size:
type: integer
title: 'The maximum number of organelle 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.'
page_token:
type: string
title: 'A page token is returned from an `OrganelleMetadata` call with more than `page_size` results. Use this token, along with the previous `OrganelleMetadata` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
table_format:
$ref: '#/components/schemas/v2OrganelleMetadataRequestOrganelleTableFormat'
title: 'Optional pre-defined template for processing a tabular data request'
include_tabular_header:
$ref: '#/components/schemas/v2IncludeTabularHeader'
title: 'Whether this request for tabular data should include the header row'
v2OrganelleSort:
type: object
properties:
field:
type: string
direction:
$ref: '#/components/schemas/v2SortDirection'
v2OrganismQueryRequest:
type: object
properties:
organism_query:
type: string
taxon_query:
type: string
title: 'NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank'
tax_rank_filter:
$ref: '#/components/schemas/v2OrganismQueryRequestTaxRankFilter'
title: 'Set the scope of searched tax ranks when filtering by gene or genome. Not used for ''all'''
taxon_resource_filter:
$ref: '#/components/schemas/v2OrganismQueryRequestTaxonResourceFilter'
title: 'Limit results to those with gene or genome counts (no filter by default)'
exact_match:
type: boolean
title: 'If true, only return results that exactly match the provided name or tax-id'
v2OrthologRequest:
type: object
properties:
gene_id:
type: integer
returned_content:
$ref: '#/components/schemas/v2OrthologRequestContentType'
title: 'Return either gene-ids, or entire gene metadata'
taxon_filter:
type: array
items:
type: string
page_size:
type: integer
title: 'The maximum number of gene reports 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.'
page_token:
type: string
title: 'A page token is returned from an `OrthologRequest` call with more than `page_size` results. Use this token, along with the previous `OrthologRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
v2ProkaryoteGeneRequest:
type: object
properties:
accessions:
type: array
items:
type: string
include_annotation_type:
type: array
items:
$ref: '#/components/schemas/v2Fasta'
gene_flank_config:
$ref: '#/components/schemas/v2ProkaryoteGeneRequestGeneFlankConfig'
taxon:
type: string
title: 'NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank When specified, return data from this taxon and its subtree'
v2ProkaryoteGeneRequestGeneFlankConfig:
type: object
properties:
length:
type: integer
v2Sars2ProteinDatasetRequest:
type: object
properties:
proteins:
type: array
items:
type: string
refseq_only:
type: boolean
title: 'If true, limit results to RefSeq genomes.'
annotated_only:
type: boolean
title: 'If true, limit results to annotated genomes.'
released_since:
type: string
format: date-time
title: '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 ''2020-04-01T00:00:00.000Z'''
updated_since:
type: string
format: date-time
host:
type: string
title: 'If set, limit results to genomes extracted from this host (Taxonomy ID or name) All hosts by default'
pangolin_classification:
type: string
title: 'If set, limit results to genomes classified to this lineage by the PangoLearn tool.'
geo_location:
type: string
title: 'Assemblies from this location (country or continent)'
usa_state:
type: string
title: 'Assemblies from this state (official two letter code only)'
complete_only:
type: boolean
title: 'only include complete genomes.'
table_fields:
type: array
items:
$ref: '#/components/schemas/v2VirusTableField'
include_sequence:
type: array
items:
$ref: '#/components/schemas/v2ViralSequenceType'
aux_report:
type: array
items:
$ref: '#/components/schemas/v2VirusDatasetReportType'
format:
$ref: '#/components/schemas/v2TableFormat'
title: 'Choose download format (tsv, csv or jsonl)'
v2SciNameAndIds:
type: object
properties:
sci_name_and_ids:
type: array
items:
$ref: '#/components/schemas/v2SciNameAndIdsSciNameAndId'
v2SciNameAndIdsSciNameAndId:
type: object
properties:
sci_name:
type: string
title: 'Scientific name'
tax_id:
type: string
format: uint64
title: 'NCBI Taxonomy ID'
common_name:
type: string
title: 'Common name'
matched_term:
type: string
title: 'Matched term'
rank:
$ref: '#/components/schemas/v2reportsRankType'
title: 'Rank'
group_name:
type: string
title: 'Group name (blast group)'
v2SequenceAccessionRequest:
type: object
properties:
accession:
type: string
v2SequenceReportPage:
type: object
properties:
reports:
type: array
items:
$ref: '#/components/schemas/v2reportsSequenceInfo'
total_count:
type: integer
title: '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).'
next_page_token:
type: string
title: 'A token that can be sent as `page_token` to retrieve the next page. If this field is omitted, there are no subsequent pages.'
v2SortField:
type: object
properties:
field:
type: string
direction:
$ref: '#/components/schemas/v2SortDirection'
v2TabularOutput:
type: object
properties:
data:
type: string
v2TaxonomyDatasetRequest:
type: object
properties:
tax_ids:
type: array
items:
type: integer
aux_reports:
type: array
items:
$ref: '#/components/schemas/v2TaxonomyDatasetRequestTaxonomyReportType'
v2TaxonomyFilteredSubtreeRequest:
type: object
properties:
taxons:
type: array
items:
type: string
specified_limit:
type: boolean
title: 'Limit to specified species'
rank_limits:
type: array
items:
$ref: '#/components/schemas/v2reportsRankType'
v2TaxonomyFilteredSubtreeResponse:
type: object
properties:
root_nodes:
type: array
items:
type: integer
edges:
$ref: '#/components/schemas/v2TaxonomyFilteredSubtreeResponseEdgesEntry'
warnings:
type: array
items:
$ref: '#/components/schemas/v2reportsWarning'
errors:
type: array
items:
$ref: '#/components/schemas/v2reportsError'
v2TaxonomyFilteredSubtreeResponseEdge:
type: object
properties:
visible_children:
type: array
items:
type: integer
children_status:
$ref: '#/components/schemas/v2TaxonomyFilteredSubtreeResponseEdgeChildStatus'
v2TaxonomyFilteredSubtreeResponseEdgesEntry:
description: A map.
properties:
default:
$ref: '#/components/schemas/v2TaxonomyFilteredSubtreeResponseEdge'
additionalProperties:
$ref: '#/components/schemas/v2TaxonomyFilteredSubtreeResponseEdge'
v2TaxonomyImageMetadataRequest:
type: object
properties:
taxon:
type: string
v2TaxonomyImageMetadataResponse:
type: object
properties:
tax_id:
type: string
src:
type: string
license:
type: string
attribution:
type: string
source:
type: string
image_sizes:
type: array
items:
$ref: '#/components/schemas/v2ImageSize'
format:
type: string
v2TaxonomyImageRequest:
type: object
properties:
taxon:
type: string
image_size:
$ref: '#/components/schemas/v2ImageSize'
v2TaxonomyLinksRequest:
type: object
properties:
taxon:
type: string
v2TaxonomyLinksResponse:
type: object
properties:
tax_id:
type: string
encyclopedia_of_life:
type: string
global_biodiversity_information_facility:
type: string
inaturalist:
type: string
viralzone:
type: string
wikipedia:
type: string
generic_links:
type: array
items:
$ref: '#/components/schemas/v2TaxonomyLinksResponseGenericLink'
v2TaxonomyLinksResponseGenericLink:
type: object
properties:
link_name:
type: string
link_url:
type: string
v2TaxonomyMatch:
type: object
properties:
warnings:
type: array
items:
$ref: '#/components/schemas/v2reportsWarning'
errors:
type: array
items:
$ref: '#/components/schemas/v2reportsError'
query:
type: array
items:
type: string
taxonomy:
$ref: '#/components/schemas/v2TaxonomyNode'
v2TaxonomyMetadataRequest:
type: object
properties:
taxons:
type: array
items:
type: string
returned_content:
$ref: '#/components/schemas/v2TaxonomyMetadataRequestContentType'
title: 'Return either tax-ids alone, or entire taxononmy-metadata records'
page_size:
type: integer
title: 'The maximum number of taxons 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.'
include_tabular_header:
$ref: '#/components/schemas/v2IncludeTabularHeader'
title: 'Whether this request for tabular data should include the header row'
page_token:
type: string
title: 'A page token is returned from `GetTaxonomyDataReportFor` and `GetTaxonomyNamesDataReportFor` calls with more than `page_size` results. When `page_token` is empty, all results have been retrieved.'
table_format:
$ref: '#/components/schemas/v2TaxonomyMetadataRequestTableFormat'
children:
type: boolean
title: 'Flag for tax explosion.'
ranks:
type: array
items:
$ref: '#/components/schemas/v2reportsRankType'
v2TaxonomyMetadataResponse:
type: object
properties:
messages:
type: array
items:
$ref: '#/components/schemas/v2reportsMessage'
taxonomy_nodes:
type: array
items:
$ref: '#/components/schemas/v2TaxonomyMatch'
v2TaxonomyNode:
type: object
properties:
tax_id:
type: integer
title: 'NCBI Taxonomy identifier'
organism_name:
type: string
title: 'Scientific name'
common_name:
type: string
title: 'Common name'
genbank_common_name:
type: string
title: 'GenBank common name'
acronyms:
type: array
items:
type: string
genbank_acronym:
type: string
title: 'GenBank acronym'
blast_name:
type: string
title: 'blast name for organism'
lineage:
type: array
items:
type: integer
children:
type: array
items:
type: integer
descendent_with_described_species_names_count:
type: integer
title: 'The number of descendants (grand total) that are specified.'
rank:
$ref: '#/components/schemas/v2reportsRankType'
title: 'The rank of the organism. An enumerated set of values.'
has_described_species_name:
type: boolean
title: 'If the taxonomy node has a proper species name'
counts:
type: array
items:
$ref: '#/components/schemas/v2TaxonomyNodeCountByType'
min_ord:
type: integer
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'
max_ord:
type: integer
extinct:
type: boolean
title: 'True if organism is extinct'
genomic_moltype:
type: string
title: 'genomic molecule type (dsDNA, ssDNA, ssDNA(-), ssRNA)'
v2TaxonomyNodeCountByType:
type: object
properties:
type:
$ref: '#/components/schemas/v2reportsCountType'
count:
type: integer
v2TaxonomyRelatedIdRequest:
type: object
properties:
tax_id:
type: integer
include_lineage:
type: boolean
title: 'If true, return reports for all taxonomy nodes in the lineages of the requested tax_id'
include_subtree:
type: boolean
title: 'This field is deprecated because all requests include the subtree, so it has no effect'
ranks:
type: array
items:
$ref: '#/components/schemas/v2reportsRankType'
page_size:
type: integer
title: 'The maximum number of taxids 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.'
page_token:
type: string
title: 'A page token is returned from a `GetRelatedTaxids` call with more than `page_size` results. Use this token, along with the previous `TaxonomyRelatedIdRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
v2TaxonomyTaxIdsPage:
type: object
properties:
tax_ids:
type: array
items:
type: integer
next_page_token:
type: string
title: 'A token that can be sent as `page_token` to retrieve the next page. If this field is omitted, there are no subsequent pages.'
v2VersionReply:
type: object
properties:
version:
type: string
major_ver:
type: integer
minor_ver:
type: integer
patch_ver:
type: integer
v2VirusAnnotationFilter:
type: object
properties:
accessions:
type: array
items:
type: string
taxon:
type: string
title: 'NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank'
taxons:
type: array
items:
type: string
refseq_only:
type: boolean
title: 'If true, limit results to RefSeq genomes.'
annotated_only:
type: boolean
title: 'If true, limit results to annotated genomes.'
released_since:
type: string
format: date-time
title: '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 ''2020-04-01T00:00:00.000Z'''
updated_since:
type: string
format: date-time
host:
type: string
title: 'If set, limit results to genomes extracted from this host (Taxonomy ID or name) All hosts by default'
pangolin_classification:
type: string
title: 'If set, limit results to genomes classified to this lineage by the PangoLearn tool.'
geo_location:
type: string
title: 'Assemblies from this location (country or continent)'
usa_state:
type: string
title: 'Assemblies from this state (official two letter code only)'
complete_only:
type: boolean
title: 'only include complete genomes.'
v2VirusAnnotationReportRequest:
type: object
properties:
filter:
$ref: '#/components/schemas/v2VirusAnnotationFilter'
table_fields:
type: array
items:
type: string
table_format:
type: string
title: 'Optional pre-defined template for processing a tabular data request'
page_size:
type: integer
title: 'The maximum number of virus data reports 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.'
page_token:
type: string
title: 'A page token is returned from a `GetVirusDataReports` call with more than `page_size` results. Use this token, along with the previous `VirusDataReportRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
v2VirusAvailability:
type: object
properties:
valid_accessions:
type: array
items:
type: string
invalid_accessions:
type: array
items:
type: string
message:
type: string
v2VirusAvailabilityRequest:
type: object
properties:
accessions:
type: array
items:
type: string
v2VirusDataReportRequest:
type: object
properties:
filter:
$ref: '#/components/schemas/v2VirusDatasetFilter'
title: 'All the supported filters for virus requests'
returned_content:
$ref: '#/components/schemas/v2VirusDataReportRequestContentType'
title: 'Return either virus genome accessions, or complete virus metadata'
table_fields:
type: array
items:
type: string
table_format:
type: string
title: 'Optional pre-defined template for processing a tabular data request'
page_size:
type: integer
title: 'The maximum number of virus data reports 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.'
page_token:
type: string
title: 'A page token is returned from a `GetVirusDataReports` call with more than `page_size` results. Use this token, along with the previous `VirusDataReportRequest` parameters, to retrieve the next page of results. When `page_token` is empty, all results have been retrieved.'
v2VirusDatasetFilter:
type: object
properties:
accessions:
type: array
items:
type: string
taxon:
type: string
title: 'NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank'
taxons:
type: array
items:
type: string
refseq_only:
type: boolean
title: 'If true, limit results to RefSeq genomes.'
annotated_only:
type: boolean
title: 'If true, limit results to annotated genomes.'
released_since:
type: string
format: date-time
title: '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 ''2020-04-01T00:00:00.000Z'''
updated_since:
type: string
format: date-time
host:
type: string
title: 'If set, limit results to genomes extracted from this host (Taxonomy ID or name) All hosts by default'
pangolin_classification:
type: string
title: 'If set, limit results to genomes classified to this lineage by the PangoLearn tool.'
geo_location:
type: string
title: 'Assemblies from this location (country or continent)'
usa_state:
type: string
title: 'Assemblies from this state (official two letter code only)'
complete_only:
type: boolean
title: 'only include complete genomes.'
v2VirusDatasetRequest:
type: object
properties:
accessions:
type: array
items:
type: string
taxon:
type: string
title: 'NCBI Taxonomy ID or name (common or scientific) at any taxonomic rank'
taxons:
type: array
items:
type: string
refseq_only:
type: boolean
title: 'If true, limit results to RefSeq genomes.'
annotated_only:
type: boolean
title: 'If true, limit results to annotated genomes.'
released_since:
type: string
format: date-time
title: '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 ''2020-04-01T00:00:00.000Z'''
updated_since:
type: string
format: date-time
host:
type: string
title: 'If set, limit results to genomes extracted from this host (Taxonomy ID or name) All hosts by default'
pangolin_classification:
type: string
title: 'If set, limit results to genomes classified to this lineage by the PangoLearn tool.'
geo_location:
type: string
title: 'Assemblies from this location (country or continent)'
usa_state:
type: string
title: 'Assemblies from this state (official two letter code only)'
complete_only:
type: boolean
title: 'only include complete genomes.'
table_fields:
type: array
items:
$ref: '#/components/schemas/v2VirusTableField'
include_sequence:
type: array
items:
$ref: '#/components/schemas/v2ViralSequenceType'
aux_report:
type: array
items:
$ref: '#/components/schemas/v2VirusDatasetReportType'
format:
$ref: '#/components/schemas/v2TableFormat'
title: 'Choose download format (tsv, csv or jsonl)'
use_psg:
type: boolean
title: 'Experimental approach to retrieving sequence data.'
v2reportsANIMatch:
type: object
properties:
assembly:
type: string
title: 'Accession of the submitted organism best match type-strain assembly or best match type-strain assembly'
organism_name:
type: string
title: 'Taxonomic name of the submitted organism or best match type-strain organism'
category:
$ref: '#/components/schemas/v2reportsANITypeCategory'
title: 'Type category'
ani:
type: number
format: float
title: 'Percent average nucleotide identity'
assembly_coverage:
type: number
format: float
title: 'Percent coverage of the query assembly by the submitted organism or best match type assembly'
type_assembly_coverage:
type: number
format: float
title: 'Percent coverage of the submitted organism or best match type assembly by the query assembly'
v2reportsAdditionalSubmitter:
type: object
properties:
genbank_accession:
type: string
title: 'genbank accession of extra sequence'
refseq_accession:
type: string
title: 'genbank accession of extra sequence'
chr_name:
type: string
title: 'chromosome name'
molecule_type:
type: string
title: 'molecule type'
submitter:
type: string
title: 'Name of submitter'
bioproject_accession:
type: string
title: 'Bioproject accession'
v2reportsAnnotation:
type: object
properties:
assembly_accession:
type: string
title: 'Genome assembly accession'
assembly_name:
type: string
title: 'Genome assembly name'
annotation_name:
type: string
title: 'Genome annotation name'
annotation_release_date:
type: string
title: 'Genome annotation release date'
genomic_locations:
type: array
items:
$ref: '#/components/schemas/v2reportsGenomicLocation'
v2reportsAnnotationInfo:
type: object
properties:
name:
type: string
title: 'Annotation name'
provider:
type: string
title: 'Source of the annotation'
release_date:
type: string
title: 'Annotation release date'
report_url:
type: string
title: 'Annotation report web address'
stats:
$ref: '#/components/schemas/v2reportsFeatureCounts'
busco:
$ref: '#/components/schemas/v2reportsBuscoStat'
method:
type: string
title: 'Software tools used to calculate annotation'
pipeline:
type: string
title: 'NCBI annotation pipeline used to calculate annotation'
software_version:
type: string
title: 'NCBI annotation pipeline software version'
status:
type: string
title: 'Type of annotation'
release_version:
type: string
v2reportsAssemblyDataReport:
type: object
properties:
accession:
type: string
title: 'The GenColl assembly accession'
current_accession:
type: string
title: 'The latest GenColl assembly accession for this revision chain'
paired_accession:
type: string
title: 'The GenBank or RefSeq assembly accession paired with this assembly'
source_database:
$ref: '#/components/schemas/v2reportsSourceDatabase'
title: 'Source of the accession. The paired accession, if it exists, is from the other database.'
organism:
$ref: '#/components/schemas/v2reportsOrganism'
assembly_info:
$ref: '#/components/schemas/v2reportsAssemblyInfo'
title: 'Metadata for the genome assembly submission'
assembly_stats:
$ref: '#/components/schemas/v2reportsAssemblyStats'
title: 'Global statistics for the genome assembly'
organelle_info:
type: array
items:
$ref: '#/components/schemas/v2reportsOrganelleInfo'
additional_submitters:
type: array
items:
$ref: '#/components/schemas/v2reportsAdditionalSubmitter'
annotation_info:
$ref: '#/components/schemas/v2reportsAnnotationInfo'
title: 'Metadata and statistics for the genome assembly annotation, when available'
wgs_info:
$ref: '#/components/schemas/v2reportsWGSInfo'
title: 'Metadata pertaining to the Whole Genome Shotgun (WGS) record for the genome assemblies that are complete genomes. Those that are clone-based do not have WGS-master records.'
type_material:
$ref: '#/components/schemas/v2reportsTypeMaterial'
checkm_info:
$ref: '#/components/schemas/v2reportsCheckM'
title: 'Metadata on the completeness and contamination of this assembly'
average_nucleotide_identity:
$ref: '#/components/schemas/v2reportsAverageNucleotideIdentity'
v2reportsAssemblyDataReportPage:
type: object
properties:
reports:
type: array
items:
$ref: '#/components/schemas/v2reportsAssemblyDataReport'
content_type:
$ref: '#/components/schemas/v2reportsContentType'
total_count:
type: integer
title: 'The total count of available datasets (ignoring the page_size parameter).'
next_page_token:
type: string
title: 'A token that can be sent as `page_token` to retrieve the next page. If this field is omitted, there are no subsequent pages.'
messages:
type: array
items:
$ref: '#/components/schemas/v2reportsMessage'
v2reportsAssemblyInfo:
type: object
properties:
assembly_level:
type: string
title: 'The level at which a genome has been assembled'
assembly_status:
$ref: '#/components/schemas/v2reportsAssemblyStatus'
title: 'The GenColl assembly status'
paired_assembly:
$ref: '#/components/schemas/v2reportsPairedAssembly'
title: 'Metadata from the GenBank or RefSeq assembly paired with this one'
assembly_name:
type: string
title: 'The assembly submitter''s name for the genome assembly, when provided. Otherwise, a default name in the form ASM#####v# is assigned'
assembly_long_name:
type: string
assembly_type:
type: string
title: 'Chromosome content of the submitted genome assembly'
bioproject_lineage:
type: array
items:
$ref: '#/components/schemas/v2reportsBioProjectLineage'
bioproject_accession:
type: string
submission_date:
type: string
title: 'Date the assembly was submitted to NCBI (being replaced by release date - should maintain until most CLI users upgrade)'
release_date:
type: string
title: 'Date the assembly was made available by NCBI. This field is not returned by versions of the datasets Command Line Interface (CLI) program < 15.'
description:
type: string
title: 'Long description for this genome'
submitter:
type: string
title: 'The submitting consortium or organization. Full submitter information is available in the BioProject'
refseq_category:
type: string
title: 'The RefSeq Category, if present, indicates whether the assembly is a reference genome'
synonym:
type: string
title: 'Genome name ascribed to this assembly by the UC Santa Cruz genome browser'
linked_assembly:
type: string
title: 'The accession.version and designation (principal or alternate pseudohaplotype) of a paired genome assembly derived from the same diploid individual'
linked_assemblies:
type: array
items:
$ref: '#/components/schemas/v2reportsLinkedAssembly'
atypical:
$ref: '#/components/schemas/v2reportsAtypicalInfo'
title: 'Information on atypical genomes - genomes that have assembly issues or are otherwise atypical'
genome_notes:
type: array
items:
type: string
sequencing_tech:
type: string
title: 'Sequencing technology used to sequence this genome'
assembly_method:
type: string
title: 'Genome assembly method'
grouping_method:
type: string
biosample:
$ref: '#/components/schemas/v2reportsBioSampleDescriptor'
title: 'NCBI BioSample from which the sequences in the genome assembly were obtained.'
blast_url:
type: string
title: 'URL to blast page for this assembly'
comments:
type: string
title: 'Freeform comments'
suppression_reason:
type: string
title: 'The reason for the assembly is suppressed, for suppressed assemblies'
diploid_role:
$ref: '#/components/schemas/v2reportsLinkedAssemblyType'
v2reportsAssemblyRevision:
type: object
properties:
genbank_accession:
type: string
refseq_accession:
type: string
assembly_name:
type: string
assembly_level:
$ref: '#/components/schemas/v2reportsAssemblyLevel'
release_date:
type: string
submission_date:
type: string
sequencing_technology:
type: string
v2reportsAssemblyStats:
type: object
properties:
total_number_of_chromosomes:
type: integer
title: 'Count of nuclear chromosomes, organelles and plasmids in a submitted genome assembly'
total_sequence_length:
type: string
format: uint64
title: 'Total sequence length of the nuclear genome including unplaced and unlocalized sequences'
total_ungapped_length:
type: string
format: uint64
title: 'Total length of all top-level sequences ignoring gaps. Any stretch of 10 or more Ns in a sequence is treated like a gap'
number_of_contigs:
type: integer
title: 'Total number of sequence contigs in the assembly. Any stretch of 10 or more Ns in a sequence is treated as a gap between two contigs in a scaffold when counting contigs and calculating contig N50 & L50 values'
contig_n50:
type: integer
title: 'Length such that sequence contigs of this length or longer include half the bases of the assembly'
contig_l50:
type: integer
title: 'Number of sequence contigs that are longer than, or equal to, the N50 length and therefore include half the bases of the assembly'
number_of_scaffolds:
type: integer
title: 'Number of scaffolds including placed, unlocalized, unplaced, alternate loci and patch scaffolds'
scaffold_n50:
type: integer
title: 'Length such that scaffolds of this length or longer include half the bases of the assembly'
scaffold_l50:
type: integer
title: 'Number of scaffolds that are longer than, or equal to, the N50 length and therefore include half the bases of the assembly'
gaps_between_scaffolds_count:
type: integer
title: 'Number of unspanned gaps between scaffolds'
number_of_component_sequences:
type: integer
title: 'Total number of component WGS or clone sequences in the assembly'
gc_count:
type: string
format: uint64
title: 'The number of GC base-pairs in the assembly'
gc_percent:
type: number
format: float
title: 'The percentage of GC base-pairs in the assembly'
genome_coverage:
type: string
title: 'Genome assembly coverage'
number_of_organelles:
type: integer
title: 'number of organelles'
v2reportsAtypicalInfo:
type: object
properties:
is_atypical:
type: boolean
title: 'If true there are assembly issues or the assembly is in some way non-standard'
warnings:
type: array
items:
type: string
v2reportsAverageNucleotideIdentity:
type: object
properties:
taxonomy_check_status:
$ref: '#/components/schemas/v2reportsAverageNucleotideIdentityTaxonomyCheckStatus'
title: 'Indicates whether the ANI result is consistent with the submitted organism'
match_status:
$ref: '#/components/schemas/v2reportsAverageNucleotideIdentityMatchStatus'
title: 'Indicates the specific type of ANI result that supports the Taxonomy check status'
submitted_organism:
type: string
title: 'Taxonomic name of the query assembly'
submitted_species:
type: string
title: 'Species name of the query assembly'
category:
$ref: '#/components/schemas/v2reportsANITypeCategory'
title: 'Category of type or validated assembly'
submitted_ani_match:
$ref: '#/components/schemas/v2reportsANIMatch'
best_ani_match:
$ref: '#/components/schemas/v2reportsANIMatch'
comment:
type: string
title: 'Additional information about the ANI result'
v2reportsBioProject:
type: object
properties:
accession:
type: string
title: 'BioProject accession'
title:
type: string
title: 'Title of the BioProject provided by the submitter'
parent_accession:
type: string
parent_accessions:
type: array
items:
type: string
v2reportsBioProjectLineage:
type: object
properties:
bioprojects:
type: array
items:
$ref: '#/components/schemas/v2reportsBioProject'
v2reportsBioSampleAttribute:
type: object
properties:
name:
type: string
value:
type: string
v2reportsBioSampleContact:
type: object
properties:
lab:
type: string
title: 'Submitter lab name.'
v2reportsBioSampleDataReport:
type: object
properties:
accession:
type: string
title: 'BioSample Accession identifier'
last_updated:
type: string
title: 'When the biosample object was last updated.'
publication_date:
type: string
title: 'BioSample object publication date.'
submission_date:
type: string
title: 'BioSample object submission date.'
sample_ids:
type: array
items:
$ref: '#/components/schemas/v2reportsBioSampleId'
description:
$ref: '#/components/schemas/v2reportsBioSampleDescription'
title: 'BioSample description.'
owner:
$ref: '#/components/schemas/v2reportsBioSampleOwner'
title: 'BioSample owner.'
models:
type: array
items:
type: string
bioprojects:
type: array
items:
$ref: '#/components/schemas/v2reportsBioProject'
package:
type: string
title: 'Package identifier.'
attributes:
type: array
items:
$ref: '#/components/schemas/v2reportsBioSampleAttribute'
status:
$ref: '#/components/schemas/v2reportsBioSampleStatus'
title: 'Current status of the object.'
age:
type: string
title: 'Age at the time of sampling'
biomaterial_provider:
type: string
title: 'Name and address of the lab or PI'
breed:
type: string
title: 'Breed name'
collected_by:
type: string
title: 'Name of persons or institute who collected the sample'
collection_date:
type: string
title: 'Date on which the sample was collected'
cultivar:
type: string
title: 'Cultivated variety of plant'
dev_stage:
type: string
title: 'Developmental stage at the time of sampling'
ecotype:
type: string
title: 'Population within a given species adapted to a local habitat'
geo_loc_name:
type: string
title: 'Geographical origin of the sample'
host:
type: string
title: 'The natural host to the organism'
host_disease:
type: string
title: 'Name of relevant disease'
identified_by:
type: string
title: 'Name of the taxonomist who identified the specimen'
ifsac_category:
type: string
title: 'Interagency Food Safety Analytics Collaboration (IFSAC) category'
isolate:
type: string
title: 'Description of the specific individual from which the sample was derived'
isolate_name_alias:
type: string
title: 'Other IDs associated with this isolate'
isolation_source:
type: string
title: 'Source of the sample'
lat_lon:
type: string
title: 'Geogrpahic coordinates of the location where the sample was collected'
project_name:
type: string
title: 'Name of the project'
sample_name:
type: string
title: 'Sample name in source database'
serovar:
type: string
title: 'Taxonomic name below subspecies. Same as serotype.'
sex:
type: string
title: 'Physical sex of sampled organism'
source_type:
type: string
title: 'Controlled vocabulary describing the isolation source'
strain:
type: string
title: 'Strain name'
sub_species:
type: string
title: 'Sub-species taxonomic name'
tissue:
type: string
title: 'Type of tissue from which the sample was derived'
serotype:
type: string
title: 'Taxonomic name below subspecies. Same as serovar'
v2reportsBioSampleDataReportPage:
type: object
properties:
reports:
type: array
items:
$ref: '#/components/schemas/v2reportsBioSampleDataReport'
total_count:
type: integer
title: 'The total count of available datasets (ignoring the page_size parameter).'
next_page_token:
type: string
title: 'A token that can be sent as `page_token` to retrieve the next page. If this field is omitted, there are no subsequent pages.'
messages:
type: array
items:
$ref: '#/components/schemas/v2reportsMessage'
v2reportsBioSampleDescription:
type: object
properties:
title:
type: string
organism:
$ref: '#/components/schemas/v2reportsOrganism'
comment:
type: string
v2reportsBioSampleDescriptor:
type: object
properties:
accession:
type: string
last_updated:
type: string
publication_date:
type: string
submission_date:
type: string
sample_ids:
type: array
items:
$ref: '#/components/schemas/v2reportsBioSampleId'
description:
$ref: '#/components/schemas/v2reportsBioSampleDescription'
owner:
$ref: '#/components/schemas/v2reportsBioSampleOwner'
models:
type: array
items:
type: string
bioprojects:
type: array
items:
$ref: '#/components/schemas/v2reportsBioProject'
package:
type: string
attributes:
type: array
items:
$ref: '#/components/schemas/v2reportsBioSampleAttribute'
status:
$ref: '#/components/schemas/v2reportsBioSampleStatus'
age:
type: string
title: 'Age at the time of sampling'
biomaterial_provider:
type: string
title: 'Name and address of the lab or PI'
breed:
type: string
title: 'Breed name'
collected_by:
type: string
title: 'Name of persons or institute who collected the sample'
collection_date:
type: string
title: 'Date on which the sample was collected'
cultivar:
type: string
title: 'Cultivated variety of plant'
dev_stage:
type: string
title: 'Developmental stage at the time of sampling'
ecotype:
type: string
title: 'Population within a given species adapted to a local habitat'
geo_loc_name:
type: string
title: 'Geographical origin of the sample'
host:
type: string
title: 'The natural host to the organism'
host_disease:
type: string
title: 'Name of relevant disease'
identified_by:
type: string
title: 'Name of the taxonomist who identified the specimen'
ifsac_category:
type: string
title: 'Interagency Food Safety Analytics Collaboration (IFSAC) category'
isolate:
type: string
title: 'Description of the specific individual from which the sample was derived'
isolate_name_alias:
type: string
title: 'Other IDs associated with this isolate'
isolation_source:
type: string
title: 'Source of the sample'
lat_lon:
type: string
title: 'Geographic coordinates of the location where the sample was collected'
project_name:
type: string
title: 'Name of the project'
sample_name:
type: string
title: 'Sample name in source database'
serovar:
type: string
title: 'Taxonomic name below subspecies. Same as serotype.'
sex:
type: string
title: 'Physical sex of sampled organism'
source_type:
type: string
title: 'Controlled vocabulary describing the isolation source'
strain:
type: string
title: 'Strain name'
sub_species:
type: string
title: 'Sub-species taxonomic name'
tissue:
type: string
title: 'Type of tissue from which the sample was derived'
serotype:
type: string
title: 'Taxonomic name below subspecies. Same as serovar'
v2reportsBioSampleId:
type: object
properties:
db:
type: string
label:
type: string
value:
type: string
v2reportsBioSampleOwner:
type: object
properties:
name:
type: string
contacts:
type: array
items:
$ref: '#/components/schemas/v2reportsBioSampleContact'
v2reportsBioSampleStatus:
type: object
properties:
status:
type: string
when:
type: string
v2reportsBuscoStat:
type: object
properties:
busco_lineage:
type: string
title: 'BUSCO Lineage'
busco_ver:
type: string
title: 'BUSCO Version'
complete:
type: number
format: float
title: 'BUSCO score: Complete'
single_copy:
type: number
format: float
title: 'BUSCO score: Single Copy'
duplicated:
type: number
format: float
title: 'BUSCO score: Duplicated'
fragmented:
type: number
format: float
title: 'BUSCO score: Fragmented'
missing:
type: number
format: float
title: 'BUSCO score: Missing'
total_count:
type: string
format: uint64
title: 'BUSCO score: Total Count'
v2reportsCheckM:
type: object
properties:
checkm_marker_set:
type: string
title: 'What taxonomic group is used as the basis for comparison with this assembly with regards to checkM values'
checkm_species_tax_id:
type: integer
title: 'The species-level taxid for this assemblies checkM dataset'
checkm_marker_set_rank:
type: string
title: 'CheckM taxonomic rank of checkm_marker_set'
checkm_version:
type: string
title: 'CheckM software version'
completeness:
type: number
format: float
title: 'What percent complete is this assembly'
contamination:
type: number
format: float
title: 'What is the contamination percentage for this assembly'
completeness_percentile:
type: number
format: float
title: 'The percent of assemblies under the taxonomic grouping ''checkm_marker_set'' that this assembly is as-or-more complete than.'
v2reportsClassification:
type: object
properties:
superkingdom:
$ref: '#/components/schemas/v2reportsTaxData'
kingdom:
$ref: '#/components/schemas/v2reportsTaxData'
phylum:
$ref: '#/components/schemas/v2reportsTaxData'
class:
$ref: '#/components/schemas/v2reportsTaxData'
order:
$ref: '#/components/schemas/v2reportsTaxData'
family:
$ref: '#/components/schemas/v2reportsTaxData'
genus:
$ref: '#/components/schemas/v2reportsTaxData'
species:
$ref: '#/components/schemas/v2reportsTaxData'
domain:
$ref: '#/components/schemas/v2reportsTaxData'
title: 'NOTE: These are out of order'
realm:
$ref: '#/components/schemas/v2reportsTaxData'
v2reportsConservedDomain:
type: object
properties:
accession:
type: string
title: 'cdd accession'
name:
type: string
range:
$ref: '#/components/schemas/v2reportsRange'
title: 'range on the protein'
v2reportsError:
type: object
properties:
assembly_error_code:
$ref: '#/components/schemas/v2reportsErrorAssemblyErrorCode'
gene_error_code:
$ref: '#/components/schemas/v2reportsErrorGeneErrorCode'
organelle_error_code:
$ref: '#/components/schemas/v2reportsErrorOrganelleErrorCode'
virus_error_code:
$ref: '#/components/schemas/v2reportsErrorVirusErrorCode'
taxonomy_error_code:
$ref: '#/components/schemas/v2reportsErrorTaxonomyErrorCode'
reason:
type: string
message:
type: string
invalid_identifiers:
type: array
items:
type: string
v2reportsFeatureCounts:
type: object
properties:
gene_counts:
$ref: '#/components/schemas/v2reportsGeneCounts'
title: 'Counts of gene types'
v2reportsGeneCounts:
type: object
properties:
total:
type: integer
title: 'Total number of annotated genes'
protein_coding:
type: integer
title: 'Count of annotated genes that encode a protein'
non_coding:
type: integer
title: 'Count of transcribed non-coding genes (e.g. lncRNAs, miRNAs, rRNAs, etc...) excludes transcribed pseudogenes'
pseudogene:
type: integer
title: 'Count of transcribed and non-transcribed pseudogenes'
other:
type: integer
title: 'Count of genic region GeneIDs and non-genic regulatory GeneIDs'
v2reportsGeneDataReportPage:
type: object
properties:
reports:
type: array
items:
$ref: '#/components/schemas/v2reportsGeneReportMatch'
messages:
type: array
items:
$ref: '#/components/schemas/v2reportsMessage'
total_count:
type: integer
title: 'The total count of available genes (ignoring the page_size parameter).'
next_page_token:
type: string
title: 'A token that can be sent as `page_token` to retrieve the next page. If this field is omitted, there are no subsequent pages.'
v2reportsGeneDescriptor:
type: object
properties:
gene_id:
type: string
format: uint64
title: 'NCBI Gene ID'
symbol:
type: string
title: 'Gene symbol'
description:
type: string
title: 'Gene name'
tax_id:
type: string
format: uint64
title: 'NCBI Taxonomy ID for the organism'
taxname:
type: string
title: 'Taxonomic name of the organism'
common_name:
type: string
title: 'Common name of the organism'
type:
$ref: '#/components/schemas/v2reportsGeneType'
title: 'Type of gene'
rna_type:
$ref: '#/components/schemas/v2reportsRnaType'
orientation:
$ref: '#/components/schemas/v2reportsOrientation'
title: 'Direction of the gene relative to the genome coordinates'
reference_standards:
type: array
items:
$ref: '#/components/schemas/v2reportsGenomicRegion'
genomic_regions:
type: array
items:
$ref: '#/components/schemas/v2reportsGenomicRegion'
chromosomes:
type: array
items:
type: string
nomenclature_authority:
$ref: '#/components/schemas/v2reportsNomenclatureAuthority'
swiss_prot_accessions:
type: array
items:
type: string
ensembl_gene_ids:
type: array
items:
type: string
omim_ids:
type: array
items:
type: string
synonyms:
type: array
items:
type: string
replaced_gene_id:
type: string
format: uint64
title: 'The NCBI Gene ID for the gene that was merged into the current gene record'
annotations:
type: array
items:
$ref: '#/components/schemas/v2reportsAnnotation'
transcript_count:
type: integer
title: 'Number of transcripts encoded by the gene'
protein_count:
type: integer
title: 'Number of proteins encoded by the gene'
transcript_type_counts:
type: array
items:
$ref: '#/components/schemas/v2reportsTranscriptTypeCount'
gene_groups:
type: array
items:
$ref: '#/components/schemas/v2reportsGeneGroup'
summary:
type: array
items:
$ref: '#/components/schemas/v2reportsGeneSummary'
gene_ontology:
$ref: '#/components/schemas/v2reportsGeneOntology'
locus_tag:
type: string
v2reportsGeneGroup:
type: object
properties:
id:
type: string
title: 'Gene group identifier, currently these only include gene ortholog sets'
method:
type: string
title: 'Method used to calculate the gene group, currently this only includes "NCBI Ortholog"'
v2reportsGeneOntology:
type: object
properties:
assigned_by:
type: string
title: 'The database that made the annotation'
molecular_functions:
type: array
items:
$ref: '#/components/schemas/v2reportsProcessMetadata'
biological_processes:
type: array
items:
$ref: '#/components/schemas/v2reportsProcessMetadata'
cellular_components:
type: array
items:
$ref: '#/components/schemas/v2reportsProcessMetadata'
v2reportsGeneReportMatch:
type: object
properties:
gene:
$ref: '#/components/schemas/v2reportsGeneDescriptor'
product:
$ref: '#/components/schemas/v2reportsProductDescriptor'
query:
type: array
items:
type: string
warnings:
type: array
items:
$ref: '#/components/schemas/v2reportsWarning'
warning:
$ref: '#/components/schemas/v2reportsWarning'
errors:
type: array
items:
$ref: '#/components/schemas/v2reportsError'
v2reportsGeneSummary:
type: object
properties:
source:
type: string
title: 'Source of the gene summary'
description:
type: string
title: 'Gene summary text itself that describes the gene'
date:
type: string
title: 'Date that the gene summary was last updated'
v2reportsGenomeAnnotation:
type: object
properties:
gene_id:
type: string
format: uint64
title: 'NCBI Gene ID'
symbol:
type: string
title: 'gene symbol'
description:
type: string
title: 'gene name'
name:
type: string
tax_id:
type: string
format: uint64
title: 'NCBI Taxonomy ID for the organism'
taxname:
type: string
title: 'Taxonomic name of the organism'
common_name:
type: string
title: 'Common name of the organism'
type:
$ref: '#/components/schemas/v2reportsGeneType'
title: 'Deprecated'
gene_type:
type: string
title: 'WIP - SEQUI-5271 - TODO fix breaking changes'
rna_type:
$ref: '#/components/schemas/v2reportsRnaType'
orientation:
$ref: '#/components/schemas/v2reportsOrientation'
locus_tag:
type: string
reference_standards:
type: array
items:
$ref: '#/components/schemas/v2reportsGenomicRegion'
genomic_regions:
type: array
items:
$ref: '#/components/schemas/v2reportsGenomicRegion'
transcripts:
type: array
items:
$ref: '#/components/schemas/v2reportsTranscript'
proteins:
type: array
items:
$ref: '#/components/schemas/v2reportsProtein'
chromosomes:
type: array
items:
type: string
swiss_prot_accessions:
type: array
items:
type: string
ensembl_gene_ids:
type: array
items:
type: string
omim_ids:
type: array
items:
type: string
synonyms:
type: array
items:
type: string
annotations:
type: array
items:
$ref: '#/components/schemas/v2reportsAnnotation'
v2reportsGenomeAnnotationReportMatch:
type: object
properties:
annotation:
$ref: '#/components/schemas/v2reportsGenomeAnnotation'
query:
type: array
items:
type: string
warning:
$ref: '#/components/schemas/v2reportsWarning'
errors:
type: array
items:
$ref: '#/components/schemas/v2reportsError'
row_id:
type: string
v2reportsGenomeAnnotationReportPage:
type: object
properties:
reports:
type: array
items:
$ref: '#/components/schemas/v2reportsGenomeAnnotationReportMatch'
messages:
type: array
items:
$ref: '#/components/schemas/v2reportsMessage'
total_count:
type: integer
title: 'The total count of available genes (ignoring the page_size parameter).'
next_page_token:
type: string
title: 'A token that can be sent as `page_token` to retrieve the next page. If this field is omitted, there are no subsequent pages.'
v2reportsGenomicLocation:
type: object
properties:
genomic_accession_version:
type: string
sequence_name:
type: string
genomic_range:
$ref: '#/components/schemas/v2reportsRange'
exons:
type: array
items:
$ref: '#/components/schemas/v2reportsRange'
v2reportsGenomicRegion:
type: object
properties:
gene_range:
$ref: '#/components/schemas/v2reportsSeqRangeSet'
title: 'The range of this Gene record on this genomic region.'
type:
$ref: '#/components/schemas/v2reportsGenomicRegionGenomicRegionType'
title: 'Type of genomic region'
v2reportsInfraspecificNames:
type: object
properties:
breed:
type: string
title: 'A homogenous group of animals within a domesticated species'
cultivar:
type: string
title: 'A variety of plant within a species produced and maintained by cultivation'
ecotype:
type: string
title: 'A population or subspecies occupying a distinct habitat'
isolate:
type: string
title: 'The individual isolate from which the sequences in the genome assembly were derived'
sex:
type: string
title: 'Male or female'
strain:
type: string
title: 'A genetic variant, subtype or culture within a species'
v2reportsIsolate:
type: object
properties:
name:
type: string
title: 'BioSample harmonized attribute names https://www.ncbi.nlm.nih.gov/biosample/docs/attributes/'
source:
type: string
title: 'Source material from which the viral specimen was isolated'
collection_date:
type: string
title: 'The collection date for the sample from which the viral nucleotide sequence was derived'
v2reportsLineageOrganism:
type: object
properties:
tax_id:
type: integer
title: 'NCBI Taxonomy identifier'
name:
type: string
title: 'Scientific name'
v2reportsLinkedAssembly:
type: object
properties:
linked_assembly:
type: string
title: 'The linked assembly accession'
assembly_type:
$ref: '#/components/schemas/v2reportsLinkedAssemblyType'
title: 'The linked assembly type'
v2reportsMaturePeptide:
type: object
properties:
accession_version:
type: string
name:
type: string
length:
type: integer
v2reportsMessage:
type: object
properties:
error:
$ref: '#/components/schemas/v2reportsError'
warning:
$ref: '#/components/schemas/v2reportsWarning'
v2reportsNameAndAuthority:
type: object
properties:
name:
type: string
title: 'This could be the scientific name, common name, synonym, etc. depending on the context.'
authority:
type: string
title: 'The authority that this name was created by. The authority is typically represented by the author(s) name and the year in which it was published.'
type_strains:
type: array
items:
$ref: '#/components/schemas/v2reportsTaxonomyTypeMaterial'
curator_synonym:
type: string
title: 'The primary synonym of the scientific name.'
homotypic_synonyms:
type: array
items:
$ref: '#/components/schemas/v2reportsNameAndAuthority'
heterotypic_synonyms:
type: array
items:
$ref: '#/components/schemas/v2reportsNameAndAuthority'
other_synonyms:
type: array
items:
$ref: '#/components/schemas/v2reportsNameAndAuthority'
informal_names:
type: array
items:
type: string
basionym:
$ref: '#/components/schemas/v2reportsNameAndAuthority'
title: 'The originally described name, no longer in use. Attached to the type material and species description.'
publications:
type: array
items:
$ref: '#/components/schemas/v2reportsNameAndAuthorityPublication'
notes:
type: array
items:
$ref: '#/components/schemas/v2reportsNameAndAuthorityNote'
formal:
type: boolean
title: 'Indicates whether the name is formal (i.e. compliant)'
v2reportsNameAndAuthorityNote:
type: object
properties:
name:
type: string
title: 'Name of the notation.'
note:
type: string
title: 'Note text.'
note_classifier:
$ref: '#/components/schemas/v2reportsNameAndAuthorityNoteClassifier'
title: 'Note classification'
v2reportsNameAndAuthorityPublication:
type: object
properties:
name:
type: string
title: 'Name of the publication (article, book, etc.).'
citation:
type: string
title: 'Citation to the publication.'
v2reportsNomenclatureAuthority:
type: object
properties:
authority:
type: string
title: 'The nomenclature authority for this gene record'
identifier:
type: string
title: 'The nomenclature authority identifier for this gene record'
v2reportsOrganelle:
type: object
properties:
description:
$ref: '#/components/schemas/v2reportsOrganelleType'
genbank:
$ref: '#/components/schemas/v2reportsSequenceInformation'
refseq:
$ref: '#/components/schemas/v2reportsSequenceInformation'
organism:
$ref: '#/components/schemas/v2reportsOrganism'
title: 'Taxon for the organelle'
bioprojects:
type: array
items:
$ref: '#/components/schemas/v2reportsBioProject'
biosample:
$ref: '#/components/schemas/v2reportsOrganelleBiosample'
title: 'The associated BioSample.'
gene_counts:
$ref: '#/components/schemas/v2reportsOrganelleGeneCounts'
length:
type: integer
title: 'Genome length'
topology:
$ref: '#/components/schemas/v2reportsOrganelleTopology'
gene_count:
type: integer
v2reportsOrganelleBiosample:
type: object
properties:
accession:
type: string
title: 'BioSample Accession identifier'
v2reportsOrganelleDataReports:
type: object
properties:
messages:
type: array
items:
$ref: '#/components/schemas/v2reportsMessage'
reports:
type: array
items:
$ref: '#/components/schemas/v2reportsOrganelle'
total_count:
type: integer
title: '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).'
next_page_token:
type: string
title: 'A token that can be sent as `page_token` to retrieve the next page. If this field is omitted, there are no subsequent pages.'
v2reportsOrganelleGeneCounts:
type: object
properties:
total:
type: integer
title: 'Total number of annotated genes'
protein_coding:
type: integer
title: 'Count of annotated genes that encode a protein'
rrna:
type: integer
title: 'Count of ribosomal RNAs'
trna:
type: integer
title: 'Count of transfer RNAs'
lncrna:
type: integer
title: 'Count of long, non-coding RNAs'
v2reportsOrganelleInfo:
type: object
properties:
assembly_name:
type: string
title: 'Name of associated nuclear assembly'
infraspecific_name:
type: string
title: 'The strain, breed, cultivar or ecotype of the organism from which the sequences in the assembly were derived'
bioproject:
type: array
items:
type: string
description:
type: string
title: 'Long description of the organelle genome'
total_seq_length:
type: string
format: uint64
title: 'Sequence length of the organelle genome'
submitter:
type: string
title: 'Name of submitter'
v2reportsOrganism:
type: object
properties:
tax_id:
type: integer
title: 'NCBI Taxonomy identifier'
sci_name:
type: string
title: 'Scientific name'
organism_name:
type: string
title: 'Scientific name'
common_name:
type: string
title: 'Common name'
lineage:
type: array
items:
$ref: '#/components/schemas/v2reportsLineageOrganism'
strain:
type: string
pangolin_classification:
type: string
infraspecific_names:
$ref: '#/components/schemas/v2reportsInfraspecificNames'
v2reportsPairedAssembly:
type: object
properties:
accession:
type: string
title: 'The GenColl assembly accession of the GenBank or RefSeq assembly paired with this one'
status:
$ref: '#/components/schemas/v2reportsAssemblyStatus'
title: 'GenColl Assembly status from paired record'
annotation_name:
type: string
title: 'Annotation name from paired record'
only_genbank:
type: string
title: 'Sequences that are only included in the GenBank assembly'
only_refseq:
type: string
title: 'Sequences that are only included in the RefSeq assembly'
changed:
type: string
title: 'Sequences present on both the GenBank and the RefSeq assemblies that have been changed, e.g., contaminated sequence in the GenBank assembly has been replaced with a gap'
manual_diff:
type: string
title: 'Additional details about sequence differences between the GenBank and RefSeq assemblies'
refseq_genbank_are_different:
type: boolean
title: 'boolean indication on whether there are any differences between the GenBank and RefSeq assemblies'
v2reportsProcessMetadata:
type: object
properties:
name:
type: string
title: 'Gene ontology term name'
go_id:
type: string
title: 'Gene ontology identifier'
evidence_code:
type: string
title: 'Indicates how the annotation is supported'
qualifier:
type: string
title: 'Explicitly link gene products to GO terms'
reference:
$ref: '#/components/schemas/v2reportsReference'
title: 'Source of evidence supporting the GO annotation'
v2reportsProductDescriptor:
type: object
properties:
gene_id:
type: string
format: uint64
title: 'NCBI Gene ID'
symbol:
type: string
title: 'gene symbol'
description:
type: string
title: 'gene name'
tax_id:
type: string
format: uint64
title: 'NCBI Taxonomy ID for the organism'
taxname:
type: string
title: 'Taxonomic name of the organism'
common_name:
type: string
title: 'Common name of the organism'
type:
$ref: '#/components/schemas/v2reportsGeneType'
title: 'Type of gene'
rna_type:
$ref: '#/components/schemas/v2reportsRnaType'
title: 'Type of RNA'
transcripts:
type: array
items:
$ref: '#/components/schemas/v2reportsTranscript'
transcript_count:
type: integer
title: 'Number of transcripts encoded by the gene'
protein_count:
type: integer
title: 'Number of proteins encoded by the gene'
transcript_type_counts:
type: array
items:
$ref: '#/components/schemas/v2reportsTranscriptTypeCount'
v2reportsProtein:
type: object
properties:
accession_version:
type: string
title: 'RefSeq protein accession with version'
name:
type: string
title: 'Protein name'
length:
type: integer
title: 'Protein length in amino acids'
isoform_name:
type: string
title: 'Protein isoform name'
ensembl_protein:
type: string
title: 'Ensembl protein accession with version'
mature_peptides:
type: array
items:
$ref: '#/components/schemas/v2reportsMaturePeptide'
v2reportsRange:
type: object
properties:
begin:
type: string
format: uint64
title: 'Sequence start position'
end:
type: string
format: uint64
title: 'Sequence stop position'
orientation:
$ref: '#/components/schemas/v2reportsOrientation'
title: 'Direction relative to the genome'
order:
type: integer
title: 'The position of this sequence in a group of sequences'
ribosomal_slippage:
type: integer
title: 'When ribosomal slippage is desired, fill out slippage amount between this and previous range.'
v2reportsReference:
type: object
properties:
pmids:
type: array
items:
type: string
format: uint64
v2reportsSeqRangeSet:
type: object
properties:
accession_version:
type: string
title: 'NCBI Accession.version of the sequence'
range:
type: array
items:
$ref: '#/components/schemas/v2reportsRange'
v2reportsSeqRangeSetFasta:
type: object
properties:
seq_id:
type: string
title: 'Seq_id may include location info in addition to a sequence accession'
accession_version:
type: string
title: 'Accession and version of the viral nucleotide sequence'
title:
type: string
sequence_hash:
type: string
title: 'Unique identifier for identical sequences'
range:
type: array
items:
$ref: '#/components/schemas/v2reportsRange'
v2reportsSequenceInfo:
type: object
properties:
assembly_accession:
type: string
title: 'The GenColl assembly accession'
chr_name:
type: string
title: 'The name of the associated chromosome. The name "Un" indicates that the chromosome is unknown.'
ucsc_style_name:
type: string
title: 'Name ascribed to this sequence by the UC Santa Cruz genome browser'
sort_order:
type: integer
title: 'A sort order value assigned to the sequence'
assigned_molecule_location_type:
type: string
title: 'The type of molecule represented by the sequence'
refseq_accession:
type: string
title: 'The RefSeq accession of the sequence'
assembly_unit:
type: string
title: 'The NCBI Assembly accession of the associated assembly unit. Assembly units can include the primary assembly and non-nuclear assembly units'
length:
type: integer
title: 'The length of the sequence in nucleotides'
genbank_accession:
type: string
title: 'The GenBank accession of the sequence'
gc_count:
type: string
format: uint64
title: 'The number of GC base-pairs in the chromosome'
gc_percent:
type: number
format: float
title: 'The percentage of GC base-pairs in the chromosome'
unlocalized_count:
type: integer
title: 'Number of scaffolds that are unlocalized on a given chromosome'
assembly_unplaced_count:
type: integer
title: 'Number of unplaced scaffolds for a given assembly accession'
role:
type: string
sequence_name:
type: string
title: 'The sequence name'
v2reportsSequenceInformation:
type: object
properties:
accession:
type: string
title: 'The accession.version of the organelle genomic nucleotide sequence.'
submission_date:
type: string
title: 'Date record was submitted to GenBank or Curated into RefSeq (ISO 8601)'
submitter:
type: string
title: 'The submitter, e.g. NCBI Genome Project for RefSeq'
v2reportsTaxData:
type: object
properties:
name:
type: string
title: 'Taxonomic name'
id:
type: integer
title: 'NCBI Taxonomy identifier'
v2reportsTaxonomyDataReportPage:
type: object
properties:
reports:
type: array
items:
$ref: '#/components/schemas/v2reportsTaxonomyReportMatch'
messages:
type: array
items:
$ref: '#/components/schemas/v2reportsMessage'
total_count:
type: integer
title: 'The total count of available taxons (ignoring the page_size parameter).'
next_page_token:
type: string
title: 'A token that can be sent as `page_token` to retrieve the next page. If this field is omitted, there are no subsequent pages.'
v2reportsTaxonomyNamesDataReportPage:
type: object
properties:
reports:
type: array
items:
$ref: '#/components/schemas/v2reportsTaxonomyNamesReportMatch'
messages:
type: array
items:
$ref: '#/components/schemas/v2reportsMessage'
total_count:
type: integer
title: 'The total count of available taxons (ignoring the page_size parameter).'
next_page_token:
type: string
title: 'A page token. A token that can be used in a future request as `page_token` to retrieve the next page. If this field is emtpy then there are no subsequent pages available.'
v2reportsTaxonomyNamesDescriptor:
type: object
properties:
tax_id:
type: string
format: uint64
title: 'NCBI Taxonomy identifier'
rank:
$ref: '#/components/schemas/v2reportsRankType'
title: 'The taxonomic rank of the taxonomic node.'
current_scientific_name:
$ref: '#/components/schemas/v2reportsNameAndAuthority'
title: 'The currently accepted name chosen out of all synonyms for the taxonomic node.'
group_name:
type: string
title: 'Group name for the species.'
curator_common_name:
type: string
title: 'The canonical common name.'
other_common_names:
type: array
items:
type: string
general_notes:
type: array
items:
type: string
links_from_type:
type: string
title: 'TBD'
citations:
type: array
items:
$ref: '#/components/schemas/v2reportsTaxonomyNamesDescriptorCitation'
current_scientific_name_is_formal:
type: boolean
title: 'Specify if the current scientific name is considered ''formal'' or not.'
v2reportsTaxonomyNamesDescriptorCitation:
type: object
properties:
full_citation:
type: string
short_citation:
type: string
pmid:
type: string
format: uint64
v2reportsTaxonomyNamesReportMatch:
type: object
properties:
taxonomy:
$ref: '#/components/schemas/v2reportsTaxonomyNamesDescriptor'
title: 'Detailed taxonomic information related to the requested node.'
query:
type: array
items:
type: string
warning:
$ref: '#/components/schemas/v2reportsWarning'
title: 'Warnings associated with this request. Any warning associated with this request. This is represented by a Warning object which is separately documented.'
errors:
type: array
items:
$ref: '#/components/schemas/v2reportsError'
v2reportsTaxonomyNode:
type: object
properties:
tax_id:
type: integer
title: 'NCBI Taxonomy identifier'
rank:
$ref: '#/components/schemas/v2reportsRankType'
title: 'The taxonomic rank of the taxonomic node.'
current_scientific_name:
$ref: '#/components/schemas/v2reportsNameAndAuthority'
title: 'The currently accepted name chosen out of all synonyms for the taxonomic node.'
basionym:
$ref: '#/components/schemas/v2reportsNameAndAuthority'
title: 'The originally described name, no longer in use. Attached to the type material and species description.'
curator_common_name:
type: string
title: 'The canonical common name.'
group_name:
type: string
title: 'A common name describing large, well-known taxa.'
has_type_material:
type: boolean
title: 'A boolean that indicates whether or not type material is available for the species.'
classification:
$ref: '#/components/schemas/v2reportsClassification'
title: 'A subset of parent nodes including well-established ranks.'
parents:
type: array
items:
type: integer
children:
type: array
items:
type: integer
counts:
type: array
items:
$ref: '#/components/schemas/v2reportsTaxonomyNodeCountByType'
genomic_moltype:
type: string
title: 'Genomic molecule type (dsDNA, ssDNA, ssDNA(-), ssRNA)'
current_scientific_name_is_formal:
type: boolean
title: 'Specify if the current scientific name is considered ''formal'' or not.'
secondary_tax_ids:
type: array
items:
type: integer
v2reportsTaxonomyNodeCountByType:
type: object
properties:
type:
$ref: '#/components/schemas/v2reportsCountType'
count:
type: integer
v2reportsTaxonomyReportMatch:
type: object
properties:
taxonomy:
$ref: '#/components/schemas/v2reportsTaxonomyNode'
query:
type: array
items:
type: string
warning:
$ref: '#/components/schemas/v2reportsWarning'
errors:
type: array
items:
$ref: '#/components/schemas/v2reportsError'
v2reportsTaxonomyTypeMaterial:
type: object
properties:
type_strain_name:
type: string
title: 'The strain name of the type material.'
type_strain_id:
type: string
title: 'The strain ID of the type material.'
bio_collection_id:
type: string
title: 'The biocollection ID of the type material.'
bio_collection_name:
type: string
title: 'The biocollection name of the type material.'
collection_type:
type: array
items:
$ref: '#/components/schemas/v2reportsCollectionType'
type_class:
type: string
title: 'Type material classification.'
v2reportsTranscript:
type: object
properties:
accession_version:
type: string
title: 'RefSeq transcript accession with version'
name:
type: string
title: 'RefSeq transcript name'
length:
type: integer
title: 'RefSeq transcript length in nucleotides'
cds:
$ref: '#/components/schemas/v2reportsSeqRangeSet'
genomic_locations:
type: array
items:
$ref: '#/components/schemas/v2reportsGenomicLocation'
ensembl_transcript:
type: string
title: 'Ensembl transcript accession with version'
protein:
$ref: '#/components/schemas/v2reportsProtein'
type:
$ref: '#/components/schemas/v2reportsTranscriptTranscriptType'
title: 'Indicates transcript protein-coding potential and whether it was computationally predicted'
select_category:
$ref: '#/components/schemas/v2reportsTranscriptSelectCategory'
v2reportsTranscriptTypeCount:
type: object
properties:
type:
$ref: '#/components/schemas/v2reportsTranscriptTranscriptType'
title: 'Type of transcript'
count:
type: integer
title: 'Number of transcripts of a particular type'
v2reportsTypeMaterial:
type: object
properties:
type_label:
type: string
type_display_text:
type: string
v2reportsVirusAnnotationReport:
type: object
properties:
accession:
type: string
isolate_name:
type: string
genes:
type: array
items:
$ref: '#/components/schemas/v2reportsVirusGene'
v2reportsVirusAnnotationReportPage:
type: object
properties:
reports:
type: array
items:
$ref: '#/components/schemas/v2reportsVirusAnnotationReport'
total_count:
type: integer
title: 'The total count of available assemblies (ignoring the page_size parameter).'
next_page_token:
type: string
title: 'A token that can be sent as `page_token` to retrieve the next page. If this field is omitted, there are no subsequent pages.'
v2reportsVirusAssembly:
type: object
properties:
accession:
type: string
title: 'The accession.version of the viral nucleotide sequence. Includes both GenBank and RefSeq accessions'
is_complete:
type: boolean
is_annotated:
type: boolean
title: 'The viral genome has been annotated by either the submitter (GenBank) or by NCBI (RefSeq)'
isolate:
$ref: '#/components/schemas/v2reportsIsolate'
source_database:
type: string
title: 'Indicates if the source of the viral nucleotide record is from a GenBank submitter or from NCBI-derived curation (RefSeq)'
protein_count:
type: integer
title: 'The total count of annotated proteins including both proteins and polyproteins but not processed mature peptides'
host:
$ref: '#/components/schemas/v2reportsOrganism'
title: 'Taxon from which the virus sample was isolated'
virus:
$ref: '#/components/schemas/v2reportsOrganism'
title: 'Viral taxon'
bioprojects:
type: array
items:
type: string
location:
$ref: '#/components/schemas/v2reportsVirusAssemblyCollectionLocation'
update_date:
type: string
title: 'Date the viral nucleotide accession was last updated in NCBI Virus'
release_date:
type: string
title: 'Date the viral nucleotide accession was first released in NCBI Virus'
nucleotide_completeness:
type: string
title: 'Value describing if the of the viral nucleotide sequence represents a complete or partial genome'
completeness:
$ref: '#/components/schemas/v2reportsVirusAssemblyCompleteness'
title: 'Indicates whether the viral nucleotide sequence represents a complete or partial genome'
length:
type: integer
title: 'Length of the viral nucleotide sequence'
gene_count:
type: integer
title: 'Total count of genes annotated on the viral nucleotide sequence'
mature_peptide_count:
type: integer
title: 'Total count of processed mature peptides annotated on the viral nucleotide sequence'
biosample:
type: string
title: 'Associated Biosample accessions'
mol_type:
type: string
title: 'ICTV (International Committee on Taxonomy of Viruses) viral classification based on nucleic acid composition, strandedness and method of replication'
nucleotide:
$ref: '#/components/schemas/v2reportsSeqRangeSetFasta'
title: 'The whole genomic nucleotide record of the CDS feature.'
purpose_of_sampling:
$ref: '#/components/schemas/v2reportsPurposeOfSampling'
title: 'SARS-CoV-2 only, indicates whether the sequence was collected randomly for epedimiology studies'
sra_accessions:
type: array
items:
type: string
submitter:
$ref: '#/components/schemas/v2reportsVirusAssemblySubmitterInfo'
title: 'Name, affiliation, and country of the submitter(s)'
lab_host:
type: string
title: 'This sequence is from viruses passaged in this host'
is_lab_host:
type: boolean
title: 'If true, this sequence is from viruses passaged in a laboratory'
is_vaccine_strain:
type: boolean
title: 'If true, this sequence is derived from a virus used as a vaccine or potential vaccine'
segment:
type: string
title: 'The virus segment'
v2reportsVirusAssemblyCollectionLocation:
type: object
properties:
geographic_location:
type: string
title: 'Country of virus specimen collection'
geographic_region:
type: string
title: 'Region of virus specimen collection'
usa_state:
type: string
title: 'Two letter abbreviation of the state of the virus specifime collection (if United States)'
v2reportsVirusAssemblySubmitterInfo:
type: object
properties:
names:
type: array
items:
type: string
affiliation:
type: string
title: 'The submitter''s organization and/or institution'
country:
type: string
title: 'The country representing the submitter''s affilation'
v2reportsVirusDataReportPage:
type: object
properties:
reports:
type: array
items:
$ref: '#/components/schemas/v2reportsVirusAssembly'
total_count:
type: integer
title: 'The total count of available assemblies (ignoring the page_size parameter).'
next_page_token:
type: string
title: 'A token that can be sent as `page_token` to retrieve the next page. If this field is omitted, there are no subsequent pages.'
v2reportsVirusGene:
type: object
properties:
name:
type: string
gene_id:
type: integer
nucleotide:
$ref: '#/components/schemas/v2reportsSeqRangeSetFasta'
title: 'The interval on the genomic nucleotide record of the CDS feature.'
cds:
type: array
items:
$ref: '#/components/schemas/v2reportsVirusPeptide'
v2reportsVirusPeptide:
type: object
properties:
accession:
type: string
title: 'Protein accession and version'
name:
type: string
title: 'Protein name'
other_names:
type: array
items:
type: string
nucleotide:
$ref: '#/components/schemas/v2reportsSeqRangeSetFasta'
title: 'The interval on the genomic nucleotide record of this mature-peptide feature'
protein:
$ref: '#/components/schemas/v2reportsSeqRangeSetFasta'
title: 'The full polyprotein record or interval on the polyprotein for mature-peptide features'
pdb_ids:
type: array
items:
type: string
cdd:
type: array
items:
$ref: '#/components/schemas/v2reportsConservedDomain'
uni_prot_kb:
$ref: '#/components/schemas/v2reportsVirusPeptideUniProtId'
title: 'UniProt identifier'
mature_peptide:
type: array
items:
$ref: '#/components/schemas/v2reportsVirusPeptide'
protein_completeness:
$ref: '#/components/schemas/v2reportsVirusPeptideViralPeptideCompleteness'
title: 'Protein completeness'
v2reportsVirusPeptideUniProtId:
type: object
properties:
id:
type: string
title: 'UniProt ID'
name:
type: string
title: 'UniProt name'
v2reportsWGSInfo:
type: object
properties:
wgs_project_accession:
type: string
title: 'WGS project accession'
master_wgs_url:
type: string
title: 'WGS project Nucleotide web address'
wgs_contigs_url:
type: string
title: 'WGS project Sequence set browser web address'
v2reportsWarning:
type: object
properties:
gene_warning_code:
$ref: '#/components/schemas/v2reportsWarningGeneWarningCode'
reason:
type: string
message:
type: string
replaced_id:
$ref: '#/components/schemas/v2reportsWarningReplacedId'
unrecognized_identifier:
type: string
v2reportsWarningReplacedId:
type: object
properties:
requested:
type: string
returned:
type: string
v2AnnotationForAssemblyType:
type: string
enum:
- GENOME_GFF
- GENOME_GBFF
- GENOME_GB
- RNA_FASTA
- PROT_FASTA
- GENOME_GTF
- CDS_FASTA
- GENOME_FASTA
- SEQUENCE_REPORT
v2AnnotationForOrganelleType:
type: string
enum:
- GENOME_FASTA
- CDS_FASTA
- PROTEIN_FASTA
v2AssemblyDatasetDescriptorsFilterAssemblySource:
type: string
enum:
- all
- refseq
- genbank
v2AssemblyDatasetDescriptorsFilterAssemblyVersion:
type: string
enum:
- current
- all_assemblies
title: 'The assembly status - current (latest), or all assemblies, which adds replaced and suppressed'
v2AssemblyDatasetDescriptorsFilterMetagenomeDerivedFilter:
type: string
enum:
- METAGENOME_DERIVED_UNSET
- metagenome_derived_only
- metagenome_derived_exclude
v2AssemblyDatasetDescriptorsFilterTypeMaterialCategory:
type: string
enum:
- NONE
- TYPE_MATERIAL
- TYPE_MATERIAL_CLADE
- TYPE_MATERIAL_NEOTYPE
- TYPE_MATERIAL_REFTYPE
- PATHOVAR_TYPE
- TYPE_MATERIAL_SYN
v2AssemblyDatasetReportsRequestContentType:
type: string
enum:
- COMPLETE
- ASSM_ACC
- PAIRED_ACC
v2AssemblyDatasetRequestResolution:
type: string
enum:
- FULLY_HYDRATED
- DATA_REPORT_ONLY
v2AssemblyLinksReplyAssemblyLinkType:
type: string
enum:
- GDV_LINK
- FTP_LINK
- ASSEMBLY_PUBMED
- BLAST_LINK
- ASSEMBLY_NUCCORE
- ASSEMBLY_NUCCORE_REFSEQ
- ASSEMBLY_NUCCORE_GENBANK
title: 'Types of assembly links that may be returned'
v2Fasta:
type: string
enum:
- FASTA_UNSPECIFIED
- FASTA_GENE
- FASTA_RNA
- FASTA_PROTEIN
- FASTA_GENE_FLANK
- FASTA_CDS
- FASTA_5P_UTR
- FASTA_3P_UTR
v2GeneDatasetReportsRequestContentType:
type: string
enum:
- COMPLETE
- IDS_ONLY
- PRODUCT
- COUNTS_ONLY
title: 'Specify a specific group of values to be returned for dataset reports. These options do not apply to product reports.'
v2GeneDatasetRequestContentType:
type: string
enum:
- COMPLETE
- IDS_ONLY
v2GeneDatasetRequestGeneDatasetReportType:
type: string
enum:
- DATASET_REPORT
- PRODUCT_REPORT
v2GeneLinksReplyGeneLinkType:
type: string
enum:
- GENE_LINK
- GDV_LINK
- ORTHOLOG_LINK
- MCGV_LINK
title: 'Types of gene links that may be returned'
v2GeneType:
type: string
enum:
- UNKNOWN
- tRNA
- rRNA
- snRNA
- scRNA
- snoRNA
- PROTEIN_CODING
- PSEUDO
- TRANSPOSON
- miscRNA
- ncRNA
- BIOLOGICAL_REGION
- OTHER
title: 'NB: GeneType values match Entrez Gene'
v2GenomeAnnotationRequestAnnotationType:
type: string
enum:
- GENOME_FASTA
- RNA_FASTA
- PROT_FASTA
v2GenomeAnnotationRequestGenomeAnnotationTableFormat:
type: string
enum:
- NO_TABLE
- SUMMARY
- PRODUCT
v2ImageSize:
type: string
enum:
- UNSPECIFIED
- SMALL
- MEDIUM
v2IncludeTabularHeader:
type: string
enum:
- INCLUDE_TABULAR_HEADER_FIRST_PAGE_ONLY
- INCLUDE_TABULAR_HEADER_ALWAYS
- INCLUDE_TABULAR_HEADER_NEVER
v2OrganelleMetadataRequestContentType:
type: string
enum:
- COMPLETE
- ASSM_ACC
v2OrganelleMetadataRequestOrganelleTableFormat:
type: string
enum:
- ORGANELLE_TABLE_FORMAT_NO_TABLE
- SUMMARY
v2OrganismQueryRequestTaxRankFilter:
type: string
enum:
- species
- higher_taxon
v2OrganismQueryRequestTaxonResourceFilter:
type: string
enum:
- TAXON_RESOURCE_FILTER_ALL
- TAXON_RESOURCE_FILTER_GENOME
- TAXON_RESOURCE_FILTER_GENE
- TAXON_RESOURCE_FILTER_ORGANELLE
v2OrthologRequestContentType:
type: string
enum:
- COMPLETE
- IDS_ONLY
v2SortDirection:
type: string
enum:
- SORT_DIRECTION_UNSPECIFIED
- SORT_DIRECTION_ASCENDING
- SORT_DIRECTION_DESCENDING
v2TableFormat:
type: string
enum:
- tsv
- csv
- jsonl
v2TaxonomyDatasetRequestTaxonomyReportType:
type: string
enum:
- TAXONOMY_SUMMARY
- NAMES_REPORT
v2TaxonomyFilteredSubtreeResponseEdgeChildStatus:
type: string
enum:
- UNSPECIFIED
- HAS_MORE_CHILDREN
- NO_VISIBLE_CHILDREN
title: 'If these are changed before v1 is retired, code that converts v2 to v1 responses in python/private/src/ncbi_private/datasets/services/taxonomy/v1/dataset.py may need to be updated.'
v2TaxonomyMetadataRequestContentType:
type: string
enum:
- COMPLETE
- TAXIDS
- METADATA
v2TaxonomyMetadataRequestTableFormat:
type: string
enum:
- SUMMARY
title: 'Optional pre-defined template for processing a tabular data request'
v2ViralSequenceType:
type: string
enum:
- GENOME
- CDS
- PROTEIN
- NONE
- BIOSAMPLE
v2VirusDataReportRequestContentType:
type: string
enum:
- COMPLETE
- ACCESSIONS_ONLY
title: 'Specify a specific group of values to be returned, currently either all fields or accessions only'
v2VirusDatasetReportType:
type: string
enum:
- DATASET_REPORT
- ANNOTATION
- BIOSAMPLE_REPORT
v2VirusTableField:
type: string
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
v2reportsANITypeCategory:
type: string
enum:
- ANI_CATEGORY_UNKNOWN
- claderef
- category_na
- neotype
- no_type
- pathovar
- reftype
- suspected_type
- syntype
- type
v2reportsAssemblyLevel:
type: string
enum:
- chromosome
- scaffold
- contig
- complete_genome
title: 'The level of the genome assembly: Chromosome, Scaffold, Contig or Complete Genome'
v2reportsAssemblyStatus:
type: string
enum:
- ASSEMBLY_STATUS_UNKNOWN
- current
- previous
- suppressed
- retired
v2reportsAverageNucleotideIdentityMatchStatus:
type: string
enum:
- BEST_MATCH_STATUS_UNKNOWN
- approved_mismatch
- below_threshold_match
- below_threshold_mismatch
- best_match_status
- derived_species_match
- genus_match
- low_coverage
- mismatch
- status_na
- species_match
- subspecies_match
- synonym_match
- lineage_match
- below_threshold_lineage_match
v2reportsAverageNucleotideIdentityTaxonomyCheckStatus:
type: string
enum:
- TAXONOMY_CHECK_STATUS_UNKNOWN
- OK
- Failed
- Inconclusive
v2reportsCollectionType:
type: string
enum:
- no_collection_type
- collection_culture_collection
- specimen_voucher
v2reportsContentType:
type: string
enum:
- COMPLETE
- ASSM_ACC
- PAIRED_ACC
v2reportsCountType:
type: string
enum:
- COUNT_TYPE_UNSPECIFIED
- COUNT_TYPE_ASSEMBLY
- COUNT_TYPE_GENE
- COUNT_TYPE_tRNA
- COUNT_TYPE_rRNA
- COUNT_TYPE_snRNA
- COUNT_TYPE_scRNA
- COUNT_TYPE_snoRNA
- COUNT_TYPE_PROTEIN_CODING
- COUNT_TYPE_PSEUDO
- COUNT_TYPE_TRANSPOSON
- COUNT_TYPE_miscRNA
- COUNT_TYPE_ncRNA
- COUNT_TYPE_BIOLOGICAL_REGION
- COUNT_TYPE_OTHER
- COUNT_TYPE_ORGANELLE
v2reportsErrorAssemblyErrorCode:
type: string
enum:
- UNKNOWN_ASSEMBLY_ERROR_CODE
- INVALID_BIOPROJECT_IDS
- NO_ASSEMBLIES_FOR_BIOPROJECTS
- INVALID_TAXON
- MISSING_SEARCH_FIELD
- INVALID_BIOSAMPLE_IDS
- NO_ASSEMBLIES_FOR_BIOSAMPLE_IDS
- NO_ASSEMBLIES_FOR_ASSEMBLY_NAMES
- INVALID_WGS_ACCESSIONS
- NO_ASSEMBLIES_FOR_WGS_ACCESSIONS
v2reportsErrorGeneErrorCode:
type: string
enum:
- UNKNOWN_GENE_ERROR_CODE
- INCOMPLETE_LOOKUP_SYMBOL
- INVALID_TAXON_GENE_ARGUMENT
v2reportsErrorOrganelleErrorCode:
type: string
enum:
- UNKNOWN_ORGANELLE_ERROR_CODE
- INVALID_ORGANELLE_TAXON
- NO_ORGANELLES_FOR_ACCESSION
v2reportsErrorTaxonomyErrorCode:
type: string
enum:
- UNKNOWN_TAXONOMY_ERROR_CODE
- INVALID_TAXONOMY_TAXON
v2reportsErrorVirusErrorCode:
type: string
enum:
- UNKNOWN_VIRUS_ERROR_CODE
v2reportsGeneType:
type: string
enum:
- UNKNOWN
- tRNA
- rRNA
- snRNA
- scRNA
- snoRNA
- PROTEIN_CODING
- PSEUDO
- TRANSPOSON
- miscRNA
- ncRNA
- BIOLOGICAL_REGION
- OTHER
title: 'NB: GeneType values match Entrez Gene'
v2reportsGenomicRegionGenomicRegionType:
type: string
enum:
- UNKNOWN
- REFSEQ_GENE
- PSEUDOGENE
- BIOLOGICAL_REGION
- OTHER
v2reportsLinkedAssemblyType:
type: string
enum:
- LINKED_ASSEMBLY_TYPE_UNKNOWN
- alternate_pseudohaplotype_of_diploid
- principal_pseudohaplotype_of_diploid
- maternal_haplotype_of_diploid
- paternal_haplotype_of_diploid
- haplotype_1
- haplotype_2
- haplotype_3
- haplotype_4
- haploid
v2reportsNameAndAuthorityNoteClassifier:
type: string
enum:
- no_authority_classifier
- effective_name
- nomen_approbbatum
- ictv_accepted
title: 'Class of authority If the authority has any special classification, such as having been effectively and validly published or having been included in an approved list.'
v2reportsOrganelleTopology:
type: string
enum:
- TOPOLOGY_UNKNOWN
- Circular
- Linear
- Tandem
v2reportsOrganelleType:
type: string
enum:
- ORGANELLE_TYPE_UNKNOWN
- Mitochondrion
- Chloroplast
- Plastid
- Kinetoplast
- Apicoplast
- Chromatophore
- Cyanelle
v2reportsOrientation:
type: string
enum:
- none
- plus
- minus
v2reportsPurposeOfSampling:
type: string
enum:
- PURPOSE_OF_SAMPLING_UNKNOWN
- PURPOSE_OF_SAMPLING_BASELINE_SURVEILLANCE
v2reportsRankType:
type: string
enum:
- NO_RANK
- SUPERKINGDOM
- DOMAIN
- REALM
- 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
title: 'Rank level'
v2reportsRnaType:
type: string
enum:
- rna_UNKNOWN
- premsg
- tmRna
v2reportsSourceDatabase:
type: string
enum:
- SOURCE_DATABASE_UNSPECIFIED
- SOURCE_DATABASE_GENBANK
- SOURCE_DATABASE_REFSEQ
v2reportsTranscriptSelectCategory:
type: string
enum:
- SELECT_UNKNOWN
- REFSEQ_SELECT
- MANE_SELECT
- MANE_PLUS_CLINICAL
v2reportsTranscriptTranscriptType:
type: string
enum:
- UNKNOWN
- PROTEIN_CODING
- NON_CODING
- PROTEIN_CODING_MODEL
- NON_CODING_MODEL
v2reportsVirusAssemblyCompleteness:
type: string
enum:
- UNKNOWN
- COMPLETE
- PARTIAL
v2reportsVirusPeptideViralPeptideCompleteness:
type: string
enum:
- UNKNOWN
- COMPLETE
- PARTIAL
v2reportsWarningGeneWarningCode:
type: string
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
- NO_GENE_ANNOTATION_FOUND
- ABOVE_SPECIES_TAXON
protobufAny:
type: object
properties:
type_url:
type: string
value:
type: string
format: byte
rpcStatus:
type: object
properties:
code:
type: integer
format: int32
message:
type: string
details:
type: array
items:
$ref: '#/components/schemas/protobufAny'