htsget-openapi.yaml

openapi: 3.0.3
servers:
  - description: htsget genomics api
    url: htsget/1
info:
  description: This data retrieval API bridges from existing genomics bulk data transfers to a client/server model
  version: 1.3.0
  title: htsget
  contact:
    name: GA4GH
    email: security-notification@ga4gh.org
externalDocs:
  description: htsget specification
  url: https://samtools.github.io/hts-specs/htsget.html
paths:
  /reads/{id}:
    get:
      summary: Gets the reads from a pre-indexed id
      operationId: searchReadId
      description: |
        Searches a pre-indexed object id
      parameters:
        - $ref: '#/components/parameters/idPathParam'
        - in: query
          name: format
          required: false
          schema:
            $ref: '#/components/schemas/FormatReads'
        - $ref: '#/components/parameters/classParam'
        - $ref: '#/components/parameters/referenceNameParam'
        - $ref: '#/components/parameters/startParam'
        - $ref: '#/components/parameters/endParam'
        - in: query
          name: fields
          required: false
          schema:
            $ref: '#/components/schemas/FieldsReads'
        - in: query
          name: tags
          required: false
          schema:
            $ref: '#/components/schemas/TagsReads'
        - in: query
          name: notags
          required: false
          schema:
            $ref: '#/components/schemas/NoTagsReads'

      responses:
        200:
          description: results matching criteria
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/htsgetResponseReads'
        400:
          $ref: '#/components/responses/400BadRequestResponse'
        401:
          $ref: '#/components/responses/401UnauthorizedResponse'
        403:
          $ref: '#/components/responses/403ForbiddenResponse'
        404:
          $ref: '#/components/responses/404NotFoundResponse'
        500:
          $ref: '#/components/responses/500InternalServerErrorResponse'
        default:
          $ref: '#/components/responses/500InternalServerErrorResponse'

      security:
        - htsget_auth:
          - read:genomic_reads
    
    post:
      summary: Get htsget ticket for reads data streaming
      operationId: postRead
      description: |
        Servers may optionally accept `POST` requests to enable alignment data
        streaming of more than one genomic region 
      parameters:
        - $ref: '#/components/parameters/idPathParam'
      requestBody:
        description: Specify output format, fields, genomic regions, etc.
        required: false
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RequestBodyReads'
      responses:
        200:
          description: Successfully retrieved ticket for streaming alignment file
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/htsgetResponseReads'
        400:
          $ref: '#/components/responses/400BadRequestResponse'
        401:
          $ref: '#/components/responses/401UnauthorizedResponse'
        403:
          $ref: '#/components/responses/403ForbiddenResponse'
        404:
          $ref: '#/components/responses/404NotFoundResponse'
        413:
          $ref: '#/components/responses/413PayloadTooLargeResponse'
        500:
          $ref: '#/components/responses/500InternalServerErrorResponse'
        default:
          $ref: '#/components/responses/500InternalServerErrorResponse'

  /variants/{id}:
    get:
      summary: Gets the variants from a pre-indexed id
      operationId: searchVariantId
      description: Searches a pre-indexed object id
      parameters:
        - $ref: '#/components/parameters/idPathParam'
        - in: query
          name: format
          required: false
          schema:
            $ref: '#/components/schemas/FormatVariants'
        - $ref: '#/components/parameters/classParam'
        - $ref: '#/components/parameters/referenceNameParam'
        - $ref: '#/components/parameters/startParam'
        - $ref: '#/components/parameters/endParam'
        - in: query
          name: tags
          required: false
          schema:
            $ref: '#/components/schemas/TagsVariants'
        - in: query
          name: notags
          required: false
          schema:
            $ref: '#/components/schemas/NoTagsVariants'

      responses:
        200:
          description: results matching criteria
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/htsgetResponseVariants'
        400:
          $ref: '#/components/responses/400BadRequestResponse'
        401:
          $ref: '#/components/responses/401UnauthorizedResponse'
        403:
          $ref: '#/components/responses/403ForbiddenResponse'
        404:
          $ref: '#/components/responses/404NotFoundResponse'
        500:
          $ref: '#/components/responses/500InternalServerErrorResponse'
        default:
          $ref: '#/components/responses/500InternalServerErrorResponse'

      security:
        - htsget_auth:
          - read:genomic_variants
    
    post:
      summary: Get htsget ticket for variant data streaming
      operationId: postVariant
      description: |
        Servers may optionally accept `POST` requests to enable variant data
        streaming of more than one genomic region.
      parameters:
        - $ref: '#/components/parameters/idPathParam'
      requestBody:
        description: Specify output format, genomic regions, etc.
        required: false
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RequestBodyVariants'
      responses:
        200:
          description: Successfully retrieved ticket for streaming variant file
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/htsgetResponseVariants'
        400:
          $ref: '#/components/responses/400BadRequestResponse'
        401:
          $ref: '#/components/responses/401UnauthorizedResponse'
        403:
          $ref: '#/components/responses/403ForbiddenResponse'
        404:
          $ref: '#/components/responses/404NotFoundResponse'
        413:
          $ref: '#/components/responses/413PayloadTooLargeResponse'
        500:
          $ref: '#/components/responses/500InternalServerErrorResponse'
        default:
          $ref: '#/components/responses/500InternalServerErrorResponse'

  /reads/service-info:
    get:
      summary: Get htsget reads API service info
      description: Retrieves GA4GH Service Info, and htsget reads API features supported by the web service
      operationId: readsServiceInfo
      responses:
        '200':
          description: displays configuration of htsget service reads API
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/htsgetServiceInfo'
        '500':
          description: Internal Server Error
  /variants/service-info:
    get:
      summary: Get htsget variants API service info
      description: Retrieves GA4GH Service Info, and htsget variants API features supported by the web service
      operationId: variantsServiceInfo
      responses:
        '200':
          description: displays configuration of htsget service variants API
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/htsgetServiceInfo'
        '500':
          description: Internal Server Error

components:
  schemas:
    htsgetResponse:
      type: object
      required:
        - htsget
      properties:
        htsget:
          type: object
          description: Container for response object
          required:
            - format
          properties:
            format:
              type: string
              description: Response data is in this format
            md5:
              type: string
              description: MD5 digest of the blob resulting from concatenating all of the payload data
              example: 8a6049fad4943ff4c6de5c22df97d001
    
    htsgetResponseReads:
      allOf:
        - $ref: '#/components/schemas/htsgetResponse'
        - properties:
            htsget:
              properties:
                format:
                  example: BAM
                  enum: [BAM, CRAM]
                urls:
                  type: array
                  description: An array providing URLs from which raw alignment data can be retrieved
                  items:
                    $ref: '#/components/schemas/htsgetUrlReads'
              required:
                - urls
    
    htsgetResponseVariants:
      allOf:
        - $ref: '#/components/schemas/htsgetResponse'
        - properties:
            htsget:
              properties:
                format:
                  example: VCF
                  enum: [VCF, BCF]
                urls:
                  type: array
                  description: An array providing URLs from which raw variant data can be retrieved
                  items:
                    $ref: '#/components/schemas/htsgetUrlVariants'
              required:
                - urls

    htsgetUrl:
      type: object
      required:
        - url
      properties:
        url:
          type: string
          description: URL to download data block
        headers:
          type: object
          description: JSON object of key-value pairs representing HTTP headers. If supplied, the client MUST provide these as headers to the data download url
        class:
          type: string
          description: Indicates whether the header or body of the requested file will be retrieved by this url
          example: body
          enum: [header, body]

    htsgetUrlReads:
      allOf:
        - $ref: '#/components/schemas/htsgetUrl'
        - example:
            - url: data:application/vnd.ga4gh.vcf;base64,QkFNAQ==
            - url: https://htsget.blocksrv.example/sample1234/run1.bam
              headers:
                Authorization: Bearer xxxxx
                Range: bytes=65536-1003750

    htsgetUrlVariants:
      allOf:
        - $ref: '#/components/schemas/htsgetUrl'
        - example:
            - url: https://example.com/sample1234/run1.vcf

    FormatReads:
      type: string
      description: Desired alignment file format
      enum: [BAM, CRAM]
      example: BAM
      default: BAM
    
    FormatVariants:
      type: string
      description: Desired variant file format
      enum: [VCF, BCF]
      example: VCF
      default: VCF

    Class:
      type: string
      description: Request different classes of data. By default, i.e., when class is not specified, the response will represent a complete read or variant data stream, encompassing SAM/CRAM/VCF headers, body data records, and EOF marker
      enum: [header]
      example: header

    ReferenceName:
      type: string
      description: Reference sequence name
      example: chr1

    Start:
      type: integer
      description: The start position of the range on the reference, 0-based, inclusive
      format: int64
      minimum: 0
      example: 12312

    End:
      type: integer
      description: The end position of the range on the reference, 0-based exclusive
      format: int64
      minimum: 0
      example: 99999

    Region:
      type: object
      description: A genomic region to return
      properties:
        referenceName:
          $ref: '#/components/schemas/ReferenceName'
        start:
          $ref: '#/components/schemas/Start'
        end:
          $ref: '#/components/schemas/End'
      required:
        - referenceName

    FieldsReads:
      type: array
      description: A list of SAM fields to include. By default, i.e., when fields is not specified, all fields will be included
      items:
        type: string        
        example: [QNAME, RNAME]
        enum:
          - QNAME
          - FLAG
          - RNAME
          - POS
          - MAPQ
          - CIGAR
          - RNEXT
          - PNEXT
          - TLEN
          - SEQ
          - QUAL
    
    TagsReads:
      type: array
      description: A list of SAM tags to include. By default, i.e., when tags is not specified, all tags will be included
      items:
        type: string
        example: [MD, NM]
    
    TagsVariants:
      type: array
      description: A list of tags to include, by default all
      items:
        type: string

    NoTagsReads:
      type: array
      description: A list of SAM tags to exclude. By default, i.e., when notags is not specified, no tags will be excluded
      items:
        type: string
        example: [OQ]
    
    NoTagsVariants:
      type: array
      description: A list of tags to exclude, default none

    RequestBody:
      type: object
      properties:
        regions:
          type: array
          description: A list of genomic regions to return. If not present, the entire file will be returned.
          items:
            $ref: '#/components/schemas/Region'

    RequestBodyReads:
      allOf:
        - type: object
          properties:
            format:
              $ref: '#/components/schemas/FormatReads'
            class:
              $ref: '#/components/schemas/Class'
            fields:
              $ref: '#/components/schemas/FieldsReads'
            tags:
              $ref: '#/components/schemas/TagsReads'
            notags:
              $ref: '#/components/schemas/NoTagsReads'
        - $ref: '#/components/schemas/RequestBody'

    RequestBodyVariants:
      allOf:
        - type: object
          properties:
            format:
              $ref: '#/components/schemas/FormatVariants'
            class:
              $ref: '#/components/schemas/Class'
            tags:
              $ref: '#/components/schemas/TagsVariants'
            notags:
              $ref: '#/components/schemas/NoTagsVariants'
        - $ref: '#/components/schemas/RequestBody'

    ServiceInfo:
      type: object
      '$ref': https://raw.githubusercontent.com/ga4gh-discovery/ga4gh-service-info/v1.0.0/service-info.yaml#/components/schemas/Service
    htsgetServiceInfo:
      allOf:
        - '$ref': '#/components/schemas/ServiceInfo'
        - type: object
          properties:
            htsget:
              type: object
              description: extended attributes for htsget
              properties:
                datatype:
                    type: string
                    description: >
                      Indicates the htsget datatype category ('reads' or 'variants')
                      served by the ticket endpoint related to this service-info
                      endpoint
                    enum: [reads, variants]
                    example: reads
                formats:
                  type: array
                  description: >
                    List of alignment or variant file formats supported
                    by the htsget endpoint. If absent, clients cannot make 
                    assumptions about what formats are supported ahead
                    of making a query.
                  items:
                    type: string
                    enum: [BAM, CRAM, VCF, BCF]
                fieldsParameterEffective:
                  type: boolean
                  description: >
                    Indicates whether the web service supports alignment field
                    inclusion/exclusion via the `fields` parameter. If absent,
                    clients cannot make assumptions about whether the `fields`
                    parameter is effective ahead of making a query.
                tagsParametersEffective:
                  type: boolean
                  description: >
                    Indicates whether the web service supports alignment tag
                    inclusion/exclusion via the `tags` and `notags` parameters.
                    If absent, clients cannot make assumptions about whether the
                    `tags` and `notags` parameters are effective ahead of making
                    a query.
        - type: object
          description: >
            This response extends the GA4GH Service Info specification
            with htsget-specific properties under the 'htsget' attribute.
            ServiceType 'artifact' property MUST be 'htsget' for both reads 
            and variants endpoints.
          required:
            - type
          properties:
            type:
              type: object
              required:
                - artifact
              properties:
                artifact:
                  type: string
                  enum: [htsget]
                  example: htsget

    Error:
      type: object
      description: Generic error response object
      required:
        - htsget
      properties:
        htsget:
          type: object
          description: Container for the error response object
          required:
            - error
            - message
          properties:
            error:
              type: string
              description: The type of error
            message:
              type: string
              description: A message specific to the error providing information on how to debug the problem. Clients MAY display this message to the user.
    InvalidAuthenticationError:
      allOf:
        - $ref: '#/components/schemas/Error'
        - type: object
          description: Authorization provided is invalid
          properties:
            htsget:
              properties:
                error:
                  example: InvalidAuthentication
                message:
                  example: Invalid authentication credentials provided
    PermissionDeniedError:
      allOf:
        - $ref: '#/components/schemas/Error'
        - type: object
          description: Authorization is required to access the resource
          properties:
            htsget:
              properties:
                error:
                  example: PermissionDenied
                message:
                  example: Client is not authorized to access this resource
    NotFoundError:
      allOf:
        - $ref: '#/components/schemas/Error'
        - type: object
          description: The resource requested was not found
          properties:
            htsget:
                properties:
                    error:
                        example: NotFound
                    message:
                        example: The requested resource could not be found
    UnsupportedFormatError:
      allOf:
        - $ref: '#/components/schemas/Error'
        - type: object
          description: The requested file format is not supported by the server
          properties:
            htsget:
              properties:
                error:
                  example: UnsupportedFormat
                message:
                  example: The requested file format is not supported by the server
    InvalidInputError:
      allOf:
        - $ref: '#/components/schemas/Error'
        - type: object
          description: The request parameters do not adhere to the specification
          properties:
            htsget:
              properties:
                error:
                  example: InvalidInput
                message:
                  example: The request parameters do not adhere to the specification
    InvalidRangeError:
      allOf:
        - $ref: '#/components/schemas/Error'
        - type: object
          description: The requested range cannot be satisfied
          properties:
            htsget:
              properties:
                error:
                  example: InvalidRange
                message:
                  example: The requested range cannot be satisfied
    PayloadTooLargeError:
      allOf:
        - $ref: '#/components/schemas/Error'
        - type: object
          description: POST request size is too large
          properties:
            htsget:
              properties:
                error:
                  example: PayloadTooLarge
                message:
                  example: POST request size is too large
    InternalServerError:
      allOf:
        - $ref: '#/components/schemas/Error'
        - type: object
          description: Internal server error
          properties:
            htsget:
              properties:
                error:
                  example: InternalServerError
                message:
                  example: An internal server error occurred

  parameters:
    idPathParam:
      in: path
      name: id
      description: read or variant object identifier
      required: true
      schema:
        type: string
    classParam:
      in: query
      name: class
      required: false
      schema:
        $ref: '#/components/schemas/Class'
    referenceNameParam:
      in: query
      name: referenceName
      required: false
      schema:
        $ref: '#/components/schemas/ReferenceName'
    startParam:
      in: query
      name: start
      required: false
      schema:
        $ref: '#/components/schemas/Start'
    endParam:
      in: query
      name: end
      required: false
      schema:
        $ref: '#/components/schemas/End'

  securitySchemes:
    htsget_auth:
      type: oauth2
      flows:
        authorizationCode:
          authorizationUrl: https://example.com/api/oauth/dialog
          tokenUrl: https://example.com/api/oauth/token
          scopes:
            read:genomic_reads: read access to genomic reads
            read:genomic_variants: read access to genomic variants

  responses:
    400BadRequestResponse:
      description: Bad request
      content:
        application/json:
          schema:
            oneOf:
              - $ref: '#/components/schemas/UnsupportedFormatError'
              - $ref: '#/components/schemas/InvalidInputError'
              - $ref: '#/components/schemas/InvalidRangeError'
    401UnauthorizedResponse:
      description: Unauthorized
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/InvalidAuthenticationError'
    403ForbiddenResponse:
      description: Forbidden
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/PermissionDeniedError'
    404NotFoundResponse:
      description: NotFound
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/NotFoundError'
    413PayloadTooLargeResponse:
      description: PayloadTooLarge
      content:
       application/json:
         schema:
           $ref: '#/components/schemas/PayloadTooLargeError'
    500InternalServerErrorResponse:
      description: Internal Server Error
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/InternalServerError'