PubChem Structure Search API

openapi: 3.0.3
info:
  title: PubChem PUG REST Compounds Structure Search API
  description: 'PUG REST is a REST-style version of PUG (Power User Gateway), a web interface for accessing PubChem data and services. PUG REST provides access to the data in PubChem Compounds as well as specialized chemical structure search services.


    The service supports various input formats including chemical names, SMILES strings, InChI identifiers, and direct database identifiers. It can return data in multiple formats including JSON, XML, CSV, SDF, and PNG images.

    '
  version: 1.0.0
  contact:
    email: pubchem-help@ncbi.nlm.nih.gov
  license:
    name: Public Domain
    url: https://www.ncbi.nlm.nih.gov/home/about/policies/
servers:
- url: https://pubchem.ncbi.nlm.nih.gov/rest/pug
  description: PubChem PUG REST API
tags:
- name: Structure Search
  description: Chemical structure search operations
paths:
  /compound/fastsubstructure/smiles/{smiles}/cids/{format}:
    get:
      tags:
      - Structure Search
      summary: Substructure search by SMILES
      description: Perform substructure search using SMILES string
      parameters:
      - name: smiles
        in: path
        required: true
        schema:
          type: string
        description: SMILES string (URL-encoded)
        example: C3=NC1=C(C=NC2=C1C=NC=C2)[N]3
      - name: format
        in: path
        required: true
        schema:
          type: string
          enum:
          - XML
          - JSON
          - JSONP
          - ASNT
          - ASNB
          default: JSON
        description: Output format
      - name: MatchIsotopes
        in: query
        schema:
          type: boolean
          default: false
        description: Atoms must be of the specified isotope
      - name: MatchCharges
        in: query
        schema:
          type: boolean
          default: false
        description: Atoms must match the specified charge
      - name: RingsNotEmbedded
        in: query
        schema:
          type: boolean
          default: false
        description: Rings may not be embedded in a larger system
      - name: SingleDoubleBondsMatch
        in: query
        schema:
          type: boolean
          default: true
        description: Single or double bonds match aromatic bonds
      - name: ChainsMatchRings
        in: query
        schema:
          type: boolean
          default: true
        description: Chain bonds in query may match rings in hits
      - name: StripHydrogen
        in: query
        schema:
          type: boolean
          default: false
        description: Remove explicit hydrogens before searching
      - name: Stereo
        in: query
        schema:
          type: string
          enum:
          - ignore
          - exact
          - relative
          - nonconflicting
          default: ignore
        description: How to handle stereo
      - name: MaxSeconds
        in: query
        schema:
          type: integer
        description: Maximum search time in seconds
      - name: MaxRecords
        in: query
        schema:
          type: integer
          default: 2000000
        description: Maximum number of hits
      - name: listkey
        in: query
        schema:
          type: string
        description: Restrict to matches within hits from prior search
      - name: callback
        in: query
        schema:
          type: string
        description: Callback function name for JSONP format
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/IdentifierList'
        '400':
          $ref: '#/components/responses/BadRequest'
        '404':
          $ref: '#/components/responses/NotFound'
        '503':
          $ref: '#/components/responses/ServiceUnavailable'
        '504':
          $ref: '#/components/responses/Timeout'
  /compound/fastsuperstructure/cid/{cid}/cids/{format}:
    get:
      tags:
      - Structure Search
      summary: Superstructure search by CID
      description: Perform superstructure search using compound CID
      parameters:
      - name: cid
        in: path
        required: true
        schema:
          type: integer
        description: Compound ID (CID)
        example: 2244
      - name: format
        in: path
        required: true
        schema:
          type: string
          enum:
          - XML
          - JSON
          - JSONP
          - ASNT
          - ASNB
          default: JSON
        description: Output format
      - name: MatchIsotopes
        in: query
        schema:
          type: boolean
          default: false
        description: Atoms must be of the specified isotope
      - name: MatchCharges
        in: query
        schema:
          type: boolean
          default: false
        description: Atoms must match the specified charge
      - name: MaxSeconds
        in: query
        schema:
          type: integer
        description: Maximum search time in seconds
      - name: MaxRecords
        in: query
        schema:
          type: integer
          default: 2000000
        description: Maximum number of hits
      - name: callback
        in: query
        schema:
          type: string
        description: Callback function name for JSONP format
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/IdentifierList'
        '400':
          $ref: '#/components/responses/BadRequest'
        '404':
          $ref: '#/components/responses/NotFound'
        '503':
          $ref: '#/components/responses/ServiceUnavailable'
        '504':
          $ref: '#/components/responses/Timeout'
  /compound/fastsimilarity_2d/cid/{cid}/cids/{format}:
    get:
      tags:
      - Structure Search
      summary: 2D similarity search by CID
      description: Perform 2D similarity search using compound CID
      parameters:
      - name: cid
        in: path
        required: true
        schema:
          type: integer
        description: Compound ID (CID)
        example: 2244
      - name: format
        in: path
        required: true
        schema:
          type: string
          enum:
          - XML
          - JSON
          - JSONP
          - ASNT
          - ASNB
          default: JSON
        description: Output format
      - name: Threshold
        in: query
        schema:
          type: integer
          minimum: 0
          maximum: 100
          default: 90
        description: Minimum Tanimoto score for a hit
      - name: MaxSeconds
        in: query
        schema:
          type: integer
        description: Maximum search time in seconds
      - name: MaxRecords
        in: query
        schema:
          type: integer
          default: 2000000
        description: Maximum number of hits
      - name: listkey
        in: query
        schema:
          type: string
        description: Restrict to matches within hits from prior search
      - name: callback
        in: query
        schema:
          type: string
        description: Callback function name for JSONP format
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/IdentifierList'
        '400':
          $ref: '#/components/responses/BadRequest'
        '404':
          $ref: '#/components/responses/NotFound'
        '503':
          $ref: '#/components/responses/ServiceUnavailable'
        '504':
          $ref: '#/components/responses/Timeout'
  /compound/fastidentity/smiles/{smiles}/cids/{format}:
    get:
      tags:
      - Structure Search
      summary: Identity search by SMILES
      description: Perform identity search using SMILES string
      parameters:
      - name: smiles
        in: path
        required: true
        schema:
          type: string
        description: SMILES string (URL-encoded)
        example: CCCCC
      - name: format
        in: path
        required: true
        schema:
          type: string
          enum:
          - XML
          - JSON
          - JSONP
          - ASNT
          - ASNB
          default: JSON
        description: Output format
      - name: identity_type
        in: query
        schema:
          type: string
          enum:
          - same_connectivity
          - same_tautomer
          - same_stereo
          - same_isotope
          - same_stereo_isotope
          - nonconflicting_stereo
          - same_isotope_nonconflicting_stereo
          default: same_stereo_isotope
        description: Type of identity matching
      - name: MaxSeconds
        in: query
        schema:
          type: integer
        description: Maximum search time in seconds
      - name: MaxRecords
        in: query
        schema:
          type: integer
          default: 2000000
        description: Maximum number of hits
      - name: listkey
        in: query
        schema:
          type: string
        description: Restrict to matches within hits from prior search
      - name: callback
        in: query
        schema:
          type: string
        description: Callback function name for JSONP format
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/IdentifierList'
        '400':
          $ref: '#/components/responses/BadRequest'
        '404':
          $ref: '#/components/responses/NotFound'
        '503':
          $ref: '#/components/responses/ServiceUnavailable'
        '504':
          $ref: '#/components/responses/Timeout'
  /compound/fastformula/{formula}/cids/{format}:
    get:
      tags:
      - Structure Search
      summary: Molecular formula search
      description: Perform molecular formula search
      parameters:
      - name: formula
        in: path
        required: true
        schema:
          type: string
        description: Molecular formula
        example: C10H21N
      - name: format
        in: path
        required: true
        schema:
          type: string
          enum:
          - XML
          - JSON
          - JSONP
          - ASNT
          - ASNB
          default: JSON
        description: Output format
      - name: AllowOtherElements
        in: query
        schema:
          type: boolean
          default: false
        description: Allow other elements to be present in addition to those specified
      - name: MaxSeconds
        in: query
        schema:
          type: integer
        description: Maximum search time in seconds
      - name: MaxRecords
        in: query
        schema:
          type: integer
          default: 2000000
        description: Maximum number of hits
      - name: listkey
        in: query
        schema:
          type: string
        description: Restrict to matches within hits from prior search
      - name: callback
        in: query
        schema:
          type: string
        description: Callback function name for JSONP format
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/IdentifierList'
        '400':
          $ref: '#/components/responses/BadRequest'
        '404':
          $ref: '#/components/responses/NotFound'
        '503':
          $ref: '#/components/responses/ServiceUnavailable'
        '504':
          $ref: '#/components/responses/Timeout'
components:
  schemas:
    IdentifierList:
      type: object
      description: List of identifiers
      properties:
        IdentifierList:
          type: object
          properties:
            CID:
              type: array
              items:
                type: integer
            SID:
              type: array
              items:
                type: integer
            AID:
              type: array
              items:
                type: integer
            ListKey:
              type: string
            CacheKey:
              type: string
            Size:
              type: integer
    Fault:
      type: object
      description: Error response
      properties:
        Fault:
          type: object
          properties:
            Code:
              type: string
            Message:
              type: string
            Details:
              type: array
              items:
                type: string
  responses:
    Timeout:
      description: The request timed out, from server overload or too broad a request
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Fault'
        application/xml:
          schema:
            $ref: '#/components/schemas/Fault'
    NotFound:
      description: The input record was not found (e.g. invalid CID)
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Fault'
        application/xml:
          schema:
            $ref: '#/components/schemas/Fault'
    ServiceUnavailable:
      description: Too many requests or server is busy, retry later
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Fault'
        application/xml:
          schema:
            $ref: '#/components/schemas/Fault'
        text/html:
          schema:
            type: string
    BadRequest:
      description: Request is improperly formed (syntax error in the URL, POST body, etc.)
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Fault'
        application/xml:
          schema:
            $ref: '#/components/schemas/Fault'