Generative Models

Explore SoTA Deep-Learning models for exploring novel chemical space

Capturing the complexity of novel chemical spaces requires advanced AI solutions to assist in generating diverse yet relevant molecular structures. Pending AI makes available a suite of pre-trained generative models, each designed with specific capabilities to address various drug discovery challenges.

Models can be fine-tuned to adapt to unique chemical subspaces, enhancing iteration speed for Hit Identification in early Drug Discovery. Contact us to learn more about custom model training and fine-tuning.

See here for more information on our Generative AI capability.

List models

get

Retrieve a list of models. Key-based pagination is supported. See query parameters for more details on how to retrieve the next or previous page of results.

Required scopes

This endpoint requires the following scopes:

Authorizations

OAuth2implicitRequired

OAuth2 authentication.

Authenticate using the Pending AI authorization server through an implicit OAuth2 flow. You will be redirected to a Pending AI login page to authenticate and authorize access to your account. After authorization, you will be redirected back to the original application with an access token. Ensure that the application is registered with Pending AI and/or that the correct redirect URI is configured. Contact Pending AI support for more information if the application is not registered.

Authorization URL:

AuthorizationstringRequired

Bearer token authentication.

Provide a valid Pending AI authentication token. Generating tokens can be done manually through the Pending AI CLI. Ensure you have an existing account or register now.

pendingai auth login
pendingai auth token

Query parameters

limitinteger · min: 1 · max: 100Optional

Limit the number of resources returned within the data field of the paged response. The field may contain fewer items than the specified limit when there are not enough items to return.

Default: 5Example: 5

next-pageany ofOptional

A key used to navigate pagination results. The given value must match an id for the specific resource object type. If provided, the paged response will contain resources from the next 'page', or those that were submitted before the matched resource (reverse chronological order).

Example: id_32RD0TWLolsAdFKufk3p4eE1ttK

string · min: 1 · max: 255OptionalPattern: ^\w+$

nullOptional

prev-pageany ofOptional

A key used to navigate pagination results. The given value must match an id for the specific resource object type. If provided, the paged response will contain resources from the previous 'page', or those that were submitted after the matched resource (reverse chronological order).

Example: id_32RD0TWLolsAdFKufk3p4eE1ttK

string · min: 1 · max: 255OptionalPattern: ^\w+$

nullOptional

Responses

200

Returns a list of models.

application/json

has_morebooleanRequired

A boolean flag that indicates whether there are more items available to be fetched on subsequent pages. Used for pagination control.

objectstringOptional

The type of resource.

Default: listPattern: ^\w+$

422

Validation Error

application/json

500

Response Validation Error

application/json

get

/models

GET /generator/v1/models HTTP/1.1
Host: api.pending.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

{
  "data": [
    {
      "description": "Model Description.",
      "id": "id_32RD0TWLolsAdFKufk3p4eE1ttK",
      "metadata": {
        "parameters": 124000000,
        "training_time": "2d"
      },
      "name": "Model Name",
      "object": "object",
      "summary": {
        "accuracy": 0.95,
        "loss": 0.05,
        "sampling_time": "100ms"
      },
      "version": "v1.0.0/beta"
    }
  ],
  "has_more": true,
  "object": "list"
}

Retrieve a model

get

Retrieves a model and a detailed overview of its different features. Model information can optionally include metadata and summary statistics with other identifiable fields.

Required scopes

This endpoint requires the following scopes:

Authorizations

OAuth2implicitRequired

OAuth2 authentication.

Authorization URL:

AuthorizationstringRequired

Bearer token authentication.

Provide a valid Pending AI authentication token. Generating tokens can be done manually through the Pending AI CLI. Ensure you have an existing account or register now.

pendingai auth login
pendingai auth token

Path parameters

model_idstring · min: 1 · max: 255Required

A unique identifier for a model resource.

Example: mod_32RD0TWLolsAdFKufk3p4eE1ttKPattern: ^\w+$

Responses

200

Returns the model.

application/json

A model resource represents a machine learning model that can be used for generating samples of molecular structures in batches of SMILES strings. Each model leverages a specific architecture and set of parameters to produce novel and diverse molecules.

descriptionany ofOptional

Optional description for the model.

Example: Model Description.

stringOptionalPattern: ^[A-Za-z0-9\s.,;:!?]+$

nullOptional

idstringRequired

The unique resource identifier.

Example: id_32RD0TWLolsAdFKufk3p4eE1ttKPattern: ^\w+$

nameany ofOptional

Optional name for the model.

Example: Model Name

stringOptionalPattern: ^[A-Za-z0-9\s.,;:!?]+$

nullOptional

objectstringRequired

The type of resource.

Example: objectPattern: ^\w+$

versionany ofOptional

Optional version for the model.

Example: v1.0.0/beta

stringOptionalPattern: ^[A-Za-z0-9\s.,;:!?]+$

nullOptional

404

Model resource not found.

application/json

422

Validation Error

application/json

500

Response Validation Error

application/json

get

/models/{model_id}

GET /generator/v1/models/{model_id} HTTP/1.1
Host: api.pending.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

{
  "description": "Model Description.",
  "id": "id_32RD0TWLolsAdFKufk3p4eE1ttK",
  "metadata": {
    "parameters": 124000000,
    "training_time": "2d"
  },
  "name": "Model Name",
  "object": "object",
  "summary": {
    "accuracy": 0.95,
    "loss": 0.05,
    "sampling_time": "100ms"
  },
  "version": "v1.0.0/beta"
}

Retrieve a model status

get

Retrieve the status of a model. Sampling is made available by the Pending AI platform and may be affected by heavy traffic or resource constraints. Check the status of a model before sampling to ensure it is available.

Required scopes

This endpoint requires the following scopes:

Authorizations

OAuth2implicitRequired

OAuth2 authentication.

Authorization URL:

AuthorizationstringRequired

Bearer token authentication.

Provide a valid Pending AI authentication token. Generating tokens can be done manually through the Pending AI CLI. Ensure you have an existing account or register now.

pendingai auth login
pendingai auth token

Path parameters

model_idstring · min: 1 · max: 255Required

A unique identifier for a model resource.

Example: mod_32RD0TWLolsAdFKufk3p4eE1ttKPattern: ^\w+$

Responses

200

Returns the model status.

application/json

Output model for retrieving the status of a model.

statusstring · enumRequired

The status of the model. Requesting samples from the model depends on the model being online. Generating structures can also timeout or be unavailable if the model is offline.

Possible values:

404

Model resource not found.

application/json

422

Validation Error

application/json

500

Response Validation Error

application/json

get

/models/{model_id}/status

GET /generator/v1/models/{model_id}/status HTTP/1.1
Host: api.pending.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

{
  "status": "online"
}

Last updated 5 months ago

Was this helpful?

hashtagList models

hashtagRetrieve a model

hashtagRetrieve a model status

List models

Retrieve a model

Retrieve a model status