## Start an ADME prediction

`$ boltz-api predictions:adme start`

**post** `/compute/v1/predictions/adme`

Submit a prediction job that returns Tier 1 ADME summary values for each requested molecule.

### Parameters

- `--input: object { molecules }`

- `--model: "adme-v1"`

  Model to use for prediction

- `--idempotency-key: optional string`

  Client-provided key to prevent duplicate submissions on retries

- `--workspace-id: optional string`

  Target workspace ID (admin keys only; ignored for workspace keys)

### Returns

- `PredictionAdmeStartResponse: object { id, completed_at, created_at, 12 more }`

  - `id: string`

    Unique prediction identifier

  - `completed_at: string`

  - `created_at: string`

  - `data_deleted_at: string`

    When the input/output data was deleted, or null if still available

  - `error: object { code, message, details }`

    Error details when failed

    - `code: string`

      Machine-readable error code

    - `message: string`

      Human-readable error message

    - `details: optional unknown`

      Additional field-level error details keyed by input path, when available.

  - `expires_at: string`

    When this resource and its associated data will be permanently deleted. Null while still in progress.

  - `input: object { molecules }`

    Prediction input (null if data deleted)

    - `molecules: array of object { smiles, id }`

      Molecules to score (1-128 per request). Results are returned in the same order as this list.

      - `smiles: string`

        SMILES string of the molecule to predict ADME properties for.

      - `id: optional string`

        Optional client-provided identifier. Returned as `external_id` in the matching output item.

  - `livemode: boolean`

    Whether this resource was created with a live API key.

  - `model: "adme-v1"`

    Model used for prediction

  - `output: object { molecules }`

    Prediction output when succeeded

    - `molecules: array of object { id, adme, error, 3 more }  or object { id, adme, error, 3 more }`

      Per-molecule results in the same order as the request. Successful molecules carry an `adme` summary. Failed molecules carry `status: "failed"` and a non-null `error`.

      - `AdmeMoleculeSucceeded: object { id, adme, error, 3 more }`

        - `id: string`

          Internally generated molecule identifier.

        - `adme: object { lipophilicity, permeability, solubility }`

          Tier 1 ADME summary values for this molecule.

          - `lipophilicity: number`

            Lipophilicity score from the internal LogD prediction.

          - `permeability: number`

            Permeability score for this molecule.

          - `solubility: "high-confidence" or "medium-confidence" or "high-risk"`

            Solubility judgement for this molecule.

            - `"high-confidence"`

            - `"medium-confidence"`

            - `"high-risk"`

        - `error: unknown`

        - `smiles: string`

          Echoed SMILES from the request.

        - `status: "succeeded"`

        - `external_id: optional string`

          Client-provided molecule identifier, if one was supplied.

      - `AdmeMoleculeFailed: object { id, adme, error, 3 more }`

        - `id: string`

          Internally generated molecule identifier.

        - `adme: unknown`

        - `error: object { code, message, details }`

          - `code: string`

            Machine-readable error code

          - `message: string`

            Human-readable error message

          - `details: optional unknown`

            Additional field-level error details keyed by input path, when available.

        - `smiles: string`

          Echoed SMILES from the request.

        - `status: "failed"`

        - `external_id: optional string`

          Client-provided molecule identifier, if one was supplied.

  - `started_at: string`

  - `status: "pending" or "running" or "succeeded" or "failed"`

    - `"pending"`

    - `"running"`

    - `"succeeded"`

    - `"failed"`

  - `version: string`

    Model version used for prediction

  - `workspace_id: string`

    Workspace ID

  - `idempotency_key: optional string`

    Client-provided idempotency key

### Example

```cli
boltz-api predictions:adme start \
  --api-key 'My API Key' \
  --input '{molecules: [{smiles: x}]}' \
  --model adme-v1
```

#### Response

```json
{
  "id": "id",
  "completed_at": "2019-12-27T18:11:19.117Z",
  "created_at": "2019-12-27T18:11:19.117Z",
  "data_deleted_at": "2019-12-27T18:11:19.117Z",
  "error": {
    "code": "code",
    "message": "message",
    "details": {}
  },
  "expires_at": "2019-12-27T18:11:19.117Z",
  "input": {
    "molecules": [
      {
        "smiles": "x",
        "id": "x"
      }
    ]
  },
  "livemode": true,
  "model": "adme-v1",
  "output": {
    "molecules": [
      {
        "id": "id",
        "adme": {
          "lipophilicity": 0,
          "permeability": 0,
          "solubility": "high-confidence"
        },
        "error": null,
        "smiles": "smiles",
        "status": "succeeded",
        "external_id": "external_id"
      }
    ]
  },
  "started_at": "2019-12-27T18:11:19.117Z",
  "status": "pending",
  "version": "version",
  "workspace_id": "workspace_id",
  "idempotency_key": "idempotency_key"
}
```