Generated Data Catalog

Generated Data catalog for Data Generation output available to your account. The catalog call itself does not deduct Wallet Credits.

GET/v2/datasets/catalog

Generated Data Catalog

Returns current Generated Data rows visible to your account and the protein UUIDs you can use for data access.

cURL
curl -G https://api.omtx.ai/v2/datasets/catalog \
  -H "x-api-key: YOUR_API_KEY"
Response
{
  "catalog": {
    "items": [
      {
        "dataset_id": "dataset-generated-v2",
        "protein_uuid": "43d75238-ae2a-5935-8ade-30115565034e",
        "protein_name": "Generated Protein",
        "uniprot_id": null,
        "sequence": null,
        "vintage": "20260201_om1",
        "vintage_id": "9512ba4b-8a67-4310-9100-fcb6fb06cf70",
        "is_public": false,
        "num_data_points": 83143571,
        "num_actives": 450612,
        "num_inactives": 82692959
      }
    ],
    "count": 1
  },
  "data_generated": {
    "items": [
      {
        "protein_uuid": "43d75238-ae2a-5935-8ade-30115565034e",
        "protein_name": "Generated Protein",
        "generation_status": "ready",
        "license_kind": "data_generation",
        "dataset_id": "dataset-generated-v2",
        "latest_vintage_id": "9512ba4b-8a67-4310-9100-fcb6fb06cf70",
        "latest_vintage": "20260201_om1",
        "is_public": false,
        "num_data_points": 83143571,
        "num_actives": 450612,
        "num_inactives": 82692959
      }
    ],
    "count": 1
  },
  "accessible_generated_protein_uuids": [
    "43d75238-ae2a-5935-8ade-30115565034e"
  ],
  "accessible_dataset_ids": [
    "dataset-generated-v2"
  ]
}
  • No Wallet Credits charge for catalog discovery.
  • catalog is retained for response compatibility and is scoped to the Generated Data rows available to this account; current Data Access workflows use data_generated.
  • data_generated contains Generated Data rows you can currently use
  • accessible_generated_protein_uuids is the deduplicated list of Generated Data protein UUIDs available to your account right now
  • dataset_id, latest_vintage, and latest_vintage_id are provenance metadata for the current data version Om resolved for that protein.
  • accessible_dataset_ids is compatibility metadata for the current resolved data versions; do not use dataset IDs as request inputs.
  • Generated Data downloads require qualifying Data Generation output for that protein_uuid.
  • Use a Generated Data protein_uuid with client.load_binders(...) / client.load_nonbinders(...) (recommended) or /v2/data-access/shards for direct signed URL access.
  • In the app, use Generate > Generated Models for account-accessible protein-specific model discovery; programmatically, use client.models.catalog() / /v2/models/catalog. Use this catalog for Generated Data access.

Response Fields

  • catalog.items[] --- Scoped compatibility rows derived from the same accessible Generated Data set; current Data Access workflows use data_generated.items[]
  • catalog.count --- Number of scoped compatibility catalog rows
  • data_generated.items[] --- Generated Data rows currently available to your account
  • data_generated.count --- Number of user generation rows
  • accessible_generated_protein_uuids[] --- Deduplicated list of Generated Data protein UUIDs available to your account
  • data_generated.items[].dataset_id --- Provenance metadata for the current data version; not a request input
  • data_generated.items[].latest_vintage / latest_vintage_id --- Current data version label and ID for reproducibility
  • accessible_dataset_ids[] --- Compatibility metadata for current resolved data versions; requests still use protein_uuid only

Python SDK

Python
from omtx import OmClient

client = OmClient(api_key="YOUR_API_KEY")

# Get Generated Data catalog payload
catalog = client.datasets.catalog()

print(f"Generated Data rows: {catalog['data_generated']['count']}")
print(f"Generated Data protein UUIDs: {len(catalog['accessible_generated_protein_uuids'])}")

# Recommended next step: load binder/non-binder pools from Generated Data
items = catalog["data_generated"]["items"]
if not items:
    raise RuntimeError("No Generated Data is available for this API key.")

binders = client.load_binders(
    protein_uuid=items[0]["protein_uuid"],
    n=1000,
    sample_seed=42,
)
nonbinders = client.load_nonbinders(
    protein_uuid=items[0]["protein_uuid"],
    n=10000,
    sample_seed=42,
)
print("Loaded shapes:", binders.shape, nonbinders.shape)