DatasetItem

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/a-alpha-bio/refs/heads/main/json-schema/a-alpha-bio-dataset-item.json",
  "title": "DatasetItem",
  "description": "A single dataset item.",
  "x-generated": "2026-08-06",
  "x-method": "derived",
  "x-source": "openapi/a-alpha-bio-atlas-data-product-openapi-original.json#/components/schemas/DatasetItem",
  "properties": {
    "id": {
      "type": "string",
      "title": "Id",
      "description": "Dataset identifier",
      "examples": [
        "ab1001"
      ]
    },
    "name": {
      "type": "string",
      "title": "Name",
      "description": "Display name of the dataset",
      "examples": [
        "AlphaBlock 1001"
      ]
    },
    "experiment": {
      "type": "string",
      "title": "Experiment",
      "description": "Brief description of the experiment",
      "examples": [
        "This dataset explores the local affinity landscape..."
      ]
    },
    "details": {
      "type": "string",
      "title": "Details",
      "description": "Detailed description with bullet points",
      "examples": [
        "* Paratope coverage: >600 mutations..."
      ]
    },
    "modes": {
      "items": {
        "$ref": "#/$defs/DataMode"
      },
      "type": "array",
      "title": "Modes",
      "description": "Available data modes for this dataset",
      "examples": [
        [
          {
            "file_type": "csv.gz",
            "name": "source"
          },
          {
            "file_type": "csv.gz",
            "name": "ml"
          }
        ]
      ]
    },
    "release_date": {
      "type": "string",
      "title": "Release Date",
      "description": "Release date of the dataset",
      "examples": [
        "2024-01-15"
      ]
    },
    "version": {
      "type": "string",
      "title": "Version",
      "description": "Current version of the dataset",
      "examples": [
        "1"
      ]
    },
    "status": {
      "type": "string",
      "title": "Status",
      "description": "Workflow status of this dataset version (draft, pending_review, published, retracted). Non-published statuses are only ever returned to admins previewing with drafts included.",
      "default": "published",
      "examples": [
        "published",
        "draft"
      ]
    },
    "locked": {
      "type": "boolean",
      "title": "Locked",
      "description": "Whether the dataset is locked (user has no access to data)",
      "default": true,
      "examples": [
        false
      ]
    },
    "coming_soon": {
      "type": "boolean",
      "title": "Coming Soon",
      "description": "Whether the dataset is an upcoming release shown as a teaser. When true the metadata is visible but the data is not yet available to anyone; the card is always locked.",
      "default": false,
      "examples": [
        false
      ]
    },
    "url": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Url",
      "description": "URL to the dataset page in the web portal",
      "examples": [
        "https://data.aalphabio.tools/dataset/ab1001"
      ]
    },
    "structure_count": {
      "type": "integer",
      "title": "Structure Count",
      "description": "Number of structure files (.cif) available in the structures directory",
      "default": 0,
      "examples": [
        74973
      ]
    },
    "tasks": {
      "items": {
        "type": "string"
      },
      "type": "array",
      "title": "Tasks",
      "description": "List of task types for this dataset",
      "examples": [
        [
          "optimization",
          "design"
        ]
      ]
    },
    "binder": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Binder",
      "description": "Binder type for this dataset",
      "examples": [
        "VHH"
      ]
    },
    "target": {
      "items": {
        "type": "string"
      },
      "type": "array",
      "title": "Target",
      "description": "List of target types for this dataset",
      "examples": [
        [
          "viral",
          "COVID"
        ]
      ]
    },
    "product": {
      "type": "string",
      "title": "Product",
      "description": "Product slug for this dataset",
      "examples": [
        "atlas-vhh",
        "exclusive",
        "open-source"
      ]
    },
    "product_display_name": {
      "type": "string",
      "title": "Product Display Name",
      "description": "Human-readable product name",
      "examples": [
        "Atlas VHH Consortia",
        "Exclusive",
        "Open Source"
      ]
    },
    "product_kind": {
      "$ref": "#/$defs/ProductKind",
      "description": "Category of the dataset's product",
      "examples": [
        "consortium",
        "exclusive",
        "open-source"
      ]
    },
    "source": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Source",
      "description": "Product release name (for datasets in a named product release)",
      "examples": [
        "VHH Q1 2025"
      ]
    },
    "a_size": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "title": "A Size",
      "description": "Number of A (binder) sequences in the dataset",
      "examples": [
        500
      ]
    },
    "alpha_size": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "title": "Alpha Size",
      "description": "Number of Alpha (target) sequences in the dataset",
      "examples": [
        200
      ]
    },
    "total_ppi_count": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "title": "Total Ppi Count",
      "description": "Total number of protein-protein interactions measured",
      "examples": [
        100000
      ]
    },
    "unique_ppi_count": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "title": "Unique Ppi Count",
      "description": "Number of unique protein-protein interactions",
      "examples": [
        50000
      ]
    },
    "density": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "title": "Density",
      "description": "Fraction of (a_size * alpha_size) grid actually observed",
      "examples": [
        0.52
      ]
    },
    "tags": {
      "items": {
        "type": "string"
      },
      "type": "array",
      "title": "Tags",
      "description": "List of tags for this dataset",
      "examples": [
        [
          "dSSM",
          "optimization"
        ]
      ]
    },
    "has_tutorial": {
      "type": "boolean",
      "title": "Has Tutorial",
      "description": "Whether this dataset has a Jupyter notebook tutorial available",
      "default": false,
      "examples": [
        true
      ]
    }
  },
  "type": "object",
  "required": [
    "id",
    "name",
    "experiment",
    "details",
    "modes",
    "release_date",
    "version",
    "product",
    "product_display_name",
    "product_kind"
  ],
  "$defs": {
    "DataMode": {
      "properties": {
        "name": {
          "type": "string",
          "title": "Name",
          "description": "Mode name",
          "examples": [
            "source",
            "ml"
          ]
        },
        "file_type": {
          "type": "string",
          "title": "File Type",
          "description": "File type (csv or csv.gz)",
          "examples": [
            "csv.gz"
          ]
        }
      },
      "type": "object",
      "required": [
        "name",
        "file_type"
      ],
      "title": "DataMode",
      "description": "A data mode available for a dataset."
    },
    "ProductKind": {
      "type": "string",
      "enum": [
        "consortium",
        "exclusive",
        "licensable",
        "open-source"
      ],
      "title": "ProductKind",
      "description": "Category that a `product_types` row belongs to.\n\nStored on `ProductTypeEnum.kind`. Drives access control:\n\n- `open-source` bypasses license and subscription checks.\n- `consortium` gates access behind a `ProductSubscription` scoped to\n  the product (with `product_release.release_date` as the subscriber\n  gate); per-block `dataset_licenses` rows grant perpetual access.\n- `licensable` has no subscription path; access requires a\n  `dataset_licenses` row. Any number of companies can be licensed.\n- `exclusive` has no subscription path AND restricts licensing to a\n  single company — the dataset's `designer`. Exclusive blocks are\n  also always hidden from non-licensees (the\n  `metadata_visible_to_public` flag is ignored)."
    }
  }
}