{ "openapi": "3.0.1", "info": { "title": "Beacon v2 Genomics Extractor", "description": "Point at ANY GA4GH Beacon v2 endpoint (Progenetix, Cancer Cell Lines, ELIXIR/BSC) and pull biosamples, individuals, genomic variants, cohorts, datasets or filtering terms into clean flat rows. Auto-detects skip/limit paging, keeps the full record in _raw. Pay per record.", "version": "0.1", "x-build-id": "kt6LrHWs6RwQBdB3d" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datamule~beacon-v2-genomics-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datamule-beacon-v2-genomics-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datamule~beacon-v2-genomics-extractor/runs": { "post": { "operationId": "runs-sync-datamule-beacon-v2-genomics-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datamule~beacon-v2-genomics-extractor/run-sync": { "post": { "operationId": "run-sync-datamule-beacon-v2-genomics-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "sources" ], "properties": { "sources": { "title": "Beacon v2 base URL(s)", "type": "array", "description": "One or more GA4GH Beacon v2 base/root URLs. Examples: https://progenetix.org/beacon (Progenetix), https://cancercelllines.org/beacon (Cancer Cell Lines), https://beacons.bsc.es/beacon/v2.0.0 (ELIXIR Spain / BSC). Point at the beacon BASE — do NOT append an endpoint like /biosamples.", "items": { "type": "string" } }, "endpoint": { "title": "Endpoint (entry type)", "enum": [ "biosamples", "individuals", "g_variants", "analyses", "runs", "cohorts", "datasets", "filtering_terms", "info", "configuration", "entry_types", "map" ], "type": "string", "description": "Which Beacon v2 endpoint to query. Record endpoints (biosamples, individuals, g_variants, analyses, runs) emit one row per matched record and are paginated. Collection endpoints (cohorts, datasets) emit one row per collection. filtering_terms lists a beacon's queryable ontology terms. info / configuration / entry_types / map are single-object discovery maps of what a beacon exposes.", "default": "biosamples" }, "filters": { "title": "Filters (ontology term IDs)", "type": "array", "description": "Optional Beacon filtering terms — CURIE-style ontology IDs applied to record queries, e.g. NCIT:C7376 (a cancer type), or an ICD-O / UBERON / EFO term. Some beacons (the bycon family: Progenetix, Cancer Cell Lines) REQUIRE at least one filter to return biosample/individual records (an unfiltered query returns HTTP 422 \"no valid query\"). Use filtering_terms mode to discover valid IDs for a beacon. Leave empty for beacons that serve records unfiltered (e.g. ELIXIR/BSC).", "items": { "type": "string" } }, "requestParameters": { "title": "Request parameters (optional)", "type": "object", "description": "Optional extra Beacon query parameters as a JSON object, applied to every request. For g_variants (genomic variant) queries the range model uses e.g. {\"referenceName\": \"9\", \"start\": \"21000000\", \"end\": \"22000000\", \"variantType\": \"DEL\"}. The paging skip/limit and requestedGranularity are managed for you." }, "granularity": { "title": "Granularity", "enum": [ "record", "count", "boolean", "aggregated" ], "type": "string", "description": "Beacon requestedGranularity. \"record\" (default) returns full records; \"count\" / \"boolean\" return only aggregate discovery answers (numTotalResults / exists) with no patient-level data — many beacons only permit these for protected datasets. \"aggregated\" returns summary counts.", "default": "record" }, "maxRecords": { "title": "Max records (total)", "minimum": 1, "type": "integer", "description": "Maximum total number of rows to emit across all sources. skip/limit paging is followed until this cap is reached, so a huge beacon never runs forever. Each returned row is one billable event. Default 1000.", "default": 1000 }, "bearerToken": { "title": "Bearer token (optional)", "type": "string", "description": "Optional OAuth2 bearer token for auth-gated beacons that expose protected datasets. Sent as Authorization: Bearer ***. NOT required for public beacons (Progenetix, Cancer Cell Lines, ELIXIR/BSC) — leave empty. Never logged." }, "extraHeaders": { "title": "Extra request headers", "type": "object", "description": "Optional extra HTTP headers to send with every request, as a JSON object, e.g. an API-key header a specific beacon node requires. Leave empty for public beacons." } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }