{ "openapi": "3.0.1", "info": { "title": "Europe PMC — Biomedical Knowledge Graph & Literature Mining", "description": "Turn a biomedical topic into a knowledge graph and evidence corpus from Europe PMC. Mines genes, diseases, chemicals, organisms and deposited datasets (GEO, ENA, PDB) from full text, builds entity co-occurrence networks, tracks emerging entities, and exports Neo4j/Gephi CSV. No API key.", "version": "1.1", "x-build-id": "s9BtAu8Z5PKANi8qR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ryanclinton~europe-pmc-search/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ryanclinton-europe-pmc-search", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ryanclinton~europe-pmc-search/runs": { "post": { "operationId": "runs-sync-ryanclinton-europe-pmc-search", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ryanclinton~europe-pmc-search/run-sync": { "post": { "operationId": "run-sync-ryanclinton-europe-pmc-search", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "query" ], "properties": { "query": { "title": "Search Query", "type": "string", "description": "Search query. Supports free text and field-specific syntax like TITLE:\"term\", AUTH:\"name\", DOI:10.xxx", "default": "CRISPR gene editing" }, "queryPreset": { "title": "Query Preset", "enum": [ "general", "clinical_trials", "reviews_only", "preprints_only", "open_full_text", "datasets_available", "recent_high_impact" ], "type": "string", "description": "Expert query construction without the Lucene syntax. Adds the right Europe PMC filters on top of your query. clinical_trials / reviews_only restrict by publication type; preprints_only = bioRxiv/medRxiv; open_full_text = open-access full text in Europe PMC; datasets_available = papers with deposited data accessions; recent_high_impact = last 5 years sorted by citations.", "default": "general" }, "author": { "title": "Author Name", "type": "string", "description": "Filter by author name (e.g. \"Smith J\")" }, "journal": { "title": "Journal Name", "type": "string", "description": "Filter by journal name (e.g. \"Nature\")" }, "dateFrom": { "title": "Date From", "type": "string", "description": "Start date in YYYY-MM-DD format" }, "dateTo": { "title": "Date To", "type": "string", "description": "End date in YYYY-MM-DD format" }, "openAccessOnly": { "title": "Open Access Only", "type": "boolean", "description": "Only return open access publications", "default": false }, "source": { "title": "Source Database", "enum": [ "", "MED", "PMC", "PPR" ], "type": "string", "description": "Filter by source database", "default": "" }, "sortBy": { "title": "Sort By", "enum": [ "RELEVANCE", "CITED desc", "P_PDATE_D desc" ], "type": "string", "description": "Sort order for results" }, "maxResults": { "title": "Max Results", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of results to return (max 500)", "default": 50 }, "includeMinedEntities": { "title": "Mine biological entities (full-text)", "type": "boolean", "description": "Fetch text-mined biological entities (genes, proteins, diseases, chemicals, organisms, data accessions) extracted from each paper's full text via the Europe PMC Annotations API. Adds the minedEntities and accessions fields. Makes extra API calls (one batch per ~8 papers), so it is off by default.", "default": false }, "entityRollup": { "title": "Entity rollup records", "type": "boolean", "description": "Emit per-entity aggregate records (recordType 'entity') across the result set — genes, diseases, chemicals, organisms, and datasets (accessions) with paper counts, summed citations, and example papers. Answers 'which genes/diseases/datasets dominate this topic'. Enables entity mining automatically.", "default": false }, "includeNetworks": { "title": "Entity co-occurrence network", "type": "boolean", "description": "Emit entity co-occurrence edge records (recordType 'edge', e.g. TP53 — glioblastoma with a co-occurrence weight) plus nodes.csv and edges.csv in the key-value store, ready for Neo4j / Gephi / Cytoscape / GraphRAG. Enables entity mining automatically.", "default": false }, "emitSummary": { "title": "Emit corpus summary record", "type": "boolean", "description": "Append a run-level summary record (recordType 'summary') with corpus composition: preprint vs peer-reviewed share, open-access share, top MeSH topics, top funders, top mined entities, and most-referenced datasets. Also mirrored to the SUMMARY key-value store key.", "default": true }, "outputProfile": { "title": "Output Profile", "enum": [ "standard", "compact" ], "type": "string", "description": "standard returns the full record. compact drops the authors list, abstract, and per-paper entity arrays (keeping counts) for lean agent / LLM consumption.", "default": "standard" }, "flattenForCsv": { "title": "Flatten for CSV", "type": "boolean", "description": "Flatten nested arrays and objects to delimited strings (authors, MeSH terms, funders, mined entities become single columns) for clean CSV / spreadsheet export.", "default": false } } }, "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 } } } } } } } } } }