Pricing

from $2.00 / 1,000 paper fetcheds

Europe PMC — Biomedical Knowledge Graph & Literature Mining

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.

Pricing

from $2.00 / 1,000 paper fetcheds

Rating

0.0

(0)

Developer

Ryan Clinton

Actor stats

Bookmarked

Total users

Monthly active users

10 days ago

Last modified

Categories

Developer tools

recordType

Optional

Record discriminator. Stable enum: 'paper' (a publication), 'entity' (a gene/disease/chemical/organism/dataset aggregate across the result set), 'edge' (an entity co-occurrence link), 'summary' (run-level corpus composition), 'error'.

Type:string | null

entityType

Optional

On entity records: stable enum 'gene', 'disease', 'chemical', 'organism', 'accession' (dataset).

Type:string | null

name

Optional

On entity records: the entity name (e.g. 'TP53', 'glioblastoma', 'GSE181897').

Type:string | null

paperCount

Optional

On entity records: number of papers in the result set mentioning this entity.

Type:integer | null

totalCitations

Optional

On entity records: summed citations of the papers mentioning this entity.

Type:integer | null

firstYear

Optional

On entity records: earliest publication year mentioning this entity (within the result set).

Type:integer | null

lastYear

Optional

On entity records: latest publication year mentioning this entity (within the result set).

Type:integer | null

recentPaperCount

Optional

On entity records: papers mentioning this entity in the recent 2-year window.

Type:integer | null

priorPaperCount

Optional

On entity records: papers mentioning this entity in the prior 2-year window.

Type:integer | null

trend

Optional

On entity records: stable enum 'rising', 'stable', 'falling', 'new', 'insufficient-data' (recent vs prior window, within the result set).

Type:string | null

topCoOccurring

Optional

On entity records: up to 5 top co-occurring entities { name, entityType, weight } (only when includeNetworks is on).

Type:

exampleCanonicalIds

Optional

On entity records: up to 5 example paper canonicalIds mentioning this entity.

Type:

sourceType

Optional

On edge records: entity type of the edge source.

Type:string | null

target

Optional

On edge records: the target entity name.

Type:string | null

targetType

Optional

On edge records: entity type of the edge target.

Type:string | null

relationship

Optional

On edge records: relationship type for graph import. Additive enum (currently 'CO_OCCURS').

Type:string | null

weight

Optional

On edge records: co-occurrence count (papers mentioning both entities).

Type:integer | null

normalizedWeight

Optional

On edge records: weight normalized 0-100 against the strongest edge, for visualization.

Type:integer | null

failureType

Optional

On error records only. Stable enum: 'invalid-input' (bad/missing query), 'runtime-error' (unexpected failure). Absent on paper/summary records.

Type:string | null

pmid

Optional

PubMed ID

Type:string | null

pmcid

Optional

PubMed Central ID

Type:string | null

doi

Optional

Digital Object Identifier

Type:string | null

title

Optional

Title of the publication

Type:string | null

authorString

Optional

Comma-separated author names

Type:string | null

authors

Optional

List of authors with details

Type:

journalTitle

Optional

Journal title

Type:string | null

journalVolume

Optional

Journal volume

Type:string | null

journalIssue

Optional

Journal issue

Type:string | null

pageInfo

Optional

Page numbers

Type:string | null

pubYear

Optional

Publication year

Type:string | null

firstPublicationDate

Optional

Date of first publication

Type:string | null

abstractText

Optional

Abstract text

Type:string | null

citedByCount

Optional

Number of citations

Type:integer | null

isOpenAccess

Optional

Whether the publication is open access

Type:boolean | null

inPMC

Optional

Whether available in PubMed Central

Type:boolean | null

inEPMC

Optional

Whether available in Europe PMC

Type:boolean | null

source

Optional

Source database (MED = PubMed, PMC = full text, PPR = preprint, AGR = Agricola, etc.)

Type:string | null

canonicalId

Optional

Single best cross-system join key, prefixed by scheme: doi: > pmid: > pmcid: > source:id.

Type:string | null

isPreprint

Optional

True when the record is a preprint (source PPR — bioRxiv / medRxiv / Research Square). PubMed does not index these.

Type:boolean | null

publicationStatus

Optional

Stable enum: 'preprint' (not yet peer-reviewed) or 'peer-reviewed'.

Type:string | null

isReview

Optional

Factual flag: the publication type includes 'review'. A convenience filter, not an evidence grade.

Type:boolean | null

isClinicalTrial

Optional

Factual flag: the publication type includes 'clinical trial'. A convenience filter, not an evidence grade.

Type:boolean | null

accessLevel

Optional

Can the full text be read? Stable enum: 'open-fulltext' (open-access full text in Europe PMC), 'restricted-fulltext' (full text exists behind access), 'abstract-only'.

Type:string | null

pubType

Optional

Publication types

Type:

meshTerms

Optional

MeSH descriptor terms

Type:

grants

Optional

Funder / grant linkage: array of { agency, grantId }.

Type:

funders

Optional

Distinct funding agency names behind the paper.

Type:

accessions

Optional

Deposited dataset / sequence accessions text-mined from the paper (ENA, PDB, UniProt, GEO, ArrayExpress). Array of { name, count, uri }. Populated only when includeMinedEntities is on.

Type:

accessionCount

Optional

Number of distinct data accessions referenced by the paper.

Type:integer | null

minedEntities

Optional

Text-mined biological entities bucketed by ontology type: genesProteins, diseases, chemicals, organisms, cellTypes, goTerms, other. Each a { name, count, uri } array. Null unless includeMinedEntities is on.

Type:

minedEntityCount

Optional

Total distinct mined entities (including accessions) for the paper.

Type:integer | null

completeness

Optional

Deterministic metadata-completeness signal: { score (0-1, fraction of 7 key fields present), hasDoi, hasAbstract, hasMeshTerms, hasAffiliations, hasFullText, hasFunding, hasDataAccessions }. Filter reliable records by completeness.score.

Type:

emergingEntities

Optional

On the summary record (when entityRollup is on and the corpus spans 2+ years): biological entities rising in the recent window vs the prior window — { windowNote, genes[], diseases[], chemicals[], datasets[] }, each { name, recentPaperCount, priorPaperCount }.

Type:

networkStats

Optional

On the summary record (when includeNetworks is on): knowledge-graph size — { nodeCount, edgeCount }.

Type:

summary

Optional

Plain-English one-line summary of the record (status, title, citations, access, entity counts).

Type:string | null

fullTextUrl

Optional

URL to full text (HTML or PDF)

Type:string | null

europePmcUrl

Optional

Link to Europe PMC article page

Type:string | null

extractedAt

Optional

ISO timestamp of data extraction

Type:string | null

Other properties may be included.

Europe PMC Literature Scraper

parseforge/europepmc-scraper

Scrape Europe PMC for biomedical research papers. Search by title, author, MeSH terms, journal. Get DOI, abstract, full-text URLs, citations, references, open-access status. No API key required.

ParseForge

Europe PMC Scientific Literature Scraper

parseforge/europe-pmc-scraper

Query Europe PMC with the full TITLE, AUTH, JOURNAL, and DOI syntax. Returns PMID, DOI, title, authors, abstract, journal, publication year, citation count, open access flag, and source. Useful for systematic reviews, literature mining, and biomedical research workflows.

ParseForge

Europe PMC Scraper

crawlergang/europe-pmc-scraper

Scrape Europe PMC, 42M+ biomedical literature records including PubMed, PubMed Central, patents, and preprints. Search publications, get article details by PMID or DOI, and retrieve citation/reference lists.

Crawler Gang

5.0

Europe PMC Scraper

crawlerbros/europe-pmc-scraper

Crawler Bros

Google Knowledge Graph

seemuapps/google-knowledge-graph

Enrich a list of entity names (people, companies, places, things) with metadata from the Google Knowledge Graph.

Andrew

Europe PMC Articles Scraper

parseforge/europe-pmc-articles-scraper

Search Europe PMC across millions of life sciences articles with any free text query. Returns PMID, PMCID, DOI, title, authors, journal, year, and abstract snippet. Useful for systematic reviews, citation harvesting, drug target evidence collection, and literature monitoring.

ParseForge

Open Science Evidence Finder

mrbridge/open-science-evidence-finder

Find, verify, deduplicate, and score open scientific metadata from OpenAlex, Crossref, arXiv, and Europe PMC for LLM source grounding.

MrBridge

Knowledge Intelligence Engine — Website to Markdown for RAG

ryanclinton/website-content-to-markdown

Turn any website, documentation site or help centre into a retrieval-ready knowledge corpus for RAG and AI search. Clean Markdown plus chunks, change detection, deduplication, retrieval scoring, version awareness and a full corpus audit, in one run.

Ryan Clinton

Google Fast Search Scraper

kaix/google-search-scraper

🔥 ~$0.05/1K results 🔥 Search Google and get structured results including web pages, images, and Knowledge Graph entities. Returns titles, URLs, snippets, and full metadata. Supports geo-targeting, language, date filtering, sorting, and auto-pagination up to 100 results.

Kai

Website To LLM Knowledge Pack

attainable_iota/website-to-llm-knowledge-pack

Crawl any website and turn it into an LLM-ready knowledge pack. This Actor extracts clean main text + metadata, follows links with depth/URL filters, and outputs per-page dataset items plus knowledge.jsonl, knowledge.md, and manifest.json for RAG/embeddings pipelines.