Skip to content

Instantly share code, notes, and snippets.

@nutjob4life
Created April 28, 2026 19:39
Show Gist options
  • Select an option

  • Save nutjob4life/9c59218642e1731a6dc652dbd5fbc78c to your computer and use it in GitHub Desktop.

Select an option

Save nutjob4life/9c59218642e1731a6dc652dbd5fbc78c to your computer and use it in GitHub Desktop.
#!/usr/bin/env python3
"""Print publication PMID values grouped by RDF subject URI."""
try:
from rdflib import Graph, URIRef
except ImportError as exc:
raise SystemExit("Missing dependency: install rdflib with `python3 -m pip install rdflib`.") from exc
RDF_URL = "https://edrn.jpl.nasa.gov/cancerdataexpo/rdf-data/publications/@@rdf"
PMID = URIRef("http://edrn.nci.nih.gov/rdf/schema.rdf#pmid")
def main() -> None:
graph = Graph()
graph.parse(RDF_URL)
for subject in sorted(set(graph.subjects(predicate=PMID)), key=str):
pmids = sorted({str(pmid) for pmid in graph.objects(subject, PMID)})
for pmid in pmids:
print(f"{subject}\t{pmid}")
if __name__ == "__main__":
main()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment