This repository quantifies term cooccurrence in MEDLINE. It's designed for computing the cooccurence of all pairs between two MeSH termsets. The repository computes MEDLINE cooccurences for the Rephetio hetnet. See the corresponding Thinklab discussion for more information.

• eutility.py defines an esearch_query function for retreiving PubMed IDs matching a user-defined query.
• cooccurrence.py computes the cooccurences bewteen two termsets, whose associated PubMed IDs have been retrieved.

• diseases.ipynb computes disease-disease cooccurrence
• symptoms.ipynb computes symptom-disease cooccurrence
• tissues.ipynb computes anatomy-disease cooccurrence. This notebook depends on data/disease-pmids.tsv.gz, a dataset created by symptoms.ipynb.

This repository is released under CC0 1.0.