{"id":22141236,"url":"https://github.com/hetio/medline","last_synced_at":"2025-07-25T23:31:59.091Z","repository":{"id":31949429,"uuid":"35519232","full_name":"hetio/medline","owner":"hetio","description":"Computing term cooccurrence in MEDLINE","archived":false,"fork":false,"pushed_at":"2021-04-13T16:17:06.000Z","size":145985,"stargazers_count":16,"open_issues_count":0,"forks_count":4,"subscribers_count":4,"default_branch":"main","last_synced_at":"2024-05-02T06:00:22.936Z","etag":null,"topics":["anatomy","cooccurrence","diseases","hetionet","literature","medline","pubmed","rephetio","symptoms","text-mining"],"latest_commit_sha":null,"homepage":"https://doi.org/10.15363/thinklab.d67","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hetio.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2015-05-13T00:18:54.000Z","updated_at":"2024-05-02T06:00:22.937Z","dependencies_parsed_at":"2022-08-24T14:22:28.636Z","dependency_job_id":null,"html_url":"https://github.com/hetio/medline","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hetio%2Fmedline","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hetio%2Fmedline/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hetio%2Fmedline/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hetio%2Fmedline/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hetio","download_url":"https://codeload.github.com/hetio/medline/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":227629031,"owners_count":17796054,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["anatomy","cooccurrence","diseases","hetionet","literature","medline","pubmed","rephetio","symptoms","text-mining"],"created_at":"2024-12-01T21:11:36.676Z","updated_at":"2024-12-01T21:11:37.152Z","avatar_url":"https://github.com/hetio.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Computing term cooccurrence in MEDLINE\n\nThis repository quantifies term cooccurrence in MEDLINE.\nIt's designed for computing the cooccurence of all pairs between two MeSH termsets.\nThe repository computes MEDLINE cooccurences for the Rephetio hetnet.\nSee the corresponding [Thinklab discussion](https://doi.org/10.15363/thinklab.d67 \"Mining knowledge from MEDLINE articles and their indexed MeSH terms\") for more information.\n\n## Modules\n\n+ [`eutility.py`](eutility.py) defines an `esearch_query` function for retreiving PubMed IDs matching a user-defined query.\n+ [`cooccurrence.py`](cooccurrence.py) computes the cooccurences bewteen two termsets,\n  whose associated PubMed IDs have been retrieved.\n\n## Notebooks\n\nThe following notebooks were used to compute relationships for Hetionet v1.0 by [Project Rephetio](https://git.dhimmel.com/rephetio-manuscript/):\n\n+ [`diseases.ipynb`](diseases.ipynb) computes disease-disease cooccurrence\n+ [`symptoms.ipynb`](symptoms.ipynb) computes symptom-disease cooccurrence\n+ [`tissues.ipynb`](tissues.ipynb) computes anatomy-disease cooccurrence.\n  This notebook depends on `data/disease-pmids.tsv.gz`,\n  a dataset created by `symptoms.ipynb`.\n\nThe following notebooks are for a more general analysis to support custom user queries:\n\n- [`download-topics.ipynb`](download-topics.ipynb) downloads the PubMed IDs for all MeSH descriptors and supplementary disease concepts and saves this to [`data/mesh-term-topics-noexp.jsonl.gz`](data/mesh-term-topics-noexp.jsonl.gz).\n- [`cooccur-topics.ipynb`](cooccur-topics.ipynb) reads `mesh-term-topics-noexp.jsonl.gz` to compute cooccurrence between a user-selected term with all other MeSH terms.\n\n## Environment\n\n```shell\n# create environment\nconda env create --file=environment.yml\n\n# update environment\nconda env update --file=environment.yml\n\n# activate environment\nconda activate medline\n\n# run jupyter lab for notebook development\njupyter lab\n```\n\n## History\n\nOn 2021-04-09, ownership of this repository on GitHub was changed from `dhimmel/medline` to `hetio/medline`.\nThe `hetio` organization has GitHub LFS quota,\nproviding a more convenient way to store large compressed files.\n\nAt the time of the transfer, the only default (and only) branch was `gh-pages`.\nThe `gh-pages` branch was renamed to `pre-lfs-archive`.\nA new default branch `main` was created, whose history has been migrated to use Git LFS.\nFor the version of this repository used by Project Rephetio to create Hetionet v1.0,\nrefer to the [v1.0 release](https://github.com/hetio/medline/releases/tag/v1.0).\n\n## Comparison to MRCOC\n\nMEDLINE [produces co-occurrence files](https://ii.nlm.nih.gov/MRCOC.shtml) under the codename MRCOC.\nMore information is available in the 2016 report [Building an Updated MEDLINE Co-Occurrences (MRCOC) File](https://ii.nlm.nih.gov/MRCOC/MRCOC_Doc_2016.pdf).\nThese files might be a viable alternative to the analyses in this repository for certain applications.\nHowever, they don't appear to contain topics for supplemental concept records\n(for example MeSH term [`C000591739`](https://id.nlm.nih.gov/mesh/2020/C000591739.html)).\nFeel free to open an issue with additional insights on or comparisons to MRCOC.\n\n## License\n\nThis repository is released under [CC0 1.0](https://creativecommons.org/publicdomain/zero/1.0/ \"CC0 1.0 Universal: Public Domain Dedication\").\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhetio%2Fmedline","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhetio%2Fmedline","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhetio%2Fmedline/lists"}