PubMed embedding
===================================
|pip| |downloads| |paper|
Building PubMed embedding, automatically.
Install the package
----------------------------------
As usual, just install from Pypi:
.. code:: shell
pip install pubmed_embedding
Usage examples
----------------------------------
You can retrieve embedding for PubMed IDs of interest as such:
BERT
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. code:: python
from pubmed_embedding import get_pubmed_embedding_from_curies
pubmed_ids = ["PMID:24774509", "PMID:15170967", "PMID:7850793"]
bert_features = get_pubmed_embedding_from_curies(
curies=pubmed_ids,
version="pubmed_bert_30_11_2022"
)
And the result is:
|BERT|
SciBERT
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. code:: python
scibert_features = get_pubmed_embedding_from_curies(
curies=pubmed_ids,
version="pubmed_scibert_30_11_2022"
)
And the result is:
|SciBERT|
Specter
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. code:: python
spected_features = get_pubmed_embedding_from_curies(
curies=pubmed_ids,
version="pubmed_specter_30_11_2022"
)
And the result is:
|Specter|
Citing this work
-----------------------------
If you have found these datasets useful, please do cite:
.. code:: bib
@software{cappellettiPubMed2022,
author = {Cappelletti, Luca and Fontana, Tommaso and Reese, Justin},
month = {12},
title = {{BM25-weighted BERT-based embedding of PubMed}},
url = {https://github.com/LucaCappelletti94/pubmed_embedding},
version = {1.0.14},
year = {2022}
}
.. |BERT| image:: https://github.com/LucaCappelletti94/pubmed_embedding/blob/main/bert.png?raw=true
.. |SciBERT| image:: https://github.com/LucaCappelletti94/pubmed_embedding/blob/main/scibert.png?raw=true
.. |Specter| image:: https://github.com/LucaCappelletti94/pubmed_embedding/blob/main/specter.png?raw=true
.. |pip| image:: https://badge.fury.io/py/pubmed-embedding.svg
:target: https://badge.fury.io/py/pubmed-embedding
:alt: Pypi project
.. |downloads| image:: https://pepy.tech/badge/pubmed-embedding
:target: https://pepy.tech/badge/pubmed-embedding
:alt: Pypi total project downloads
.. |paper| image:: https://img.shields.io/badge/DOI-10.48550/arXiv.2110.06196-blue.svg
:target: https://github.com/LucaCappelletti94/pubmed_embedding/blob/main/BM25_weighted_BERT_based_embedding_of_PubMed.pdf
:alt: Paper
Raw data
{
"_id": null,
"home_page": "https://github.com/LucaCappelletti94/pubmed_graph",
"name": "pubmed-embedding",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.6.0",
"maintainer_email": "",
"keywords": "SciBERT,PubMed,BM25",
"author": "Luca Cappelletti",
"author_email": "",
"download_url": "https://files.pythonhosted.org/packages/a4/12/04dc1c9ee422036cf60786e0e7c2cd738fc15af3e39229b056274da80f38/pubmed_embedding-1.0.14.tar.gz",
"platform": null,
"description": "PubMed embedding\n===================================\n|pip| |downloads| |paper|\n\nBuilding PubMed embedding, automatically.\n\n\nInstall the package\n----------------------------------\nAs usual, just install from Pypi:\n\n.. code:: shell\n\n pip install pubmed_embedding\n\n\nUsage examples\n----------------------------------\nYou can retrieve embedding for PubMed IDs of interest as such:\n\nBERT\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n.. code:: python\n\n from pubmed_embedding import get_pubmed_embedding_from_curies\n\n pubmed_ids = [\"PMID:24774509\", \"PMID:15170967\", \"PMID:7850793\"]\n\n bert_features = get_pubmed_embedding_from_curies(\n curies=pubmed_ids,\n version=\"pubmed_bert_30_11_2022\"\n )\n\nAnd the result is:\n\n|BERT|\n\n\nSciBERT\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n.. code:: python\n\n scibert_features = get_pubmed_embedding_from_curies(\n curies=pubmed_ids,\n version=\"pubmed_scibert_30_11_2022\"\n )\n \nAnd the result is:\n\n|SciBERT|\n\nSpecter\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n.. code:: python\n\n spected_features = get_pubmed_embedding_from_curies(\n curies=pubmed_ids,\n version=\"pubmed_specter_30_11_2022\"\n )\n\nAnd the result is:\n\n|Specter|\n\nCiting this work\n-----------------------------\nIf you have found these datasets useful, please do cite:\n\n.. code:: bib\n\n @software{cappellettiPubMed2022,\n author = {Cappelletti, Luca and Fontana, Tommaso and Reese, Justin},\n month = {12},\n title = {{BM25-weighted BERT-based embedding of PubMed}},\n url = {https://github.com/LucaCappelletti94/pubmed_embedding},\n version = {1.0.14},\n year = {2022}\n }\n\n\n\n.. |BERT| image:: https://github.com/LucaCappelletti94/pubmed_embedding/blob/main/bert.png?raw=true\n.. |SciBERT| image:: https://github.com/LucaCappelletti94/pubmed_embedding/blob/main/scibert.png?raw=true\n.. |Specter| image:: https://github.com/LucaCappelletti94/pubmed_embedding/blob/main/specter.png?raw=true\n\n.. |pip| image:: https://badge.fury.io/py/pubmed-embedding.svg\n :target: https://badge.fury.io/py/pubmed-embedding\n :alt: Pypi project\n\n.. |downloads| image:: https://pepy.tech/badge/pubmed-embedding\n :target: https://pepy.tech/badge/pubmed-embedding\n :alt: Pypi total project downloads \n\n.. |paper| image:: https://img.shields.io/badge/DOI-10.48550/arXiv.2110.06196-blue.svg\n :target: https://github.com/LucaCappelletti94/pubmed_embedding/blob/main/BM25_weighted_BERT_based_embedding_of_PubMed.pdf\n :alt: Paper",
"bugtrack_url": null,
"license": "BSD3",
"summary": "A tool to work with pre-computed large pubmed embedding.",
"version": "1.0.14",
"split_keywords": [
"scibert",
"pubmed",
"bm25"
],
"urls": [
{
"comment_text": "",
"digests": {
"md5": "da227d8455868c13b8ae3b60d022b850",
"sha256": "4a7b16fe671c00f7725d4bfa5ab1bbeb1afea7e84e2d19f10e7fd21483317f65"
},
"downloads": -1,
"filename": "pubmed_embedding-1.0.14.tar.gz",
"has_sig": false,
"md5_digest": "da227d8455868c13b8ae3b60d022b850",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6.0",
"size": 29951,
"upload_time": "2022-12-02T18:06:51",
"upload_time_iso_8601": "2022-12-02T18:06:51.097677Z",
"url": "https://files.pythonhosted.org/packages/a4/12/04dc1c9ee422036cf60786e0e7c2cd738fc15af3e39229b056274da80f38/pubmed_embedding-1.0.14.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2022-12-02 18:06:51",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "LucaCappelletti94",
"github_project": "pubmed_graph",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "pubmed-embedding"
}
JSON
