{"id":28512546,"url":"https://github.com/ncbi/bioconceptvec","last_synced_at":"2026-03-03T23:03:01.870Z","repository":{"id":145849443,"uuid":"184434741","full_name":"ncbi/BioConceptVec","owner":"ncbi","description":null,"archived":false,"fork":false,"pushed_at":"2020-02-26T05:02:04.000Z","size":63032,"stargazers_count":41,"open_issues_count":1,"forks_count":13,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-07-04T01:36:31.082Z","etag":null,"topics":["biomedical-concept-embeddings","biomedical-text-mining","deep-learning","protein-protein-interaction","text-mining","word-embeddings"],"latest_commit_sha":null,"homepage":null,"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/ncbi.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,"governance":null}},"created_at":"2019-05-01T15:10:35.000Z","updated_at":"2025-03-07T14:34:58.000Z","dependencies_parsed_at":"2023-05-18T11:18:10.421Z","dependency_job_id":null,"html_url":"https://github.com/ncbi/BioConceptVec","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ncbi/BioConceptVec","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ncbi%2FBioConceptVec","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ncbi%2FBioConceptVec/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ncbi%2FBioConceptVec/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ncbi%2FBioConceptVec/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ncbi","download_url":"https://codeload.github.com/ncbi/BioConceptVec/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ncbi%2FBioConceptVec/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30064793,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-03T18:21:05.932Z","status":"ssl_error","status_checked_at":"2026-03-03T18:20:59.341Z","response_time":61,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["biomedical-concept-embeddings","biomedical-text-mining","deep-learning","protein-protein-interaction","text-mining","word-embeddings"],"created_at":"2025-06-09T00:38:24.847Z","updated_at":"2026-03-03T23:03:01.865Z","avatar_url":"https://github.com/ncbi.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# BioConceptVec: \u003cbr\u003e\u003csmall\u003ecreating and evaluating literature-based biomedical concept embeddings on a large scale\u003c/small\u003e\r\n\r\n[![HitCount](http://hits.dwyl.com/ncbi-nlp/BioConceptVec.svg)](http://hits.dwyl.com/ncbi-nlp/BioConceptVec)\r\n\r\n## Table of contents\r\n\r\n* [Text corpora](#text-corpora)\r\n* [Named Entity Recognition (NER) tools](#pubtator)\r\n* [BioConceptVec: embeddings and concept files](#bioconceptvec)\r\n* [Tutorial](#tutorial)\r\n* [Datasets](#dataset)\r\n* [References](#references)\r\n* [Acknowledgments](#acknowledgments)\r\n\r\n\r\n## Text corpora\r\n\u003ca name=\"text-corpora\"\u003e\u003c/a\u003e\r\nWe created BioConceptVec using the entire [PubMed](https://www.ncbi.nlm.nih.gov/pubmed/). The texts were split and tokenized using [NLTK](https://www.nltk.org/). We also lowercased all the words.\r\n\r\n\r\n## Using PubTator for annotating concepts in the PubMed\r\n\u003ca name=\"pubtator\"\u003e\u003c/a\u003e\r\nWe employed [PubTator](https://www.ncbi.nlm.nih.gov/research/pubtator/) to annotate biomedical concepts in the PubMed. It covers genes, mutations, chemicals, diseases and cellines. The trained embeddings contain over 400,000 concepts.\r\n\r\n## BioConceptVec: embeddings and concept files\r\n\u003ca name=\"bioconceptvec\"\u003e\u003c/a\u003e\r\nWe release four versions of BioConceptVec (cbow, skip-gram, glove and fastText). For each version, we make both the **embedding**(contains concepts and other words) in binary format and the **concept-only** file in json format available.\r\n\r\n1. **BioConceptVec cbow:** [embedding](https://ftp.ncbi.nlm.nih.gov/pub/lu/BioConceptVec/bioconceptvec_word2vec_cbow.bin) (2.4GB) and [concept-only](https://ftp.ncbi.nlm.nih.gov/pub/lu/BioConceptVec/concept_cbow.json) (798MB).\r\n2. **BioConceptVec skip-gram:** [embedding](https://ftp.ncbi.nlm.nih.gov/pub/lu/BioConceptVec/bioconceptvec_word2vec_skipgram.bin) (2.4GB) and [concept-only](https://ftp.ncbi.nlm.nih.gov/pub/lu/BioConceptVec/concept_skip.json) (812MB).\r\n3. **BioConceptVec glove:** [embedding](https://ftp.ncbi.nlm.nih.gov/pub/lu/BioConceptVec/bioconceptvec_glove.bin) (2.4GB) and [concept-only](https://ftp.ncbi.nlm.nih.gov/pub/lu/BioConceptVec/concept_glove.json) (835MB).\r\n4. **BioConceptVec fastText:** [embedding](https://ftp.ncbi.nlm.nih.gov/pub/lu/BioConceptVec/bioconceptvec_fasttext.bin) (2.4GB) and [concept-only](https://ftp.ncbi.nlm.nih.gov/pub/lu/BioConceptVec/concept_fast.json) (813MB).\r\n\r\n\r\n## Tutorial\r\n\u003ca name=\"pubtator\"\u003e\u003c/a\u003e\r\nYou can find [this tutorial](https://github.com/ncbi-nlp/BioConceptVec/blob/master/bioconcept_tutorial.ipynb) on how to use BioConceptVec (for both embedding and concept-only files) for a quick start.\r\n\r\n## Datasets\r\n\u003ca name=\"dataset\"\u003e\u003c/a\u003e\r\nWe also make all the 9 evaluation datasets publicly available. It covers 4 applications:\r\n\r\n1. [**Drug-Gene interactions**](https://github.com/ncbi-nlp/BioConceptVec/tree/master/datasets/drug_gene_interactions). The dataset contains (1) ID: the instance ID, (2) num_of_genes: the number of genes for this instance, (3) pos_rel_genes: the IDs of related genes, and (4) neg_rel_genes: the IDs of unrelated genes.\r\n\r\n2. [**Gene-Gene interactions**](https://github.com/ncbi-nlp/BioConceptVec/tree/master/datasets/gene_gene_interactions). 5 datasets on gene-gene interactions have the same format as above.\r\n\r\n3. [**Protein-Protein interaction**](https://github.com/ncbi-nlp/BioConceptVec/tree/master/datasets/protein_protein_interactions). It contains two datasets: (1) combined: protein-protein interactions created based on STRING combined scores and (2) exp700: protein-protein interactions created based on STRING experimental scores over 700. Both datasets contain train, valid and test files. The file contains (1) query: query protein ID, (2) subject: subject protein ID, (3) score: STRING score and (4) label: whether it is a protein-protein interaction.\r\n\r\n4. [**Drug-Drug interaction**](https://github.com/ncbi-nlp/BioConceptVec/tree/master/datasets/drug_drug_interactions). This dataset is from [Drug-Drug interaction semeval-2013](https://www.cs.york.ac.uk/semeval-2013/task9/). Please see the details there.\r\n\r\n## References\r\nWhen using our resources, please cite the following papers:\r\n\r\nChen, Q., Lee, K., Yan, S., Kim, S., Wei, C. H., \u0026 Lu, Z. (2019). [BioConceptVec: creating and evaluating literature-based biomedical concept embeddings on a large scale](https://arxiv.org/ftp/arxiv/papers/1912/1912.10846.pdf). To appear in PLOS Computational Biology.\r\n\r\n## Acknowledgments\r\n\u003ca name=\"acknowledgments\"\u003e\u003c/a\u003e\r\nThis work was supported by the Intramural Research Programs of the National Institutes of Health, National Library of Medicine. \r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fncbi%2Fbioconceptvec","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fncbi%2Fbioconceptvec","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fncbi%2Fbioconceptvec/lists"}