{"id":"https://openalex.org/W4393648974","doi":"https://doi.org/10.5281/zenodo.2530898","title":"Molecular Biology Open Access Pubmed Word and Sentence Representations","display_name":"Molecular Biology Open Access Pubmed Word and Sentence Representations","publication_year":2018,"publication_date":"2018-07-19","ids":{"openalex":"https://openalex.org/W4393648974","doi":"https://doi.org/10.5281/zenodo.2530898"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:2530898","is_oa":true,"landing_page_url":"https://zenodo.org/record/2530898","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/2530898","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087346345","display_name":"Gully Burns","orcid":"https://orcid.org/0000-0003-1493-865X"},"institutions":[{"id":"https://openalex.org/I4210121800","display_name":"Chan Zuckerberg Initiative (United States)","ror":"https://ror.org/02qenvm24","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Burns, Gully","raw_affiliation_strings":["Chan Zuckerberg Initiative"],"raw_orcid":"https://orcid.org/0000-0003-1493-865X","affiliations":[{"raw_affiliation_string":"Chan Zuckerberg Initiative","institution_ids":["https://openalex.org/I4210121800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042303431","display_name":"Xiangci Li","orcid":"https://orcid.org/0000-0002-7493-9534"},"institutions":[{"id":"https://openalex.org/I4210147455","display_name":"Institute of Information Science","ror":"https://ror.org/055q8rh54","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210147455"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Li, Xiangci","raw_affiliation_strings":["USC Information Science Institute"],"raw_orcid":"https://orcid.org/0000-0002-7493-9534","affiliations":[{"raw_affiliation_string":"USC Information Science Institute","institution_ids":["https://openalex.org/I4210147455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030248499","display_name":"Nanyun Peng","orcid":"https://orcid.org/0000-0002-8509-6595"},"institutions":[{"id":"https://openalex.org/I4210147455","display_name":"Institute of Information Science","ror":"https://ror.org/055q8rh54","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210147455"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Peng, Nanyun","raw_affiliation_strings":["USC Information Science Institute"],"raw_orcid":"https://orcid.org/0000-0002-8509-6595","affiliations":[{"raw_affiliation_string":"USC Information Science Institute","institution_ids":["https://openalex.org/I4210147455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9754999876022339,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9754999876022339,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9621000289916992,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6981186270713806},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6952824592590332},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5107200145721436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49223437905311584},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40390801429748535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3473496437072754},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.12019658088684082}],"concepts":[{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6981186270713806},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6952824592590332},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5107200145721436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49223437905311584},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40390801429748535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3473496437072754},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.12019658088684082}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:2530898","is_oa":true,"landing_page_url":"https://zenodo.org/record/2530898","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},{"id":"doi:10.5281/zenodo.2530898","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.2530898","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:2530898","is_oa":true,"landing_page_url":"https://zenodo.org/record/2530898","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2375873920","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W2392760275","https://openalex.org/W2083530853","https://openalex.org/W2982905616","https://openalex.org/W2009831055","https://openalex.org/W2393172683","https://openalex.org/W3204019825","https://openalex.org/W2296205523"],"abstract_inverted_index":{"<strong>Natural":[0],"Language":[1],"Embeddings":[2],"about":[3],"Molecular":[4],"Biology</strong>":[5],"This":[6,225],"dataset":[7],"is":[8,226,346,368,375,410,435],"concerned":[9],"with":[10,31,87,231,334],"developing":[11],"a":[12,88,221,227,237,273,282,330,347,360,369,389],"tailored":[13],"training":[14,395,423],"data":[15,396,424],"set":[16],"for":[17,73,139,240,269,276,325],"word":[18,408,433],"and":[19,66,71,108,118,124,158,163,173,179,213,372],"sentence":[20,250,261,304,316,371],"embedding":[21],"based":[22],"on":[23,263,392,420],"biomedical":[24],"text":[25,258,353,374],"that":[26],"has":[27],"some":[28],"component":[29],"associated":[30],"molecular":[32,47,74,89],"work":[33,41],"(as":[34],"opposed":[35],"to":[36,59,82,85,281,328],"the":[37,93,143,232,245,249,252,260,270,277,294,300,303,306,312,315,318,322,344,352,373,393,399,407,421,430],"other":[38],"range":[39],"of":[40,51,205,248,259,272,279,293,299,302,311,314,355,406,429],"indexed":[42],"in":[43,251,383,412,437],"PubMed":[44,196,326],"like":[45],"non":[46],"clinical":[48],"work,":[49],"studies":[50],"human":[52],"behavior,":[53],"etc).":[54],"<strong>Raw":[55],"Data</strong>":[56],"In":[57],"order":[58],"develop":[60],"natural":[61],"language":[62],"embeddings":[63,409,434],"(for":[64],"words":[65],"sentences),":[67],"we":[68],"queried":[69],"PMC":[70,200,216],"MEDLINE":[72],"papers":[75,86],"only":[76],"by":[77],"using":[78,398],"high-level":[79],"MeSH":[80,95],"terms":[81,141],"restrict":[83],"interest":[84],"focus.":[90],"We":[91,210,320,350,387,416],"used":[92],"following":[94,144,233],"terms:":[96],"Cells":[97],"[A11]":[98],"Multiprotein":[99],"Complexes":[100],"[D05.500]":[101],"Protein":[102],"Aggregates":[103],"[D05.875]":[104],"Hormones":[105],"[D06]":[106],"Enzymes":[107],"Coenzymes":[109],"[D08]":[110,112],"Carbohydrates":[111],"Lipids":[113],"[D10]":[114],"Amino":[115],"Acids,":[116,122,171,177],"Peptides":[117],"Proteins":[119],"[D12]":[120],"Nucleic":[121],"Nucleotides":[123],"Nucleosides":[125],"[D13]":[126],"Biological":[127],"Factors":[128],"[D23]":[129],"Pharmaceutical":[130],"Preparations":[131],"[D26]":[132],"Metabolism":[133],"[G03]":[134],"Genetic":[135],"Phenomena":[136],"[G06]":[137],"Queries":[138],"these":[140,206,356],"use":[142],"string:":[145],"\"cells\"[MeSH":[146],"Terms]":[147],"OR":[148,151,154,161,165,167,169,175,181,184,187,189,193],"\"Multiprotein":[149],"Complexes\"[mh]":[150],"\"Protein":[152],"Aggregates\"[mh]":[153],"\"Hormones,":[155],"Hormone":[156,159],"Substitutes,":[157],"Antagonists\"[mh]":[160],"\"Enzymes":[162],"Coenzymes\"[mh]":[164],"\"Carbohydrates\"[mh]":[166],"\"Lipids\"[mh]":[168],"\"Amino":[170],"Peptides,":[172],"Proteins\"[mh]":[174],"\"Nucleic":[176],"Nucleotides,":[178],"Nucleosides\"[mh]":[180],"\"Biological":[182],"Factors\"[mh]":[183],"\"Pharmaceutical":[185],"Preparations\"[mh]":[186],"\"Metabolism\"[mh]":[188],"\"Cell":[190],"Physiological":[191],"Phenomena\"[mh]":[192,195],"\"Genetic":[194],"returns":[197],"11,447,521":[198],"abstracts.":[199],"returns,":[201],"1,720,266":[202],"documents,":[203],"509,722":[204],"are":[207,381],"open":[208,217],"access.":[209],"downloaded,":[211],"parsed":[212],"concatenated":[214,351],"403,825":[215],"access":[218],"documents":[219],"into":[220,359],"single":[222,361,370],"file":[223,230,332,363],"`molecular_oa_pmc.tsv`.":[224],"33GB":[228],"TSV":[229],"columns:":[234,336],"File:Paragraph":[235],"-":[236,244,256,267,285,289,297,309],"unique":[238],"identifier":[239],"each":[241,366],"paragraph":[242],"SentenceId":[243],"local":[246],"number":[247],"document":[253],"Sentence":[254],"Text":[255,349],"tokenized":[257],"(based":[262],"ClearTk's":[264],"TokenAnnotator.java)":[265],"Codes":[266],"<code>exLink</code>":[268],"presence":[271,278],"citation,":[274],"<code>inLink</code>":[275],"link":[280],"Figure":[283,286],"Figures":[284],"codes":[287],"Headings":[288],"High":[290],"level":[291],"section":[292],"paper":[295,307,319],"Offset_Begin":[296],"offset":[298,310],"start":[301,313],"within":[305,317],"Offset_End":[308],"repeated":[321],"same":[323],"process":[324],"abstracts":[327],"generate":[329],"3.6G":[331],"(`molecular_oa_medline.tsv`)":[333],"three":[335,379],"Pubmed":[337],"ID":[338],"A":[339,403,426],"Boolean":[340],"value":[341],"indicating":[342],"whether":[343],"article":[345],"review":[348],"columns":[354],"two":[357],"files":[358,380],"30GB":[362],"(`molecular_oa.txt`)":[364],"where":[365],"line":[367],"fully":[376],"tokenized.":[377],"These":[378],"archived":[382],"`molecular_oa_raw_text.tar.gz`.":[384],"<strong>Fasttext":[385],"Embedding</strong>":[386,415],"trained":[388,417],"fasttext":[390],"model":[391],"raw":[394,422],"(https://fasttext.cc/)":[397],"standard":[400],"`skipgram`":[401],"parameter.":[402],"gzipped":[404,427],"copy":[405,428],"included":[411,436],"`fasttext.model.vec.gz`":[413],"<strong>GloVe":[414],"GloVe":[418],"models":[419],"(https://nlp.stanford.edu/projects/glove/).":[425],"best":[431],"performing":[432],"`bio_GloVe_300.tar.gz`":[438]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}