{"id":"https://openalex.org/W2051689038","doi":"https://doi.org/10.1371/journal.pcbi.1000597","title":"Biomedical Text Mining and Its Applications","display_name":"Biomedical Text Mining and Its Applications","publication_year":2009,"publication_date":"2009-12-23","ids":{"openalex":"https://openalex.org/W2051689038","doi":"https://doi.org/10.1371/journal.pcbi.1000597","mag":"2051689038","pmid":"https://pubmed.ncbi.nlm.nih.gov/20041219"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1000597","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1000597","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1000597&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1000597&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002036038","display_name":"Raul Rodriguez\u2010Esteban","orcid":"https://orcid.org/0000-0002-9494-9609"},"institutions":[{"id":"https://openalex.org/I180857899","display_name":"Pfizer (United States)","ror":"https://ror.org/01xdqrp08","country_code":"US","type":"company","lineage":["https://openalex.org/I180857899"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Raul Rodriguez-Esteban","raw_affiliation_strings":["Pfizer Research Technology Center, Cambridge, Massachusetts, USA. raul.rodriguez-esteban@pfizer.com","Pfizer Research Technology Center, Cambridge, Massachusetts, USA"],"affiliations":[{"raw_affiliation_string":"Pfizer Research Technology Center, Cambridge, Massachusetts, USA. raul.rodriguez-esteban@pfizer.com","institution_ids":["https://openalex.org/I180857899"]},{"raw_affiliation_string":"Pfizer Research Technology Center, Cambridge, Massachusetts, USA","institution_ids":["https://openalex.org/I180857899"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5002036038"],"corresponding_institution_ids":["https://openalex.org/I180857899"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":3.2353,"has_fulltext":true,"cited_by_count":108,"citation_normalized_percentile":{"value":0.92332917,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"5","issue":"12","first_page":"e1000597","last_page":"e1000597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9994999766349792,"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":0.9994999766349792,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.977400004863739,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9764999747276306,"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/biomedical-text-mining","display_name":"Biomedical text mining","score":0.8274441957473755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6838072538375854},{"id":"https://openalex.org/keywords/toolbox","display_name":"Toolbox","score":0.46603459119796753},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.40457683801651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39038529992103577},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3768985867500305},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3364632725715637},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3313749432563782}],"concepts":[{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.8274441957473755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6838072538375854},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.46603459119796753},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.40457683801651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39038529992103577},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3768985867500305},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3364632725715637},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3313749432563782},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057386","descriptor_name":"Search Engine","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057386","descriptor_name":"Search Engine","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057386","descriptor_name":"Search Engine","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1371/journal.pcbi.1000597","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1000597","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1000597&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS Computational Biology","raw_type":"journal-article"},{"id":"pmid:20041219","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20041219","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:doaj.org/article:1bbf74750815412ba8b4dba065d9d540","is_oa":true,"landing_page_url":"https://doaj.org/article/1bbf74750815412ba8b4dba065d9d540","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 5, Iss 12, p e1000597 (2009)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2791166","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2791166","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1000597","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1000597","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1000597&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2051689038.pdf","grobid_xml":"https://content.openalex.org/works/W2051689038.grobid-xml"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W155571897","https://openalex.org/W1480287196","https://openalex.org/W1487177365","https://openalex.org/W1512367497","https://openalex.org/W1521652389","https://openalex.org/W1541931954","https://openalex.org/W1550258693","https://openalex.org/W1567787856","https://openalex.org/W1574901103","https://openalex.org/W1581056166","https://openalex.org/W1598532231","https://openalex.org/W1982428412","https://openalex.org/W1987388904","https://openalex.org/W1987931406","https://openalex.org/W1991421174","https://openalex.org/W1993755899","https://openalex.org/W2014849717","https://openalex.org/W2031950862","https://openalex.org/W2039612385","https://openalex.org/W2044514479","https://openalex.org/W2048140075","https://openalex.org/W2067096102","https://openalex.org/W2071221957","https://openalex.org/W2074156599","https://openalex.org/W2079672926","https://openalex.org/W2080948989","https://openalex.org/W2093157872","https://openalex.org/W2094344445","https://openalex.org/W2097869005","https://openalex.org/W2099794271","https://openalex.org/W2100592161","https://openalex.org/W2100822723","https://openalex.org/W2100979380","https://openalex.org/W2102672399","https://openalex.org/W2104768328","https://openalex.org/W2107141268","https://openalex.org/W2109555487","https://openalex.org/W2112723752","https://openalex.org/W2113617961","https://openalex.org/W2115007282","https://openalex.org/W2123439964","https://openalex.org/W2123939104","https://openalex.org/W2124617249","https://openalex.org/W2125552472","https://openalex.org/W2126259921","https://openalex.org/W2126261436","https://openalex.org/W2126687787","https://openalex.org/W2127241285","https://openalex.org/W2127603354","https://openalex.org/W2127994383","https://openalex.org/W2129113459","https://openalex.org/W2132180308","https://openalex.org/W2132784310","https://openalex.org/W2135063148","https://openalex.org/W2139259976","https://openalex.org/W2140519398","https://openalex.org/W2142741334","https://openalex.org/W2144181601","https://openalex.org/W2144896636","https://openalex.org/W2145819879","https://openalex.org/W2147558260","https://openalex.org/W2151124162","https://openalex.org/W2154896031","https://openalex.org/W2158505321","https://openalex.org/W2159203162","https://openalex.org/W2159675211","https://openalex.org/W2164620224","https://openalex.org/W2164666853","https://openalex.org/W2166057395","https://openalex.org/W2166596803","https://openalex.org/W2169918010","https://openalex.org/W3153661842","https://openalex.org/W4240689716"],"related_works":["https://openalex.org/W3185751515","https://openalex.org/W1479703980","https://openalex.org/W2749535755","https://openalex.org/W1553529581","https://openalex.org/W4206039273","https://openalex.org/W4232119327","https://openalex.org/W2911489562","https://openalex.org/W2134429551","https://openalex.org/W3183808544","https://openalex.org/W2188854577"],"abstract_inverted_index":{"This":[0,212],"tutorial":[1,24],"is":[2,80,111,126,138,158,170],"intended":[3],"for":[4,120,230,239],"biologists":[5,8],"and":[6,33,90,150,205,234],"computational":[7],"interested":[9,54],"in":[10,55,102,215,242],"adding":[11],"text":[12,60,73,133,136,144,167,169,218],"mining":[13,61,134,219],"tools":[14],"to":[15,42,59,65,104,113,223],"their":[16,202,208],"bioinformatics":[17],"toolbox.":[18],"As":[19],"an":[20],"illustrative":[21],"example,":[22,198],"the":[23,26,43,75,117,139],"examines":[25],"relationship":[27],"between":[28],"progressive":[29],"multifocal":[30],"leukoencephalopathy":[31],"(PML)":[32],"antibodies.":[34],"Recent":[35],"cases":[36],"of":[37,45,72,77,226,232],"PML":[38],"have":[39],"been":[40],"associated":[41],"administration":[44],"some":[46,161],"monoclonal":[47],"antibodies":[48],"such":[49],"as":[50,164],"efalizumab":[51],"[1].":[52],"Those":[53],"a":[56,78,85,88,91,96,172],"further":[57],"introduction":[58],"may":[62],"also":[63],"want":[64],"read":[66],"other":[67,124],"reviews":[68],"[2]\u2013[4].\r\n\r\nUnderstanding":[69],"large":[70],"amounts":[71],"with":[74,87,116,143,166],"aid":[76],"computer":[79,86],"harder":[81],"than":[82],"simply":[83],"equipping":[84],"grammar":[89],"dictionary.":[92],"A":[93],"computer,":[94],"like":[95],"human,":[97],"needs":[98],"certain":[99],"specialized":[100],"knowledge":[101,119],"order":[103],"understand":[105],"text.":[106,227],"The":[107],"scientific":[108,182,240],"field":[109],"that":[110,141,145,217],"dedicated":[112],"train":[114],"computers":[115],"right":[118],"this":[121],"task":[122],"(among":[123],"tasks)":[125],"called":[127],"natural":[128],"language":[129],"processing":[130],"(NLP).":[131],"Biomedical":[132],"(henceforth,":[135,152],"mining)":[137],"subfield":[140],"deals":[142],"comes":[146],"from":[147,181,244],"biology,":[148],"medicine,":[149],"chemistry":[151],"biomedical":[153],"text).":[154],"Another":[155],"popular":[156],"name":[157],"BioNLP,":[159],"which":[160],"practitioners":[162],"use":[163],"synonymous":[165],"mining.\r\n\r\nBiomedical":[168],"not":[171,194],"homogeneous":[173],"realm":[174],"[5].":[175],"Medical":[176],"records":[177],"are":[178,193,221,237],"written":[179],"differently":[180],"articles,":[183],"sequence":[184],"annotations,":[185],"or":[186],"public":[187],"health":[188],"guidelines.":[189],"Moreover,":[190],"local":[191],"dialects":[192],"uncommon":[195],"[6].":[196],"For":[197],"medical":[199],"centers":[200],"develop":[201],"own":[203],"jargons":[204],"laboratories":[206],"create":[207],"idiosyncratic":[209],"protein":[210],"nomenclatures.":[211],"variability":[213],"means,":[214],"practice,":[216],"applications":[220],"tailored":[222],"specific":[224],"types":[225],"In":[228],"particular,":[229],"reasons":[231],"availability":[233],"cost,":[235],"many":[236],"designed":[238],"abstracts":[241],"English":[243],"Medline.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":12}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}