{"id":"https://openalex.org/W2114617827","doi":"https://doi.org/10.1109/csb.2003.1227433","title":"Using natural language processing and the gene ontology to populate a structured pathway database","display_name":"Using natural language processing and the gene ontology to populate a structured pathway database","publication_year":2004,"publication_date":"2004-03-30","ids":{"openalex":"https://openalex.org/W2114617827","doi":"https://doi.org/10.1109/csb.2003.1227433","mag":"2114617827"},"language":"en","primary_location":{"id":"doi:10.1109/csb.2003.1227433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055761904","display_name":"D. Dehoney","orcid":null},"institutions":[{"id":"https://openalex.org/I1296342797","display_name":"Pharmaceutical Product Development (United States)","ror":"https://ror.org/01sjx9496","country_code":"US","type":"company","lineage":["https://openalex.org/I1296342797"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"D. Dehoney","raw_affiliation_strings":["PPD Discovery, Inc., USA"],"affiliations":[{"raw_affiliation_string":"PPD Discovery, Inc., USA","institution_ids":["https://openalex.org/I1296342797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085724154","display_name":"Rachel Harte","orcid":null},"institutions":[{"id":"https://openalex.org/I1296342797","display_name":"Pharmaceutical Product Development (United States)","ror":"https://ror.org/01sjx9496","country_code":"US","type":"company","lineage":["https://openalex.org/I1296342797"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Harte","raw_affiliation_strings":["PPD Discovery, Inc., USA"],"affiliations":[{"raw_affiliation_string":"PPD Discovery, Inc., USA","institution_ids":["https://openalex.org/I1296342797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059027378","display_name":"Yijuan Lu","orcid":"https://orcid.org/0000-0002-9855-8365"},"institutions":[{"id":"https://openalex.org/I1296342797","display_name":"Pharmaceutical Product Development (United States)","ror":"https://ror.org/01sjx9496","country_code":"US","type":"company","lineage":["https://openalex.org/I1296342797"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Y. Lu","raw_affiliation_strings":["PPD Discovery, Inc., USA"],"affiliations":[{"raw_affiliation_string":"PPD Discovery, Inc., USA","institution_ids":["https://openalex.org/I1296342797"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076088202","display_name":"Daniel J. Chin","orcid":"https://orcid.org/0000-0002-2266-9501"},"institutions":[{"id":"https://openalex.org/I1296342797","display_name":"Pharmaceutical Product Development (United States)","ror":"https://ror.org/01sjx9496","country_code":"US","type":"company","lineage":["https://openalex.org/I1296342797"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Chin","raw_affiliation_strings":["PPD Discovery, Inc., USA"],"affiliations":[{"raw_affiliation_string":"PPD Discovery, Inc., USA","institution_ids":["https://openalex.org/I1296342797"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055761904"],"corresponding_institution_ids":["https://openalex.org/I1296342797"],"apc_list":null,"apc_paid":null,"fwci":0.1169,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.48128096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"646","last_page":"647"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9997000098228455,"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":0.9997000098228455,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.994700014591217,"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/computer-science","display_name":"Computer science","score":0.8296329975128174},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5782339572906494},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5211105942726135},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.5167345404624939},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.4753941297531128},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.46043911576271057},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4548438787460327},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41924411058425903},{"id":"https://openalex.org/keywords/gene-nomenclature","display_name":"Gene nomenclature","score":0.4132731854915619},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41229328513145447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39284875988960266},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3230826258659363},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2693325877189636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8296329975128174},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5782339572906494},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5211105942726135},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.5167345404624939},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.4753941297531128},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.46043911576271057},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4548438787460327},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41924411058425903},{"id":"https://openalex.org/C62177273","wikidata":"https://www.wikidata.org/wiki/Q5531556","display_name":"Gene nomenclature","level":4,"score":0.4132731854915619},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41229328513145447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39284875988960266},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3230826258659363},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2693325877189636},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C514705636","wikidata":"https://www.wikidata.org/wiki/Q863247","display_name":"Nomenclature","level":3,"score":0.0},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/csb.2003.1227433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8999999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1981933378","https://openalex.org/W2118618483","https://openalex.org/W2139259976","https://openalex.org/W2143349571"],"related_works":["https://openalex.org/W2361805396","https://openalex.org/W2972254340","https://openalex.org/W1805912688","https://openalex.org/W2373973507","https://openalex.org/W1515070932","https://openalex.org/W2022231341","https://openalex.org/W4250902763","https://openalex.org/W4255476312","https://openalex.org/W2351154965","https://openalex.org/W2041503010"],"abstract_inverted_index":{"Reading":[0],"literature":[1,21],"is":[2,26,48],"one":[3,49],"of":[4,20,42,46,114,126],"the":[5,18,40,56,109,121,141],"most":[6],"time":[7],"consuming":[8],"tasks":[9],"a":[10,27,35,67,105,124,160,165,190,205,235],"busy":[11],"scientist":[12],"has":[13],"to":[14,23,29,55,72,89,93,107,145,178,201,244],"contend":[15],"with.":[16],"As":[17,123],"volume":[19],"continues":[22],"grow":[24],"there":[25],"need":[28],"sort":[30],"through":[31],"this":[32,229,239],"information":[33,203,225],"in":[34,81,228,234],"more":[36],"efficient":[37],"manner.":[38],"Mapping":[39],"pathways":[41],"genes":[43,210],"and":[44,63,112,116,129,147,184,211,217,238,249],"proteins":[45,212],"interest":[47],"goal":[50],"that":[51],"requires":[52],"frequent":[53],"reference":[54],"literature.":[57,122],"Pathway":[58],"databases":[59,76,85],"can":[60],"help":[61],"here":[62],"scientists":[64,131],"currently":[65],"have":[66,103],"choice":[68],"between":[69],"buying":[70],"access":[71],"externally":[73],"curated":[74],"pathway":[75,236],"or":[77,91],"building":[78],"their":[79],"own":[80],"house.":[82],"However":[83],"such":[84],"are":[86],"either":[87],"expensive":[88],"license":[90],"slow":[92],"populate":[94],"manually.":[95],"Building":[96],"upon":[97],"easily":[98],"available,":[99],"open-source":[100],"tools":[101],"we":[102,132,158],"developed":[104],"pipeline":[106],"automate":[108],"collection,":[110],"structuring":[111],"storage":[113],"gene":[115,142],"protein":[117],"interaction":[118,154],"data":[119,151,247],"from":[120,181,204],"team":[125],"both":[127],"biologists":[128],"computer":[130],"integrated":[133],"our":[134],"natural":[135],"language":[136],"processing":[137],"(NLP)":[138],"software":[139],"with":[140,164],"ontology":[143],"(GO)":[144],"collect":[146],"translate":[148],"unstructured":[149],"text":[150],"into":[152],"structured":[153,227],"data.":[155],"For":[156],"NLP":[157],"used":[159,200],"machine":[161],"learning":[162],"approach":[163],"rule":[166],"induction":[167],"program,":[168],"RAPIER":[169,175],"(http://www.":[170],"cs.":[171],"utexas.":[172],"edu/users/mUrapier.":[173],"html).":[174],"was":[176,187,226,232],"modified":[177],"learn":[179],"rules":[180,198],"tagged":[182,192],"documents,":[183],"then":[185],"it":[186,231],"trained":[188],"on":[189],"corpus":[191,207],"by":[193],"expert":[194],"curators.":[195],"The":[196],"resulting":[197],"were":[199,213,220],"extract":[202],"test":[206],"automatically.":[208],"Extracted":[209],"mapped":[214,221],"onto":[215,222],"Locuslink,":[216],"extracted":[218],"interactions":[219],"GO.":[223],"Once":[224],"way":[230],"stored":[233],"database":[237],"formal":[240],"structure":[241],"allowed":[242],"us":[243],"perform":[245],"advanced":[246],"mining":[248],"visualization.":[250]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
