{"id":"https://openalex.org/W3028004304","doi":"https://doi.org/10.1145/3386052.3386069","title":"Corpus Construction of Precision Medicine","display_name":"Corpus Construction of Precision Medicine","publication_year":2020,"publication_date":"2020-01-19","ids":{"openalex":"https://openalex.org/W3028004304","doi":"https://doi.org/10.1145/3386052.3386069","mag":"3028004304"},"language":"en","primary_location":{"id":"doi:10.1145/3386052.3386069","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3386052.3386069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 10th International Conference on Bioscience, Biochemistry and Bioinformatics","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/A5065337330","display_name":"Xuejing Ren","orcid":"https://orcid.org/0009-0005-5923-1422"},"institutions":[{"id":"https://openalex.org/I200296433","display_name":"Chinese Academy of Medical Sciences & Peking Union Medical College","ror":"https://ror.org/02drdmm93","country_code":"CN","type":"education","lineage":["https://openalex.org/I200296433"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuejing Ren","raw_affiliation_strings":["Institute of Medical Information, Chinese Academy of Medical Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Medical Information, Chinese Academy of Medical Sciences, Beijing, China","institution_ids":["https://openalex.org/I200296433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100897311","display_name":"Xinying An","orcid":null},"institutions":[{"id":"https://openalex.org/I200296433","display_name":"Chinese Academy of Medical Sciences & Peking Union Medical College","ror":"https://ror.org/02drdmm93","country_code":"CN","type":"education","lineage":["https://openalex.org/I200296433"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinying An","raw_affiliation_strings":["Institute of Medical Information, Chinese Academy of Medical Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Medical Information, Chinese Academy of Medical Sciences, Beijing, China","institution_ids":["https://openalex.org/I200296433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007598870","display_name":"Shaoping Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I200296433","display_name":"Chinese Academy of Medical Sciences & Peking Union Medical College","ror":"https://ror.org/02drdmm93","country_code":"CN","type":"education","lineage":["https://openalex.org/I200296433"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoping Fan","raw_affiliation_strings":["Institute of Medical Information, Chinese Academy of Medical Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Medical Information, Chinese Academy of Medical Sciences, Beijing, China","institution_ids":["https://openalex.org/I200296433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065337330"],"corresponding_institution_ids":["https://openalex.org/I200296433"],"apc_list":null,"apc_paid":null,"fwci":0.0829,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43107928,"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":"74","last_page":"77"},"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/T10028","display_name":"Topic Modeling","score":0.984499990940094,"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":0.9678999781608582,"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":0.6412551999092102},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4176599681377411},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34936755895614624},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3268807530403137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6412551999092102},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4176599681377411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34936755895614624},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3268807530403137}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3386052.3386069","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3386052.3386069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 10th International Conference on Bioscience, Biochemistry and Bioinformatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2048140075","https://openalex.org/W2116159459","https://openalex.org/W2126276057","https://openalex.org/W2153138487","https://openalex.org/W2163107094","https://openalex.org/W2346452181"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W3204019825"],"abstract_inverted_index":{"[Background]For":[0],"advancing":[1],"biomedical":[2,18,32,45,56,130,168,242],"text-mining":[3],"research,":[4],"formal":[5],"evaluations":[6],"and":[7,40,61,69,79,88,106,127,156,181,196,210,262],"manually":[8],"annotated":[9],"text":[10,158,169],"corpus":[11,19,33,57,120,233,251],"are":[12,58],"critically":[13],"important.":[14],"In":[15],"terms":[16],"of":[17,43,52,55,66,71,85,96,136,145,163,175,189,205,213,226,241,249],"construction,":[20],"in":[21,104,217],"order":[22],"to":[23,121,151,166,255,260],"meet":[24],"different":[25,31,35],"needs,":[26],"many":[27],"scholars":[28,259],"have":[29,62,114,178,252],"built":[30],"with":[34],"emphasis.":[36],"Through":[37],"horizontal":[38],"observation":[39],"vertical":[41],"comparison":[42],"existing":[44],"corpus,":[46,159],"it":[47],"is":[48,91,101,110,161],"found":[49],"that":[50],"most":[51],"the":[53,67,83,97,107,129,134,227,238,250,256],"entities":[54,72,90,100],"roughly":[59],"classified":[60],"narrow":[63],"coverage.":[64],"Most":[65],"classification":[68,84],"sub-classification":[70],"only":[73,221],"includes":[74],"genes,":[75],"proteins,":[76],"drugs,":[77],"diseases":[78,191],"other":[80,89],"entities,":[81],"while":[82],"pathways,":[86],"mutations":[87],"rarely":[92],"involved.":[93],"The":[94],"exploration":[95],"relationship":[98,108],"between":[99],"not":[102],"enough":[103],"depth":[105],"type":[109],"uncomprehensive.":[111],"Therefore,":[112],"we":[113,220],"developed":[115],"our":[116],"own":[117],"precise":[118,231],"medical":[119,125,232],"store":[122],"more":[123,154],"comprehensive":[124,155],"knowledge":[126],"enrich":[128],"corpus.[Methods]Through":[131],"repeated":[132],"iteration":[133],"process":[135,240],"article":[137],"selection,":[138],"systematic":[139],"evaluation,":[140],"manual":[141,182],"annotation,":[142,146],"formulating":[143],"consensus":[144],"cross":[147],"validation,":[148],"submission":[149],"assessment":[150],"form":[152],"a":[153,173,223],"authoritative":[157],"which":[160,236],"also":[162],"great":[164],"significance":[165],"promote":[167],"mining":[170],"research.[Results]At":[171],"present,":[172,246],"total":[174],"6000":[176],"articles":[177,188,204,212],"been":[179,253],"auto":[180],"annotated.":[183],"Each":[184],"1000":[185],"PubMed":[186],"English":[187],"cardiovascular":[190],"(circulatory":[192],"system)":[193,200,209],"intestinal":[194],"neoplasm":[195,198,207],"liver":[197],"(digestive":[199],"metabolic":[201],"diseases;":[202],"1500":[203],"lung":[206,228],"(respiratory":[208],"500":[211],"neurological":[214],"diseases.":[215],"(but":[216],"this":[218],"issue,":[219],"had":[222],"detailed":[224],"illustration":[225],"neoplasm.[Conclusion]A":[229],"high-quality":[230],"was":[234],"constructed,":[235],"promotes":[237],"research":[239],"data":[243],"mining.":[244],"At":[245],"some":[247],"resources":[248],"opened":[254],"public,":[257],"welcome":[258],"use":[261],"put":[263],"forward":[264],"valuable":[265],"suggestions.":[266]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}