{"id":"https://openalex.org/W1594705974","doi":"https://doi.org/10.1109/csb.2003.1227431","title":"Identifying gene and protein names from biological texts","display_name":"Identifying gene and protein names from biological texts","publication_year":2004,"publication_date":"2004-03-30","ids":{"openalex":"https://openalex.org/W1594705974","doi":"https://doi.org/10.1109/csb.2003.1227431","mag":"1594705974"},"language":"en","primary_location":{"id":"doi:10.1109/csb.2003.1227431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227431","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/A5031976204","display_name":"W. Xuan","orcid":"https://orcid.org/0009-0000-7435-6876"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"W. Xuan","raw_affiliation_strings":["Mental Health Research Institute and Department of Psychatry, University of Michigan, Ann Arbor, MI, USA","Dept. of Psychiatry, Michigan Univ., Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"Mental Health Research Institute and Department of Psychatry, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Dept. of Psychiatry, Michigan Univ., Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049286080","display_name":"Stanley J. Watson","orcid":"https://orcid.org/0000-0003-4980-5523"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S.J. Watson","raw_affiliation_strings":["Mental Health Research Institute and Department of Psychatry, University of Michigan, Ann Arbor, MI, USA","Dept. of Psychiatry, Michigan Univ., Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"Mental Health Research Institute and Department of Psychatry, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Dept. of Psychiatry, Michigan Univ., Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007964297","display_name":"Huda Akil","orcid":"https://orcid.org/0000-0003-0623-1056"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Akil","raw_affiliation_strings":["Mental Health Research Institute and Department of Psychatry, University of Michigan, Ann Arbor, MI, USA","Dept. of Psychiatry, Michigan Univ., Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"Mental Health Research Institute and Department of Psychatry, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Dept. of Psychiatry, Michigan Univ., Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108018249","display_name":"Fan Meng","orcid":"https://orcid.org/0000-0001-8002-0615"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"F. Meng","raw_affiliation_strings":["Mental Health Research Institute and Department of Psychatry, University of Michigan, Ann Arbor, MI, USA","Dept. of Psychiatry, Michigan Univ., Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"Mental Health Research Institute and Department of Psychatry, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Dept. of Psychiatry, Michigan Univ., Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031976204"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.3508,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.55374543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"639","last_page":"643"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":1.0,"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":1.0,"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":0.9860000014305115,"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":0.9783999919891357,"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":0.7175014019012451},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.620513379573822},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5969935655593872},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4861585795879364},{"id":"https://openalex.org/keywords/gene-nomenclature","display_name":"Gene nomenclature","score":0.46816062927246094},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4636218845844269},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.45373857021331787},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4420601427555084},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4323849678039551},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.43178796768188477},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4260636568069458},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40730899572372437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35792624950408936},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.14208802580833435},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.11231774091720581},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.07857391238212585},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07494735717773438},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07390612363815308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7175014019012451},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.620513379573822},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5969935655593872},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4861585795879364},{"id":"https://openalex.org/C62177273","wikidata":"https://www.wikidata.org/wiki/Q5531556","display_name":"Gene nomenclature","level":4,"score":0.46816062927246094},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4636218845844269},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.45373857021331787},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4420601427555084},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4323849678039551},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.43178796768188477},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4260636568069458},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40730899572372437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35792624950408936},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.14208802580833435},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11231774091720581},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.07857391238212585},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07494735717773438},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07390612363815308},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/csb.2003.1227431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227431","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":0.6600000262260437,"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":17,"referenced_works":["https://openalex.org/W1508431184","https://openalex.org/W1592053870","https://openalex.org/W1991154713","https://openalex.org/W2000484009","https://openalex.org/W2008085355","https://openalex.org/W2095800292","https://openalex.org/W2130260860","https://openalex.org/W2134769633","https://openalex.org/W2144001613","https://openalex.org/W2158040974","https://openalex.org/W2165270659","https://openalex.org/W2167895352","https://openalex.org/W6630433919","https://openalex.org/W6635275303","https://openalex.org/W6648116614","https://openalex.org/W6650339521","https://openalex.org/W6652231536"],"related_works":["https://openalex.org/W2358294942","https://openalex.org/W4367460280","https://openalex.org/W2004087619","https://openalex.org/W4321472216","https://openalex.org/W2557094866","https://openalex.org/W2469016277","https://openalex.org/W2362196274","https://openalex.org/W2757101400","https://openalex.org/W1982302668","https://openalex.org/W2240384024"],"abstract_inverted_index":{"Extracting":[0],"and":[1,4,19,54,62,68,78,118,125],"identifying":[2],"gene":[3,53,67],"protein":[5,55,69],"names":[6,70,87],"from":[7],"literature":[8,72,98,136],"is":[9],"a":[10,60,74,106,130],"critical":[11],"step":[12],"for":[13,133],"mining":[14,137],"functional":[15],"information":[16,99],"of":[17,32,76,97],"genes":[18],"proteins.":[20],"While":[21],"extensive":[22],"efforts":[23],"have":[24],"been":[25],"devoted":[26],"to":[27,46,65,88],"this":[28],"important":[29],"task,":[30],"most":[31],"them":[33],"were":[34],"aiming":[35],"at":[36],"extracting":[37],"gene/protein":[38,102],"name":[39,50],"per":[40],"se":[41],"without":[42],"paying":[43],"much":[44],"attention":[45],"associate":[47],"the":[48,85,94],"extracted":[49,86],"with":[51,100],"existing":[52,101],"database":[56],"entries.":[57],"We":[58],"developed":[59],"simple":[61],"efficient":[63],"method":[64,112,121],"identify":[66],"in":[71],"using":[73],"combination":[75],"heuristic":[77],"statistical":[79],"strategies.":[80],"Our":[81,120],"approach":[82],"will":[83],"map":[84],"individual":[89],"LocusLink":[90],"entries":[91],"thus":[92],"enable":[93],"seamless":[95],"integration":[96],"databases.":[103],"Evaluation":[104],"on":[105],"test":[107],"corpus":[108],"shows":[109],"that":[110],"our":[111],"can":[113,126],"achieve":[114],"both":[115],"high":[116],"recall":[117],"precision.":[119],"exhibits":[122],"good":[123],"performance":[124],"be":[127],"used":[128],"as":[129],"building":[131],"block":[132],"large":[134],"biomedical":[135],"systems.":[138]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}