{"id":"https://openalex.org/W2045749702","doi":"https://doi.org/10.1186/1471-2105-12-s8-s7","title":"Multi-stage gene normalization for full-text articles with context-based species filtering for dynamic dictionary entry selection","display_name":"Multi-stage gene normalization for full-text articles with context-based species filtering for dynamic dictionary entry selection","publication_year":2011,"publication_date":"2011-10-03","ids":{"openalex":"https://openalex.org/W2045749702","doi":"https://doi.org/10.1186/1471-2105-12-s8-s7","mag":"2045749702","pmid":"https://pubmed.ncbi.nlm.nih.gov/22151087"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-12-s8-s7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-s8-s7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-S8-S7","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-S8-S7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030771512","display_name":"Richard Tzong\u2010Han Tsai","orcid":"https://orcid.org/0000-0003-0513-107X"},"institutions":[{"id":"https://openalex.org/I99908691","display_name":"Yuan Ze University","ror":"https://ror.org/01fv1ds98","country_code":"TW","type":"education","lineage":["https://openalex.org/I99908691"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Richard Tzong-Han Tsai","raw_affiliation_strings":["Department of Computer Science and Engineering, Yuan Ze University, Chung Li, Taiwan, ROC. thtsai@saturn.yzu.edu.tw","Department of Computer Science & Engineering, Yuan Ze University, Chung-Li, Taiwan, R.O.C.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Yuan Ze University, Chung Li, Taiwan, ROC. thtsai@saturn.yzu.edu.tw","institution_ids":["https://openalex.org/I99908691"]},{"raw_affiliation_string":"Department of Computer Science & Engineering, Yuan Ze University, Chung-Li, Taiwan, R.O.C.#TAB#","institution_ids":["https://openalex.org/I99908691"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016587469","display_name":"Po\u2010Ting Lai","orcid":"https://orcid.org/0000-0003-2025-318X"},"institutions":[{"id":"https://openalex.org/I99908691","display_name":"Yuan Ze University","ror":"https://ror.org/01fv1ds98","country_code":"TW","type":"education","lineage":["https://openalex.org/I99908691"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Po-Ting Lai","raw_affiliation_strings":["Department of Computer Science and Engineering, Yuan Ze University, Chung Li, Taiwan, R.O.C","Department of Computer Science & Engineering, Yuan Ze University, Chung-Li, Taiwan, R.O.C.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Yuan Ze University, Chung Li, Taiwan, R.O.C","institution_ids":["https://openalex.org/I99908691"]},{"raw_affiliation_string":"Department of Computer Science & Engineering, Yuan Ze University, Chung-Li, Taiwan, R.O.C.#TAB#","institution_ids":["https://openalex.org/I99908691"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030771512"],"corresponding_institution_ids":["https://openalex.org/I99908691"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.1331,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.52920934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"12","issue":"S8","first_page":"S7","last_page":"S7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9147999882698059,"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":0.9147999882698059,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.03660000115633011,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.010499999858438969,"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/normalization","display_name":"Normalization (sociology)","score":0.7267501354217529},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7224981188774109},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5642563104629517},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.48502200841903687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4639785885810852},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42530032992362976},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39742717146873474},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32076478004455566},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11345919966697693}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7267501354217529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7224981188774109},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5642563104629517},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.48502200841903687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4639785885810852},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42530032992362976},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39742717146873474},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32076478004455566},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11345919966697693},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005796","descriptor_name":"Genes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005796","descriptor_name":"Genes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005796","descriptor_name":"Genes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"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}],"locations_count":3,"locations":[{"id":"doi:10.1186/1471-2105-12-s8-s7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-s8-s7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-S8-S7","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:22151087","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22151087","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:europepmc.org:2278685","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3269942","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-12-s8-s7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-s8-s7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-S8-S7","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.7300000190734863}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2045749702.pdf","grobid_xml":"https://content.openalex.org/works/W2045749702.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W174941419","https://openalex.org/W398859631","https://openalex.org/W1522276896","https://openalex.org/W1991154713","https://openalex.org/W1991476714","https://openalex.org/W1996250712","https://openalex.org/W2014362743","https://openalex.org/W2023839984","https://openalex.org/W2097898123","https://openalex.org/W2098740402","https://openalex.org/W2100751507","https://openalex.org/W2105114854","https://openalex.org/W2124176947","https://openalex.org/W2129113459","https://openalex.org/W2147880316","https://openalex.org/W2154142897","https://openalex.org/W2156909104","https://openalex.org/W2159640576","https://openalex.org/W2168422272","https://openalex.org/W2172016350","https://openalex.org/W2321621029","https://openalex.org/W2912691995","https://openalex.org/W3082398767","https://openalex.org/W3197473240","https://openalex.org/W4236654676","https://openalex.org/W4300022934"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2953716828","https://openalex.org/W2904857019","https://openalex.org/W2944728705","https://openalex.org/W3011538607","https://openalex.org/W2904022177","https://openalex.org/W4321441197","https://openalex.org/W2359348847","https://openalex.org/W4294432981","https://openalex.org/W4321276295"],"abstract_inverted_index":{"BACKGROUND:":[0],"Gene":[1],"normalization":[2],"(GN)":[3],"is":[4,26,312,327],"the":[5,9,27,31,86,93,123,130,133,168,186,191,208,216,253,263,271,280,289],"task":[6,29],"of":[7,13,23,30,88,96,111,132,163,170,291],"identifying":[8],"unique":[10],"database":[11],"IDs":[12],"genes":[14],"and":[15,65,151,161,193,244,249,276,303],"proteins":[16],"in":[17,61,158,190,226,252,268,277],"literature.":[18],"The":[19,42],"best-known":[20],"public":[21],"competition":[22],"GN":[24,28,83,103,138,149],"systems":[25,267],"BioCreative":[32,101,199,217,265,305],"challenge,":[33],"which":[34,155],"has":[35],"been":[36],"held":[37],"four":[38],"times":[39],"since":[40],"2003.":[41],"last":[43],"two":[44,50,176],"BioCreatives,":[45],"II.5":[46],"&":[47],"III,":[48],"had":[49],"significant":[51],"differences":[52],"from":[53],"earlier":[54],"tasks:":[55],"firstly,":[56],"they":[57,67],"provided":[58,135],"full-length":[59],"articles":[60],"addition":[62],"to":[63,122,180,185,239,321],"abstracts;":[64],"secondly,":[66],"included":[68],"multiple":[69,89,171],"species":[70,73,90,187,211],"without":[71],"providing":[72],"ID":[74],"information.":[75],"Full":[76],"papers":[77],"introduce":[78],"more":[79,328],"complex":[80],"targets":[81],"for":[82,99],"processing,":[84],"while":[85],"inclusion":[87,169],"vastly":[91],"increases":[92],"potential":[94],"size":[95],"dictionaries":[97],"needed":[98],"GN.":[100],"III":[102,200,218,266,306],"uses":[104,202],"Threshold":[105],"Average":[106],"Precision":[107],"at":[108,223],"a":[109,117,147,152,164,203],"median":[110],"k":[112],"errors":[113],"per":[114],"query":[115],"(TAP-k),":[116],"new":[118],"measure":[119],"closely":[120],"related":[121,184],"well-known":[124],"average":[125,219],"precision,":[126],"but":[127,325],"also":[128],"reflecting":[129],"reliability":[131],"score":[134],"by":[136,222,246],"each":[137],"system.":[139],"RESULTS:":[140],"To":[141,166],"use":[142],"full-paper":[143],"text,":[144],"we":[145,174,236],"employed":[146],"multi-stage":[148],"algorithm":[150],"ranking":[153],"method":[154],"exploit":[156],"information":[157],"different":[159],"sections":[160],"parts":[162],"paper.":[165],"handle":[167],"unknown":[172],"species,":[173],"developed":[175],"context-based":[177],"dynamic":[178,233,260,294,310,323],"strategies":[179,297],"select":[181],"dictionary":[182,205,234,295],"entries":[183],"that":[188],"appear":[189],"paper-section-wide":[192],"article-wide":[194,322],"context.":[195],"Our":[196,258,285],"originally":[197],"submitted":[198],"system":[201],"static":[204,301],"containing":[206],"only":[207],"most":[209,304],"common":[210],"entries.":[212],"It":[213],"already":[214],"exceeds":[215],"team":[220],"performance":[221],"least":[224],"24%":[225],"every":[227],"evaluation.":[228],"However,":[229],"using":[230],"our":[231,292,299],"proposed":[232,293],"strategies,":[235],"were":[237],"able":[238],"further":[240],"improve":[241],"TAP-5,":[242],"TAP-10,":[243],"TAP-20":[245],"16.47%,":[247],"13.57%":[248],"6.01%,":[250],"respectively":[251],"Gold":[254],"50":[255,273],"test":[256,274],"set.":[257,283],"best":[259,264],"strategy":[261,302,311,324],"outperforms":[262],"TAP-10":[269],"on":[270,279],"Silver":[272,281],"set":[275],"TAP-5":[278],"507":[282],"CONCLUSIONS:":[284],"experimental":[286],"results":[287],"demonstrate":[288],"superiority":[290],"selection":[296],"over":[298],"original":[300],"participant":[307],"systems.":[308],"Section-wide":[309],"preferred":[313],"because":[314],"it":[315,326],"achieves":[316],"very":[317],"similar":[318],"TAP-k":[319],"scores":[320],"efficient.":[329]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}
