{"id":"https://openalex.org/W7097222201","doi":null,"title":"32 Genome Informatics 16(2): 32\u201344 (2005) Supporting the Curation of Biological Databases with Reusable Text Mining","display_name":"32 Genome Informatics 16(2): 32\u201344 (2005) Supporting the Curation of Biological Databases with Reusable Text Mining","publication_year":2008,"publication_date":"2008-04-02","ids":{"openalex":"https://openalex.org/W7097222201"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.102.41","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.102.41","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.jsbi.org/journal/GIW05/GIW05F011.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5052502655","display_name":"Olivo Miotto","orcid":"https://orcid.org/0000-0001-8060-6771","observed_orcids":["https://orcid.org/0000-0001-8060-6771"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olivo Miotto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Tin Wee Tan Vladimir Brusic","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tin Wee Tan Vladimir Brusic","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34549356,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9657999873161316,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9657999873161316,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.031599998474121094,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.00039999998989515007,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/text-mining","display_name":"text mining","score":0.6899999976158142},{"id":"https://openalex.org/keywords/document-classification","display_name":"document classification","score":0.9449999928474426},{"id":"https://openalex.org/keywords/allergen-cross-reactivity","display_name":"allergen cross-reactivity","score":0.8579999804496765},{"id":"https://openalex.org/keywords/pubmed-abstracts","display_name":"PubMed abstracts","score":0.9819999933242798},{"id":"https://openalex.org/keywords/feature-scoring","display_name":"feature scoring","score":0.625},{"id":"https://openalex.org/keywords/neural-network","display_name":"artificial neural networks","score":0.7009999752044678},{"id":"https://openalex.org/keywords/cart-classifier","display_name":"CART classifier","score":0.7099999785423279},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.34299999475479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803000211715698},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6162999868392944},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.4860000014305115},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C20901353","wikidata":"https://www.wikidata.org/wiki/Q4117139","display_name":"Biological database","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.41350001096725464},{"id":"https://openalex.org/C191630685","wikidata":"https://www.wikidata.org/wiki/Q4027615","display_name":"Informatics","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38269999623298645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37389999628067017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37279999256134033},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3619000017642975},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3546999990940094},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.335999995470047},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33230000734329224},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.32260000705718994},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C107763842","wikidata":"https://www.wikidata.org/wiki/Q181040","display_name":"Clef","level":3,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.102.41","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.102.41","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.jsbi.org/journal/GIW05/GIW05F011.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1499898004","https://openalex.org/W2104655105","https://openalex.org/W1964670939","https://openalex.org/W2913593516","https://openalex.org/W2124348066","https://openalex.org/W2104544690","https://openalex.org/W2123579157","https://openalex.org/W2974691684","https://openalex.org/W7095369021","https://openalex.org/W2770900687"],"abstract_inverted_index":{"Curators":[0],"of":[1,22,38,48,60,67,88,95,116,161],"biological":[2],"databases":[3],"transfer":[4],"knowledge":[5],"from":[6],"scientific":[7],"publications,":[8],"a":[9,46,52,68,100],"laborious":[10],"and":[11,63,122,128],"expensive":[12],"manual":[13],"process.":[14],"Machine":[15],"learning":[16],"algorithms":[17,120],"can":[18,42,157],"reduce":[19],"the":[20,36,65,86,114,142,146,153,159],"workload":[21],"curators":[23,57],"by":[24,58],"filtering":[25],"relevant":[26],"biomedical":[27],"literature,":[28],"though":[29],"their":[30],"widespread":[31],"adoption":[32],"will":[33],"depend":[34],"on":[35],"availability":[37],"intuitive":[39],"tools":[40],"that":[41,76,107,152],"be":[43],"configured":[44],"for":[45,55],"variety":[47],"tasks.":[49],"We":[50,112],"propose":[51,156],"new":[53],"method":[54,73,97,154],"supporting":[56],"means":[59],"document":[61],"categorization,":[62],"describe":[64],"architecture":[66],"curator-oriented":[69],"tool":[70],"implementing":[71],"this":[72,89,96],"using":[74,131],"techniques":[75],"require":[77],"no":[78],"computational":[79],"linguistic":[80],"or":[81],"programming":[82],"expertise.":[83],"To":[84],"demonstrate":[85],"feasibility":[87],"approach,":[90],"we":[91,155],"prototyped":[92],"an":[93],"application":[94],"to":[98,125,164],"support":[99],"real":[101],"curation":[102],"task:":[103],"identifying":[104],"PubMed":[105],"abstracts":[106],"contain":[108],"allergen":[109],"cross-reactivity":[110],"information.":[111],"tested":[113],"performance":[115,140,162],"two":[117],"different":[118],"classifier":[119,144],"(CART":[121],"ANN),":[123],"applied":[124],"both":[126],"composite":[127],"single-word":[129],"features,":[130],"several":[132],"feature":[133],"scoring":[134],"functions.":[135],"Both":[136],"classifiers":[137],"exceeded":[138],"our":[139],"targets,":[141],"ANN":[143],"yielding":[145],"best":[147],"results.":[148],"These":[149],"results":[150],"show":[151],"deliver":[158],"level":[160],"needed":[163],"assist":[165],"database":[166],"curation.":[167]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-27T00:00:00"}