{"id":"https://openalex.org/W2015872073","doi":"https://doi.org/10.1093/database/bau113","title":"A robust data-driven approach for gene ontology annotation","display_name":"A robust data-driven approach for gene ontology annotation","publication_year":2014,"publication_date":"2014-11-25","ids":{"openalex":"https://openalex.org/W2015872073","doi":"https://doi.org/10.1093/database/bau113","mag":"2015872073","pmid":"https://pubmed.ncbi.nlm.nih.gov/25425037"},"language":"en","primary_location":{"id":"doi:10.1093/database/bau113","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bau113","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bau113/8248798/bau113.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bau113/8248798/bau113.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5105212035","display_name":"Yanpeng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I166722992","display_name":"University of Massachusetts Chan Medical School","ror":"https://ror.org/0464eyp60","country_code":"US","type":"education","lineage":["https://openalex.org/I166722992"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Y. Li","raw_affiliation_strings":["Department of Quantitative Health Sciences, University of Massachusetts Medical School, Worcester, MA, USA, Department of Computer Science, University of Massachusetts, Amherst, MA, USA and VA Central Western Massachusetts, Worcester, MA, USA liyanpeng.lyp@gmail.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Quantitative Health Sciences, University of Massachusetts Medical School, Worcester, MA, USA, Department of Computer Science, University of Massachusetts, Amherst, MA, USA and VA Central Western Massachusetts, Worcester, MA, USA liyanpeng.lyp@gmail.com","institution_ids":["https://openalex.org/I166722992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017601806","display_name":"Hong Yu","orcid":"https://orcid.org/0000-0001-9263-5035"},"institutions":[{"id":"https://openalex.org/I166722992","display_name":"University of Massachusetts Chan Medical School","ror":"https://ror.org/0464eyp60","country_code":"US","type":"education","lineage":["https://openalex.org/I166722992"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Yu","raw_affiliation_strings":["Department of Quantitative Health Sciences, University of Massachusetts Medical School, Worcester, MA, USA, Department of Computer Science, University of Massachusetts, Amherst, MA, USA and VA Central Western Massachusetts, Worcester, MA, USA Department of Quantitative Health Sciences, University of Massachusetts Medical School, Worcester, MA, USA, Department of Computer Science, University of Massachusetts, Amherst, MA, USA and VA Central Western Massachusetts, Worcester, MA, USA Department of Quantitative Health Sciences, University of Massachusetts Medical School, Worcester, MA, USA, Department of Computer Science, University of Massachusetts, Amherst, MA, USA and VA Central Western Massachusetts, Worcester, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Quantitative Health Sciences, University of Massachusetts Medical School, Worcester, MA, USA, Department of Computer Science, University of Massachusetts, Amherst, MA, USA and VA Central Western Massachusetts, Worcester, MA, USA Department of Quantitative Health Sciences, University of Massachusetts Medical School, Worcester, MA, USA, Department of Computer Science, University of Massachusetts, Amherst, MA, USA and VA Central Western Massachusetts, Worcester, MA, USA Department of Quantitative Health Sciences, University of Massachusetts Medical School, Worcester, MA, USA, Department of Computer Science, University of Massachusetts, Amherst, MA, USA and VA Central Western Massachusetts, Worcester, MA, USA","institution_ids":["https://openalex.org/I166722992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I166722992"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":0.1396,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.52696798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2014","issue":"0","first_page":"bau113","last_page":"bau113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9929999709129333,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9918000102043152,"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":0.8106437921524048},{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.7584875822067261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6221306920051575},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5754069685935974},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.45745575428009033},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.44807836413383484},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44761356711387634},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38349565863609314},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34572240710258484},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.19733580946922302},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.09775778651237488}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106437921524048},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.7584875822067261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6221306920051575},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5754069685935974},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.45745575428009033},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.44807836413383484},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44761356711387634},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38349565863609314},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34572240710258484},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.19733580946922302},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.09775778651237488}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012015","descriptor_name":"Reference Standards","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012015","descriptor_name":"Reference Standards","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012015","descriptor_name":"Reference Standards","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D063990","descriptor_name":"Gene Ontology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D063990","descriptor_name":"Gene Ontology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D063990","descriptor_name":"Gene Ontology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/database/bau113","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bau113","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bau113/8248798/bau113.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},{"id":"pmid:25425037","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25425037","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":"Database : the journal of biological databases and curation","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:4243380","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4243380","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Database (Oxford)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/database/bau113","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bau113","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bau113/8248798/bau113.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1259772160","display_name":null,"funder_award_id":"GM095476","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G7183281665","display_name":null,"funder_award_id":"R01 GM095476","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2015872073.pdf","grobid_xml":"https://content.openalex.org/works/W2015872073.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1590993728","https://openalex.org/W1603229901","https://openalex.org/W1607454220","https://openalex.org/W2018874418","https://openalex.org/W2047782770","https://openalex.org/W2056119436","https://openalex.org/W2063993968","https://openalex.org/W2064030835","https://openalex.org/W2102770365","https://openalex.org/W2103017472","https://openalex.org/W2103316358","https://openalex.org/W2106148045","https://openalex.org/W2118020653","https://openalex.org/W2121844933","https://openalex.org/W2129113459","https://openalex.org/W2131730455","https://openalex.org/W2149684865","https://openalex.org/W2154142897","https://openalex.org/W2156362066","https://openalex.org/W2166183437","https://openalex.org/W2435251607","https://openalex.org/W2911964244","https://openalex.org/W2917056928"],"related_works":["https://openalex.org/W3173084154","https://openalex.org/W2982021180","https://openalex.org/W2251497876","https://openalex.org/W2241081188","https://openalex.org/W2128567707","https://openalex.org/W2962745453","https://openalex.org/W1515518862","https://openalex.org/W2360571912","https://openalex.org/W1597783326","https://openalex.org/W2475889241"],"abstract_inverted_index":{"Gene":[0],"ontology":[1],"(GO)":[2],"and":[3,13,117,129,143,155,167,201,209,228,240],"GO":[4,31,44,172,185,205,216],"annotation":[5,21,32],"are":[6],"important":[7],"resources":[8],"for":[9],"biological":[10],"information":[11,179,239],"management":[12],"knowledge":[14],"discovery,":[15],"but":[16],"the":[17,37,50,67,71,74,123,171,184,202,235,245,248,261,271],"speed":[18],"of":[19,26,39,112,204,221,237],"manual":[20],"became":[22],"a":[23,81,93,194,210,253,257],"major":[24],"bottleneck":[25],"database":[27],"curation.":[28],"BioCreative":[29],"IV":[30],"task":[33,63],"aims":[34],"to":[35,46,84,182,189],"evaluate":[36],"performance":[38,132,157,220],"system":[40],"that":[41,99,197,234],"automatically":[42],"assigns":[43],"terms":[45,206],"genes":[47],"based":[48,213],"on":[49,153,214],"narrative":[51],"sentences":[52,87],"in":[53,61,114,119,137,207,269],"biomedical":[54],"literature.":[55],"This":[56],"article":[57],"presents":[58],"our":[59,222,265],"work":[60],"this":[62],"as":[64,66],"well":[65],"experimental":[68,262],"results":[69],"after":[70],"competition.":[72],"For":[73,170],"evidence":[75,86,191],"sentence":[76,192],"extraction":[77],"subtask,":[78,175],"we":[79,126,176,251],"built":[80],"binary":[82],"classifier":[83],"identify":[85],"using":[88,193,256],"reference":[89],"distance":[90],"estimator":[91],"(RDE),":[92],"recently":[94],"proposed":[95],"semi-supervised":[96],"learning":[97,161],"method":[98,147,181,212],"learns":[100],"new":[101],"features":[102,136],"from":[103],"around":[104],"10":[105],"million":[106],"unlabeled":[107],"sentences,":[108],"achieving":[109],"an":[110,178],"F1":[111,131,154,227,255],"19.3%":[113],"exact":[115],"match":[116],"32.5%":[118],"relaxed":[120],"match.":[121],"In":[122,140,247],"post-submission":[124,249],"experiment,":[125],"obtained":[127,252],"22.1%":[128],"35.7%":[130],"by":[133],"incorporating":[134],"bigram":[135],"RDE":[138],"learning.":[139],"both":[141,270],"development":[142],"test":[144],"sets,":[145],"RDE-based":[146],"achieved":[148],"over":[149],"20%":[150],"relative":[151],"improvement":[152],"AUC":[156],"against":[158],"classical":[159],"supervised":[160],"methods,":[162],"e.g.":[163],"support":[164],"vector":[165],"machine":[166],"logistic":[168],"regression.":[169],"term":[173,186],"prediction":[174],"developed":[177],"retrieval-based":[180],"retrieve":[183],"most":[187],"relevant":[188],"each":[190],"ranking":[195],"function":[196],"combined":[198],"cosine":[199],"similarity":[200],"frequency":[203,238],"documents,":[208],"filtering":[211,242],"high-level":[215],"classes.":[217],"The":[218],"best":[219],"submitted":[223],"runs":[224],"was":[225],"7.8%":[226],"22.2%":[229],"hierarchy":[230,241],"F1.":[231],"We":[232],"found":[233],"incorporation":[236],"substantially":[243],"improved":[244],"performance.":[246],"evaluation,":[250],"10.6%":[254],"simpler":[258],"setting.":[259],"Overall,":[260],"analysis":[263],"showed":[264],"approaches":[266],"were":[267],"robust":[268],"two":[272],"tasks.":[273]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}