{"id":"https://openalex.org/W2109410256","doi":"https://doi.org/10.1109/ijcbs.2009.68","title":"Semi-supervised Learning of Text Classification on Bacterial Protein-Protein Interaction Documents","display_name":"Semi-supervised Learning of Text Classification on Bacterial Protein-Protein Interaction Documents","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2109410256","doi":"https://doi.org/10.1109/ijcbs.2009.68","mag":"2109410256"},"language":"en","primary_location":{"id":"doi:10.1109/ijcbs.2009.68","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcbs.2009.68","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Joint Conference on Bioinformatics, Systems Biology and Intelligent Computing","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/A5102973802","display_name":"Guixian Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]},{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]},{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Guixian Xu","raw_affiliation_strings":["College of Computer Science, Beijing Institute of Technology, Beijing, China","Department of Bio, Georgetown University Medical Center, Washington D.C., DC, USA"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Department of Bio, Georgetown University Medical Center, Washington D.C., DC, USA","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082774439","display_name":"Zhendong Niu","orcid":"https://orcid.org/0000-0002-0576-7572"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhendong Niu","raw_affiliation_strings":["College of Computer Science, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012975089","display_name":"Peter Uetz","orcid":"https://orcid.org/0000-0001-6194-4927"},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Uetz","raw_affiliation_strings":["J. Craig Venter Institute, Rockville, MD, USA"],"affiliations":[{"raw_affiliation_string":"J. Craig Venter Institute, Rockville, MD, USA","institution_ids":["https://openalex.org/I1301553790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101586852","display_name":"Xu Gao","orcid":"https://orcid.org/0000-0003-3513-225X"},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Gao","raw_affiliation_strings":["North China Grid Company Limited, Beijing, China"],"affiliations":[{"raw_affiliation_string":"North China Grid Company Limited, Beijing, China","institution_ids":["https://openalex.org/I17442442"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043127823","display_name":"Xuping Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I91935597","display_name":"University of South China","ror":"https://ror.org/03mqfn238","country_code":"CN","type":"education","lineage":["https://openalex.org/I91935597"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuping Qin","raw_affiliation_strings":["University of South China, Hunan, China"],"affiliations":[{"raw_affiliation_string":"University of South China, Hunan, China","institution_ids":["https://openalex.org/I91935597"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101585391","display_name":"Hongfang Liu","orcid":"https://orcid.org/0000-0003-2570-3741"},"institutions":[{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]},{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongfang Liu","raw_affiliation_strings":["Department of Bio, Georgetown University Medical Center, Washington D.C., DC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Bio, Georgetown University Medical Center, Washington D.C., DC, USA","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102973802"],"corresponding_institution_ids":["https://openalex.org/I125839683","https://openalex.org/I184565670","https://openalex.org/I2799903593"],"apc_list":null,"apc_paid":null,"fwci":0.5249,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.66159576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"18","issue":null,"first_page":"263","last_page":"270"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9915000200271606,"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":0.9868999719619751,"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":0.8051779270172119},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.5583505034446716},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5462011098861694},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.517983078956604},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5124357342720032},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4908815026283264},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3496854305267334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33414649963378906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8051779270172119},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.5583505034446716},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5462011098861694},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.517983078956604},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5124357342720032},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4908815026283264},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3496854305267334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33414649963378906},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcbs.2009.68","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcbs.2009.68","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Joint Conference on Bioinformatics, Systems Biology and Intelligent Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6200000047683716,"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/W22461475","https://openalex.org/W1558318887","https://openalex.org/W1861993554","https://openalex.org/W1969387993","https://openalex.org/W2102162073","https://openalex.org/W2120433106","https://openalex.org/W2122076882","https://openalex.org/W2133699278","https://openalex.org/W2139259976","https://openalex.org/W2144949988","https://openalex.org/W2156772624","https://openalex.org/W2159583324","https://openalex.org/W2160238006","https://openalex.org/W2168602944","https://openalex.org/W6633537095","https://openalex.org/W6639315830","https://openalex.org/W6685036661"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4231274751","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W2571255492","https://openalex.org/W4239293476"],"abstract_inverted_index":{"Protein-protein":[0],"interaction":[1],"(PPI)":[2],"network":[3],"is":[4,21,46,83,91,102,159,181,189,200,238,266,289],"essential":[5],"to":[6,48,75,190,201,239,267,290],"understand":[7],"the":[8,66,89,104,173,186,197,217,269,292],"fundamental":[9],"processes":[10],"governing":[11],"cell":[12],"biology.":[13],"The":[14,263,286],"mining":[15,67],"and":[16,27,63,68,152,164,196,225,258,274],"curation":[17,40,69],"of":[18,70,111,133,138,150,156,219],"PPI":[19,31,71,121,222],"knowledge":[20,32,122],"critical":[22],"for":[23,179,221,313],"analyzing":[24],"high-throughput":[25],"genomics":[26],"proteomics":[28],"data.":[29],"Several":[30],"bases":[33,123],"have":[34,49],"been":[35,170],"generated":[36],"through":[37],"expensive":[38],"manual":[39],"but":[41],"far":[42],"from":[43,119,162],"comprehensive.":[44],"It":[45],"desired":[47],"a":[50,94,108,130,147,153,182,232,241,247],"document":[51,77,87,223,255],"classification":[52,78,224],"system":[53],"which":[54,168,251],"can":[55,114],"classify":[56],"documents":[57,113,135,158,166,194,278,300],"as":[58,208,256,281,283,302],"PPI-related":[59,62],"or":[60,98,118,210],"not":[61,141],"therefore":[64],"assist":[65],"knowledge.":[72],"In":[73,212],"order":[74],"build":[76],"systems,":[79],"an":[80],"annotated":[81],"corpus":[82,90],"needed":[84],"where":[85,136,185],"each":[86,253,314],"in":[88,172,304],"tagged":[92],"with":[93,124],"label":[95],"(either":[96],"positive":[97,112,163],"negative).":[99],"However,":[100],"it":[101],"usually":[103],"case":[105],"that":[106],"only":[107],"small":[109,148],"number":[110,132,149,155],"be":[115],"obtained":[116],"manually":[117],"existing":[120],"literature":[125],"evidences.":[126],"Meanwhile,":[127],"there":[128],"are":[129,140],"large":[131,154],"unlabeled":[134,157,277,299],"most":[137],"them":[139],"PPI-related.":[142],"Machine":[143],"learning":[144,161,249,309],"based":[145,230],"on":[146,231],"positives":[151],"called":[160],"unlabelled":[165,254,261],"(LPU)":[167],"has":[169],"studied":[171],"general":[174],"domain.":[175],"A":[176],"popular":[177],"approach":[178],"LPU":[180,220],"two-step":[183,228,315],"strategy":[184],"first":[187],"step":[188,199],"obtain":[191,240],"reliable":[192,284],"negative":[193,242,270,282,293,303],"(RN)":[195],"second":[198,264],"refine":[202,268],"RN":[203],"using":[204],"various":[205],"methods":[206],"such":[207],"clustering":[209],"boosting.":[211],"this":[213],"paper,":[214],"we":[215],"tackle":[216],"problem":[218],"compare":[226],"three":[227],"procedures":[229],"public":[233],"data":[234,243,271,294],"set,":[235],"Reuters-21578.":[236],"One":[237],"set":[244,272,295],"by":[245,297],"building":[246],"machine":[248,308],"classifier":[250],"treats":[252],"negatives":[257],"then":[259],"classifies":[260],"documents.":[262],"procedure":[265,288],"iteratively":[273,296],"consider":[275],"those":[276],"always":[279],"classified":[280,301],"negatives.":[285],"third":[287],"augment":[291],"including":[298],"any":[305],"iteration.":[306],"Three":[307],"algorithms":[310],"were":[311],"deployed":[312],"procedure.":[316]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}