{"id":"https://openalex.org/W2094092623","doi":"https://doi.org/10.1109/bmei.2011.6098714","title":"Protein-protein interaction extraction from bio-literature with compact features and data sampling strategy","display_name":"Protein-protein interaction extraction from bio-literature with compact features and data sampling strategy","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W2094092623","doi":"https://doi.org/10.1109/bmei.2011.6098714","mag":"2094092623"},"language":"en","primary_location":{"id":"doi:10.1109/bmei.2011.6098714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bmei.2011.6098714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 4th International Conference on Biomedical Engineering and Informatics (BMEI)","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/A5100400400","display_name":"Hongtao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongtao Zhang","raw_affiliation_strings":["State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Tech, Tsinghua University, Beijing, China","State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology,Tsinghua University,Beijing 100084,China)"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Tech, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology,Tsinghua University,Beijing 100084,China)","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047922360","display_name":"Minglie Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minglie Huang","raw_affiliation_strings":["State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Tech, Tsinghua University, Beijing, China","State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology,Tsinghua University,Beijing 100084,China)"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Tech, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology,Tsinghua University,Beijing 100084,China)","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100452969","display_name":"Xiaoyan Zhu","orcid":"https://orcid.org/0000-0001-9616-9289"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Zhu","raw_affiliation_strings":["State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Tech, Tsinghua University, Beijing, China","State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology,Tsinghua University,Beijing 100084,China)"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Tech, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology,Tsinghua University,Beijing 100084,China)","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100400400"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3909,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.62177673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"20","issue":null,"first_page":"1767","last_page":"1771"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9921000003814697,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9745000004768372,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/computer-science","display_name":"Computer science","score":0.7736132740974426},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6483871936798096},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5908589363098145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5838386416435242},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.553707480430603},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.49910664558410645},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4770171642303467},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47122275829315186},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45989516377449036},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.44974851608276367},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.411952942609787},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4105130136013031}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7736132740974426},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6483871936798096},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5908589363098145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5838386416435242},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.553707480430603},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.49910664558410645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4770171642303467},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47122275829315186},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45989516377449036},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.44974851608276367},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.411952942609787},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4105130136013031},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/bmei.2011.6098714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bmei.2011.6098714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 4th International Conference on Biomedical Engineering and Informatics (BMEI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1493270114","https://openalex.org/W1831729862","https://openalex.org/W1982428412","https://openalex.org/W1996787131","https://openalex.org/W1997271825","https://openalex.org/W2016928406","https://openalex.org/W2023639956","https://openalex.org/W2085989833","https://openalex.org/W2102770365","https://openalex.org/W2117689108","https://openalex.org/W2121844933","https://openalex.org/W2130745297","https://openalex.org/W2132288458","https://openalex.org/W2138776277","https://openalex.org/W2141605886","https://openalex.org/W2155723007","https://openalex.org/W2166111585","https://openalex.org/W2167426290","https://openalex.org/W2951911250","https://openalex.org/W4252684946","https://openalex.org/W6629460809","https://openalex.org/W6638557778","https://openalex.org/W7048424596"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W3009369890","https://openalex.org/W4312490297","https://openalex.org/W2062212388"],"abstract_inverted_index":{"A":[0],"large":[1],"number":[2],"of":[3,22,80,95,125],"protein-protein":[4],"interactions":[5],"(PPIs)":[6],"have":[7],"buried":[8],"in":[9,44,147],"massive":[10],"biomedical":[11],"articles":[12],"published":[13],"over":[14],"the":[15,20,40,52,78,98,114,126,133,150],"years.":[16],"This":[17],"leads":[18],"to":[19,61,63,76,92,112,120,132],"development":[21],"automatic":[23],"PPI":[24],"extraction":[25],"methods.":[26],"However,":[27],"existing":[28],"methods":[29,46],"based":[30,109],"on":[31,97,110,149],"supervised":[32],"machine":[33],"learning":[34],"still":[35],"face":[36],"some":[37],"challenges:":[38],"(1)":[39],"feature":[41,81],"space":[42],"exploited":[43],"these":[45,84],"is":[47],"very":[48],"sparse;":[49],"and":[50,73],"(2)":[51],"data":[53,106,122],"used":[54],"for":[55],"training":[56],"are":[57,129],"imbalanced":[58],"with":[59],"respect":[60],"categories":[62],"be":[64],"classified.":[65],"In":[66,118],"this":[67,138],"paper,":[68],"we":[69,103],"first":[70],"construct":[71],"rich":[72],"compact":[74],"features":[75],"alleviate":[77],"issue":[79],"sparseness.":[82],"With":[83],"features,":[85],"our":[86,140],"method":[87,141],"outperforms":[88],"baselines":[89],"by":[90],"up":[91],"an":[93],"F-score":[94,148],"9.58%":[96],"original":[99,151],"AIMed":[100,152],"corpus.":[101,153],"Furthermore,":[102],"propose":[104],"a":[105,143],"sampling":[107],"strategy":[108],"under-sampling":[111],"address":[113],"class":[115,128],"imbalance":[116],"problem.":[117],"order":[119],"re-balance":[121],"distribution,":[123],"samples":[124],"majority":[127],"removed":[130],"according":[131],"prediction":[134],"results":[135],"iteratively.":[136],"By":[137],"means,":[139],"achieves":[142],"further":[144],"2.49%":[145],"improvement":[146]},"counts_by_year":[{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}