{"id":"https://openalex.org/W4313261557","doi":"https://doi.org/10.1093/bioinformatics/btac841","title":"Imbalanced classification for protein subcellular localization with multilabel oversampling","display_name":"Imbalanced classification for protein subcellular localization with multilabel oversampling","publication_year":2022,"publication_date":"2022-12-29","ids":{"openalex":"https://openalex.org/W4313261557","doi":"https://doi.org/10.1093/bioinformatics/btac841","pmid":"https://pubmed.ncbi.nlm.nih.gov/36579866"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac841","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac841","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac841/48514064/btac841.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","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":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac841/48514064/btac841.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035307407","display_name":"Priyanka Rana","orcid":"https://orcid.org/0000-0001-6468-8236"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Priyanka Rana","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales , Sydney, NSW 2052, Australia"],"raw_orcid":"https://orcid.org/0000-0001-6468-8236","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales , Sydney, NSW 2052, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055952724","display_name":"Arcot Sowmya","orcid":"https://orcid.org/0000-0001-9236-5063"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Arcot Sowmya","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales , Sydney, NSW 2052, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales , Sydney, NSW 2052, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023548565","display_name":"Erik Meijering","orcid":"https://orcid.org/0000-0001-8015-8358"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Erik Meijering","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales , Sydney, NSW 2052, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales , Sydney, NSW 2052, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041567418","display_name":"Yang Song","orcid":"https://orcid.org/0000-0003-1283-1672"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Yang Song","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales , Sydney, NSW 2052, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales , Sydney, NSW 2052, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041567418"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.6361,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91333049,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"39","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.34929999709129333,"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"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.34929999709129333,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.21699999272823334,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.17190000414848328,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/oversampling","display_name":"Oversampling","score":0.9280892610549927},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7136374711990356},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7091478109359741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5929739475250244},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5585294365882874},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.41712841391563416},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3994281589984894},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39490240812301636},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.08608028292655945}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.9280892610549927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7136374711990356},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7091478109359741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5929739475250244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5585294365882874},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.41712841391563416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3994281589984894},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39490240812301636},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.08608028292655945},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000066491","descriptor_name":"Clinical Decision-Making","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000066491","descriptor_name":"Clinical Decision-Making","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000066491","descriptor_name":"Clinical Decision-Making","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000066491","descriptor_name":"Clinical Decision-Making","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":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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021381","descriptor_name":"Protein Transport","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021381","descriptor_name":"Protein Transport","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021381","descriptor_name":"Protein Transport","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021381","descriptor_name":"Protein Transport","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btac841","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac841","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac841/48514064/btac841.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","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":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36579866","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36579866","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/106950","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.4/106950","pdf_url":"https://unsworks.unsw.edu.au/bitstreams/dd931182-60d0-4529-ae27-8f4d31c26aae/download","source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics, 39, 1, btac841","raw_type":"http://purl.org/coar/resource_type/c_6501"},{"id":"pmh:oai:pubmedcentral.nih.gov:9825308","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9825308","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btac841","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac841","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac841/48514064/btac841.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","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":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320312169","display_name":"National Computational Infrastructure","ror":"https://ror.org/04yx6dh41"},{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1045349118","https://openalex.org/W1971955426","https://openalex.org/W1994356124","https://openalex.org/W1994616650","https://openalex.org/W2052684427","https://openalex.org/W2077467360","https://openalex.org/W2098157753","https://openalex.org/W2115444722","https://openalex.org/W2119466907","https://openalex.org/W2133223948","https://openalex.org/W2616487990","https://openalex.org/W2754319208","https://openalex.org/W2756357106","https://openalex.org/W2757254843","https://openalex.org/W2954996726","https://openalex.org/W2991083105","https://openalex.org/W3096655658","https://openalex.org/W3158777740","https://openalex.org/W3167781169","https://openalex.org/W3176923149","https://openalex.org/W4205674121","https://openalex.org/W4290714445","https://openalex.org/W4295922987","https://openalex.org/W4307644744"],"related_works":["https://openalex.org/W3196098778","https://openalex.org/W3211250490","https://openalex.org/W4360584310","https://openalex.org/W2953675148","https://openalex.org/W2981515171","https://openalex.org/W2924282518","https://openalex.org/W80466363","https://openalex.org/W3080872054","https://openalex.org/W3082059448","https://openalex.org/W4313640622"],"abstract_inverted_index":{"MOTIVATION:":[0],"Subcellular":[1],"localization":[2,60],"of":[3,26,91,114,128,130,136,160,168,229],"human":[4],"proteins":[5,34,50],"is":[6,61,104,192,227,253],"essential":[7],"to":[8,62,80,111,209],"comprehend":[9],"their":[10,58],"functions":[11],"and":[12,23,29,43,88,116,132,165,170,184,187,199,205],"roles":[13],"in":[14,18,21,101,173,244],"physiological":[15],"processes,":[16],"which":[17],"turn":[19],"helps":[20],"diagnostic":[22],"prognostic":[24],"studies":[25,121],"pathological":[27],"conditions":[28],"impacts":[30],"clinical":[31],"decision-making.":[32],"Since":[33],"reside":[35],"at":[36,39,249,255,263],"multiple":[37],"locations":[38,46],"the":[40,54,85,89,95,112,126,149,153,158,166,174,178,215,224],"same":[41],"time":[42],"few":[44],"subcellular":[45,59],"host":[47],"far":[48],"more":[49,107],"than":[51,236],"other":[52],"locations,":[53],"computational":[55],"task":[56],"for":[57,94,147,152,202,233],"train":[63],"a":[64,81,188,206],"multilabel":[65,102],"classifier":[66],"while":[67],"handling":[68],"data":[69,99,141,161,203,260],"imbalance.":[70],"In":[71],"imbalanced":[72],"data,":[73],"minority":[74,96,117,133,137,154,171,183,234],"classes":[75,87,172,235],"are":[76,247,261],"underrepresented,":[77],"thus":[78],"leading":[79],"heavy":[82],"bias":[83],"towards":[84],"majority":[86,115,131,169],"degradation":[90],"predictive":[92],"capability":[93],"classes.":[97,118,155],"Furthermore,":[98],"imbalance":[100,162],"settings":[103],"an":[105],"even":[106],"complex":[108],"problem":[109],"due":[110],"coexistence":[113],"RESULTS:":[119],"Our":[120],"reveal":[122],"that":[123,194,223],"based":[124],"on":[125,177,214],"extent":[127],"concurrence":[129,167],"classes,":[134,186],"oversampling":[135,190],"samples":[138],"through":[139],"appropriate":[140],"augmentation":[142,204],"techniques":[143],"holds":[144],"promising":[145],"scope":[146],"boosting":[148],"classification":[150],"performance":[151],"We":[156],"measured":[157],"magnitude":[159],"per":[163],"class":[164],"dataset.":[175],"Based":[176],"obtained":[179],"values,":[180],"we":[181],"identified":[182],"medium":[185],"new":[189],"method":[191,226],"proposed":[193,225],"includes":[195],"non-linear":[196],"mixup,":[197],"geometric":[198],"colour":[200],"transformations":[201],"sampling":[207],"approach":[208],"prepare":[210],"minibatches.":[211],"Performance":[212],"evaluation":[213],"Human":[216],"Protein":[217],"Atlas":[218],"Kaggle":[219],"challenge":[220],"dataset":[221],"shows":[222],"capable":[228],"achieving":[230],"better":[231],"predictions":[232],"existing":[237],"methods.":[238],"AVAILABILITY":[239],"AND":[240],"IMPLEMENTATION:":[241],"Data":[242],"used":[243],"this":[245],"study":[246],"available":[248,254,262],"https://www.kaggle.com/competitions/human-protein-atlas-image-classification/data.":[250],"Source":[251],"code":[252],"https://github.com/priyarana/Protein-subcellular-localisation-method.":[256],"SUPPLEMENTARY":[257],"INFORMATION:":[258],"Supplementary":[259],"Bioinformatics":[264],"online.":[265]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-08T08:47:23.578185","created_date":"2025-10-10T00:00:00"}
