{"id":"https://openalex.org/W3123157506","doi":"https://doi.org/10.1155/2021/6675279","title":"Handling Imbalance Classification Virtual Screening Big Data Using Machine Learning Algorithms","display_name":"Handling Imbalance Classification Virtual Screening Big Data Using Machine Learning Algorithms","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3123157506","doi":"https://doi.org/10.1155/2021/6675279","mag":"3123157506"},"language":"en","primary_location":{"id":"doi:10.1155/2021/6675279","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/6675279","pdf_url":"https://downloads.hindawi.com/journals/complexity/2021/6675279.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://downloads.hindawi.com/journals/complexity/2021/6675279.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090985535","display_name":"Sahar K. Hussin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sahar K. Hussin","raw_affiliation_strings":["Communication and Computers Engineering Department Alshrouck Academy, Cairo, Egypt"],"affiliations":[{"raw_affiliation_string":"Communication and Computers Engineering Department Alshrouck Academy, Cairo, Egypt","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045319374","display_name":"Salah Abdel-Mageid","orcid":"https://orcid.org/0000-0001-9316-3922"},"institutions":[{"id":"https://openalex.org/I23075662","display_name":"Taibah University","ror":"https://ror.org/01xv1nn60","country_code":"SA","type":"education","lineage":["https://openalex.org/I23075662"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Salah M. Abdelmageid","raw_affiliation_strings":["Computer Engineering Department, Collage of Comp. Science and Engineering, Taibah University, Medina, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Collage of Comp. Science and Engineering, Taibah University, Medina, Saudi Arabia","institution_ids":["https://openalex.org/I23075662"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005353440","display_name":"Adel Alkhalil","orcid":"https://orcid.org/0000-0003-3135-9174"},"institutions":[{"id":"https://openalex.org/I4210088963","display_name":"University of Ha'il","ror":"https://ror.org/013w98a82","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210088963"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Adel Alkhalil","raw_affiliation_strings":["College of Computer Science and Engineering, University of Hai'l, Hai'l, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, University of Hai'l, Hai'l, Saudi Arabia","institution_ids":["https://openalex.org/I4210088963"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080555226","display_name":"Yasser Omar","orcid":"https://orcid.org/0000-0002-7079-1894"},"institutions":[{"id":"https://openalex.org/I59272784","display_name":"Arab Academy for Science, Technology, and Maritime Transport","ror":"https://ror.org/0004vyj87","country_code":"EG","type":"education","lineage":["https://openalex.org/I59272784"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Yasser M. Omar","raw_affiliation_strings":["Arab Academy for Science Technology and Maritime Transport, Cairo, Egypt"],"affiliations":[{"raw_affiliation_string":"Arab Academy for Science Technology and Maritime Transport, Cairo, Egypt","institution_ids":["https://openalex.org/I59272784"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108735635","display_name":"Mahmoud I. Marie","orcid":null},"institutions":[{"id":"https://openalex.org/I184834183","display_name":"Al-Azhar University","ror":"https://ror.org/05fnp1145","country_code":"EG","type":"education","lineage":["https://openalex.org/I184834183"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Mahmoud I. Marie","raw_affiliation_strings":["Computer and System Engineering Department, Al-Azhar University, Cairo, Egypt"],"affiliations":[{"raw_affiliation_string":"Computer and System Engineering Department, Al-Azhar University, Cairo, Egypt","institution_ids":["https://openalex.org/I184834183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045926954","display_name":"Rabie \u0391. Ramadan","orcid":"https://orcid.org/0000-0002-0281-9381"},"institutions":[{"id":"https://openalex.org/I4210088963","display_name":"University of Ha'il","ror":"https://ror.org/013w98a82","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210088963"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Rabie A. Ramadan","raw_affiliation_strings":["College of Computer Science and Engineering, University of Hai'l, Hai'l, Saudi Arabia","Computer Engineering Department, Cairo Universality, Cairo, Egypt"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, University of Hai'l, Hai'l, Saudi Arabia","institution_ids":["https://openalex.org/I4210088963"]},{"raw_affiliation_string":"Computer Engineering Department, Cairo Universality, Cairo, Egypt","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5045926954"],"corresponding_institution_ids":["https://openalex.org/I4210088963"],"apc_list":{"value":2300,"currency":"USD","value_usd":2300},"apc_paid":{"value":2300,"currency":"USD","value_usd":2300},"fwci":2.2387,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.89690909,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"2021","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":0.9998000264167786,"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":0.9998000264167786,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.996399998664856,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9894999861717224,"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/oversampling","display_name":"Oversampling","score":0.8945326805114746},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7734020948410034},{"id":"https://openalex.org/keywords/virtual-screening","display_name":"Virtual screening","score":0.7592707276344299},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.6574413180351257},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5943185687065125},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5570411682128906},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5517211556434631},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48927876353263855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4590458273887634},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.43855246901512146},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43241795897483826},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.42417019605636597},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.4180341362953186},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.41711241006851196},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.09656715393066406}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.8945326805114746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7734020948410034},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.7592707276344299},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6574413180351257},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5943185687065125},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5570411682128906},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5517211556434631},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48927876353263855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4590458273887634},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.43855246901512146},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43241795897483826},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.42417019605636597},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.4180341362953186},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.41711241006851196},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.09656715393066406},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1155/2021/6675279","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/6675279","pdf_url":"https://downloads.hindawi.com/journals/complexity/2021/6675279.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:hin:complx:6675279","is_oa":false,"landing_page_url":"http://downloads.hindawi.com/journals/complexity/2021/6675279.xml","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:28849350eb54460288cac53db9348760","is_oa":true,"landing_page_url":"https://doaj.org/article/28849350eb54460288cac53db9348760","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complexity, Vol 2021 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1155/2021/6675279","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/6675279","pdf_url":"https://downloads.hindawi.com/journals/complexity/2021/6675279.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.44999998807907104,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3123157506.pdf","grobid_xml":"https://content.openalex.org/works/W3123157506.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1510850304","https://openalex.org/W1941659294","https://openalex.org/W1968506227","https://openalex.org/W1968996837","https://openalex.org/W1984428215","https://openalex.org/W1985930887","https://openalex.org/W1986087295","https://openalex.org/W1986515506","https://openalex.org/W2003998164","https://openalex.org/W2023639956","https://openalex.org/W2052260244","https://openalex.org/W2066803237","https://openalex.org/W2074978477","https://openalex.org/W2079775628","https://openalex.org/W2085398335","https://openalex.org/W2088059023","https://openalex.org/W2112208320","https://openalex.org/W2114968414","https://openalex.org/W2121780366","https://openalex.org/W2125335678","https://openalex.org/W2126734246","https://openalex.org/W2131725992","https://openalex.org/W2132901471","https://openalex.org/W2145344497","https://openalex.org/W2148143831","https://openalex.org/W2148444192","https://openalex.org/W2171647935","https://openalex.org/W2413919997","https://openalex.org/W2626779422","https://openalex.org/W2783671211","https://openalex.org/W2796724526","https://openalex.org/W2800344222","https://openalex.org/W2883346555","https://openalex.org/W2889158284","https://openalex.org/W2889276168","https://openalex.org/W2896365426","https://openalex.org/W3014206128"],"related_works":["https://openalex.org/W2883697671","https://openalex.org/W3008487931","https://openalex.org/W2790778417","https://openalex.org/W3014300295","https://openalex.org/W2043890830","https://openalex.org/W3118882535","https://openalex.org/W3205795685","https://openalex.org/W2782959932","https://openalex.org/W2734587838","https://openalex.org/W3213030203"],"abstract_inverted_index":{"Virtual":[0],"screening":[1,19,41,65],"is":[2,129],"the":[3,18,23,78,92,96,102,121,178,185],"most":[4,82],"critical":[5],"process":[6],"in":[7],"drug":[8],"discovery,":[9],"and":[10,45,53,60,143,163,175],"it":[11],"relies":[12],"on":[13,157,177],"machine":[14],"learning":[15],"to":[16,29,33,62,86,119,171],"facilitate":[17],"process.":[20],"It":[21],"enables":[22],"discovery":[24],"of":[25,123,153],"molecules":[26],"that":[27,184],"bind":[28],"a":[30,35,69,73,108],"specific":[31],"protein":[32],"form":[34],"drug.":[36],"Despite":[37],"its":[38],"benefits,":[39],"virtual":[40,64],"generates":[42],"enormous":[43],"data":[44,58,136],"suffers":[46],"from":[47],"drawbacks":[48],"such":[49],"as":[50,131],"high":[51,88,141,148],"dimensions":[52],"imbalance.":[54],"This":[55],"paper":[56,106],"tackles":[57],"imbalance":[59],"aims":[61],"improve":[63],"accuracy,":[66],"especially":[67],"for":[68,91,101],"minority":[70,103,135],"dataset.":[71],"For":[72],"dataset":[74],"identified":[75,139],"without":[76],"considering":[77],"data\u2019s":[79],"imbalanced":[80,124],"nature,":[81],"classification":[83],"methods":[84],"tend":[85],"have":[87],"predictive":[89],"accuracy":[90,97,142],"majority":[93],"category.":[94,104],"However,":[95],"was":[98,169],"significantly":[99],"poor":[100],"The":[105,126,166],"proposes":[107],"K":[109],"\u2010mean":[110],"algorithm":[111,128],"coupled":[112],"with":[113],"Synthetic":[114],"Minority":[115],"Oversampling":[116],"Technique":[117],"(SMOTE)":[118],"overcome":[120],"problem":[122],"datasets.":[125,180],"proposed":[127,167,186],"named":[130],"KSMOTE.":[132],"Using":[133],"KSMOTE,":[134],"can":[137,144],"be":[138,145],"at":[140,147],"detected":[146],"precision.":[149],"A":[150],"large":[151],"set":[152],"experiments":[154],"were":[155],"implemented":[156],"Apache":[158],"Spark":[159],"using":[160],"numeric":[161],"PaDEL":[162],"fingerprint":[164],"descriptors.":[165],"solution":[168,187],"compared":[170],"both":[172],"no\u2010sampling":[173],"method":[174],"SMOTE":[176],"same":[179],"Experimental":[181],"results":[182],"showed":[183],"outperformed":[188],"other":[189],"methods.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}