{"id":"https://openalex.org/W3004855102","doi":"https://doi.org/10.1109/bibm47256.2019.8983213","title":"Novel K-Means Clustering-based Undersampling and Feature Selection for Drug Discovery Applications","display_name":"Novel K-Means Clustering-based Undersampling and Feature Selection for Drug Discovery Applications","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3004855102","doi":"https://doi.org/10.1109/bibm47256.2019.8983213","mag":"3004855102"},"language":"en","primary_location":{"id":"doi:10.1109/bibm47256.2019.8983213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm47256.2019.8983213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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/A5077993329","display_name":"Vishnu Sripriya Akondi","orcid":null},"institutions":[{"id":"https://openalex.org/I82495205","display_name":"University of Alabama in Huntsville","ror":"https://ror.org/02zsxwr40","country_code":"US","type":"education","lineage":["https://openalex.org/I82495205"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishnu Sripriya Akondi","raw_affiliation_strings":["University of Alabama in Huntsville,Department of Computer Science,Huntsville,USA","Department of Computer Science, University of Alabama in Huntsville, Huntsville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alabama in Huntsville,Department of Computer Science,Huntsville,USA","institution_ids":["https://openalex.org/I82495205"]},{"raw_affiliation_string":"Department of Computer Science, University of Alabama in Huntsville, Huntsville, USA","institution_ids":["https://openalex.org/I82495205"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087934737","display_name":"Vineetha Menon","orcid":"https://orcid.org/0000-0001-6916-5346"},"institutions":[{"id":"https://openalex.org/I82495205","display_name":"University of Alabama in Huntsville","ror":"https://ror.org/02zsxwr40","country_code":"US","type":"education","lineage":["https://openalex.org/I82495205"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vineetha Menon","raw_affiliation_strings":["University of Alabama in Hunstville,Department of Computer Science,Huntsville,USA","Department of Computer Science, University of Alabama in Hunstville, Huntsville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alabama in Hunstville,Department of Computer Science,Huntsville,USA","institution_ids":["https://openalex.org/I82495205"]},{"raw_affiliation_string":"Department of Computer Science, University of Alabama in Hunstville, Huntsville, USA","institution_ids":["https://openalex.org/I82495205"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015943958","display_name":"J\u00e9r\u00f4me Baudry","orcid":"https://orcid.org/0000-0002-1969-1679"},"institutions":[{"id":"https://openalex.org/I82495205","display_name":"University of Alabama in Huntsville","ror":"https://ror.org/02zsxwr40","country_code":"US","type":"education","lineage":["https://openalex.org/I82495205"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jerome Baudry","raw_affiliation_strings":["University of Alabama in Huntsville,Department of Biological Sciences,Huntsville,USA","Department of Biological Sciences, University of Alabama in Huntsville, Huntsville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alabama in Huntsville,Department of Biological Sciences,Huntsville,USA","institution_ids":["https://openalex.org/I82495205"]},{"raw_affiliation_string":"Department of Biological Sciences, University of Alabama in Huntsville, Huntsville, USA","institution_ids":["https://openalex.org/I82495205"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032822983","display_name":"Jana Whittle","orcid":null},"institutions":[{"id":"https://openalex.org/I82495205","display_name":"University of Alabama in Huntsville","ror":"https://ror.org/02zsxwr40","country_code":"US","type":"education","lineage":["https://openalex.org/I82495205"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jana Whittle","raw_affiliation_strings":["University of Alabama in Huntsville,Department of Biological Sciences,Huntsville,USA","Department of Biological Sciences, University of Alabama in Huntsville, Huntsville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alabama in Huntsville,Department of Biological Sciences,Huntsville,USA","institution_ids":["https://openalex.org/I82495205"]},{"raw_affiliation_string":"Department of Biological Sciences, University of Alabama in Huntsville, Huntsville, USA","institution_ids":["https://openalex.org/I82495205"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82495205"],"apc_list":null,"apc_paid":null,"fwci":1.4152,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84461635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2771","last_page":"2778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9977999925613403,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9922999739646912,"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":0.9884999990463257,"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/undersampling","display_name":"Undersampling","score":0.846086323261261},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.8255079984664917},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7193864583969116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7100174427032471},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6754510998725891},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6372429132461548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6000341176986694},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5524015426635742},{"id":"https://openalex.org/keywords/business-process-discovery","display_name":"Business process discovery","score":0.5335890054702759},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4717443883419037},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4606025815010071},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4598478078842163},{"id":"https://openalex.org/keywords/drug","display_name":"Drug","score":0.4401557445526123},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40819358825683594},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.24108818173408508},{"id":"https://openalex.org/keywords/work-in-process","display_name":"Work in process","score":0.1590598225593567},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.14859545230865479},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14012661576271057},{"id":"https://openalex.org/keywords/pharmacology","display_name":"Pharmacology","score":0.12011224031448364}],"concepts":[{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.846086323261261},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.8255079984664917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7193864583969116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7100174427032471},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6754510998725891},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6372429132461548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6000341176986694},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5524015426635742},{"id":"https://openalex.org/C93453677","wikidata":"https://www.wikidata.org/wiki/Q1017580","display_name":"Business process discovery","level":5,"score":0.5335890054702759},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4717443883419037},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4606025815010071},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4598478078842163},{"id":"https://openalex.org/C2780035454","wikidata":"https://www.wikidata.org/wiki/Q8386","display_name":"Drug","level":2,"score":0.4401557445526123},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40819358825683594},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.24108818173408508},{"id":"https://openalex.org/C174998907","wikidata":"https://www.wikidata.org/wiki/Q357662","display_name":"Work in process","level":2,"score":0.1590598225593567},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.14859545230865479},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14012661576271057},{"id":"https://openalex.org/C98274493","wikidata":"https://www.wikidata.org/wiki/Q128406","display_name":"Pharmacology","level":1,"score":0.12011224031448364},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C207505557","wikidata":"https://www.wikidata.org/wiki/Q4374012","display_name":"Business process modeling","level":4,"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/C85345410","wikidata":"https://www.wikidata.org/wiki/Q851587","display_name":"Business process","level":3,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm47256.2019.8983213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm47256.2019.8983213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1500036797","https://openalex.org/W2006020859","https://openalex.org/W2148143831","https://openalex.org/W2162073574","https://openalex.org/W2328207411","https://openalex.org/W2563206593","https://openalex.org/W2913359477","https://openalex.org/W6758263807"],"related_works":["https://openalex.org/W2109073422","https://openalex.org/W2887783772","https://openalex.org/W2101754595","https://openalex.org/W2534887053","https://openalex.org/W2026172757","https://openalex.org/W4249381695","https://openalex.org/W4389292014","https://openalex.org/W1597404095","https://openalex.org/W2530048721","https://openalex.org/W4312723856"],"abstract_inverted_index":{"Drug":[0],"discovery":[1,30,80,193,212],"refers":[2],"to":[3,17,74,88,133,155],"the":[4,14,28,59,67,78,107,112,124,157,168,178,187,191,198,205],"process":[5,31,47],"of":[6,8,56,115,127,171,190,197,207],"identification":[7],"specific-disease":[9],"causing":[10],"proteins":[11,180],"and":[12,42,76,85,145,182,184],"underscores":[13],"research":[15],"efforts":[16],"derive":[18],"a":[19,152],"new":[20],"medication":[21],"that":[22,58,166],"targets":[23],"these":[24],"proteins.":[25],"As":[26],"such":[27,105],"drug":[29,61,79,117,173,192,211],"entails":[32],"significant":[33],"challenges":[34],"as":[35,106],"it":[36,65],"is":[37],"time":[38],"consuming,":[39],"data":[40],"intensive,":[41],"involves":[43],"an":[44],"expensive":[45],"developmental":[46],"which":[48],"demands":[49],"rigorous":[50],"lab":[51],"testing":[52],"with":[53],"high":[54],"rates":[55,189],"uncertainty":[57],"given":[60],"will":[62],"succeed.":[63],"Therefore,":[64,148],"highlights":[66],"crucial":[68],"need":[69],"for":[70,82,92,143,177,210],"machine":[71,137,163,200],"learning":[72,138,164,201],"methods":[73],"automate":[75],"hasten":[77],"pipeline":[81],"improved":[83],"healthcare":[84],"assist":[86],"clinicians":[87],"make":[89],"informed":[90],"decisions":[91],"in-vitro":[93],"testing.":[94],"However,":[95],"most":[96],"real-world":[97],"biomedical":[98],"datasets":[99],"suffer":[100],"from":[101],"statistical":[102],"ill-conditioning":[103],"issues":[104],"class":[108,114,158],"imbalance":[109,159],"problem":[110,160],"where":[111],"fewer":[113],"potential":[116,172],"candidate":[118,174],"protein":[119],"conformations":[120,176],"are":[121,140],"overshadowed":[122],"by":[123],"larger":[125],"protein-pool":[126],"non-drug":[128],"candidates.":[129],"Hence,":[130],"this":[131,149],"leads":[132],"erroneous":[134],"conclusions":[135],"when":[136],"techniques":[139,165],"directly":[141],"employed":[142],"data-learning":[144],"classification":[146],"purposes.":[147],"work":[150],"takes":[151],"revolutionary":[153],"stance":[154],"counter":[156],"through":[161],"advanced":[162],"maximize":[167],"prediction":[169],"rate":[170],"molecular":[175],"target":[179],"ADORA2A":[181],"OPRK1":[183],"subsequently":[185],"reduces":[186],"failure":[188],"process.":[194,213],"Experimental":[195],"evaluation":[196],"proposed":[199],"methodologies":[202],"further":[203],"substantiates":[204],"effectiveness":[206],"our":[208],"approach":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}