{"id":"https://openalex.org/W2901776501","doi":"https://doi.org/10.1109/iccabs.2018.8542075","title":"Improved Decoy Selection via Machine Learning and Ranking","display_name":"Improved Decoy Selection via Machine Learning and Ranking","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2901776501","doi":"https://doi.org/10.1109/iccabs.2018.8542075","mag":"2901776501"},"language":"en","primary_location":{"id":"doi:10.1109/iccabs.2018.8542075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccabs.2018.8542075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 8th International Conference on Computational Advances in Bio and Medical Sciences (ICCABS)","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/A5101677914","display_name":"Nasrin Akhter","orcid":"https://orcid.org/0000-0001-8976-5875"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nasrin Akhter","raw_affiliation_strings":["Department of Computer Science, George Mason University, Fairfax, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063725454","display_name":"Gopinath Chennupati","orcid":"https://orcid.org/0000-0002-6223-8570"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gopinath Chennupati","raw_affiliation_strings":["Information Sciences Group, Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Group, Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057625550","display_name":"Hristo Djidjev","orcid":"https://orcid.org/0000-0001-9286-8824"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hristo Djidjev","raw_affiliation_strings":["Information Sciences Group, Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Group, Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044722808","display_name":"Amarda Shehu","orcid":"https://orcid.org/0000-0001-5230-4610"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amarda Shehu","raw_affiliation_strings":["School of Systems Biology, George Mason University, Fairfax, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Systems Biology, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1804,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53443187,"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":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9998000264167786,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9998000264167786,"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":0.9987999796867371,"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":0.9962000250816345,"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/decoy","display_name":"Decoy","score":0.8762409090995789},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6463189721107483},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6462500691413879},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6228752136230469},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6036404967308044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5685622692108154},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5316852927207947},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5169646143913269},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.47569191455841064},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4504358768463135},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.43492555618286133},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.4229477643966675},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.41697028279304504},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1265564262866974}],"concepts":[{"id":"https://openalex.org/C2779179475","wikidata":"https://www.wikidata.org/wiki/Q3545649","display_name":"Decoy","level":3,"score":0.8762409090995789},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6463189721107483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6462500691413879},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6228752136230469},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6036404967308044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5685622692108154},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5316852927207947},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5169646143913269},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.47569191455841064},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4504358768463135},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.43492555618286133},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.4229477643966675},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.41697028279304504},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1265564262866974},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C170493617","wikidata":"https://www.wikidata.org/wiki/Q208467","display_name":"Receptor","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccabs.2018.8542075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccabs.2018.8542075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 8th International Conference on Computational Advances in Bio and Medical Sciences (ICCABS)","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":2,"referenced_works":["https://openalex.org/W2109801072","https://openalex.org/W2794328361"],"related_works":["https://openalex.org/W2415073839","https://openalex.org/W1555596338","https://openalex.org/W1238053778","https://openalex.org/W2350944221","https://openalex.org/W4239355779","https://openalex.org/W4388745254","https://openalex.org/W2980082554","https://openalex.org/W1517228774","https://openalex.org/W2767419625","https://openalex.org/W2389704471"],"abstract_inverted_index":{"Selection":[0],"of":[1,31,69,85,89,112,115,121,132,171],"biologically-active/native":[2],"tertiary":[3],"structures":[4,7],"among":[5],"decoy":[6,37,107,156,204],"computed":[8,77],"by":[9,129],"template":[10],"-free":[11],"protein":[12],"structure":[13,225],"prediction":[14],"methods":[15,26,39],"remains":[16,152],"a":[17,103,153,163],"challenging":[18],"problem.":[19],"The":[20,253],"scoring/energy":[21],"function":[22],"that":[23,65,96,137,168,243],"guides":[24],"these":[25,140],"is":[27,201],"an":[28,60,175],"unreliable":[29],"indicator":[30],"nativeness.":[32],"Currently,":[33],"the":[34,67,72,76,86,122,126,130,188,217,222,229,244,265],"most":[35],"popular":[36],"selection":[38,100,108],"rely":[40],"on":[41,45,191,197,203,216,238],"clustering":[42,105],"decoys":[43,78,212],"based":[44,98,196,215],"structural":[46],"similarity":[47],"but":[48],"achieve":[49],"varied":[50,149,260],"success":[51],"and":[52,193,209,263],"are":[53,213],"computationally":[54],"expensive":[55],"for":[56],"large":[57],"datasets.":[58],"Recently,":[59],"alternative":[61],"multi":[62],"-model":[63],"approach":[64],"utilizes":[66,169],"concepts":[68],"basins":[70,172,195,230],"in":[71,82,110,136,206,232,270],"energy":[73,176],"landscape":[74,177],"housing":[75],"has":[79],"shown":[80],"promise":[81],"overcoming":[83],"some":[84],"li":[87],"mitations":[88],"clustering-based":[90],"approaches.":[91],"A":[92],"separate":[93],"paper":[94],"shows":[95,242],"ranking":[97],"basin":[99,189],"strategies":[101],"outperform":[102],"standard":[104],"-based":[106,248],"method":[109,255],"terms":[111],"purity":[113,192],"(percentage":[114],"true":[116],"positives":[117,134],"relative":[118],"to":[119,144,155,226,267],"size":[120],"selected":[123,127,231],"basins(s),":[124],"penalizing":[125],"basin(s)":[128],"extent":[131],"false":[133],"found":[135],"basin(s)).":[138],"Despite":[139],"promising":[141],"results,":[142],"failing":[143],"perform":[145],"consistently":[146,257],"well":[147,258],"over":[148,259],"test":[150,261],"cases":[151,262],"bottleneck":[154],"selection.":[157],"In":[158,183],"this":[159,271],"work,":[160],"we":[161,186],"propose":[162],"two-phase":[164],"machine":[165,246],"learning-based":[166],"framework":[167,249],"characteristics":[170],"extracted":[173],"from":[174,221],"together":[178],"with":[179],"three":[180],"knowledge-based":[181],"potentials.":[182],"phase":[184,207,233],"1,":[185],"regress":[187],"features":[190,205],"rank":[194],"predicted":[198,218],"purity.":[199],"Regression":[200],"applied":[202],"2,":[208],"potentially":[210],"non-native":[211],"eliminated":[214],"root-mean-squared":[219],"deviation":[220],"(unknown)":[223],"native":[224],"further":[227,268],"purify":[228],"1.":[234],"Empirical":[235],"investigation":[236],"conducted":[237],"18":[239],"benchmark":[240],"proteins":[241],"proposed":[245,254],"learning":[247],"offers":[250],"better":[251],"performance.":[252],"performs":[256],"opens":[264],"way":[266],"research":[269],"direction.":[272]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}