{"id":"https://openalex.org/W3128793699","doi":"https://doi.org/10.1109/bibm49941.2020.9313299","title":"Decoy Selection in Protein Structure Determination via Symmetric Non-negative Matrix Factorization","display_name":"Decoy Selection in Protein Structure Determination via Symmetric Non-negative Matrix Factorization","publication_year":2020,"publication_date":"2020-12-16","ids":{"openalex":"https://openalex.org/W3128793699","doi":"https://doi.org/10.1109/bibm49941.2020.9313299","mag":"3128793699"},"language":"en","primary_location":{"id":"doi:10.1109/bibm49941.2020.9313299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm49941.2020.9313299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5018934664","display_name":"Kazi Lutful Kabir","orcid":"https://orcid.org/0000-0003-4021-6618"},"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":"Kazi Lutful Kabir","raw_affiliation_strings":["George Mason University, Fairfax, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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 (CCS-3) Group, Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences (CCS-3) Group, Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082559067","display_name":"Raviteja Vangara","orcid":"https://orcid.org/0000-0001-5272-6207"},"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":"Raviteja Vangara","raw_affiliation_strings":["Fluid dynamics & Solid mechanics (T-3), Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fluid dynamics & Solid mechanics (T-3), 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 (CCS-3) Group, Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences (CCS-3) Group, Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079029372","display_name":"Boian S. Alexandrov","orcid":"https://orcid.org/0000-0001-8636-4603"},"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":"Boian S. Alexandrov","raw_affiliation_strings":["Physics & Chemistry of Materials (T-1), Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Physics & Chemistry of Materials (T-1), 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":["George Mason University, Fairfax, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9988999962806702,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9988999962806702,"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":0.9983999729156494,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9983000159263611,"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/decoy","display_name":"Decoy","score":0.9712698459625244},{"id":"https://openalex.org/keywords/casp","display_name":"CASP","score":0.7230278253555298},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7109932899475098},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5728774666786194},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5219287872314453},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5215660929679871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5167059898376465},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4915991723537445},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.47054344415664673},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4320594072341919},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"Protein structure prediction","score":0.39282122254371643},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3365101218223572},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32744961977005005},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.1933802366256714},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09593087434768677}],"concepts":[{"id":"https://openalex.org/C2779179475","wikidata":"https://www.wikidata.org/wiki/Q3545649","display_name":"Decoy","level":3,"score":0.9712698459625244},{"id":"https://openalex.org/C66153294","wikidata":"https://www.wikidata.org/wiki/Q899291","display_name":"CASP","level":4,"score":0.7230278253555298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7109932899475098},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5728774666786194},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5219287872314453},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5215660929679871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5167059898376465},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4915991723537445},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.47054344415664673},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4320594072341919},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.39282122254371643},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3365101218223572},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32744961977005005},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.1933802366256714},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09593087434768677},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm49941.2020.9313299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm49941.2020.9313299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320338304","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1504886279","https://openalex.org/W1597762634","https://openalex.org/W1979555059","https://openalex.org/W2005443451","https://openalex.org/W2015583498","https://openalex.org/W2026129540","https://openalex.org/W2052963427","https://openalex.org/W2058231807","https://openalex.org/W2067931421","https://openalex.org/W2070135644","https://openalex.org/W2077743314","https://openalex.org/W2093492509","https://openalex.org/W2097651746","https://openalex.org/W2099286799","https://openalex.org/W2099779699","https://openalex.org/W2109801072","https://openalex.org/W2110483430","https://openalex.org/W2121360793","https://openalex.org/W2130479394","https://openalex.org/W2132692097","https://openalex.org/W2144981983","https://openalex.org/W2152322845","https://openalex.org/W2161151688","https://openalex.org/W2166575328","https://openalex.org/W2173591891","https://openalex.org/W2201713963","https://openalex.org/W2285139619","https://openalex.org/W2343931134","https://openalex.org/W2517233028","https://openalex.org/W2606439133","https://openalex.org/W2769882797","https://openalex.org/W2794328361","https://openalex.org/W2888004262","https://openalex.org/W2905812122","https://openalex.org/W2912570385","https://openalex.org/W2953524386","https://openalex.org/W2980184967","https://openalex.org/W3004896252","https://openalex.org/W3005019273"],"related_works":["https://openalex.org/W4393738163","https://openalex.org/W4393502242","https://openalex.org/W4393696657","https://openalex.org/W2411998238","https://openalex.org/W2062648327","https://openalex.org/W3198923619","https://openalex.org/W2093959518","https://openalex.org/W2334085108","https://openalex.org/W3004912075","https://openalex.org/W2107127921"],"abstract_inverted_index":{"The":[0,56,123,158],"so-called":[1],"dark":[2],"proteome,":[3],"referring":[4],"to":[5,20,32,35,45,91,99,200,205],"regions":[6],"of":[7,54,133,135,141,147,188],"the":[8,33,71,83,154,162,176,182,186,189,198],"protein":[9,25,53,142],"universe":[10],"that":[11,48,161,181],"remain":[12],"inaccessible":[13],"by":[14],"either":[15],"wet-or":[16],"dry-laboratory":[17],"methods,":[18],"continues":[19],"spur":[21],"computational":[22,178],"research":[23],"in":[24,75,118,191,195],"structure":[26],"determination.":[27],"An":[28],"outstanding":[29],"challenge":[30,92],"relates":[31],"ability":[34,199],"discriminate":[36],"relevant":[37],"tertiary":[38],"structure(s)":[39],"among":[40],"many":[41],"structures,":[42],"also":[43],"referred":[44],"as":[46,60,67,173,175],"decoys,":[47],"are":[49,77],"computed":[50],"for":[51,65,137,150],"a":[52,107,119,130,138,145],"interest.":[55],"problem":[57],"is":[58,125],"known":[59],"decoy":[61,72,109,148,168,192],"selection.":[62],"While":[63],"prime":[64],"investigation":[66],"an":[68],"inference":[69],"problem,":[70],"datasets":[73],"generated":[74],"silico":[76],"sparse":[78],"and":[79,95,144],"highly":[80],"imbalanced":[81,206],"towards":[82],"negative":[84],"class":[85],"(irrelevant":[86],"structures).":[87],"These":[88],"characteristics":[89],"continue":[90],"both":[93],"supervised":[94],"unsupervised":[96],"learning":[97],"approaches":[98],"this":[100,103],"problem.":[101],"In":[102],"paper,":[104],"we":[105],"propose":[106],"novel":[108],"selection":[110,169,193],"method":[111,124,164,184],"based":[112],"on":[113,127],"symmetric":[114],"non-negative":[115],"matrix":[116],"factorization":[117],"graph":[120],"clustering":[121],"setting.":[122],"evaluated":[126],"two":[128],"datasets,":[129],"benchmark":[131],"dataset":[132,146],"ensembles":[134,149],"decoys":[136],"varied":[139],"list":[140],"molecules,":[143],"targets":[151],"drawn":[152],"from":[153],"recent":[155],"CASP":[156],"competitions.":[157],"evaluation":[159],"demonstrates":[160],"proposed":[163,183],"outperforms":[165],"several":[166],"state-of-the-art":[167],"methods.":[170],"This":[171],"performance,":[172],"well":[174],"method's":[177],"expediency,":[179],"suggest":[180],"advances":[185],"state":[187],"art":[190],"and,":[194],"particular,":[196],"our":[197],"tackle":[201],"inherent":[202],"challenges":[203],"related":[204],"datasets.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}