{"id":"https://openalex.org/W4293518000","doi":"https://doi.org/10.1109/cibcb55180.2022.9863021","title":"Automatic Diverse Subset Selection From Enzyme Families by Solving the Maximum Diversity Problem","display_name":"Automatic Diverse Subset Selection From Enzyme Families by Solving the Maximum Diversity Problem","publication_year":2022,"publication_date":"2022-08-15","ids":{"openalex":"https://openalex.org/W4293518000","doi":"https://doi.org/10.1109/cibcb55180.2022.9863021"},"language":"en","primary_location":{"id":"doi:10.1109/cibcb55180.2022.9863021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb55180.2022.9863021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","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/A5053891044","display_name":"Christian Atallah","orcid":"https://orcid.org/0000-0002-4853-4189"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Christian Atallah","raw_affiliation_strings":["Newcastle University,School of Computing,Newcastle upon Tyne,UK","School of Computing, Newcastle University, Newcastle upon Tyne, UK"],"affiliations":[{"raw_affiliation_string":"Newcastle University,School of Computing,Newcastle upon Tyne,UK","institution_ids":["https://openalex.org/I84884186"]},{"raw_affiliation_string":"School of Computing, Newcastle University, Newcastle upon Tyne, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047178967","display_name":"Katherine James","orcid":"https://orcid.org/0000-0003-0167-8393"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Katherine James","raw_affiliation_strings":["Newcastle University,School of Computing,Newcastle upon Tyne,UK","School of Computing, Newcastle University, Newcastle upon Tyne, UK"],"affiliations":[{"raw_affiliation_string":"Newcastle University,School of Computing,Newcastle upon Tyne,UK","institution_ids":["https://openalex.org/I84884186"]},{"raw_affiliation_string":"School of Computing, Newcastle University, Newcastle upon Tyne, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009223839","display_name":"Zhen Ou","orcid":null},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhen Ou","raw_affiliation_strings":["Newcastle University,School of Computing,Newcastle upon Tyne,UK","School of Computing, Newcastle University, Newcastle upon Tyne, UK"],"affiliations":[{"raw_affiliation_string":"Newcastle University,School of Computing,Newcastle upon Tyne,UK","institution_ids":["https://openalex.org/I84884186"]},{"raw_affiliation_string":"School of Computing, Newcastle University, Newcastle upon Tyne, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073240590","display_name":"James Skelton","orcid":"https://orcid.org/0000-0001-7358-8616"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Skelton","raw_affiliation_strings":["Newcastle University,School of Computing,Newcastle upon Tyne,UK","School of Computing, Newcastle University, Newcastle upon Tyne, UK"],"affiliations":[{"raw_affiliation_string":"Newcastle University,School of Computing,Newcastle upon Tyne,UK","institution_ids":["https://openalex.org/I84884186"]},{"raw_affiliation_string":"School of Computing, Newcastle University, Newcastle upon Tyne, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088579295","display_name":"David W. Markham","orcid":"https://orcid.org/0000-0001-7765-369X"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Markham","raw_affiliation_strings":["Newcastle University,School of Computing,Newcastle upon Tyne,UK","School of Computing, Newcastle University, Newcastle upon Tyne, UK"],"affiliations":[{"raw_affiliation_string":"Newcastle University,School of Computing,Newcastle upon Tyne,UK","institution_ids":["https://openalex.org/I84884186"]},{"raw_affiliation_string":"School of Computing, Newcastle University, Newcastle upon Tyne, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045914500","display_name":"James Finnigan","orcid":"https://orcid.org/0000-0002-8514-784X"},"institutions":[{"id":"https://openalex.org/I4210156129","display_name":"Prozomix (United Kingdom)","ror":"https://ror.org/05338hh70","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210156129"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Finnigan","raw_affiliation_strings":["Prozomix Ltd,Haltwhistle,UK","Prozomix Ltd, Haltwhistle, UK"],"affiliations":[{"raw_affiliation_string":"Prozomix Ltd,Haltwhistle,UK","institution_ids":["https://openalex.org/I4210156129"]},{"raw_affiliation_string":"Prozomix Ltd, Haltwhistle, UK","institution_ids":["https://openalex.org/I4210156129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059041911","display_name":"Simon J. Charnock","orcid":"https://orcid.org/0000-0003-4437-7419"},"institutions":[{"id":"https://openalex.org/I4210156129","display_name":"Prozomix (United Kingdom)","ror":"https://ror.org/05338hh70","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210156129"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon Charnock","raw_affiliation_strings":["Prozomix Ltd,Haltwhistle,UK","Prozomix Ltd, Haltwhistle, UK"],"affiliations":[{"raw_affiliation_string":"Prozomix Ltd,Haltwhistle,UK","institution_ids":["https://openalex.org/I4210156129"]},{"raw_affiliation_string":"Prozomix Ltd, Haltwhistle, UK","institution_ids":["https://openalex.org/I4210156129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089978830","display_name":"Anil Wipat","orcid":"https://orcid.org/0000-0001-7310-4191"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anil Wipat","raw_affiliation_strings":["Newcastle University,School of Computing,Newcastle upon Tyne,UK","School of Computing, Newcastle University, Newcastle upon Tyne, UK"],"affiliations":[{"raw_affiliation_string":"Newcastle University,School of Computing,Newcastle upon Tyne,UK","institution_ids":["https://openalex.org/I84884186"]},{"raw_affiliation_string":"School of Computing, Newcastle University, Newcastle upon Tyne, UK","institution_ids":["https://openalex.org/I84884186"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5053891044"],"corresponding_institution_ids":["https://openalex.org/I84884186"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0872664,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.9968000054359436,"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/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.9968000054359436,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9955000281333923,"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/T10404","display_name":"Enzyme Catalysis and Immobilization","score":0.9936000108718872,"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/scalability","display_name":"Scalability","score":0.7467890977859497},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.7049567699432373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6249017715454102},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.540876030921936},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5307267904281616},{"id":"https://openalex.org/keywords/portfolio","display_name":"Portfolio","score":0.4688376486301422},{"id":"https://openalex.org/keywords/tabu-search","display_name":"Tabu search","score":0.45655837655067444},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38057413697242737},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.37239062786102295},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.295968234539032},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2765684127807617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24948421120643616},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12388873100280762}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7467890977859497},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7049567699432373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6249017715454102},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.540876030921936},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5307267904281616},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.4688376486301422},{"id":"https://openalex.org/C123370116","wikidata":"https://www.wikidata.org/wiki/Q1424540","display_name":"Tabu search","level":2,"score":0.45655837655067444},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38057413697242737},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.37239062786102295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.295968234539032},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2765684127807617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24948421120643616},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12388873100280762},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cibcb55180.2022.9863021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb55180.2022.9863021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1970051672","https://openalex.org/W2001115404","https://openalex.org/W2013749500","https://openalex.org/W2022027915","https://openalex.org/W2060797027","https://openalex.org/W2067583942","https://openalex.org/W2072306011","https://openalex.org/W2074717268","https://openalex.org/W2083620785","https://openalex.org/W2101291993","https://openalex.org/W2109215753","https://openalex.org/W2110921177","https://openalex.org/W2111973517","https://openalex.org/W2130980674","https://openalex.org/W2133215312","https://openalex.org/W2144656637","https://openalex.org/W2158714788","https://openalex.org/W2159675211","https://openalex.org/W2162921349","https://openalex.org/W2787102209","https://openalex.org/W2808991630","https://openalex.org/W2946719847","https://openalex.org/W3096046766","https://openalex.org/W3112376646","https://openalex.org/W4224014712","https://openalex.org/W6763314214"],"related_works":["https://openalex.org/W2224940485","https://openalex.org/W2361861616","https://openalex.org/W2168643831","https://openalex.org/W2075514833","https://openalex.org/W2381791171","https://openalex.org/W4247343174","https://openalex.org/W1987877777","https://openalex.org/W2263699433","https://openalex.org/W2366189044","https://openalex.org/W2363364691"],"abstract_inverted_index":{"Enzymes":[0],"are":[1,83],"being":[2],"increasingly":[3],"exploited":[4],"in":[5,45,71],"various":[6],"industries":[7],"for":[8,55,63,91,109],"their":[9],"potential":[10],"as":[11,150],"biocatalysts.":[12],"Increasing":[13],"the":[14,23,31,46,67,92,105,141],"portfolio":[15],"of":[16,26,34,50,95,131,140],"available":[17],"and":[18,80,82,114,116,137,145],"useful":[19],"biocatalysts":[20],"depends":[21],"on":[22,66,118],"reliable":[24],"annotation":[25,36],"enzyme":[27,53,72,98,121],"catalytic":[28,143],"function.":[29],"However,":[30],"required":[32],"quality":[33],"such":[35,149],"can":[37],"only":[38],"be":[39],"confidently":[40],"guaranteed":[41],"through":[42],"experimental":[43],"characterisation":[44,57],"laboratory.":[47],"The":[48],"selection":[49,76,94],"catalytically":[51],"diverse":[52,120],"panels":[54,130],"experimentally":[56],"is":[58],"therefore":[59],"an":[60],"important":[61],"step":[62],"shedding":[64],"light":[65],"currently":[68],"unannotated":[69],"proteins":[70],"families.":[73,99,122],"As":[74],"current":[75],"methods":[77,148],"lack":[78],"efficiency":[79],"scalability,":[81],"non":[84],"systematic,":[85],"we":[86],"present":[87],"a":[88],"novel":[89],"approach":[90,127],"automatic":[93],"subsets":[96],"from":[97],"A":[100],"tabu":[101],"search":[102],"algorithm":[103],"solving":[104],"maximum":[106],"diversity":[107],"problem":[108],"sequence":[110],"identity":[111],"was":[112],"designed":[113],"implemented,":[115],"applied":[117],"three":[119],"We":[123],"show":[124],"that":[125,133],"this":[126],"automatically":[128],"selects":[129],"enzymes":[132],"contain":[134],"high":[135],"richness":[136],"relative":[138],"abundance":[139],"known":[142],"functions,":[144],"outperforms":[146],"other":[147],"k-medoids.":[151]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
