{"id":"https://openalex.org/W3109134151","doi":"https://doi.org/10.1093/bioinformatics/btaa992","title":"MAGUS: Multiple sequence Alignment using Graph clUStering","display_name":"MAGUS: Multiple sequence Alignment using Graph clUStering","publication_year":2020,"publication_date":"2020-11-17","ids":{"openalex":"https://openalex.org/W3109134151","doi":"https://doi.org/10.1093/bioinformatics/btaa992","mag":"3109134151","pmid":"https://pubmed.ncbi.nlm.nih.gov/33252662"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaa992","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa992","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/12/1666/39119282/btaa992.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/37/12/1666/39119282/btaa992.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053130831","display_name":"Vladimir Smirnov","orcid":"https://orcid.org/0000-0002-7826-1214"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vladimir Smirnov","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign , Urbana, IL 61801, USA"],"raw_orcid":"https://orcid.org/0000-0002-7826-1214","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign , Urbana, IL 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032411541","display_name":"Tandy Warnow","orcid":"https://orcid.org/0000-0001-7717-3514"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tandy Warnow","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign , Urbana, IL 61801, USA"],"raw_orcid":"https://orcid.org/0000-0001-7717-3514","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign , Urbana, IL 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032411541","https://openalex.org/A5053130831"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":3.1675,"has_fulltext":false,"cited_by_count":81,"citation_normalized_percentile":{"value":0.92990774,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"37","issue":"12","first_page":"1666","last_page":"1672"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9322999715805054,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9322999715805054,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.016100000590085983,"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":0.008299999870359898,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7400549650192261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7154699563980103},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6913384199142456},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.6807807683944702},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.6605648398399353},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5594710111618042},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5561302900314331},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45375725626945496},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.35986292362213135},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.30237120389938354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26109904050827026},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12271752953529358},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12199902534484863},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.060136228799819946}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7400549650192261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7154699563980103},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6913384199142456},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.6807807683944702},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.6605648398399353},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5594710111618042},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5561302900314331},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45375725626945496},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.35986292362213135},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30237120389938354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26109904050827026},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12271752953529358},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12199902534484863},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.060136228799819946},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btaa992","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa992","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/12/1666/39119282/btaa992.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:33252662","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33252662","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8289385","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8289385","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaa992","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa992","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/12/1666/39119282/btaa992.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6756578768","display_name":null,"funder_award_id":"ABI-1458652","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1519266993","https://openalex.org/W1588822927","https://openalex.org/W1748508858","https://openalex.org/W1969483458","https://openalex.org/W2007668764","https://openalex.org/W2008856488","https://openalex.org/W2031611770","https://openalex.org/W2056251063","https://openalex.org/W2102502076","https://openalex.org/W2119362018","https://openalex.org/W2127322768","https://openalex.org/W2140872496","https://openalex.org/W2140890018","https://openalex.org/W2142056356","https://openalex.org/W2144362290","https://openalex.org/W2147461064","https://openalex.org/W2159638180","https://openalex.org/W2163860567","https://openalex.org/W2169602699","https://openalex.org/W2982461819","https://openalex.org/W2991142785"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W2111937814","https://openalex.org/W2162923930","https://openalex.org/W2038009067","https://openalex.org/W1482324242","https://openalex.org/W2133116680","https://openalex.org/W2091678889","https://openalex.org/W2029514038","https://openalex.org/W2149492307","https://openalex.org/W1985408726"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1],"estimation":[2,31],"of":[3,29,147],"large":[4,164],"multiple":[5],"sequence":[6,45,80],"alignments":[7,52,122,134],"(MSAs)":[8],"is":[9,15,47,93,159],"a":[10,16,44,85,128,144],"basic":[11],"bioinformatics":[12],"challenge.":[13],"Divide-and-conquer":[14],"useful":[17],"approach":[18],"that":[19,98,135,153],"has":[20],"been":[21],"shown":[22],"to":[23,95,113],"improve":[24],"the":[25,56,72,102,120,124],"scalability":[26],"and":[27,38,64,111,149,158,166],"accuracy":[28,157],"MSA":[30,60],"in":[32,97,138],"established":[33],"methods":[34,61],"such":[35],"as":[36],"SAT\u00e9":[37],"PASTA.":[39],"In":[40],"these":[41],"divide-and-conquer":[42],"strategies,":[43],"dataset":[46],"divided":[48],"into":[49,68],"disjoint":[50,133],"subsets,":[51],"are":[53,181],"computed":[54],"on":[55,71,143,163,169],"subsets":[57],"using":[58,82,123],"base":[59],"(e.g.":[62],"MAFFT),":[63],"then":[65,118],"merged":[66],"together":[67],"an":[69],"alignment":[70],"full":[73],"dataset.":[74],"RESULTS:":[75],"We":[76],"present":[77,137],"MAGUS,":[78],"Multiple":[79],"Alignment":[81],"Graph":[83,125],"clUStering,":[84],"new":[86,129],"technique":[87],"for":[88,131],"computing":[89],"large-scale":[90],"alignments.":[91],"MAGUS":[92,154],"similar":[94,108],"PASTA":[96,162],"it":[99,168],"uses":[100],"nearly":[101],"same":[103],"initial":[104],"steps":[105],"(starting":[106],"tree,":[107],"decomposition":[109],"strategy,":[110],"MAFFT":[112],"compute":[114],"subset":[115,121],"alignments),":[116],"but":[117],"merges":[119],"Clustering":[126],"Merger,":[127],"method":[130],"combining":[132],"we":[136],"this":[139],"study.":[140],"Our":[141],"study,":[142],"heterogeneous":[145],"collection":[146],"biological":[148],"simulated":[150],"datasets,":[151,165],"shows":[152],"produces":[155],"improved":[156],"faster":[160],"than":[161],"matches":[167],"smaller":[170],"datasets.":[171],"AVAILABILITY":[172],"AND":[173],"IMPLEMENTATION:":[174],"MAGUS:":[175],"https://github.com/vlasmirnov/MAGUS.":[176],"SUPPLEMENTARY":[177],"INFORMATION:":[178],"Supplementary":[179],"data":[180],"available":[182],"at":[183],"Bioinformatics":[184],"online.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":8}],"updated_date":"2026-05-29T09:21:14.243279","created_date":"2025-10-10T00:00:00"}
