{"id":"https://openalex.org/W4285740661","doi":"https://doi.org/10.1109/tcbb.2022.3191848","title":"Large-Scale Multiple Sequence Alignment and the Maximum Weight Trace Alignment Merging Problem","display_name":"Large-Scale Multiple Sequence Alignment and the Maximum Weight Trace Alignment Merging Problem","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4285740661","doi":"https://doi.org/10.1109/tcbb.2022.3191848","pmid":"https://pubmed.ncbi.nlm.nih.gov/35849662"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2022.3191848","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcbb.2022.3191848","pdf_url":"https://ieeexplore.ieee.org/ielx7/8857/4359833/09832784.pdf","source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/8857/4359833/09832784.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014969856","display_name":"Paul Zaharias","orcid":"https://orcid.org/0000-0003-3550-2636"},"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":false,"raw_author_name":"Paul Zaharias","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-3550-2636","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","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":false,"raw_author_name":"Vladimir Smirnov","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, 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, 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":false,"raw_author_name":"Tandy Warnow","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, 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, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3465,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.55267592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"20","issue":"3","first_page":"1700","last_page":"1712"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","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/T10015","display_name":"Genomics and Phylogenetic Studies","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":0.9969000220298767,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9954000115394592,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.8288634419441223},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.715271532535553},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.6421070694923401},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6222349405288696},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6078138947486877},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.5137985348701477},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5082225799560547},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.49045082926750183},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.47127029299736023},{"id":"https://openalex.org/keywords/divide-and-conquer-algorithms","display_name":"Divide and conquer algorithms","score":0.4401392936706543},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41432642936706543},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3244866132736206},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.2561674416065216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23956820368766785},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18774211406707764},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07227686047554016},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.05963718891143799},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.05930185317993164}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.8288634419441223},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.715271532535553},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.6421070694923401},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6222349405288696},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6078138947486877},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.5137985348701477},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5082225799560547},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.49045082926750183},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.47127029299736023},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.4401392936706543},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41432642936706543},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3244866132736206},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.2561674416065216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23956820368766785},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18774211406707764},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07227686047554016},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.05963718891143799},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.05930185317993164},{"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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000066506","descriptor_name":"Heuristics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000066506","descriptor_name":"Heuristics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000066506","descriptor_name":"Heuristics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":2,"locations":[{"id":"doi:10.1109/tcbb.2022.3191848","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcbb.2022.3191848","pdf_url":"https://ieeexplore.ieee.org/ielx7/8857/4359833/09832784.pdf","source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:35849662","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35849662","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":{"id":"doi:10.1109/tcbb.2022.3191848","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcbb.2022.3191848","pdf_url":"https://ieeexplore.ieee.org/ielx7/8857/4359833/09832784.pdf","source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3000003317","display_name":"IIBR Informatics: Advancing Bioinformatics Methods using Ensembles of Profile Hidden Markov Models","funder_award_id":"2006069","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3750374216","display_name":"ABI Innovation: New methods for multiple sequence alignment with improved accuracy and scalability","funder_award_id":"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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285740661.pdf","grobid_xml":"https://content.openalex.org/works/W4285740661.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W47863446","https://openalex.org/W1497763703","https://openalex.org/W1515034099","https://openalex.org/W1519266993","https://openalex.org/W1588822927","https://openalex.org/W1748508858","https://openalex.org/W1963230138","https://openalex.org/W1984249061","https://openalex.org/W1992312974","https://openalex.org/W2007668764","https://openalex.org/W2030701413","https://openalex.org/W2056251063","https://openalex.org/W2070232376","https://openalex.org/W2084864929","https://openalex.org/W2086202918","https://openalex.org/W2097386339","https://openalex.org/W2102502076","https://openalex.org/W2106202847","https://openalex.org/W2107511706","https://openalex.org/W2112900913","https://openalex.org/W2123250224","https://openalex.org/W2125372717","https://openalex.org/W2127322768","https://openalex.org/W2130919252","https://openalex.org/W2140872496","https://openalex.org/W2140890018","https://openalex.org/W2142056356","https://openalex.org/W2143008661","https://openalex.org/W2144362290","https://openalex.org/W2147461064","https://openalex.org/W2149037310","https://openalex.org/W2149857793","https://openalex.org/W2154730959","https://openalex.org/W2156985047","https://openalex.org/W2159638180","https://openalex.org/W2166557397","https://openalex.org/W2169602699","https://openalex.org/W2549209567","https://openalex.org/W2896071897","https://openalex.org/W2899730448","https://openalex.org/W3094189775","https://openalex.org/W3109134151","https://openalex.org/W3197876952","https://openalex.org/W3204504530","https://openalex.org/W3208930226","https://openalex.org/W4230059016","https://openalex.org/W4236269389","https://openalex.org/W4238924195","https://openalex.org/W6629835057","https://openalex.org/W6630502198","https://openalex.org/W6704380518","https://openalex.org/W6751433836"],"related_works":["https://openalex.org/W4247094814","https://openalex.org/W2352794675","https://openalex.org/W2051228988","https://openalex.org/W108531593","https://openalex.org/W8810113","https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4249244686","https://openalex.org/W3159261607","https://openalex.org/W2052518678"],"abstract_inverted_index":{"MAGUS":[0,16,50,129],"is":[1,51,58],"a":[2,38,59,109],"recent":[3],"multiple":[4],"sequence":[5],"alignment":[6,92],"method":[7],"that":[8,56,85,99],"provides":[9],"excellent":[10],"accuracy":[11,93],"on":[12,28,117,126],"large":[13],"challenging":[14],"datasets.":[15],"uses":[17],"divide-and-conquer:":[18],"it":[19,40],"divides":[20],"the":[21,29,35,42,63,72,122],"sequences":[22],"into":[23],"disjoint":[24,30],"sets,":[25,31],"computes":[26],"alignments":[27,36],"and":[32,81,94,130],"then":[33],"merges":[34],"using":[37,78],"technique":[39],"calls":[41],"Graph":[43],"Clustering":[44],"Method":[45],"(GCM).":[46],"To":[47],"understand":[48],"why":[49],"so":[52],"accurate,":[53],"we":[54],"show":[55],"GCM":[57,98],"good":[60],"heuristic":[61],"for":[62,104,112],"NP-hard":[64],"MWT-AM":[65,86],"problem":[66],"(Maximum":[67],"Weight":[68],"Trace,":[69],"adapted":[70],"to":[71,97],"Alignment":[73],"Merging":[74],"problem).":[75],"Our":[76],"study,":[77],"both":[79],"biological":[80],"simulated":[82],"data,":[83],"establishes":[84],"scores":[87],"correlate":[88],"very":[89],"well":[90],"with":[91,121],"presents":[95],"improvements":[96],"are":[100,134],"even":[101],"better":[102],"heuristics":[103],"MWT-AM.":[105,128],"This":[106],"study":[107],"suggests":[108],"new":[110],"direction":[111],"large-scale":[113],"MSA":[114],"estimation":[115],"based":[116,125],"improved":[118],"divide-and-conquer":[119],"strategies,":[120],"merging":[123],"step":[124],"optimizing":[127],"its":[131],"enhanced":[132],"versions":[133],"available":[135],"at":[136],"https://github.com/vlasmirnov/MAGUS.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}
