{"id":"https://openalex.org/W4281482746","doi":"https://doi.org/10.1101/2022.05.23.493139","title":"SALMA: Scalable ALignment using MAFFT-Add","display_name":"SALMA: Scalable ALignment using MAFFT-Add","publication_year":2022,"publication_date":"2022-05-25","ids":{"openalex":"https://openalex.org/W4281482746","doi":"https://doi.org/10.1101/2022.05.23.493139"},"language":"en","primary_location":{"id":"doi:10.1101/2022.05.23.493139","doi":"https://doi.org/10.1101/2022.05.23.493139","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2022.05.23.493139","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2022/08/12/2022.05.23.493139.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2022/08/12/2022.05.23.493139.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032280221","display_name":"Chengze Shen","orcid":"https://orcid.org/0000-0003-2276-9892","observed_orcids":["https://orcid.org/0000-0003-2276-9892"]},"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":"Chengze Shen","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":"https://orcid.org/0000-0003-2276-9892","affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058038050","display_name":"Baqiao Liu","orcid":"https://orcid.org/0000-0002-4210-8269","observed_orcids":["https://orcid.org/0000-0002-4210-8269"]},"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":"Baqiao Liu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":"https://orcid.org/0000-0002-4210-8269","affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083515047","display_name":"Kelly Porter Williams","orcid":"https://orcid.org/0000-0002-2606-9562","observed_orcids":["https://orcid.org/0000-0002-2606-9562"]},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I4210104735"]},{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kelly P. Williams","raw_affiliation_strings":["Sandia National Laboratories - Livermore"],"raw_orcid":"https://orcid.org/0000-0002-2606-9562","affiliations":[{"raw_affiliation_string":"Sandia National Laboratories - Livermore","institution_ids":["https://openalex.org/I192454743","https://openalex.org/I4210104735"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032411541","display_name":"Tandy J. Warnow","orcid":"https://orcid.org/0000-0001-7717-3514","observed_orcids":["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":["University of Illinois at Urbana-Champaign"],"raw_orcid":"https://orcid.org/0000-0001-7717-3514","affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032411541"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9980000257492065,"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":0.9980000257492065,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.0007999999797903001,"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":0.0003000000142492354,"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/multiple-sequence-alignment","display_name":"multiple sequence alignment","score":0.9980000257492065},{"id":"https://openalex.org/keywords/salma","display_name":"Salma","score":0.8709999918937683},{"id":"https://openalex.org/keywords/mafft","display_name":"MAFFT","score":0.7049999833106995},{"id":"https://openalex.org/keywords/divide-and-conquer","display_name":"divide-and-conquer","score":0.9449999928474426},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.7630000114440918}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7032762765884399},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7022038698196411},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5160920023918152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.358673095703125},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34249746799468994},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.221479594707489},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16880127787590027},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07260280847549438},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1101/2022.05.23.493139","doi":"https://doi.org/10.1101/2022.05.23.493139","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2022.05.23.493139","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2022/08/12/2022.05.23.493139.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1101/2022.05.23.493139","doi":"https://doi.org/10.1101/2022.05.23.493139","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2022.05.23.493139","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2022/08/12/2022.05.23.493139.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"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"}],"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/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337509","display_name":"Biological and Environmental Research","ror":"https://ror.org/0114b2m14"},{"id":"https://openalex.org/F4320337547","display_name":"Laboratory Directed Research and Development","ror":"https://ror.org/01e41cf67"},{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281482746.pdf","grobid_xml":"https://content.openalex.org/works/W4281482746.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1748508858","https://openalex.org/W1846926012","https://openalex.org/W1998618859","https://openalex.org/W2031611770","https://openalex.org/W2056251063","https://openalex.org/W2113799994","https://openalex.org/W2115394533","https://openalex.org/W2127322768","https://openalex.org/W2132926880","https://openalex.org/W2135621733","https://openalex.org/W2142056356","https://openalex.org/W2143485490","https://openalex.org/W2157552136","https://openalex.org/W2159638180","https://openalex.org/W2160378127","https://openalex.org/W2460125088","https://openalex.org/W2750791471","https://openalex.org/W2809358639","https://openalex.org/W3044581192","https://openalex.org/W3095583226","https://openalex.org/W3101667854","https://openalex.org/W3109134151","https://openalex.org/W3177828909","https://openalex.org/W3193928773","https://openalex.org/W4280524234","https://openalex.org/W4313910035"],"related_works":["https://openalex.org/W4389430430","https://openalex.org/W3156190629","https://openalex.org/W3112854456","https://openalex.org/W7125492399","https://openalex.org/W4362449288","https://openalex.org/W2792034759","https://openalex.org/W7098098366","https://openalex.org/W17481062","https://openalex.org/W3109134151","https://openalex.org/W6891639788"],"abstract_inverted_index":{"Abstract":[0],"Multiple":[1],"sequence":[2,25,37,55],"alignment":[3,13,38,189],"is":[4,28,108,180,197],"essential":[5],"for":[6,46,85,156,195],"many":[7,157],"biological":[8],"downstream":[9],"analyses,":[10],"but":[11],"accurate":[12,185],"of":[14,22,51,88,171,173,182],"large":[15,142,165],"datasets,":[16],"especially":[17],"those":[18],"exhibiting":[19,48],"high":[20,41,49,168],"rates":[21,50],"evolution":[23,52],"or":[24],"length":[26,56],"heterogeneity,":[27],"still":[29],"unsolved.":[30],"We":[31,145,175],"present":[32],"SALMA,":[33],"a":[34,82,86],"new":[35],"multiple":[36],"that":[39,58,147,178],"provides":[40],"accuracy":[42,169],"and":[43,53,70,91,160],"scalability,":[44],"even":[45],"datasets":[47,166],"great":[54],"heterogeneity":[57],"arises":[59],"from":[60],"evolutionary":[61],"processes.":[62],"Like":[63],"some":[64],"prior":[65],"methods":[66],"(e.g.,":[67],"UPP,":[68],"WITCH,":[69],"MAFFT-sparsecore),":[71],"SALMA":[72,107,179,196],"operates":[73],"in":[74,106],"two":[75],"distinct":[76],"stages:":[77],"the":[78,89,92,96,100,112,117,183],"first":[79],"stage":[80,94],"computes":[81],"\u201cbackbone":[83],"alignment\u201d":[84],"subset":[87],"sequences,":[90],"second":[93],"adds":[95,111],"remaining":[97,113],"sequences":[98,115,140],"into":[99,116,141],"backbone":[101,118,143],"alignment.":[102,119],"The":[103],"main":[104],"novelty":[105],"how":[109],"it":[110,137],"(\u201cquery\u201d)":[114],"For":[120],"this":[121],"step,":[122],"which":[123],"we":[124,129],"refer":[125],"to":[126,132,135,138,163,187],"as":[127],"SALMA-add,":[128],"use":[130],"divide-and-conquer":[131],"scale":[133,162],"MAFFT-linsi--add":[134],"enable":[136],"add":[139],"alignments.":[144],"show":[146,177],"SALMA-add":[148],"has":[149],"an":[150],"advantage":[151],"over":[152],"other":[153],"sequence-adding":[154],"techniques":[155],"realistic":[158],"conditions":[159],"can":[161],"very":[164],"with":[167],"(hundreds":[170],"thousands":[172],"sequences).":[174],"also":[176],"one":[181],"most":[184],"compared":[186],"standard":[188],"methods.":[190],"Our":[191],"open":[192],"source":[193],"software":[194],"available":[198],"at":[199],"https://github.com/c5shen/SALMA":[200],".":[201]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2022-05-26T00:00:00"}
