{"id":"https://openalex.org/W4313910035","doi":"https://doi.org/10.1093/bioinformatics/btad007","title":"UPP2: fast and accurate alignment of datasets with fragmentary sequences","display_name":"UPP2: fast and accurate alignment of datasets with fragmentary sequences","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4313910035","doi":"https://doi.org/10.1093/bioinformatics/btad007","pmid":"https://pubmed.ncbi.nlm.nih.gov/36625535"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad007","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad007","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btad007/48755283/btad007.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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","license_id":"https://openalex.org/licenses/cc-by","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":"gold","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btad007/48755283/btad007.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069222630","display_name":"Minhyuk Park","orcid":"https://orcid.org/0000-0002-8676-7565"},"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":"Minhyuk Park","raw_affiliation_strings":["Department of Computer Science, University of Illinois Urbana-Champaign , Urbana, IL 61820, USA"],"raw_orcid":"https://orcid.org/0000-0002-8676-7565","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois Urbana-Champaign , Urbana, IL 61820, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032942384","display_name":"Stefan Ivanovic","orcid":"https://orcid.org/0000-0001-8147-6200"},"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":"Stefan Ivanovic","raw_affiliation_strings":["Department of Computer Science, University of Illinois Urbana-Champaign , Urbana, IL 61820, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois Urbana-Champaign , Urbana, IL 61820, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006996313","display_name":"Gillian Chu","orcid":"https://orcid.org/0000-0003-2205-730X"},"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":"Gillian Chu","raw_affiliation_strings":["Department of Computer Science, University of Illinois Urbana-Champaign , Urbana, IL 61820, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois Urbana-Champaign , Urbana, IL 61820, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032280221","display_name":"Chengze Shen","orcid":"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":["Department of Computer Science, University of Illinois Urbana-Champaign , Urbana, IL 61820, USA"],"raw_orcid":"https://orcid.org/0000-0003-2276-9892","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois Urbana-Champaign , Urbana, IL 61820, 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 Urbana-Champaign , Urbana, IL 61820, USA"],"raw_orcid":"https://orcid.org/0000-0001-7717-3514","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois Urbana-Champaign , Urbana, IL 61820, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5032411541"],"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":2.2373,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.8754045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"39","issue":"1","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":0.9787999987602234,"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":0.9787999987602234,"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":0.002300000051036477,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.0017000000225380063,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/computer-science","display_name":"Computer science","score":0.7101919651031494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4580885171890259},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3651747703552246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7101919651031494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4580885171890259},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3651747703552246}],"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":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"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/btad007","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad007","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btad007/48755283/btad007.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36625535","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36625535","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:9846425","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9846425","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9846425/pdf/btad007.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad007","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad007","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btad007/48755283/btad007.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3000003317","display_name":null,"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"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4313910035.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1646393397","https://openalex.org/W1748508858","https://openalex.org/W2007668764","https://openalex.org/W2031611770","https://openalex.org/W2033900229","https://openalex.org/W2036792999","https://openalex.org/W2056251063","https://openalex.org/W2103130355","https://openalex.org/W2107511706","https://openalex.org/W2115394533","https://openalex.org/W2127322768","https://openalex.org/W2132926880","https://openalex.org/W2138122982","https://openalex.org/W2141152740","https://openalex.org/W2142056356","https://openalex.org/W2147461064","https://openalex.org/W2153800802","https://openalex.org/W2159638180","https://openalex.org/W2160378127","https://openalex.org/W2972411752","https://openalex.org/W2991142785","https://openalex.org/W3044581192","https://openalex.org/W3109134151","https://openalex.org/W3157271872","https://openalex.org/W3193928773","https://openalex.org/W3204504530","https://openalex.org/W4245668478","https://openalex.org/W4280524234"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"MOTIVATION:":[0],"Multiple":[1],"sequence":[2,24,33,147],"alignment":[3,34,58,74],"(MSA)":[4],"is":[5,27,39,87,105,151],"a":[6,28,40,97,106],"basic":[7],"step":[8],"in":[9,63,78,112],"many":[10],"bioinformatics":[11],"pipelines.":[12],"However,":[13],"achieving":[14],"highly":[15],"accurate":[16,136,155],"alignments":[17,137],"on":[18,59,90,100,143],"large":[19,91],"datasets,":[20],"especially":[21],"those":[22],"with":[23,126],"length":[25,148],"heterogeneity,":[26],"challenging":[29],"task.":[30],"Ultra-large":[31],"multiple":[32],"using":[35,75],"Phylogeny-aware":[36],"Profiles":[37],"(UPP)":[38],"method":[41],"for":[42,109],"MSA":[43,141],"estimation":[44],"that":[45,115,132],"builds":[46],"an":[47,56],"ensemble":[48,114],"of":[49],"Hidden":[50],"Markov":[51],"Models":[52],"(eHMM)":[53],"to":[54,118,139],"represent":[55],"estimated":[57],"the":[60,64,69,73,79,113,120,153],"full-length":[61],"sequences":[62,71],"input,":[65],"and":[66,150],"then":[67],"adds":[68],"remaining":[70],"into":[72],"selected":[76],"HMMs":[77,111],"ensemble.":[80],"Although":[81],"UPP":[82,124],"provides":[83],"good":[84],"accuracy,":[85],"it":[86],"computationally":[88],"intensive":[89],"datasets.":[92],"RESULTS:":[93],"We":[94,130],"present":[95],"UPP2,":[96],"direct":[98],"improvement":[99],"UPP.":[101],"The":[102],"main":[103],"advance":[104],"fast":[107],"technique":[108],"selecting":[110],"allows":[116],"us":[117],"achieve":[119],"same":[121],"accuracy":[122],"as":[123],"but":[125],"greatly":[127],"reduced":[128],"runtime.":[129],"show":[131],"UPP2":[133],"produces":[134],"more":[135],"compared":[138],"leading":[140],"methods":[142],"datasets":[144],"exhibiting":[145],"substantial":[146],"heterogeneity":[149],"among":[152],"most":[154],"otherwise.":[156],"AVAILABILITY":[157],"AND":[158],"IMPLEMENTATION:":[159],"https://github.com/gillichu/sepp.":[160],"SUPPLEMENTARY":[161],"INFORMATION:":[162],"Supplementary":[163],"data":[164],"are":[165],"available":[166],"at":[167],"Bioinformatics":[168],"online.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}
