{"id":"https://openalex.org/W4310491011","doi":"https://doi.org/10.1093/bioinformatics/btac774","title":"Scaling neighbor joining to one million taxa with dynamic and heuristic neighbor joining","display_name":"Scaling neighbor joining to one million taxa with dynamic and heuristic neighbor joining","publication_year":2022,"publication_date":"2022-12-01","ids":{"openalex":"https://openalex.org/W4310491011","doi":"https://doi.org/10.1093/bioinformatics/btac774","pmid":"https://pubmed.ncbi.nlm.nih.gov/36453849"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac774","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac774","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac774/48448937/btac774.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","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":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac774/48448937/btac774.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064950341","display_name":"Philip T. L. C. Clausen","orcid":"https://orcid.org/0000-0002-8197-7520"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Philip T L C Clausen","raw_affiliation_strings":["Research Group for Genomic Epidemiology, National Food Institute, Technical University of Denmark , 2800 Kgs. Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-8197-7520","affiliations":[{"raw_affiliation_string":"Research Group for Genomic Epidemiology, National Food Institute, Technical University of Denmark , 2800 Kgs. Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5064950341"],"corresponding_institution_ids":["https://openalex.org/I96673099"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.0394,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.75499085,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"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":0.5009999871253967,"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":0.5009999871253967,"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":0.13199999928474426,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.05829999968409538,"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/scaling","display_name":"Scaling","score":0.7402099370956421},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6546043157577515},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5419619083404541},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5155006051063538},{"id":"https://openalex.org/keywords/taxon","display_name":"Taxon","score":0.5080766677856445},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4409253001213074},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38172563910484314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2931121587753296},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2591020166873932},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2145867645740509},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.1638638973236084},{"id":"https://openalex.org/keywords/paleontology","display_name":"Paleontology","score":0.10409307479858398},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06800726056098938}],"concepts":[{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.7402099370956421},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6546043157577515},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5419619083404541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5155006051063538},{"id":"https://openalex.org/C71640776","wikidata":"https://www.wikidata.org/wiki/Q16521","display_name":"Taxon","level":2,"score":0.5080766677856445},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4409253001213074},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38172563910484314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2931121587753296},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2591020166873932},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2145867645740509},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.1638638973236084},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.10409307479858398},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06800726056098938}],"mesh":[{"descriptor_ui":"D000066506","descriptor_name":"Heuristics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000066506","descriptor_name":"Heuristics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000066506","descriptor_name":"Heuristics","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":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","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":"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}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btac774","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac774","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac774/48448937/btac774.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","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:36453849","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36453849","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:9805563","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9805563","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":"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"},{"id":"pmh:oai:pure.atira.dk:publications/eba795b8-33d5-4d75-be8f-536935c2b86c","is_oa":true,"landing_page_url":"https://orbit.dtu.dk/en/publications/eba795b8-33d5-4d75-be8f-536935c2b86c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"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":"Clausen , P T L C 2023 , ' Scaling Neighbor-Joining to One Million Taxa with Dynamic and Heuristic Neighbor-Joining ' , Bioinformatics , vol. 39 , no. 1 , btac774 . https://doi.org/10.1093/bioinformatics/btac774","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btac774","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac774","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac774/48448937/btac774.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","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":[{"score":0.4099999964237213,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G2723464381","display_name":null,"funder_award_id":"NNF16OC0021856","funder_id":"https://openalex.org/F4320325957","funder_display_name":"Novo Nordisk Fonden"}],"funders":[{"id":"https://openalex.org/F4320325957","display_name":"Novo Nordisk Fonden","ror":"https://ror.org/04txyc737"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4310491011.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1489608363","https://openalex.org/W2014141753","https://openalex.org/W2028715154","https://openalex.org/W2031611770","https://openalex.org/W2035831318","https://openalex.org/W2096525273","https://openalex.org/W2097706568","https://openalex.org/W2109586018","https://openalex.org/W2111802622","https://openalex.org/W2120636855","https://openalex.org/W2127520112","https://openalex.org/W2134852597","https://openalex.org/W2137995988","https://openalex.org/W2591744545","https://openalex.org/W2611919322","https://openalex.org/W2789843538","https://openalex.org/W2807731504","https://openalex.org/W2889178232","https://openalex.org/W2950150251","https://openalex.org/W3003217347","https://openalex.org/W3012135270","https://openalex.org/W3036890695","https://openalex.org/W3119321472","https://openalex.org/W3154583975","https://openalex.org/W4226314289","https://openalex.org/W4239634997","https://openalex.org/W6629092883","https://openalex.org/W6674647444","https://openalex.org/W6751341652"],"related_works":["https://openalex.org/W2657261411","https://openalex.org/W3118950109","https://openalex.org/W141820298","https://openalex.org/W2049584446","https://openalex.org/W2079781215","https://openalex.org/W4378770497","https://openalex.org/W4308245303","https://openalex.org/W2014033564","https://openalex.org/W4386404313","https://openalex.org/W2910573937"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1],"neighbor-joining":[2],"(NJ)":[3],"algorithm":[4,53],"is":[5,27,69,126],"a":[6,31],"widely":[7],"used":[8],"method":[9,98],"to":[10,29,49,99,101,120,128],"perform":[11],"iterative":[12],"clustering":[13],"and":[14,86,112],"forms":[15],"the":[16,50,95,107,115],"basis":[17],"for":[18,40,72],"phylogenetic":[19],"reconstruction":[20],"in":[21],"several":[22,43],"bioinformatic":[23],"pipelines.":[24],"Although":[25],"NJ":[26,52,97,122,131],"considered":[28],"be":[30],"computationally":[32],"efficient":[33],"algorithm,":[34],"it":[35],"does":[36],"not":[37,70],"scale":[38,100],"well":[39],"datasets":[41],"exceeding":[42],"thousand":[44],"taxa":[45,104],"(>100":[46],"000).":[47],"Optimizations":[48],"canonical":[51,96],"have":[54],"been":[55],"proposed;":[56],"these":[57],"optimizations":[58],"are,":[59],"however,":[60],"achieved":[61],"through":[62],"approximations":[63],"or":[64],"extensive":[65],"memory":[66,108],"usage,":[67],"which":[68,93],"feasible":[71],"large":[73],"datasets.":[74],"RESULTS:":[75],"In":[76],"this":[77],"article,":[78],"two":[79],"new":[80],"algorithms,":[81],"dynamic":[82],"neighbor":[83,88],"joining":[84,89],"(DNJ)":[85],"heuristic":[87],"(HNJ),":[90],"are":[91,141],"presented,":[92],"optimize":[94],"millions":[102],"of":[103],"without":[105],"increasing":[106],"requirements.":[109],"Both":[110],"DNJ":[111,125],"HNJ":[113],"outperform":[114],"current":[116],"gold":[117],"standard":[118],"methods":[119],"construct":[121],"trees,":[123],"while":[124],"guaranteed":[127],"produce":[129],"exact":[130],"trees.":[132],"AVAILABILITY":[133],"AND":[134],"IMPLEMENTATION:":[135],"https://bitbucket.org/genomicepidemiology/ccphylo.git.":[136],"SUPPLEMENTARY":[137],"INFORMATION:":[138],"Supplementary":[139],"data":[140],"available":[142],"at":[143],"Bioinformatics":[144],"online.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}
