{"id":"https://openalex.org/W2577648383","doi":"https://doi.org/10.1090/dimacs/061/07","title":"A top-down method for building genome classification trees with linear binary hierarchies","display_name":"A top-down method for building genome classification trees with linear binary hierarchies","publication_year":2003,"publication_date":"2003-04-15","ids":{"openalex":"https://openalex.org/W2577648383","doi":"https://doi.org/10.1090/dimacs/061/07","mag":"2577648383"},"language":"en","primary_location":{"id":"doi:10.1090/dimacs/061/07","is_oa":false,"landing_page_url":"https://doi.org/10.1090/dimacs/061/07","pdf_url":null,"source":{"id":"https://openalex.org/S4210177973","display_name":"DIMACS series in discrete mathematics and theoretical computer science","issn_l":"1052-1798","issn":["1052-1798","2472-4793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"DIMACS Series in Discrete Mathematics and Theoretical Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075542475","display_name":"Boris Mirkin","orcid":"https://orcid.org/0000-0001-5470-8635"},"institutions":[{"id":"https://openalex.org/I98259816","display_name":"Birkbeck, University of London","ror":"https://ror.org/02mb95055","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I98259816"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Boris Mirkin","raw_affiliation_strings":["Birkbeck College, London, England"],"affiliations":[{"raw_affiliation_string":"Birkbeck College, London, England","institution_ids":["https://openalex.org/I98259816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035240489","display_name":"Eugene V. Koonin","orcid":"https://orcid.org/0000-0003-3943-8299"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eugene Koonin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075542475"],"corresponding_institution_ids":["https://openalex.org/I98259816"],"apc_list":null,"apc_paid":null,"fwci":1.4193,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.8516624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9957000017166138,"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":0.9957000017166138,"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":0.9944000244140625,"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":0.982699990272522,"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/binary-number","display_name":"Binary number","score":0.5313917398452759},{"id":"https://openalex.org/keywords/binary-tree","display_name":"Binary tree","score":0.44940584897994995},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4274471402168274},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.41766345500946045},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36967968940734863},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.329437255859375},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29548418521881104},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.14631128311157227}],"concepts":[{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5313917398452759},{"id":"https://openalex.org/C197855036","wikidata":"https://www.wikidata.org/wiki/Q380172","display_name":"Binary tree","level":2,"score":0.44940584897994995},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4274471402168274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41766345500946045},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36967968940734863},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.329437255859375},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29548418521881104},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.14631128311157227}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1090/dimacs/061/07","is_oa":false,"landing_page_url":"https://doi.org/10.1090/dimacs/061/07","pdf_url":null,"source":{"id":"https://openalex.org/S4210177973","display_name":"DIMACS series in discrete mathematics and theoretical computer science","issn_l":"1052-1798","issn":["1052-1798","2472-4793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"DIMACS Series in Discrete Mathematics and Theoretical Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.6.9362","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.6.9362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcs.bbk.ac.uk/~mirkin/papers/koomir6.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1519987066","https://openalex.org/W1570376951","https://openalex.org/W1594031697","https://openalex.org/W1980051733","https://openalex.org/W2002446259","https://openalex.org/W2010908637","https://openalex.org/W2089170463","https://openalex.org/W2099770698","https://openalex.org/W2133790733","https://openalex.org/W2143276497","https://openalex.org/W2158350566","https://openalex.org/W2166865790","https://openalex.org/W2571838872","https://openalex.org/W2783735076"],"related_works":["https://openalex.org/W2082860237","https://openalex.org/W2119695867","https://openalex.org/W2130076355","https://openalex.org/W1990804418","https://openalex.org/W1993764875","https://openalex.org/W2046158694","https://openalex.org/W2788277189","https://openalex.org/W2013243191","https://openalex.org/W1971568933","https://openalex.org/W2117258802"],"abstract_inverted_index":{"With":[0],"complete":[1],"genome":[2],"sequence":[3],"data":[4],"becoming":[5,25],"available":[6],"at":[7],"an":[8,30,54],"increasing":[9],"rate,":[10],"the":[11,16,19,40,43,59,65,70,78,120,143,164,167,181,193],"problem":[12],"of":[13,15,21,36,42,45,49,61,67,69,81,83,96,99,171,183],"classification":[14,178],"genomes":[17,46,103],"on":[18],"basis":[20],"different":[22,102],"criteria":[23],"is":[24,91],"pressing.":[26],"Here":[27],"we":[28],"present":[29],"approach":[31,74],"that":[32,114],"applies":[33],"linear":[34,151],"embedding":[35],"binary":[37,152],"hierarchies":[38],"to":[39,76,132,141,156,161],"analysis":[41],"representation":[44],"in":[47,86,113,169],"clusters":[48],"orthologs.":[50],"Rather":[51],"than":[52],"imposing":[53],"evolutionary":[55],"postulate":[56],"such":[57],"as":[58],"additivity":[60],"tree":[62],"metrics":[63],"or":[64],"principle":[66],"parsimony":[68],"character":[71],"changes,":[72],"this":[73,158],"tries":[75],"approximate":[77],"observed":[79],"patterns":[80],"presence/absence":[82],"individual":[84,89],"genes":[85],"genomes.":[87],"An":[88],"dene":[90],"modeled":[92],"by":[93,117],"a":[94,172],"cluster":[95],"orthologous":[97],"groups":[98],"proteins":[100],"from":[101,109,136],"(COG).":[104],"The":[105,150,176],"developed":[106],"method":[107,168],"differs":[108],"other":[110],"tree-building":[111],"methods":[112],"it":[115],"works":[116],"sequentially":[118],"splitting":[119,144],"entity":[121],"set":[122],"and,":[123,139,159],"accordingly,":[124],"modeling":[125],"potential":[126,182],"speciation":[127],"events.":[128],"This":[129],"allows,":[130],"first,":[131],"remove":[133],"&amp;quot;worked-out&amp;quot;":[134],"characters":[135],"further":[137],"splits":[138],"second,":[140],"stop":[142],"process":[145],"when":[146],"results":[147],"become":[148],"unreliable.":[149],"hierarchy":[153],"theory":[154],"allows":[155],"do":[157],"also,":[160],"explicitly":[162],"reformulate":[163],"criterion":[165],"and":[166],"terms":[170],"between-genome":[173],"similarity":[174],"index.":[175],"resulting":[177],"trees":[179],"have":[180],"revealing":[184],"previously":[185],"unnoticed":[186],"but":[187],"potentially":[188],"biologically":[189],"relevant":[190],"relationships":[191],"between":[192],"corresponding":[194],"organisms.":[195]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-07T06:01:17.266235","created_date":"2025-10-10T00:00:00"}
