{"id":"https://openalex.org/W2033040629","doi":"https://doi.org/10.1186/1471-2105-12-51","title":"Tree pruner: An efficient tool for selecting data from a biased genetic database","display_name":"Tree pruner: An efficient tool for selecting data from a biased genetic database","publication_year":2011,"publication_date":"2011-02-09","ids":{"openalex":"https://openalex.org/W2033040629","doi":"https://doi.org/10.1186/1471-2105-12-51","mag":"2033040629","pmid":"https://pubmed.ncbi.nlm.nih.gov/21306634","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/3045304"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-51","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-51","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-51","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032531251","display_name":"Mohan Krishnamoorthy","orcid":"https://orcid.org/0000-0002-0828-4066"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohan Krishnamoorthy","raw_affiliation_strings":["Theoretical Division , Los Alamos National Laboratory , Los Alamos, USA"],"affiliations":[{"raw_affiliation_string":"Theoretical Division , Los Alamos National Laboratory , Los Alamos, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008386220","display_name":"Pragneshkumar Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pragneshkumar Patel","raw_affiliation_strings":["Theoretical Division , Los Alamos National Laboratory , Los Alamos, USA"],"affiliations":[{"raw_affiliation_string":"Theoretical Division , Los Alamos National Laboratory , Los Alamos, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085158291","display_name":"Mirjana Dimitrijevi\u0107","orcid":"https://orcid.org/0000-0002-9094-5248"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mira Dimitrijevic","raw_affiliation_strings":["Theoretical Division , Los Alamos National Laboratory , Los Alamos, USA"],"affiliations":[{"raw_affiliation_string":"Theoretical Division , Los Alamos National Laboratory , Los Alamos, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059764237","display_name":"Jonathan Dietrich","orcid":null},"institutions":[{"id":"https://openalex.org/I2948394018","display_name":"Northrop Grumman (United States)","ror":"https://ror.org/05kewds18","country_code":"US","type":"company","lineage":["https://openalex.org/I2948394018"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Dietrich","raw_affiliation_strings":["Northrop Grumman Health IT, Rockville, USA"],"affiliations":[{"raw_affiliation_string":"Northrop Grumman Health IT, Rockville, USA","institution_ids":["https://openalex.org/I2948394018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112279481","display_name":"Margaret Green","orcid":null},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"Margaret Green","raw_affiliation_strings":["Genentech, Inc. 1 DNA Way, South San Francisco, USA"],"affiliations":[{"raw_affiliation_string":"Genentech, Inc. 1 DNA Way, South San Francisco, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109209248","display_name":"Catherine A. Macken","orcid":null},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Catherine Macken","raw_affiliation_strings":["Theoretical Division , Los Alamos National Laboratory , Los Alamos, USA"],"affiliations":[{"raw_affiliation_string":"Theoretical Division , Los Alamos National Laboratory , Los Alamos, USA","institution_ids":["https://openalex.org/I1343871089"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072,"provenance":"doaj"},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072,"provenance":"doaj"},"fwci":0.259,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":6,"citation_normalized_percentile":{"value":0.582928,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":81,"max":83},"biblio":{"volume":"12","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9988,"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":0.9988,"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/T10167","display_name":"Influenza Virus Research Studies","score":0.9917,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.986,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.7214823},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.65040153},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"phylogenetic tree","score":0.588379},{"id":"https://openalex.org/keywords/phylogenetic-analysis","display_name":"Phylogenetic Analysis","score":0.551121}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7641989},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.7214823},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.65040153},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5694945},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.54684144},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48151097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36134207},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35869697},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10074228},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015983","descriptor_name":"Selection Bias","qualifier_ui":"","qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-51","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-51","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1626282","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":["Office of Scientific and Technical Information"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3045304","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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21306634","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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-51","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-51","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":8,"referenced_works":["https://openalex.org/W113427216","https://openalex.org/W1521650410","https://openalex.org/W1584307670","https://openalex.org/W2023858176","https://openalex.org/W2049452005","https://openalex.org/W2054176046","https://openalex.org/W2103546861","https://openalex.org/W2142734829"],"related_works":["https://openalex.org/W4285312748","https://openalex.org/W4206442282","https://openalex.org/W3203767529","https://openalex.org/W2594301978","https://openalex.org/W2384505857","https://openalex.org/W2379704676","https://openalex.org/W2378744544","https://openalex.org/W2373300491","https://openalex.org/W2157743338","https://openalex.org/W1212596013"],"abstract_inverted_index":{"Large":[0],"databases":[1],"of":[2,13,32,47,68,117,144,172,220,258],"genetic":[3,14,49,102,221],"data":[4,15,50,169],"are":[5,152],"often":[6],"biased":[7,101,218],"in":[8,154],"their":[9],"representation.":[10],"Thus,":[11],"selection":[12,46,247],"with":[16,94,109,198,212,239],"desired":[17,39,95,213],"properties,":[18],"such":[19],"as":[20,114],"evolutionary":[21,96,214],"representation":[22],"or":[23,186],"shared":[24],"genotypes,":[25],"is":[26,160,202],"problematic.":[27],"Selection":[28],"on":[29,58,71,162],"the":[30,38,45,59,69,72,107,119,124,142,149,155,163,173,176,232,237,245,253,259],"basis":[31],"epidemiological":[33],"variables":[34],"may":[35,79],"not":[36],"achieve":[37],"properties.":[40],"Available":[41],"automated":[42,229],"approaches":[43,230],"to":[44,82,178,228,231,244],"influenza":[48],"make":[51],"a":[52,86,92,99,115,145,180,209,217,240],"tradeoff":[53],"between":[54],"speed":[55],"and":[56,62,66,135,249],"simplicity":[57],"one":[60],"hand":[61],"control":[63,251],"over":[64,252],"quality":[65],"contents":[67,254],"dataset":[70,78,93,121,182,211],"other":[73,199],"hand.":[74],"A":[75],"poorly":[76],"chosen":[77],"be":[80,193],"detrimental":[81],"subsequent":[83,188],"analyses.We":[84],"developed":[85],"tool,":[87],"Tree":[88,104,138,146,158,190],"Pruner,":[89],"for":[90,183,187,196,207],"obtaining":[91],"properties":[97,215],"from":[98,122,216],"large,":[100],"database.":[103],"Pruner":[105,139,147,159,191,201],"provides":[106],"user":[108,177,238],"an":[110,203,225],"interactive":[111],"phylogenetic":[112],"tree":[113,125,129],"means":[116],"editing":[118,150],"initial":[120],"which":[123],"was":[126],"inferred.":[127],"The":[128,168],"visualization":[130],"changes":[131],"dynamically,":[132],"using":[133],"colors":[134],"shading,":[136],"reflecting":[137],"actions.":[140],"At":[141],"end":[143],"session,":[148],"actions":[151],"implemented":[153,161],"dataset.":[156,260],"Currently,":[157],"Influenza":[164],"Research":[165],"Database":[166],"(IRD).":[167],"management":[170],"capabilities":[171],"IRD":[174],"allow":[175],"store":[179],"pruned":[181],"additional":[184],"pruning":[185],"analysis.":[189],"can":[192],"easily":[194],"adapted":[195],"use":[197],"organisms.Tree":[200],"efficient,":[204],"manual":[205],"tool":[206],"selecting":[208],"high-quality":[210],"database":[219],"sequences.":[222],"It":[223],"offers":[224],"important":[226],"alternative":[227],"same":[233],"goal,":[234],"by":[235],"providing":[236],"dynamic,":[241],"visual":[242],"guide":[243],"ongoing":[246],"process":[248],"ultimate":[250],"(and":[255],"therefore":[256],"quality)":[257]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2033040629","counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2024-12-05T05:55:37.529625","created_date":"2016-06-24"}