{"id":"https://openalex.org/W4400242799","doi":"https://doi.org/10.1186/s12859-024-05839-x","title":"Hitac: a hierarchical taxonomic classifier for fungal ITS sequences compatible with QIIME2","display_name":"Hitac: a hierarchical taxonomic classifier for fungal ITS sequences compatible with QIIME2","publication_year":2024,"publication_date":"2024-07-02","ids":{"openalex":"https://openalex.org/W4400242799","doi":"https://doi.org/10.1186/s12859-024-05839-x","pmid":"https://pubmed.ncbi.nlm.nih.gov/38956506"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05839-x","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-024-05839-x","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/s12859-024-05839-x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047727399","display_name":"F\u00e1bio Malcher Miranda","orcid":"https://orcid.org/0000-0002-6823-5995"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"F\u00e1bio M. Miranda","raw_affiliation_strings":["Data Analytics and Computational Statistics, Hasso Plattner Institute, Digital Engineering Faculty, University of Potsdam, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Data Analytics and Computational Statistics, Hasso Plattner Institute, Digital Engineering Faculty, University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090969979","display_name":"Vasco Azevedo","orcid":"https://orcid.org/0000-0002-4775-2280"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Vasco C. Azevedo","raw_affiliation_strings":["Institute of Biological Sciences, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Institute of Biological Sciences, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076978229","display_name":"Rommel Thiago Juc\u00e1 Ramos","orcid":"https://orcid.org/0000-0002-8032-1474"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rommel J. Ramos","raw_affiliation_strings":["Institute of Biological Sciences, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Institute of Biological Sciences, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005996110","display_name":"Bernhard Y. Renard","orcid":"https://orcid.org/0000-0003-4589-9809"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bernhard Y. Renard","raw_affiliation_strings":["Data Analytics and Computational Statistics, Hasso Plattner Institute, Digital Engineering Faculty, University of Potsdam, Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Data Analytics and Computational Statistics, Hasso Plattner Institute, Digital Engineering Faculty, University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030335109","display_name":"Vitor C. Piro","orcid":"https://orcid.org/0000-0003-1330-1286"},"institutions":[{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Vitor C. Piro","raw_affiliation_strings":["Department of Mathematics and Computer Science, Freie Universit\u00e4t Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, Freie Universit\u00e4t Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I75951250"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.0,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":85},"biblio":{"volume":"25","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10825","display_name":"Diversity and Evolution of Fungal Pathogens","score":0.995,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell 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/T10825","display_name":"Diversity and Evolution of Fungal Pathogens","score":0.995,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell 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/T10015","display_name":"RNA Sequencing Data Analysis","score":0.9933,"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/T10451","display_name":"Mycorrhizal Fungi and Plant Interactions","score":0.9926,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/taxonomic-rank","display_name":"Taxonomic rank","score":0.64875346},{"id":"https://openalex.org/keywords/fungal-diversity","display_name":"Fungal Diversity","score":0.534053},{"id":"https://openalex.org/keywords/ecosystem-functioning","display_name":"Ecosystem Functioning","score":0.529541},{"id":"https://openalex.org/keywords/functional-genomics","display_name":"Functional Genomics","score":0.514191}],"concepts":[{"id":"https://openalex.org/C189592816","wikidata":"https://www.wikidata.org/wiki/Q427626","display_name":"Taxonomic rank","level":3,"score":0.64875346},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6236072},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6080453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.56420213},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5142459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5021126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41912106},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.36341652},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33547693},{"id":"https://openalex.org/C71640776","wikidata":"https://www.wikidata.org/wiki/Q16521","display_name":"Taxon","level":2,"score":0.2778971},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.23550701}],"mesh":[{"descriptor_ui":"D021903","descriptor_name":"DNA, Ribosomal Spacer","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005658","descriptor_name":"Fungi","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":"","qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05839-x","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-024-05839-x","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.ncbi.nlm.nih.gov/pmc/articles/PMC11220968","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/38956506","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/s12859-024-05839-x","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-024-05839-x","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":[],"grants":[{"funder":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft","award_id":"458163427"},{"funder":"https://openalex.org/F4320324521","funder_display_name":"Freie Universit\u00e4t Berlin","award_id":null}],"datasets":[],"versions":[],"referenced_works_count":33,"referenced_works":["https://openalex.org/W118419743","https://openalex.org/W1928057741","https://openalex.org/W1985623566","https://openalex.org/W1998601670","https://openalex.org/W2017435247","https://openalex.org/W2036940737","https://openalex.org/W2056926089","https://openalex.org/W2069773272","https://openalex.org/W2091922579","https://openalex.org/W2096525273","https://openalex.org/W2108718991","https://openalex.org/W2110375946","https://openalex.org/W2112662762","https://openalex.org/W2113601822","https://openalex.org/W2121916820","https://openalex.org/W2129271132","https://openalex.org/W2136434605","https://openalex.org/W2142678031","https://openalex.org/W2150766729","https://openalex.org/W2151350595","https://openalex.org/W2152885278","https://openalex.org/W2158714788","https://openalex.org/W2260894375","https://openalex.org/W2596977934","https://openalex.org/W2802266517","https://openalex.org/W2803566787","https://openalex.org/W2891784361","https://openalex.org/W2900030356","https://openalex.org/W2941919318","https://openalex.org/W2953236953","https://openalex.org/W4231170962","https://openalex.org/W4306901869","https://openalex.org/W4376867625"],"related_works":["https://openalex.org/W4394984040","https://openalex.org/W4386259002","https://openalex.org/W4308716060","https://openalex.org/W4280648719","https://openalex.org/W3193043704","https://openalex.org/W3171520305","https://openalex.org/W3135126032","https://openalex.org/W2889302474","https://openalex.org/W1924178503","https://openalex.org/W1546989560"],"abstract_inverted_index":{"Abstract":[0],"Background":[1],"Fungi":[2],"play":[3],"a":[4,81,152,164,196],"key":[5],"role":[6],"in":[7,133,235,268],"several":[8],"important":[9],"ecological":[10],"functions,":[11],"ranging":[12],"from":[13],"organic":[14],"matter":[15],"decomposition":[16],"to":[17,113,136],"symbiotic":[18],"associations":[19],"with":[20,100,180],"plants.":[21],"Moreover,":[22],"fungi":[23],"naturally":[24],"inhabit":[25],"the":[26,39,48,68,85,94,114,124,181,202,236,249,261],"human":[27],"body":[28],"and":[29,57,90,102,140,171,185,195,204,220,254,270,274,279],"can":[30,76,172],"be":[31],"beneficial":[32],"when":[33,128,211],"administered":[34],"as":[35,47],"probiotics.":[36],"In":[37],"mycology,":[38],"internal":[40],"transcribed":[41],"spacer":[42],"(ITS)":[43],"region":[44],"was":[45,177],"adopted":[46],"universal":[49],"marker":[50],"for":[51,60,67,110,158,169],"classifying":[52],"fungi.":[53],"Hence,":[54],"an":[55],"accurate":[56,159],"robust":[58,153],"method":[59],"ITS":[61,160,190],"classification":[62,145],"is":[63,245,258],"not":[64],"only":[65],"desired":[66],"purpose":[69],"of":[70,87,96,116,120,143,167,192,198],"better":[71],"diversity":[72],"estimation,":[73],"but":[74],"it":[75],"also":[77],"help":[78],"us":[79],"gain":[80],"deeper":[82],"insight":[83],"into":[84],"dynamics":[86],"environmental":[88],"communities":[89],"ultimately":[91],"comprehend":[92],"whether":[93],"abundance":[95],"certain":[97],"species":[98],"correlate":[99],"health":[101],"disease.":[103],"Although":[104],"many":[105],"methods":[106,210,234],"have":[107],"been":[108],"proposed":[109],"taxonomic":[111,125,224],"classification,":[112,161],"best":[115],"our":[117],"knowledge,":[118],"none":[119],"them":[121],"fully":[122],"explore":[123],"tree":[126],"hierarchy":[127],"building":[129],"their":[130],"models.":[131],"This":[132],"turn,":[134],"leads":[135],"lower":[137],"generalization":[138],"power":[139],"higher":[141,218],"risk":[142],"committing":[144],"errors.":[146],"Results":[147],"Here":[148],"we":[149],"introduce":[150],"HiTaC,":[151],"hierarchical":[154],"machine":[155],"learning":[156],"model":[157],"which":[162,276],"requires":[163],"small":[165],"amount":[166],"data":[168],"training":[170,203],"handle":[173],"imbalanced":[174],"datasets.":[175],"HiTaC":[176,207,244],"thoroughly":[178],"evaluated":[179],"established":[182],"TAXXI":[183],"benchmark":[184],"could":[186],"correctly":[187],"classify":[188],"fungal":[189],"sequences":[191],"varying":[193],"lengths":[194],"range":[197],"identity":[199],"differences":[200],"between":[201],"test":[205],"data.":[206],"outperforms":[208],"state-of-the-art":[209],"trained":[212],"over":[213,232],"noisy":[214,238],"data,":[215],"consistently":[216],"achieving":[217],"F1-score":[219],"sensitivity":[221,227],"across":[222],"different":[223],"ranks,":[225],"improving":[226],"by":[228],"6.9":[229],"percentage":[230],"points":[231],"top":[233],"most":[237],"dataset":[239],"available":[240,247,283],"on":[241],"TAXXI.":[242],"Conclusions":[243],"publicly":[246],"at":[248,284],"Python":[250],"package":[251],"index,":[252],"BIOCONDA":[253],"Docker":[255],"Hub.":[256],"It":[257],"released":[259],"under":[260],"new":[262],"BSD":[263],"license,":[264],"allowing":[265],"free":[266],"use":[267],"academia":[269],"industry.":[271],"Source":[272],"code":[273],"documentation,":[275],"includes":[277],"installation":[278],"usage":[280],"instructions,":[281],"are":[282],"https://gitlab.com/dacs-hpi/hitac":[285],".":[286]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4400242799","counts_by_year":[],"updated_date":"2024-11-24T17:42:47.560568","created_date":"2024-07-03"}
