{"id":"https://openalex.org/W4313525600","doi":"https://doi.org/10.1109/bibm55620.2022.9995554","title":"A New Phylogeny-Driven Random Forest-Based Classification Approach for Functional Metagenomics","display_name":"A New Phylogeny-Driven Random Forest-Based Classification Approach for Functional Metagenomics","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4313525600","doi":"https://doi.org/10.1109/bibm55620.2022.9995554"},"language":"en","primary_location":{"id":"doi:10.1109/bibm55620.2022.9995554","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bibm55620.2022.9995554","pdf_url":null,"source":{"id":"https://openalex.org/S4363607730","display_name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5007782280","display_name":"Jyotsna Talreja Wassan","orcid":"https://orcid.org/0000-0002-9116-8962"},"institutions":[{"id":"https://openalex.org/I110166357","display_name":"University of Delhi","ror":"https://ror.org/04gzb2213","country_code":"IN","type":"education","lineage":["https://openalex.org/I110166357"]},{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB","IN"],"is_corresponding":false,"raw_author_name":"Jyotsna Talreja Wassan","raw_affiliation_strings":["Ulster University,School of Computing,Belfast,United Kingdom","School of Computing, Ulster University, Belfast, United Kingdom","Department of Computer Science, Maitreyi College, University of Delhi, INDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ulster University,School of Computing,Belfast,United Kingdom","institution_ids":["https://openalex.org/I138801177"]},{"raw_affiliation_string":"School of Computing, Ulster University, Belfast, United Kingdom","institution_ids":["https://openalex.org/I138801177"]},{"raw_affiliation_string":"Department of Computer Science, Maitreyi College, University of Delhi, INDIA","institution_ids":["https://openalex.org/I110166357"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379058","display_name":"Haiying Wang","orcid":"https://orcid.org/0000-0001-8358-9065"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haiying Wang","raw_affiliation_strings":["Ulster University,School of Computing,Belfast,United Kingdom","School of Computing, Ulster University, Belfast, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ulster University,School of Computing,Belfast,United Kingdom","institution_ids":["https://openalex.org/I138801177"]},{"raw_affiliation_string":"School of Computing, Ulster University, Belfast, United Kingdom","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024401909","display_name":"Huiru Zheng","orcid":"https://orcid.org/0000-0001-7648-8709"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huiru Zheng","raw_affiliation_strings":["Ulster University,School of Computing,Belfast,United Kingdom","School of Computing, Ulster University, Belfast, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ulster University,School of Computing,Belfast,United Kingdom","institution_ids":["https://openalex.org/I138801177"]},{"raw_affiliation_string":"School of Computing, Ulster University, Belfast, United Kingdom","institution_ids":["https://openalex.org/I138801177"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"32","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9962999820709229,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9962999820709229,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9934999942779541,"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/T10066","display_name":"Gut microbiota and health","score":0.9886000156402588,"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/phylogenetics","display_name":"Phylogenetics","score":0.8641470074653625},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.7553529739379883},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.708126425743103},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.6505813002586365},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.5535269975662231},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.4809545576572418},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4702272117137909},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.44480520486831665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4037743806838989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39218950271606445},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32797977328300476},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.22936540842056274},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.13231778144836426}],"concepts":[{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.8641470074653625},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.7553529739379883},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.708126425743103},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.6505813002586365},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5535269975662231},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.4809545576572418},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4702272117137909},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.44480520486831665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4037743806838989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39218950271606445},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32797977328300476},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.22936540842056274},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.13231778144836426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm55620.2022.9995554","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bibm55620.2022.9995554","pdf_url":null,"source":{"id":"https://openalex.org/S4363607730","display_name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W619739145","https://openalex.org/W1444168786","https://openalex.org/W1592827165","https://openalex.org/W1811186957","https://openalex.org/W1852605861","https://openalex.org/W1989889539","https://openalex.org/W2006465310","https://openalex.org/W2034598141","https://openalex.org/W2074003662","https://openalex.org/W2083620785","https://openalex.org/W2085284704","https://openalex.org/W2101677491","https://openalex.org/W2110300022","https://openalex.org/W2122242590","https://openalex.org/W2127672471","https://openalex.org/W2133057705","https://openalex.org/W2151409320","https://openalex.org/W2155653793","https://openalex.org/W2156546195","https://openalex.org/W2166999091","https://openalex.org/W2170951896","https://openalex.org/W2242403758","https://openalex.org/W2335934832","https://openalex.org/W2384614367","https://openalex.org/W2473355215","https://openalex.org/W2496610678","https://openalex.org/W2510675082","https://openalex.org/W2567872606","https://openalex.org/W2569013924","https://openalex.org/W2611831635","https://openalex.org/W2797302139","https://openalex.org/W2897766421","https://openalex.org/W2898551429","https://openalex.org/W2912763566","https://openalex.org/W2913777178","https://openalex.org/W2941281896","https://openalex.org/W2947372214","https://openalex.org/W2950862267","https://openalex.org/W2963546206","https://openalex.org/W4294329053","https://openalex.org/W6628505203","https://openalex.org/W6688994641","https://openalex.org/W6750874965","https://openalex.org/W6836719038"],"related_works":["https://openalex.org/W2889302474","https://openalex.org/W2174809885","https://openalex.org/W2949296710","https://openalex.org/W2057191541","https://openalex.org/W2883025420","https://openalex.org/W1992658754","https://openalex.org/W2111939425","https://openalex.org/W2065083790","https://openalex.org/W2604174992","https://openalex.org/W2375383082"],"abstract_inverted_index":{"Classifying":[0],"microbial":[1,56,80,96],"genes":[2,57],"into":[3],"their":[4],"functional":[5,61],"repertoire":[6],"is":[7,18,193],"an":[8],"important":[9],"task":[10],"for":[11,45],"metagenomic":[12,189],"studies,":[13],"where":[14],"the":[15,41,52,70,76,92,111,157,161,179,196,202],"research":[16],"community":[17],"trying":[19],"to":[20,27,60,109,131,145,159,220],"develop":[21],"Machine":[22],"Learning":[23],"(ML)":[24],"based":[25,86],"methods":[26,44,175],"achieve":[28],"good":[29],"classification":[30,84,174],"performance.":[31],"Random":[32],"Forest":[33],"(RF)":[34],"has":[35,100,169],"been":[36,101,170],"proposed":[37,166,197],"as":[38,89],"one":[39,150],"of":[40,55,95,113,151,182,213],"most":[42],"favorable":[43],"such":[46],"supervised":[47],"analysis":[48],"when":[49],"applied":[50],"over":[51,215],"abundance":[53],"profiles":[54],"mapping":[58],"them":[59],"phenotypes.":[62],"To":[63],"further":[64],"explore":[65],"and":[66,129,135,142,178],"make":[67,160],"optimization":[68],"in":[69,103,116,218],"existing":[71],"RF":[72,88,177],"model":[73],"(based":[74],"on":[75,87],"biological":[77],"relationships":[78],"between":[79],"features),":[81],"a":[82,117,210],"new":[83],"method":[85,107,181,198],"guided":[90],"by":[91,124],"evolutionary":[93],"ancestry":[94],"phylogeny,":[97],"i.e.":[98],"Phylogeny-RF,":[99],"developed":[102],"this":[104],"paper.":[105],"This":[106],"facilitates":[108],"capture":[110],"effects":[112],"phylogenetic":[114],"relatedness":[115],"ML":[118,162],"classifier":[119],"itself.":[120],"Closely":[121],"related":[122],"microbes":[123,139],"phylogeny":[125],"are":[126],"highly":[127],"correlated":[128],"tend":[130,144],"have":[132],"similar":[133],"genetic":[134],"phenotypic":[136],"traits.":[137],"Such":[138],"behave":[140],"similarly;":[141],"hence":[143],"be":[146,154],"selected":[147],"together":[148],"or":[149],"these":[152],"could":[153],"dropped":[155],"from":[156],"analysis,":[158],"process":[163],"better.":[164],"The":[165],"Phylogeny-RF":[167,208],"algorithm":[168],"compared":[171],"with":[172],"state-of-the-art":[173],"including":[176],"phylogeny-aware":[180],"MetaPhyl,":[183],"using":[184],"2":[185],"real-world":[186],"16S":[187],"rRNA":[188],"data":[190],"sets.":[191],"It":[192],"observed":[194],"that":[195],"performed":[199],"better":[200],"than":[201],"other":[203,221],"phylogeny-driven":[204],"benchmarks.":[205,222],"For":[206],"example,":[207],"attained":[209],"high":[211],"AUC":[212],"0.949":[214],"soil":[216],"microbiomes":[217],"comparison":[219]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}