{"id":"https://openalex.org/W4416802371","doi":"https://doi.org/10.1186/s12859-025-06312-z","title":"TaxaPLN: a taxonomy-aware augmentation strategy for microbiome-trait classification including metadata","display_name":"TaxaPLN: a taxonomy-aware augmentation strategy for microbiome-trait classification including metadata","publication_year":2025,"publication_date":"2025-11-28","ids":{"openalex":"https://openalex.org/W4416802371","doi":"https://doi.org/10.1186/s12859-025-06312-z","pmid":"https://pubmed.ncbi.nlm.nih.gov/41315930"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-025-06312-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06312-z","pdf_url":null,"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/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s12859-025-06312-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099464042","display_name":"Alexandre Chaussard","orcid":"https://orcid.org/0009-0001-4561-3797"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210091437","display_name":"Sorbonne Paris Cit\u00e9","ror":"https://ror.org/001z21q04","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210091437"]},{"id":"https://openalex.org/I4210147464","display_name":"Laboratoire de Probabilit\u00e9s et Mod\u00e8les Al\u00e9atoires","ror":"https://ror.org/04hjc7403","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I39804081","https://openalex.org/I4210141950","https://openalex.org/I4210147464"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Alexandre Chaussard","raw_affiliation_strings":["Laboratoire de Probabilit\u00e9s, Statistique et Mod\u00e9lisation, LPSM, Sorbonne Universit\u00e9, Universit\u00e9 Paris Cit\u00e9, CNRS, F-75005, Paris, France. alexandre.chaussard@sorbonne-universite.fr","Laboratoire de Probabilit\u00e9s, Statistique et Mod\u00e9lisation, LPSM, Sorbonne Universit\u00e9, Universit\u00e9 Paris Cit\u00e9, CNRS, F-75005, Paris, France"],"raw_orcid":"https://orcid.org/0009-0001-4561-3797","affiliations":[{"raw_affiliation_string":"Laboratoire de Probabilit\u00e9s, Statistique et Mod\u00e9lisation, LPSM, Sorbonne Universit\u00e9, Universit\u00e9 Paris Cit\u00e9, CNRS, F-75005, Paris, France. alexandre.chaussard@sorbonne-universite.fr","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I204730241","https://openalex.org/I4210091437","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Laboratoire de Probabilit\u00e9s, Statistique et Mod\u00e9lisation, LPSM, Sorbonne Universit\u00e9, Universit\u00e9 Paris Cit\u00e9, CNRS, F-75005, Paris, France","institution_ids":["https://openalex.org/I204730241","https://openalex.org/I1294671590","https://openalex.org/I4210147464","https://openalex.org/I4210091437","https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013206633","display_name":"Anna Bonnet","orcid":"https://orcid.org/0000-0003-0765-1706"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210091437","display_name":"Sorbonne Paris Cit\u00e9","ror":"https://ror.org/001z21q04","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210091437"]},{"id":"https://openalex.org/I4210147464","display_name":"Laboratoire de Probabilit\u00e9s et Mod\u00e8les Al\u00e9atoires","ror":"https://ror.org/04hjc7403","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I39804081","https://openalex.org/I4210141950","https://openalex.org/I4210147464"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Anna Bonnet","raw_affiliation_strings":["Laboratoire de Probabilit\u00e9s, Statistique et Mod\u00e9lisation, LPSM, Sorbonne Universit\u00e9, Universit\u00e9 Paris Cit\u00e9, CNRS, F-75005, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire de Probabilit\u00e9s, Statistique et Mod\u00e9lisation, LPSM, Sorbonne Universit\u00e9, Universit\u00e9 Paris Cit\u00e9, CNRS, F-75005, Paris, France","institution_ids":["https://openalex.org/I204730241","https://openalex.org/I1294671590","https://openalex.org/I4210147464","https://openalex.org/I4210091437","https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049226969","display_name":"Sylvain Le Corff","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210091437","display_name":"Sorbonne Paris Cit\u00e9","ror":"https://ror.org/001z21q04","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210091437"]},{"id":"https://openalex.org/I4210147464","display_name":"Laboratoire de Probabilit\u00e9s et Mod\u00e8les Al\u00e9atoires","ror":"https://ror.org/04hjc7403","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I39804081","https://openalex.org/I4210141950","https://openalex.org/I4210147464"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sylvain Le Corff","raw_affiliation_strings":["Laboratoire de Probabilit\u00e9s, Statistique et Mod\u00e9lisation, LPSM, Sorbonne Universit\u00e9, Universit\u00e9 Paris Cit\u00e9, CNRS, F-75005, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire de Probabilit\u00e9s, Statistique et Mod\u00e9lisation, LPSM, Sorbonne Universit\u00e9, Universit\u00e9 Paris Cit\u00e9, CNRS, F-75005, Paris, France","institution_ids":["https://openalex.org/I204730241","https://openalex.org/I1294671590","https://openalex.org/I4210147464","https://openalex.org/I4210091437","https://openalex.org/I39804081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083701333","display_name":"Harry Sokol","orcid":"https://orcid.org/0000-0002-2914-1822"},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210097159","display_name":"Assistance Publique \u2013 H\u00f4pitaux de Paris","ror":"https://ror.org/00pg5jh14","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210097159"]},{"id":"https://openalex.org/I4210105451","display_name":"F\u00e9d\u00e9ration Hospitalo-Universitaire, Paris Center for Microbiome Medicine","ror":"https://ror.org/00yyw0g86","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210105451"]},{"id":"https://openalex.org/I4210134622","display_name":"Centre de Recherche Saint-Antoine","ror":"https://ror.org/03wxndv36","country_code":"FR","type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210097159","https://openalex.org/I4210129850","https://openalex.org/I4210134622"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Harry Sokol","raw_affiliation_strings":["Centre de Recherche Saint-Antoine, CRSA, AP-HP, Sorbonne Universit\u00e9, INSERM UMRS-938, F-75012, Paris, France","Gut, Liver & Microbiome Research, FHU, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre de Recherche Saint-Antoine, CRSA, AP-HP, Sorbonne Universit\u00e9, INSERM UMRS-938, F-75012, Paris, France","institution_ids":["https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210134622","https://openalex.org/I4210097159"]},{"raw_affiliation_string":"Gut, Liver & Microbiome Research, FHU, Paris, France","institution_ids":["https://openalex.org/I4210105451"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5099464042"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I39804081","https://openalex.org/I4210091437","https://openalex.org/I4210147464"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31601921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"1","first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10066","display_name":"Gut microbiota and health","score":0.6470999717712402,"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/T10066","display_name":"Gut microbiota and health","score":0.6470999717712402,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.10000000149011612,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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":0.013799999840557575,"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/metadata","display_name":"Metadata","score":0.725600004196167},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7075999975204468},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5626000165939331},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.521399974822998},{"id":"https://openalex.org/keywords/microbiome","display_name":"Microbiome","score":0.4779999852180481},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.3617999851703644},{"id":"https://openalex.org/keywords/r-package","display_name":"R package","score":0.3610000014305115},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.34360000491142273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7985000014305115},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.725600004196167},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7075999975204468},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5626000165939331},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.521399974822998},{"id":"https://openalex.org/C143121216","wikidata":"https://www.wikidata.org/wiki/Q1330402","display_name":"Microbiome","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39320001006126404},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3720000088214874},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.3617999851703644},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33820000290870667},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3100999891757965},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3070000112056732},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.30239999294281006},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27810001373291016},{"id":"https://openalex.org/C3019978661","wikidata":"https://www.wikidata.org/wiki/Q739734","display_name":"Gut microbiome","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.2533999979496002},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.250900000333786}],"mesh":[{"descriptor_ui":"D000069196","descriptor_name":"Gastrointestinal Microbiome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069196","descriptor_name":"Gastrointestinal Microbiome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069196","descriptor_name":"Gastrointestinal Microbiome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069196","descriptor_name":"Gastrointestinal Microbiome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-025-06312-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06312-z","pdf_url":null,"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/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41315930","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41315930","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:534cdb4510cf4615862fade40c0ab647","is_oa":true,"landing_page_url":"https://doaj.org/article/534cdb4510cf4615862fade40c0ab647","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 27, Iss 1, Pp 1-19 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12763835","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12763835/","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-025-06312-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06312-z","pdf_url":null,"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/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1976526581","https://openalex.org/W2001561488","https://openalex.org/W2016073955","https://openalex.org/W2130725058","https://openalex.org/W2148143831","https://openalex.org/W2178425989","https://openalex.org/W2760103357","https://openalex.org/W2769542288","https://openalex.org/W2797413896","https://openalex.org/W2803457956","https://openalex.org/W2904250115","https://openalex.org/W2927453907","https://openalex.org/W2947189704","https://openalex.org/W2949004447","https://openalex.org/W2952200190","https://openalex.org/W2953710982","https://openalex.org/W3014950179","https://openalex.org/W3029223092","https://openalex.org/W3128912982","https://openalex.org/W3132461044","https://openalex.org/W3144187446","https://openalex.org/W3157152805","https://openalex.org/W4309028162","https://openalex.org/W4389334038","https://openalex.org/W4394759342","https://openalex.org/W4403571813","https://openalex.org/W4403680367","https://openalex.org/W4406292104","https://openalex.org/W4407163726","https://openalex.org/W4409268023","https://openalex.org/W4411529547"],"related_works":[],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1],"gut":[2],"microbiome":[3,53,80,107,127,160,170,199],"plays":[4],"a":[5,13,70,86,100,112,155,165],"crucial":[6],"role":[7],"in":[8],"human":[9],"health,":[10],"making":[11],"it":[12,186],"cornerstone":[14],"of":[15,52,59,152],"modern":[16],"biomedical":[17],"research.":[18],"To":[19,194],"study":[20],"its":[21],"structure":[22,182],"and":[23,39,55,99,135,176,183,197],"dynamics,":[24],"machine":[25],"learning":[26],"models":[27],"are":[28],"increasingly":[29],"used":[30],"to":[31,73,103],"identify":[32],"key":[33],"microbial":[34],"patterns":[35],"associated":[36],"with":[37,216],"disease":[38],"environmental":[40],"factors,":[41],"but":[42],"their":[43,174],"performance":[44],"is":[45,205],"often":[46],"limited":[47],"by":[48,77],"the":[49,56,97,149],"intrinsic":[50],"complexity":[51],"data":[54,65,87],"small":[57],"size":[58],"available":[60,212],"cohorts.":[61],"In":[62],"this":[63],"context,":[64],"augmentation":[66,88],"has":[67],"emerged":[68],"as":[69,207],"promising":[71],"strategy":[72],"overcome":[74],"these":[75],"challenges":[76],"generating":[78],"artificial":[79],"profiles.":[81],"RESULTS:":[82],"We":[83],"introduce":[84],"TaxaPLN,":[85],"method":[89],"based":[90,115],"on":[91,116,124,145,213],"PLN-Tree":[92],"generative":[93],"models,":[94],"which":[95],"leverages":[96],"taxonomy":[98],"data-driven":[101],"sampler":[102],"generate":[104],"realistic":[105],"synthetic":[106],"compositions.":[108],"Additionally,":[109],"we":[110],"propose":[111],"conditional":[113,150],"extension":[114],"feature-wise":[117],"linear":[118],"modulation,":[119],"enabling":[120],"covariate-aware":[121],"generation.":[122],"Experiments":[123],"diverse":[125,191],"curated":[126],"datasets":[128,171],"show":[129],"that":[130],"TaxaPLN":[131,153,163,204],"preserves":[132],"ecological":[133,175],"properties":[134],"generally":[136],"improves":[137],"or":[138],"maintains":[139],"predictive":[140,188],"performances,":[141],"outperforming":[142],"state-of-the-art":[143],"baselines":[144],"most":[146],"tasks.":[147],"Furthermore,":[148],"variant":[151],"establishes":[154],"new":[156],"benchmark":[157],"for":[158,168],"metadata-aware":[159],"augmentation.":[161],"CONCLUSION:":[162],"provides":[164],"model-based":[166],"framework":[167],"augmenting":[169],"while":[172],"preserving":[173],"clinical":[177],"relevance.":[178],"By":[179],"integrating":[180],"taxonomic":[181],"host":[184],"metadata,":[185],"enhances":[187],"modeling":[189],"across":[190],"real-world":[192],"settings.":[193],"facilitate":[195],"reproducible":[196],"scalable":[198],"analysis":[200],"using":[201],"our":[202],"method,":[203],"released":[206],"an":[208],"open-source":[209],"Python":[210],"package":[211],"PyPI":[214],"(plntree),":[215],"MIT-licensed":[217],"source":[218],"code":[219],"hosted":[220],"at":[221],"https://github.com/AlexandreChaussard/PLNTree-package":[222],".":[223]},"counts_by_year":[],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-11-28T00:00:00"}
