{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:13:31Z","timestamp":1760660011006,"version":"build-2065373602"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["215359\/Z\/19\/Z"],"award-info":[{"award-number":["215359\/Z\/19\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Theoretical Biology"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1016\/j.jtbi.2025.112249","type":"journal-article","created":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T09:26:32Z","timestamp":1757755592000},"page":"112249","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Modelling phylogeny in 16S rRNA gene sequencing datasets using string-based kernels"],"prefix":"10.1016","volume":"616","author":[{"given":"Jonathan","family":"Ish-Horowicz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8652-358X","authenticated-orcid":false,"given":"Sarah","family":"Filippi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.jtbi.2025.112249_bib0001","doi-asserted-by":"crossref","DOI":"10.1093\/bioadv\/vbaf045","article-title":"Quantifying uncertainty in microbiome-based prediction using gaussian processes with microbial community dissimilarities","volume":"5","author":"Adachi","year":"2025","journal-title":"Bioinfor. Adv."},{"key":"10.1016\/j.jtbi.2025.112249_bib0002","doi-asserted-by":"crossref","first-page":"350","DOI":"10.3389\/fgene.2019.00350","article-title":"An adaptive multivariate two-sample test with application to microbiome differential abundance analysis","volume":"10","author":"Banerjee","year":"2019","journal-title":"Front. Genet."},{"key":"10.1016\/j.jtbi.2025.112249_bib0003","series-title":"Symposium on Advances in Approximate Bayesian Inference","first-page":"11","article-title":"Consistency of ELBO maximization for model selection","author":"Ch\u00e9rief-Abdellatif","year":"2019"},{"key":"10.1016\/j.jtbi.2025.112249_bib0004","article-title":"Machine learning for exploring microbial inter-kingdom associations in cystic fibrosis and bronchiectasis","author":"Cuthbertson","year":"2022","journal-title":"bioRxiv"},{"issue":"1","key":"10.1016\/j.jtbi.2025.112249_bib0005","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40168-020-00810-3","article-title":"Lung function and microbiota diversity in cystic fibrosis","volume":"8","author":"Cuthbertson","year":"2020","journal-title":"Microbiome"},{"issue":"4","key":"10.1016\/j.jtbi.2025.112249_bib0006","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/gm39","article-title":"A kernel-based integration of genome-wide data for clinical decision support","volume":"1","author":"Daemen","year":"2009","journal-title":"Genome Med."},{"issue":"1","key":"10.1016\/j.jtbi.2025.112249_bib0007","doi-asserted-by":"crossref","first-page":"3030","DOI":"10.1038\/s41598-021-82726-y","article-title":"Comparison between 16s rRNA and shotgun sequencing data for the taxonomic characterization of the gut microbiota","volume":"11","author":"Durazzi","year":"2021","journal-title":"Sci. Rep."},{"key":"10.1016\/j.jtbi.2025.112249_bib0008","series-title":"Biocomputing 2012","first-page":"213","article-title":"Comparisons of distance methods for combining covariates and abundances in microbiome studies","author":"Fukuyama","year":"2012"},{"issue":"2","key":"10.1016\/j.jtbi.2025.112249_bib0009","doi-asserted-by":"crossref","first-page":"1043","DOI":"10.1214\/18-AOAS1227","article-title":"Adaptive gPCA: a method for structured dimensionality reduction","volume":"13","author":"Fukuyama","year":"2019","journal-title":"Ann. Appl. Stat."},{"issue":"6","key":"10.1016\/j.jtbi.2025.112249_bib0010","doi-asserted-by":"crossref","first-page":"e00536","DOI":"10.1128\/mSphereDirect.00536-17","article-title":"A dirichlet-multinomial bayes classifier for disease diagnosis with microbial compositions","volume":"2","author":"Gao","year":"2017","journal-title":"Msphere"},{"key":"10.1016\/j.jtbi.2025.112249_bib0011","unstructured":"[Garreau et al., 2017] Garreau, D., Jitkrittum, W., Kanagawa, M., 2017. Large sample analysis of the median heuristic. arXiv preprint arXiv: 1707.07269."},{"key":"10.1016\/j.jtbi.2025.112249_bib0012","doi-asserted-by":"crossref","first-page":"1092","DOI":"10.1016\/j.csbj.2021.01.028","article-title":"Machine learning applications in microbial ecology, human microbiome studies, and environmental monitoring","volume":"19","author":"Ghannam","year":"2021","journal-title":"Comput. Struct. Biotechnol. J."},{"issue":"1","key":"10.1016\/j.jtbi.2025.112249_bib0013","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"issue":"16","key":"10.1016\/j.jtbi.2025.112249_bib0014","doi-asserted-by":"crossref","first-page":"2522","DOI":"10.1091\/mbc.e13-04-0221","article-title":"Integration of biological data by kernels on graph nodes allows prediction of new genes involved in mitotic chromosome condensation","volume":"25","author":"H\u00e9rich\u00e9","year":"2014","journal-title":"Mol. Biol. Cell"},{"issue":"1","key":"10.1016\/j.jtbi.2025.112249_bib0015","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-021-90067-z","article-title":"The effect of taxonomic classification by full-length 16s rRNA sequencing with a synthetic long-read technology","volume":"11","author":"Jeong","year":"2021","journal-title":"Sci. Rep."},{"year":"2022","series-title":"MiRKAT-MC: a distance-based microbiome kernel association test with multi-categorical outcomes","author":"Jiang","key":"10.1016\/j.jtbi.2025.112249_bib0016"},{"issue":"1","key":"10.1016\/j.jtbi.2025.112249_bib0017","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-019-13036-1","article-title":"Evaluation of 16s rRNA gene sequencing for species and strain-level microbiome analysis","volume":"10","author":"Johnson","year":"2019","journal-title":"Nat. Commun."},{"issue":"1","key":"10.1016\/j.jtbi.2025.112249_bib0018","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40168-017-0262-x","article-title":"A powerful microbiome-based association test and a microbial taxa discovery framework for comprehensive association mapping","volume":"5","author":"Koh","year":"2017","journal-title":"Microbiome"},{"key":"10.1016\/j.jtbi.2025.112249_bib0019","doi-asserted-by":"crossref","first-page":"458","DOI":"10.3389\/fgene.2019.00458","article-title":"A distance-based kernel association test based on the generalized linear mixed model for correlated microbiome studies","volume":"10","author":"Koh","year":"2019","journal-title":"Front. Genet."},{"issue":"5","key":"10.1016\/j.jtbi.2025.112249_bib0020","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1004226","article-title":"Sparse and compositionally robust inference of microbial ecological networks","volume":"11","author":"Kurtz","year":"2015","journal-title":"PLoS Comput. Biol."},{"key":"10.1016\/j.jtbi.2025.112249_bib0021","series-title":"Biocomputing 2002","first-page":"564","article-title":"The spectrum kernel: a string kernel for SVM protein classification","author":"Leslie","year":"2001"},{"key":"10.1016\/j.jtbi.2025.112249_bib0022","first-page":"1441","article-title":"Mismatch string kernels for SVM protein classification","volume":"15","author":"Leslie","year":"2003","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jtbi.2025.112249_bib0023","series-title":"Learning Theory and Kernel Machines","first-page":"114","article-title":"Fast kernels for inexact string matching","author":"Leslie","year":"2003"},{"issue":"1","key":"10.1016\/j.jtbi.2025.112249_bib0024","doi-asserted-by":"crossref","DOI":"10.1080\/19490976.2025.2489074","article-title":"Best practices for developing microbiome-based disease diagnostic classifiers through machine learning","volume":"17","author":"Li","year":"2025","journal-title":"Gut Microb."},{"issue":"Feb","key":"10.1016\/j.jtbi.2025.112249_bib0025","first-page":"419","article-title":"Text classification using string kernels","volume":"2","author":"Lodhi","year":"2002","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"10.1016\/j.jtbi.2025.112249_bib0026","doi-asserted-by":"crossref","first-page":"3974","DOI":"10.1038\/s41598-023-30764-z","article-title":"Determining the most accurate 16s rRNA hypervariable region for taxonomic identification from respiratory samples","volume":"13","author":"L\u00f3pez-Aladid","year":"2023","journal-title":"Sci. Rep."},{"issue":"12","key":"10.1016\/j.jtbi.2025.112249_bib0027","doi-asserted-by":"crossref","first-page":"8228","DOI":"10.1128\/AEM.71.12.8228-8235.2005","article-title":"Unifrac: a new phylogenetic method for comparing microbial communities","volume":"71","author":"Lozupone","year":"2005","journal-title":"Appl. Environ. Microbiol."},{"issue":"5","key":"10.1016\/j.jtbi.2025.112249_bib0028","doi-asserted-by":"crossref","first-page":"1576","DOI":"10.1128\/AEM.01996-06","article-title":"Quantitative and qualitative \u03b2 diversity measures lead to different insights into factors that structure microbial communities","volume":"73","author":"Lozupone","year":"2007","journal-title":"Appl. Environ. Microbiol."},{"issue":"9","key":"10.1016\/j.jtbi.2025.112249_bib0029","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1008913","article-title":"A statistical model for describing and simulating microbial community profiles","volume":"17","author":"Ma","year":"2021","journal-title":"PLoS Comput. Biol."},{"year":"1979","series-title":"Multivariate Analysis","author":"Mardia","key":"10.1016\/j.jtbi.2025.112249_bib0030"},{"issue":"6","key":"10.1016\/j.jtbi.2025.112249_bib0031","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.1093\/bioinformatics\/btx682","article-title":"Unsupervised multiple kernel learning for heterogeneous data integration","volume":"34","author":"Mariette","year":"2018","journal-title":"Bioinformatics"},{"issue":"1\/2","key":"10.1016\/j.jtbi.2025.112249_bib0032","doi-asserted-by":"crossref","first-page":"65","DOI":"10.2307\/2333468","article-title":"On the compound multinomial distribution, the multivariate \u03b2-distribution, and correlations among proportions","volume":"49","author":"Mosimann","year":"1962","journal-title":"Biometrika"},{"issue":"1","key":"10.1016\/j.jtbi.2025.112249_bib0033","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1186\/s12866-021-02282-3","article-title":"Associations between the gut microbiome and metabolome in early life","volume":"21","author":"Nguyen","year":"2021","journal-title":"BMC Microbiol."},{"issue":"3","key":"10.1016\/j.jtbi.2025.112249_bib0034","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1162\/neco.2008.08-07-592","article-title":"The variational gaussian approximation revisited","volume":"21","author":"Opper","year":"2009","journal-title":"Neural Comput."},{"issue":"15","key":"10.1016\/j.jtbi.2025.112249_bib0035","doi-asserted-by":"crossref","first-page":"2574","DOI":"10.1093\/bioinformatics\/btv176","article-title":"KeBABS: an r package for kernel-based analysis of biological sequences","volume":"31","author":"Palme","year":"2015","journal-title":"Bioinformatics"},{"issue":"9","key":"10.1016\/j.jtbi.2025.112249_bib0036","first-page":"1","article-title":"MetaSPARSim: a 16s rRNA gene sequencing count data simulator","volume":"20","author":"Patuzzi","year":"2019","journal-title":"BMC Bioinfor."},{"issue":"1","key":"10.1016\/j.jtbi.2025.112249_bib0037","doi-asserted-by":"crossref","DOI":"10.2202\/1544-6115.1585","article-title":"Permutation p-values should never be zero: calculating exact p-values when permutations are randomly drawn","volume":"9","author":"Phipson","year":"2010","journal-title":"Stat. Appl. Genet. Mol. Biol."},{"issue":"3","key":"10.1016\/j.jtbi.2025.112249_bib0038","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0009490","article-title":"Fasttree 2\u2013approximately maximum-likelihood trees for large alignments","volume":"5","author":"Price","year":"2010","journal-title":"PLoS ONE"},{"issue":"1","key":"10.1016\/j.jtbi.2025.112249_bib0039","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1214\/17-AOAS1102","article-title":"Kernel-penalized regression for analysis of microbiome data","volume":"12","author":"Randolph","year":"2018","journal-title":"Ann. Appl. Stat."},{"issue":"supplement_1","key":"10.1016\/j.jtbi.2025.112249_bib0040","doi-asserted-by":"crossref","first-page":"4680","DOI":"10.1073\/pnas.1002611107","article-title":"Vaginal microbiome of reproductive-age women","volume":"108","author":"Ravel","year":"2011","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"2","key":"10.1016\/j.jtbi.2025.112249_bib0041","doi-asserted-by":"crossref","DOI":"10.1093\/gigascience\/giab005","article-title":"Mb-gan: microbiome simulation via generative adversarial network","volume":"10","author":"Rong","year":"2021","journal-title":"Gigascience"},{"year":"2004","series-title":"Kernel Methods for Pattern Analysis","author":"Shawe-Taylor","key":"10.1016\/j.jtbi.2025.112249_bib0042"},{"issue":"3","key":"10.1016\/j.jtbi.2025.112249_bib0043","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1128\/mBio.00434-20","article-title":"A framework for effective application of machine learning to microbiome-based classification problems","volume":"11","author":"Top\u00e7uo\u011flu","year":"2020","journal-title":"MBio"},{"issue":"7164","key":"10.1016\/j.jtbi.2025.112249_bib0044","doi-asserted-by":"crossref","first-page":"804","DOI":"10.1038\/nature06244","article-title":"The human microbiome project","volume":"449","author":"Turnbaugh","year":"2007","journal-title":"Nature"},{"issue":"3","key":"10.1016\/j.jtbi.2025.112249_bib0045","first-page":"4","article-title":"Gaussian processes for machine learning","volume":"2","author":"Williams","year":"2006","journal-title":"MIT Press"},{"issue":"1","key":"10.1016\/j.jtbi.2025.112249_bib0046","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13073-016-0302-3","article-title":"An adaptive association test for microbiome data","volume":"8","author":"Wu","year":"2016","journal-title":"Genome Med."},{"key":"10.1016\/j.jtbi.2025.112249_bib0047","doi-asserted-by":"crossref","first-page":"1391","DOI":"10.3389\/fmicb.2018.01391","article-title":"Predictive modeling of microbiome data using a phylogeny-regularized generalized linear mixed model","volume":"9","author":"Xiao","year":"2018","journal-title":"Front. Microbiol."},{"issue":"8","key":"10.1016\/j.jtbi.2025.112249_bib0048","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1002\/gepi.22160","article-title":"A small-sample kernel association test for correlated data with application to microbiome association studies","volume":"42","author":"Zhan","year":"2018","journal-title":"Genet. Epidemiol."},{"issue":"5","key":"10.1016\/j.jtbi.2025.112249_bib0049","doi-asserted-by":"crossref","first-page":"797","DOI":"10.1016\/j.ajhg.2015.04.003","article-title":"Testing in microbiome-profiling studies with miRKAT, the microbiome regression-based kernel association test","volume":"96","author":"Zhao","year":"2015","journal-title":"Am. J. Human Genet."}],"container-title":["Journal of Theoretical Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0022519325002152?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0022519325002152?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T08:20:12Z","timestamp":1760602812000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0022519325002152"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":49,"alternative-id":["S0022519325002152"],"URL":"https:\/\/doi.org\/10.1016\/j.jtbi.2025.112249","relation":{},"ISSN":["0022-5193"],"issn-type":[{"type":"print","value":"0022-5193"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Modelling phylogeny in 16S rRNA gene sequencing datasets using string-based kernels","name":"articletitle","label":"Article Title"},{"value":"Journal of Theoretical Biology","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jtbi.2025.112249","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"112249"}}