{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T16:40:34Z","timestamp":1784306434674,"version":"3.55.0"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"17","license":[{"start":{"date-parts":[[2020,5,25]],"date-time":"2020-05-25T00:00:00Z","timestamp":1590364800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2017-06672"],"award-info":[{"award-number":["RGPIN-2017-06672"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007658","name":"Crohn\u2019s and Colitis Canada","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007658","id-type":"DOI","asserted-by":"crossref"}]},{"name":"CCC-GEMIII"},{"DOI":"10.13039\/100007028","name":"Helmsley Charitable Trust","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007028","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"NSERC","doi-asserted-by":"publisher","award":["RGPIN-2017-06672"],"award-info":[{"award-number":["RGPIN-2017-06672"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Research supports the potential use of microbiome as a predictor of some diseases. Motivated by the findings that microbiome data is complex in nature, and there is an inherent correlation due to hierarchical taxonomy of microbial Operational Taxonomic Units (OTUs), we propose a novel machine learning method incorporating a stratified approach to group OTUs into phylum clusters. Convolutional Neural Networks (CNNs) were used to train within each of the clusters individually. Further, through an ensemble learning approach, features obtained from each cluster were then concatenated to improve prediction accuracy. Our two-step approach comprising stratification prior to combining multiple CNNs, aided in capturing the relationships between OTUs sharing a phylum efficiently, as compared to using a single CNN ignoring OTU correlations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We used simulated datasets containing 168 OTUs in 200 cases and 200 controls for model testing. Thirty-two OTUs, potentially associated with risk of disease were randomly selected and interactions between three OTUs were used to introduce non-linearity. We also implemented this novel method in two human microbiome studies: (i) Cirrhosis with 118 cases, 114 controls; (ii) type 2 diabetes (T2D) with 170 cases, 174 controls; to demonstrate the model\u2019s effectiveness. Extensive experimentation and comparison against conventional machine learning techniques yielded encouraging results. We obtained mean AUC values of 0.88, 0.92, 0.75, showing a consistent increment (5%, 3%, 7%) in simulations, Cirrhosis and T2D data, respectively, against the next best performing method, Random Forest.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and implementation<\/jats:title><jats:p>https:\/\/github.com\/divya031090\/TaxoNN_OTU.<\/jats:p><\/jats:sec><jats:sec><jats:title>Supplementary information<\/jats:title><jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaa542","type":"journal-article","created":{"date-parts":[[2020,5,20]],"date-time":"2020-05-20T03:34:14Z","timestamp":1589945654000},"page":"4544-4550","source":"Crossref","is-referenced-by-count":76,"title":["TaxoNN: ensemble of neural networks on stratified microbiome data for disease prediction"],"prefix":"10.1093","volume":"36","author":[{"given":"Divya","family":"Sharma","sequence":"first","affiliation":[{"name":"Dalla Lana School of Public Health, University of Toronto, Toronto, ON, Canada M5T 3M7 Division of Biostatistics,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew D","family":"Paterson","sequence":"additional","affiliation":[{"name":"Dalla Lana School of Public Health, University of Toronto, Toronto, ON, Canada M5T 3M7 Division of Biostatistics,"},{"name":"Genetics and Genome Biology Program, The Hospital for Sick Children, Toronto, ON, Canada, M5G 1X8"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xu","sequence":"additional","affiliation":[{"name":"Dalla Lana School of Public Health, University of Toronto, Toronto, ON, Canada M5T 3M7 Division of Biostatistics,"},{"name":"Department of Biostatistics, Princess Margaret Cancer Center, University Health Network, Toronto, ON, Canada, M5G 2C1"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2020,5,25]]},"reference":[{"key":"2023062213545673900_btaa542-B1","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1016\/j.chom.2017.04.010","article-title":"Gut microbiome function predicts response to anti-integrin biologic therapy in inflammatory bowel diseases","volume":"21","author":"Ananthakrishnan","year":"2017","journal-title":"Cell Host Microbe"},{"key":"2023062213545673900_btaa542-B2","first-page":"2560","author":"Bai","year":"2014"},{"key":"2023062213545673900_btaa542-B3","doi-asserted-by":"crossref","first-page":"1935","DOI":"10.1098\/rstb.2005.1725","article-title":"Defining operational taxonomic units using DNA barcode data","volume":"360","author":"Blaxter","year":"2005","journal-title":"Philos. Trans. R. Soc. B Biol. Sci"},{"key":"2023062213545673900_btaa542-B4","doi-asserted-by":"crossref","first-page":"934","DOI":"10.21105\/joss.00934","article-title":"q2-sample-classifier: machine-learning tools for microbiome classification and regression","volume":"3","author":"Bokulich","year":"2018","journal-title":"J. Open Res. Softw"},{"key":"2023062213545673900_btaa542-B5","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1016\/j.chom.2014.02.005","article-title":"The treatment-naive microbiome in new-onset Crohn\u2019s disease","volume":"15","author":"Gevers","year":"2014","journal-title":"Cell Host Microbe"},{"key":"2023062213545673900_btaa542-B6","first-page":"315","author":"Glorot","year":"2011"},{"key":"2023062213545673900_btaa542-B7","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"2023062213545673900_btaa542-B8","first-page":"385","article-title":"Idiot\u2019s Bayes\u2014not so stupid after all?","volume":"69","author":"Hand","year":"2001","journal-title":"Int. Stat. Rev"},{"key":"2023062213545673900_btaa542-B9","doi-asserted-by":"crossref","first-page":"993","DOI":"10.1109\/34.58871","article-title":"Neural network ensembles","volume":"12","author":"Hansen","year":"1990","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"2023062213545673900_btaa542-B10","doi-asserted-by":"crossref","first-page":"159","DOI":"10.2337\/dc14-0769","article-title":"Insights into the role of the microbiome in obesity and type 2 diabetes","volume":"38","author":"Hartstra","year":"2015","journal-title":"Diabetes Care"},{"key":"2023062213545673900_btaa542-B11","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1080\/00401706.1970.10488634","article-title":"Ridge regression: biased estimation for nonorthogonal problems","volume":"12","author":"Hoerl","year":"1970","journal-title":"Technometrics"},{"key":"2023062213545673900_btaa542-B12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-018-05184-7","article-title":"Gut microbiota associations with common diseases and prescription medications in a population-based cohort","volume":"9","author":"Jackson","year":"2018","journal-title":"Nat. Commun"},{"key":"2023062213545673900_btaa542-B13","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1038\/nature12198","article-title":"Gut metagenome in European women with normal, impaired and diabetic glucose control","volume":"498","author":"Karlsson","year":"2013","journal-title":"Nature"},{"key":"2023062213545673900_btaa542-B14","first-page":"1097","author":"Krizhevsky","year":"2012"},{"key":"2023062213545673900_btaa542-B15","first-page":"18","article-title":"Classification and regression by RandomForest","volume":"2","author":"Liaw","year":"2002","journal-title":"R News"},{"key":"2023062213545673900_btaa542-B16","doi-asserted-by":"crossref","first-page":"3242","DOI":"10.1093\/bioinformatics\/btr547","article-title":"Sparse distance-based learning for simultaneous multiclass classification and feature selection of metagenomic data","volume":"27","author":"Liu","year":"2011","journal-title":"Bioinformatics"},{"key":"2023062213545673900_btaa542-B17","doi-asserted-by":"crossref","DOI":"10.1186\/s12859-019-2833-2","article-title":"MetaNN: accurate classification of host phenotypes from metagenomic data using neural networks","volume":"20","author":"Lo","year":"2019","journal-title":"BMC Bioinformatics"},{"key":"2023062213545673900_btaa542-B18","article-title":"Ensemble of convolutional neural networks for bioimage classification","author":"Nanni","year":"2018","journal-title":"Appl. Comput. Inf"},{"key":"2023062213545673900_btaa542-B19","first-page":"1","author":"Park","year":"2016"},{"key":"2023062213545673900_btaa542-B20","doi-asserted-by":"crossref","first-page":"e1004977","DOI":"10.1371\/journal.pcbi.1004977","article-title":"Machine learning meta-analysis of large metagenomic datasets: tools and biological insights","volume":"12","author":"Pasolli","year":"2016","journal-title":"PLoS Comput. Biol"},{"key":"2023062213545673900_btaa542-B21","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1038\/nature11450","article-title":"A metagenome-wide association study of gut microbiota in type 2 diabetes","volume":"490","author":"Qin","year":"2012","journal-title":"Nature"},{"key":"2023062213545673900_btaa542-B22","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1038\/nature13568","article-title":"Alterations of the human gut microbiome in liver cirrhosis","volume":"513","author":"Qin","year":"2014","journal-title":"Nature"},{"key":"2023062213545673900_btaa542-B23","first-page":"41","author":"Rish","year":"2001"},{"key":"2023062213545673900_btaa542-B24","doi-asserted-by":"crossref","first-page":"e01976","DOI":"10.1002\/ecs2.1976","article-title":"Statistically reinforced machine learning for nonlinear patterns and variable interactions","volume":"8","author":"Ryo","year":"2017","journal-title":"Ecosphere"},{"key":"2023062213545673900_btaa542-B25","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.1053\/j.gastro.2014.01.020","article-title":"Interactions between the intestinal microbiome and liver diseases","volume":"146","author":"Schnabl","year":"2014","journal-title":"Gastroenterology"},{"key":"2023062213545673900_btaa542-B26","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1038\/nrmicro.2017.58","article-title":"The resilience of the intestinal microbiota influences health and disease","volume":"15","author":"Sommer","year":"2017","journal-title":"Nat. Rev. Microbiol"},{"key":"2023062213545673900_btaa542-B27","article-title":"Computer aided lung cancer diagnosis with deep learning algorithms","author":"Sun","year":"2016","journal-title":"Med. Imaging 2016 Comput. Aided Diagn"},{"key":"2023062213545673900_btaa542-B28","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1023\/A:1018628609742","article-title":"Least squares support vector machine classifiers","volume":"9","author":"Suykens","year":"1999","journal-title":"Neural Process. Lett"},{"key":"2023062213545673900_btaa542-B29","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J. R. Stat. Soc. Ser. B (Methodological)"},{"key":"2023062213545673900_btaa542-B30","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1186\/s12918-015-0199-2","article-title":"Inferring microbial interaction network from microbiome data using RMN algorithm","volume":"9","author":"Tsai","year":"2015","journal-title":"BMC Syst. Biol"},{"key":"2023062213545673900_btaa542-B31","author":"Tsang","year":"2017"},{"key":"2023062213545673900_btaa542-B32","doi-asserted-by":"crossref","first-page":"1413","DOI":"10.1038\/ng.3693","article-title":"Association of host genome with intestinal microbial composition in a large healthy cohort","volume":"48","author":"Turpin","year":"2016","journal-title":"Nat. Genet"},{"key":"2023062213545673900_btaa542-B33","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"},{"key":"2023062213545673900_btaa542-B34","first-page":"5525","author":"Yang","year":"2016"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa542\/33706234\/btaa542.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/17\/4544\/50677219\/btaa542.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/17\/4544\/50677219\/btaa542.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T01:28:50Z","timestamp":1722907730000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/17\/4544\/5843784"}},"subtitle":[],"editor":[{"given":"Pier","family":"Luigi Martelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2020,5,25]]},"references-count":34,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2020,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa542","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,9,1]]},"published":{"date-parts":[[2020,5,25]]}}}