{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T17:05:30Z","timestamp":1767287130465,"version":"3.48.0"},"reference-count":58,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003977","name":"Israel Science Foundation","doi-asserted-by":"publisher","award":["2435\/19"],"award-info":[{"award-number":["2435\/19"]}],"id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Edmond J. Safra Center for Bioinformatics at Tel-Aviv University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>The gut microbiome plays an important role in human health and disease, prompting large-scale studies that generate extensive datasets. A critical preprocessing step in analysing such datasets is anomaly detection, which aims to identify erroneous samples and prevent misleading statistical outcomes. Microbiome data, however, pose unique challenges such as compositionality, sparsity, interdependencies, and high dimensionality, limiting the effectiveness of conventional methods and highlighting the need for specifically-tailored approaches for anomaly detection in microbiome data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Implementation<\/jats:title>\n                    <jats:p>To address this challenge, we introduce KADAIF, a microbiome-specific anomaly detection method that generalizes the common Isolation Forest (IF) approach. As in IF, KADAIF builds an ensemble of trees, each recursively partitioning the data along randomly selected features, and measures the average depth at which samples are isolated, assuming that anomalous samples will be isolated closer to the root. Unlike IF, however, KADAIF partitions samples based on subsets of features (coupled with dimensionality reduction), addressing microbiome-specific properties such as sparsity and species interactions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We evaluate KADAIF by simulating common scenarios that introduce anomalous behavior, demonstrating that KADAIF outperforms alternative methods across various settings and datasets. Furthermore, we show that KADAIF outperforms IF in detecting anomalies also in other types of high-dimensional sparse biological data. Finally, we show KADAIF\u2019s application for identifying disease onset in longitudinal microbiome data and for partitioning cases versus controls based on the Anna Karenina principle. Combined, our work highlights KADAIF's potential to enhance microbiome data processing and downstream analyses, with beneficial implications for precision medicine studies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>An implementation of KADAIF, as well as all the code used for the analysis, is available on GitHub (https:\/\/github.com\/borenstein-lab\/KADAIF).<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf520","type":"journal-article","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T11:48:28Z","timestamp":1758196108000},"source":"Crossref","is-referenced-by-count":0,"title":["KADAIF: an anomaly detection method for complex microbiome data"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8422-303X","authenticated-orcid":false,"given":"Omri","family":"Peleg","sequence":"first","affiliation":[{"name":"Blavatnik School of Computer Science and AI, Tel Aviv University , Tel Aviv, 6997801,","place":["Israel"]}]},{"given":"Maya","family":"Raytan","sequence":"additional","affiliation":[{"name":"Blavatnik School of Computer Science and AI, Tel Aviv University , Tel Aviv, 6997801,","place":["Israel"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3002-0945","authenticated-orcid":false,"given":"Elhanan","family":"Borenstein","sequence":"additional","affiliation":[{"name":"Blavatnik School of Computer Science and AI, Tel Aviv University , Tel Aviv, 6997801,","place":["Israel"]},{"name":"Gray Faculty of Medical & Health Sciences, Tel Aviv University , Tel Aviv, 6997801,","place":["Israel"]},{"name":"Santa Fe Institute , Santa Fe, NM, 87501,","place":["United States"]}]}],"member":"286","published-online":{"date-parts":[[2025,9,19]]},"reference":[{"key":"2026010112012012300_btaf520-B1","doi-asserted-by":"publisher","first-page":"322","DOI":"10.3390\/APPLMICROBIOL3020023","article-title":"Univariate and multivariate statistical analysis of microbiome data: an overview","volume":"3","author":"Aldirawi","year":"2023","journal-title":"Appl Microbiol"},{"key":"2026010112012012300_btaf520-B2","doi-asserted-by":"publisher","DOI":"10.1093\/BIOINFORMATICS\/BTAC781","article-title":"Microbiome toolbox: methodological approaches to derive and visualize microbiome trajectories","volume":"39","author":"Banjac","year":"2023","journal-title":"Bioinformatics"},{"key":"2026010112012012300_btaf520-B3","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.3390\/JCM8091291","article-title":"Identification of a shared microbiomic and metabolomic profile in systemic autoimmune diseases","volume":"8","author":"Bellocchi","year":"2019","journal-title":"J Clin Med"},{"key":"2026010112012012300_btaf520-B4","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/3-540-49257-7_15","author":"Beyer","year":"1999"},{"key":"2026010112012012300_btaf520-B5","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1038\/s41587-019-0209-9","article-title":"Reproducible, interactive, scalable and extensible microbiome data science using QIIME 2","volume":"37","author":"Bolyen","year":"2019","journal-title":"Nat Biotechnol"},{"key":"2026010112012012300_btaf520-B6","doi-asserted-by":"publisher","first-page":"R50","DOI":"10.1186\/GB-2011-12-5-R50","article-title":"Moving pictures of the human microbiome","volume":"12","author":"Caporaso","year":"2011","journal-title":"Genome Biol"},{"key":"2026010112012012300_btaf520-B7","doi-asserted-by":"publisher","first-page":"10219","DOI":"10.1109\/ACCESS.2022.3144425","article-title":"An in-depth study and improvement of Isolation Forest","volume":"10","author":"Chabchoub","year":"2022","journal-title":"IEEE Access"},{"key":"2026010112012012300_btaf520-B8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1541880","article-title":"Anomaly detection: a survey","volume":"41","author":"Chandola","year":"2009","journal-title":"ACM Comput Surv"},{"key":"2026010112012012300_btaf520-B9","doi-asserted-by":"publisher","first-page":"e90731","DOI":"10.1371\/journal.pone.0090731","article-title":"Seasonal variation in human gut microbiome composition","volume":"9","author":"Davenport","year":"2014","journal-title":"PLoS One"},{"key":"2026010112012012300_btaf520-B10","doi-asserted-by":"publisher","first-page":"R89","DOI":"10.1186\/GB-2014-15-7-R89","article-title":"Host lifestyle affects human microbiota on daily timescales","volume":"15","author":"David","year":"2014","journal-title":"Genome Biol"},{"key":"2026010112012012300_btaf520-B11","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1038\/s41579-020-0433-9","article-title":"Gut microbiota in human metabolic health and disease","volume":"19","author":"Fan","year":"2021","journal-title":"Nat Rev Microbiol"},{"key":"2026010112012012300_btaf520-B12","doi-asserted-by":"publisher","first-page":"144777","DOI":"10.1109\/ACCESS.2019.2945129","article-title":"Development of disease prediction model based on ensemble learning approach for diabetes and hypertension","volume":"7","author":"Fitriyani","year":"2019","journal-title":"IEEE Access"},{"key":"2026010112012012300_btaf520-B13","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1038\/s41564-018-0306-4","article-title":"Gut microbiome structure and metabolic activity in inflammatory bowel disease","volume":"4","author":"Franzosa","year":"2019","journal-title":"Nat Microbiol"},{"key":"2026010112012012300_btaf520-B14","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1038\/s41591-022-01688-4","article-title":"Microbiome and metabolome features of the cardiometabolic disease spectrum","volume":"28","author":"Fromentin","year":"2022","journal-title":"Nat Med"},{"key":"2026010112012012300_btaf520-B15","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1038\/nm.4517","article-title":"Current understanding of the human microbiome","volume":"24","author":"Gilbert","year":"2018","journal-title":"Nat Med"},{"key":"2026010112012012300_btaf520-B16","doi-asserted-by":"publisher","first-page":"2224","DOI":"10.3389\/FMICB.2017.02224","article-title":"Microbiome datasets are compositional: and this is not optional","volume":"8","author":"Gloor","year":"2017","journal-title":"Front Microbiol"},{"key":"2026010112012012300_btaf520-B17","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1038\/s41592-018-0141-9","article-title":"Qiita: rapid, web-enabled microbiome meta-analysis","volume":"15","author":"Gonzalez","year":"2018","journal-title":"Nat Methods"},{"key":"2026010112012012300_btaf520-B18","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1007\/S12561-024-09435-8","article-title":"A comprehensive performance comparison study of various statistical models that accommodate challenges of the gut microbiome data","volume":"17","author":"Hajihosseini","year":"2025","journal-title":"Stat Biosci"},{"key":"2026010112012012300_btaf520-B19","doi-asserted-by":"publisher","first-page":"1479","DOI":"10.1109\/TKDE.2019.2947676","article-title":"Extended Isolation Forest","volume":"33","author":"Hariri","year":"2021","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2026010112012012300_btaf520-B20","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1038\/nature11234","article-title":"Structure, function and diversity of the healthy human microbiome","volume":"486","author":"Huttenhower","year":"2012","journal-title":"Nature"},{"key":"2026010112012012300_btaf520-B21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3233\/JAD-161141","article-title":"The gut microbiota and Alzheimer\u2019s disease","volume":"58","author":"Jiang","year":"2017","journal-title":"J Alzheimers Dis"},{"key":"2026010112012012300_btaf520-B22","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1214\/22-AOAS1623","article-title":"Bayesian classification, anomaly detection, and survival analysis using network inputs with application to the microbiome","volume":"17","author":"Josephs","year":"2023","journal-title":"Ann Appl Stat"},{"key":"2026010112012012300_btaf520-B23","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1038\/nature11412","article-title":"Comprehensive molecular portraits of human breast tumours","volume":"490","author":"Koboldt","year":"2012","journal-title":"Nature"},{"key":"2026010112012012300_btaf520-B24","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1053\/J.GASTRO.2014.02.009","article-title":"The microbiome in inflammatory bowel disease: current status and the future ahead","volume":"146","author":"Kostic","year":"2014","journal-title":"Gastroenterology"},{"year":"2021","author":"Leigh","key":"2026010112012012300_btaf520-B25","doi-asserted-by":"publisher","DOI":"10.1101\/2021.05.17.444491"},{"key":"2026010112012012300_btaf520-B26","doi-asserted-by":"publisher","first-page":"17124","DOI":"10.1038\/s41598-024-64657-6","article-title":"Early-life gut bacterial community structure predicts disease risk and athletic performance in horses bred for racing","volume":"14","author":"Leng","year":"2024","journal-title":"Sci Rep"},{"key":"2026010112012012300_btaf520-B27","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1146\/ANNUREV-STATISTICS-010814-020351","article-title":"Microbiome, metagenomics, and high-dimensional compositional data analysis","volume":"2","author":"Li","year":"2015","journal-title":"Annu Rev Stat Appl"},{"key":"2026010112012012300_btaf520-B28","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1109\/TGRS.2019.2936308","article-title":"Hyperspectral anomaly detection with kernel isolation forest","volume":"58","author":"Li","year":"2020","journal-title":"IEEE Trans Geosci Remote Sensing"},{"key":"2026010112012012300_btaf520-B29","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/978-981-13-6473-0_32","article-title":"Entropy isolation forest based on dimension entropy for anomaly detection","volume":"986","author":"Liao","year":"2019","journal-title":"Commun Comput Inform Sci"},{"key":"2026010112012012300_btaf520-B30","doi-asserted-by":"publisher","first-page":"872671","DOI":"10.3389\/FMICB.2022.872671","article-title":"Machine learning based microbiome signature to predict inflammatory bowel disease subtypes","volume":"13","author":"Li\u00f1ares-Blanco","year":"2022","journal-title":"Front Microbiol"},{"year":"2008","author":"Liu","key":"2026010112012012300_btaf520-B31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.17"},{"key":"2026010112012012300_btaf520-B32","doi-asserted-by":"publisher","first-page":"101007","DOI":"10.1016\/j.isci.2020.101007","article-title":"Testing the Anna Karenina principle in human microbiome-associated diseases","volume":"23","author":"Ma","year":"2020","journal-title":"IScience"},{"key":"2026010112012012300_btaf520-B33","doi-asserted-by":"publisher","DOI":"10.1128\/MSYSTEMS.00031-18","article-title":"American gut: an open platform for citizen science microbiome research","volume":"3","author":"McDonald","year":"2018","journal-title":"MSystems"},{"key":"2026010112012012300_btaf520-B34","doi-asserted-by":"publisher","first-page":"202","DOI":"10.4239\/WJD.V11.I5.202","article-title":"Severity of the metabolic syndrome as a predictor of prediabetes and type 2 diabetes in first degree relatives of type 2 diabetic patients: a 15-year prospective cohort study","volume":"11","author":"Meamar","year":"2020","journal-title":"World J Diabetes"},{"key":"2026010112012012300_btaf520-B35","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1038\/nature11209","article-title":"A framework for human microbiome research","volume":"486","author":"Meth\u00e9","year":"2012","journal-title":"Nature"},{"key":"2026010112012012300_btaf520-B36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/S40168-018-0514-4","article-title":"CLOUD: a non-parametric detection test for microbiome outliers","volume":"6","author":"Montassier","year":"2018","journal-title":"Microbiome"},{"key":"2026010112012012300_btaf520-B37","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1038\/s41522-022-00345-5","article-title":"The gut microbiome-metabolome dataset collection: a curated resource for integrative meta-analysis","volume":"8","author":"Muller","year":"2022","journal-title":"NPJ Biofilms Microbiomes"},{"key":"2026010112012012300_btaf520-B38","doi-asserted-by":"publisher","first-page":"2452","DOI":"10.3390\/NU14122452\/S1","article-title":"Adherence to gluten-free diet restores alpha diversity in celiac people but the microbiome composition is different to healthy people","volume":"14","author":"Palmieri","year":"2022","journal-title":"Nutrients"},{"key":"2026010112012012300_btaf520-B39","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/J.COEMR.2021.05.005","article-title":"Statistical analysis of microbiome data: the challenge of sparsity","volume":"19","author":"Pan","year":"2021","journal-title":"Curr Opin Endocr Metab Res"},{"year":"1999","author":"Preiss","key":"2026010112012012300_btaf520-B40"},{"key":"2026010112012012300_btaf520-B41","doi-asserted-by":"publisher","first-page":"1181911","DOI":"10.3389\/FPUBH.2023.1181911","article-title":"AMAnD: an automated metagenome anomaly detection methodology utilizing DeepSVDD neural networks","volume":"11","author":"Price","year":"2023","journal-title":"Front Public Health"},{"key":"2026010112012012300_btaf520-B42","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1038\/s41586-019-1238-8","article-title":"The integrative human microbiome project","volume":"569","author":"Proctor","year":"2019","journal-title":"Nature"},{"key":"2026010112012012300_btaf520-B43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/S42979-021-00518-7","article-title":"A data-driven heart disease prediction model through K-means clustering-based anomaly detection","volume":"2","author":"Ripan","year":"2021","journal-title":"SN Comput Sci"},{"key":"2026010112012012300_btaf520-B44","doi-asserted-by":"publisher","first-page":"2012","DOI":"10.1038\/s41467-019-09964-7","article-title":"Small intestinal microbial dysbiosis underlies symptoms associated with functional gastrointestinal disorders","volume":"10","author":"Saffouri","year":"2019","journal-title":"Nat Commun"},{"year":"2023","author":"Shaikh","key":"2026010112012012300_btaf520-B45","doi-asserted-by":"publisher","DOI":"10.1109\/ICAISC58445.2023.10200375"},{"key":"2026010112012012300_btaf520-B46","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1053\/j.gastro.2020.09.057","article-title":"The healthy microbiome\u2014what is the definition of a healthy gut microbiome?","volume":"160","author":"Shanahan","year":"2021","journal-title":"Gastroenterology"},{"key":"2026010112012012300_btaf520-B47","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1097\/MOG.0000000000000139","article-title":"The gut microbiome in health and in disease","volume":"31","author":"Shreiner","year":"2015","journal-title":"Curr Opin Gastroenterol"},{"key":"2026010112012012300_btaf520-B48","doi-asserted-by":"publisher","DOI":"10.1128\/mBio.02099-18","article-title":"Identifying and predicting novelty in microbiome studies","volume":"9","author":"Su","year":"2018","journal-title":"MBio"},{"key":"2026010112012012300_btaf520-B49","doi-asserted-by":"publisher","DOI":"10.1128\/msystems.00150-20","article-title":"Multiple-disease detection and classification across cohorts via microbiome search","volume":"5","author":"Su","year":"2020","journal-title":"MSystems"},{"year":"2019","author":"Sun","key":"2026010112012012300_btaf520-B50","doi-asserted-by":"publisher","DOI":"10.1109\/BIGDATA47090.2019.9006354"},{"key":"2026010112012012300_btaf520-B51","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1016\/J.ANNEPIDEM.2016.03.002","article-title":"Compositional data analysis of the microbiome: fundamentals, tools, and challenges","volume":"26","author":"Tsilimigras","year":"2016","journal-title":"Ann Epidemiol"},{"key":"2026010112012012300_btaf520-B52","doi-asserted-by":"publisher","DOI":"10.1128\/MSPHERE.00104-18","article-title":"The microbiome and metabolome of preterm infant stool are personalized and not driven by health outcomes, including necrotizing enterocolitis and late-onset sepsis","volume":"3","author":"Wandro","year":"2018","journal-title":"MSphere"},{"key":"2026010112012012300_btaf520-B53","doi-asserted-by":"publisher","first-page":"2131","DOI":"10.1136\/gutjnl-2019-319766","article-title":"Aberrant gut microbiota alters host metabolome and impacts renal failure in humans and rodents","volume":"69","author":"Wang","year":"2020","journal-title":"Gut"},{"key":"2026010112012012300_btaf520-B54","doi-asserted-by":"publisher","first-page":"2084306","DOI":"10.1080\/19490976.2022.2084306","article-title":"Gut microbiota differs between treatment outcomes early after fecal microbiota transplantation against recurrent Clostridioides difficile infection","volume":"14","author":"Wei","year":"2022","journal-title":"Gut Microbes"},{"key":"2026010112012012300_btaf520-B55","doi-asserted-by":"publisher","first-page":"12591","DOI":"10.1109\/TKDE.2023.3270293","article-title":"Deep Isolation Forest for anomaly detection","volume":"35","author":"Xu","year":"2023","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2026010112012012300_btaf520-B56","doi-asserted-by":"publisher","first-page":"968","DOI":"10.1038\/s41591-019-0458-7","article-title":"Metagenomic and metabolomic analyses reveal distinct stage-specific phenotypes of the gut microbiota in colorectal cancer","volume":"25","author":"Yachida","year":"2019","journal-title":"Nat Med"},{"key":"2026010112012012300_btaf520-B57","doi-asserted-by":"publisher","first-page":"17121","DOI":"10.1038\/nmicrobiol.2017.121","article-title":"Stress and stability: applying the Anna Karenina principle to animal microbiomes","volume":"2","author":"Zaneveld","year":"2017","journal-title":"Nat Microbiol"},{"key":"2026010112012012300_btaf520-B58","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1126\/SCIENCE.AAD3369","article-title":"Population-based metagenomics analysis reveals markers for gut microbiome composition and diversity","volume":"352","author":"Zhernakova","year":"2016","journal-title":"Science"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf520\/64326171\/btaf520.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/10\/btaf520\/64326171\/btaf520.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/10\/btaf520\/64326171\/btaf520.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T17:01:27Z","timestamp":1767286887000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf520\/8258675"}},"subtitle":[],"editor":[{"given":"Pier Luigi","family":"Martelli","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,9,19]]},"references-count":58,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf520","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"type":"print","value":"1367-4803"},{"type":"electronic","value":"1367-4811"}],"subject":[],"published-other":{"date-parts":[[2025,10]]},"published":{"date-parts":[[2025,9,19]]},"article-number":"btaf520"}}