{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:04:31Z","timestamp":1785420271383,"version":"3.56.0"},"reference-count":33,"publisher":"American Society for Microbiology","issue":"7","license":[{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.asm.org\/non-commercial-tdm-license"}],"funder":[{"name":"National Institute of Health","award":["R56AG079586"],"award-info":[{"award-number":["R56AG079586"]}]}],"content-domain":{"domain":["journals.asm.org"],"crossmark-restriction":true},"short-container-title":["mSystems"],"published-print":{"date-parts":[[2026,7,21]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title\/>\n                    <jats:p>Microbiome beta diversity analysis relies on distance-based methods, including permutational multivariate analysis of variance (PERMANOVA) combined with fixed ecological distance metrics (Bray-Curtis, Euclidean, Jaccard, and UniFrac), which treat all microbial taxa uniformly, regardless of their biological relevance to community differences. This \u201cone-size-fits-all\u201d approach may miss subtle but biologically meaningful patterns in complex microbiome data. We present Metric Learning for Statistical Inference (MeLSI), a novel machine learning framework that learns data-adaptive distance metrics optimized for detecting community composition differences in multivariate microbiome analyses. MeLSI employs an ensemble of weak learners using bootstrap sampling, feature subsampling, and gradient-based optimization to learn optimal feature weights, combined with rigorous permutation testing for statistical inference. The learned metrics can be used with PERMANOVA for hypothesis testing and with principal coordinates analysis for ordination visualization. Comprehensive validation on synthetic benchmarks and real data sets shows that MeLSI maintains proper type I error control while delivering competitive or superior statistical power for detecting subtle community shifts and, crucially, supplies interpretable feature-weight profiles that clarify which taxa drive group separation. On the DietSwap data set, MeLSI was the only method to achieve significance at \u03b1 = 0.05, demonstrating that adaptive weighting can detect diet-induced community shifts that fixed metrics miss. Across all data sets, the learned feature weights identified biologically relevant taxa while providing actionable insight that no fixed distance metric can supply. MeLSI therefore offers a statistically rigorous tool that augments beta diversity analysis with transparent, data-driven interpretability.<\/jats:p>\n                    <jats:sec>\n                      <jats:title>IMPORTANCE<\/jats:title>\n                      <jats:p>Understanding which microbes differ between groups of interest could reveal therapeutic targets and diagnostic biomarkers. However, current analysis methods treat all microbes equally (similar to using the same ruler to measure everything, regardless of what matters most). This means subtle but biologically important differences may go undetected, especially when only a few key species drive disease states while hundreds of \u201cbystander\u201d species add noise. Metric Learning for Statistical Inference (MeLSI) solves this by learning which microbes matter most for each specific comparison. In comparing male and female gut microbiomes, MeLSI identified specific bacterial families driving the differences, providing actionable biological insights that standard methods miss. This capability is particularly crucial for detecting early disease biomarkers, where differences are subtle and masked by biological variability. By telling researchers not just whether groups differ, but which specific microbes drive those differences, MeLSI accelerates the path from microbiome data to testable biological hypotheses and clinical applications.<\/jats:p>\n                    <\/jats:sec>\n                  <\/jats:sec>","DOI":"10.1128\/msystems.00407-26","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T13:01:32Z","timestamp":1782738092000},"update-policy":"https:\/\/doi.org\/10.1128\/asmj-crossmark-policy-page","source":"Crossref","is-referenced-by-count":0,"title":["MeLSI: Metric Learning for Statistical Inference in microbiome community composition analysis"],"prefix":"10.1128","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1554-6006","authenticated-orcid":true,"given":"Nathan","family":"Bresette","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/02ymw8z06","id-type":"ROR","asserted-by":"publisher"}],"name":"Roy Blunt NextGen Precision Health, University of Missouri","place":["Columbia, USA"]},{"id":[{"id":"https:\/\/ror.org\/02ymw8z06","id-type":"ROR","asserted-by":"publisher"}],"name":"Institute for Data Science and Informatics, University of Missouri","place":["Columbia, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3053-7269","authenticated-orcid":true,"given":"Aaron C.","family":"Ericsson","sequence":"additional","affiliation":[{"name":"University of Missouri Metagenomics Center","place":["Columbia, USA"]},{"name":"Department of Pathobiology and Integrative Biomedical Sciences, University of Missouri","place":["Columbia, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5345-2712","authenticated-orcid":false,"given":"Carter","family":"Woods","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/02ymw8z06","id-type":"ROR","asserted-by":"publisher"}],"name":"Roy Blunt NextGen Precision Health, University of Missouri","place":["Columbia, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5197-2219","authenticated-orcid":true,"given":"Ai-Ling","family":"Lin","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/02ymw8z06","id-type":"ROR","asserted-by":"publisher"}],"name":"Roy Blunt NextGen Precision Health, University of Missouri","place":["Columbia, USA"]},{"id":[{"id":"https:\/\/ror.org\/02ymw8z06","id-type":"ROR","asserted-by":"publisher"}],"name":"Institute for Data Science and Informatics, University of Missouri","place":["Columbia, USA"]},{"name":"Department of Radiology, University of Missouri","place":["Columbia, USA"]},{"id":[{"id":"https:\/\/ror.org\/02ymw8z06","id-type":"ROR","asserted-by":"publisher"}],"name":"Division of Biological Sciences, University of Missouri","place":["Columbia, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"235","reference":[{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.1038\/nm.4517"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1097\/MOG.0000000000000139"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra1600266"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2012.01.035"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1002\/9781118445112.stat07841"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1890\/0012-9658(2001)082[0290:FMMTCD]2.0.CO;2"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1128\/AEM.71.12.8228-8235.2005"},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1574-6941.2007.00375.x"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1574-6976.2010.00251.x"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1186\/s40168-017-0237-y"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2015.1131161"},{"key":"e_1_3_4_13_2","volume-title":"Resampling-based multiple testing: examples and methods for p-value adjustment","author":"Westfall PH","year":"1993","unstructured":"Westfall PH, Young SS. 1993. Resampling-based multiple testing: examples and methods for p-value adjustment. John Wiley & Sons, New York, NY."},{"key":"e_1_3_4_14_2","volume-title":"Permutation tests: a practical guide to resampling methods for testing hypotheses","author":"Good PI","year":"2013","unstructured":"Good PI. 2013. Permutation tests: a practical guide to resampling methods for testing hypotheses. Springer Science & Business Media, New York, NY."},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1561\/2200000019"},{"key":"e_1_3_4_16_2","doi-asserted-by":"publisher","unstructured":"Bellet A Habrard A Sebban M. 2013. A survey on metric learning for feature vectors and structured data. arXiv. doi:10.48550\/arXiv.1306.6709","DOI":"10.48550\/arXiv.1306.6709"},{"key":"e_1_3_4_17_2","first-page":"207","article-title":"Distance metric learning for large margin nearest neighbor classification","volume":"10","author":"Weinberger KQ","year":"2009","unstructured":"Weinberger KQ, Saul LK. 2009. Distance metric learning for large margin nearest neighbor classification. J Mach Learn Res 10:207\u2013244.","journal-title":"J Mach Learn Res"},{"key":"e_1_3_4_18_2","first-page":"521","volume-title":"Advances in neural information processing systems","author":"Xing EP","year":"2002","unstructured":"Xing EP, Jordan MI, Russell SJ, Ng AY. 2002. Distance metric learning with application to clustering with side-information, p 521\u2013528. In Advances in neural information processing systems. Vol. 15."},{"key":"e_1_3_4_19_2","first-page":"49","article-title":"On the generalized distance in statistics","volume":"2","author":"Mahalanobis PC","year":"1936","unstructured":"Mahalanobis PC. 1936. On the generalized distance in statistics. Proc Natl Inst Sci India 2:49\u201355.","journal-title":"Proc Natl Inst Sci India"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1004977"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.2202\/1544-6115.1585"},{"key":"e_1_3_4_23_2","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms5344"},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms7342"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-4109-0"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/s004420100716"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1995.tb02031.x"},{"key":"e_1_3_4_28_2","unstructured":"Oksanen J Blanchet FG Friendly M Kindt R Legendre P McGlinn D Minchin PR O\u2019Hara RB Simpson GL Solymos P et al.. 2020. Vegan: community ecology package. R Package Version 2.5-7. Available from: https:\/\/CRAN.R-project.org\/package=vegan"},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24277-4"},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1233521"},{"key":"e_1_3_4_31_2","doi-asserted-by":"publisher","DOI":"10.1080\/19490976.2016.1203502"},{"key":"e_1_3_4_32_2","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/4178607"},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289694"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1442-9993.1993.tb00438.x"}],"container-title":["mSystems"],"original-title":[],"contributor":[{"given":"Shi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"reviewer"}]}],"language":"en","link":[{"URL":"https:\/\/journals.asm.org\/doi\/pdf\/10.1128\/msystems.00407-26","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.asm.org\/doi\/pdf\/10.1128\/msystems.00407-26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T13:03:35Z","timestamp":1784639015000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.asm.org\/doi\/10.1128\/msystems.00407-26"}},"subtitle":[],"editor":[{"given":"Gail","family":"Rosen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,21]]},"references-count":33,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7,21]]}},"alternative-id":["10.1128\/msystems.00407-26"],"URL":"https:\/\/doi.org\/10.1128\/msystems.00407-26","relation":{},"ISSN":["2379-5077"],"issn-type":[{"value":"2379-5077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,21]]},"assertion":[{"value":"2026-04-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e00407-26"}}