{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T19:02:59Z","timestamp":1784401379892,"version":"3.55.0"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:00:00Z","timestamp":1784332800000},"content-version":"vor","delay-in-days":17,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Fecal microbiota transplantation (FMT) has emerged as a highly effective treatment for recurrent Clostridioides difficile infection and is being actively investigated for numerous other conditions. While multi-omics studies have revealed dynamic changes in microbial communities and host metabolism following FMT, existing approaches are primarily descriptive and lack the ability to model individual patient trajectories or identify early biomarkers of treatment response. Small-sample, multi-omics, longitudinal prediction presents unique computational challenges: high dimensionality ($p \\gg n$), multi-omics integration, temporal dynamics, and interpretability. Here, we present Hierarchical Multi-Omics Trajectory Prediction (HMOTP), a purpose-built machine learning framework that addresses these challenges through hierarchical feature construction, multilevel attention mechanisms, and patient-specific trajectory prediction. We evaluated HMOTP on 15 patients with recurrent Clostridioides difficile infection who underwent FMT, with lipidomics and metagenomics profiling at four timepoints spanning 6 months. Notably, naively concatenating multi-omics features degraded Random Forest performance ($93.33\\%$ to $87.18\\%$ accuracy), whereas HMOTP\u2019s hierarchical integration benefited from the additional omics layer, demonstrating that its advantage stems from structure, not from access to more data. Through hierarchical interpretability, HMOTP identified key biomarkers and revealed cross-omics associations between host lipid metabolism and microbial energy pathways, demonstrating utility for longitudinal modeling and biological discovery in FMT response. HMOTP provides a generalizable, principled framework for personalized medicine applications across small-sample multi-omics problems. Source code and a demo dataset are publicly available.<\/jats:p>","DOI":"10.1093\/bib\/bbag389","type":"journal-article","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:45:22Z","timestamp":1784400322000},"source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Multi-Omics Trajectory Prediction for fecal microbiota transplantation: a novel machine learning framework for small-sample longitudinal multi-omics integration"],"prefix":"10.1093","volume":"27","author":[{"given":"Zhou","family":"Yi-Hui","sequence":"first","affiliation":[{"name":"Departments of Biological Sciences and Statistics , 1 Lampe Drive, NC State University, Raleigh, NC, 27695,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sun","family":"George","sequence":"additional","affiliation":[{"name":"High Dimensional Predictive Biology Lab , 1 Lampe Drive, NC State University, Raleigh, NC, 27695,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,18]]},"reference":[{"key":"2026071814451519600_ref1","first-page":"649","article-title":"Effect of fecal microbiota transplantation on recurrence in multiply recurrent Clostridioides difficile infection: a randomized clinical trial","volume":"174","author":"Kelly","year":"2021","journal-title":"Ann Intern Med"},{"key":"2026071814451519600_ref2","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1111\/apt.14201","article-title":"Systematic review with meta-analysis: the efficacy of faecal microbiota transplantation for the treatment of recurrent and refractory clostridium difficile infection","volume":"46","author":"Baunwall","year":"2017","journal-title":"Aliment Pharmacol Ther"},{"key":"2026071814451519600_ref3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12866-023-03123-1","article-title":"Multi-omics analysis of fecal microbiota transplantation\u2019s impact on functional constipation and comorbid depression and anxiety","volume":"23","author":"Zheng","year":"2023","journal-title":"BMC Microbiol"},{"key":"2026071814451519600_ref4","first-page":"1856","article-title":"Multi-omic analyses identify mucosa bacteria and fecal metabolites associated with weight loss after fecal microbiota transplantation","volume":"28","author":"Yu","year":"2022","journal-title":"Nat Med"},{"key":"2026071814451519600_ref5","doi-asserted-by":"crossref","first-page":"874922","DOI":"10.3389\/fimmu.2022.874922","article-title":"Metagenomic and metabolomic analyses reveal synergistic effects of fecal microbiota transplantation and anti-PD-1 therapy on treating colorectal cancer","volume":"13","author":"Wang","year":"2022","journal-title":"Front Immunol"},{"key":"2026071814451519600_ref6","first-page":"1","article-title":"Efficacy and safety of fecal microbiota transplantation combined with immune checkpoint inhibitors in treating advanced solid tumors: a systematic review and meta-analysis","volume":"23","author":"Wang","year":"2025","journal-title":"BMC Med"},{"key":"2026071814451519600_ref7","doi-asserted-by":"publisher","first-page":"946","DOI":"10.1053\/j.gastro.2013.08.058","article-title":"Therapeutic potential of fecal microbiota transplantation","volume":"145","author":"Smits","year":"2013","journal-title":"Gastroenterology"},{"key":"2026071814451519600_ref8","first-page":"925726","article-title":"Multi-omics study on gut microbiota related to faecal microbiota transplantation","volume":"12","author":"Zhang","year":"2022","journal-title":"Front Cell Infect Microbiol"},{"key":"2026071814451519600_ref9","first-page":"fiz095","article-title":"Gut microbial and metabolomic profiles after fecal microbiota transplantation in pediatric ulcerative colitis patients","volume":"95","author":"Kump","year":"2019","journal-title":"FEMS Microbiol Ecol"},{"key":"2026071814451519600_ref10","first-page":"1028","article-title":"Multi-omics analysis of a fecal microbiota transplantation trial identifies novel aspects of acute GVHD pathogenesis","volume":"30","author":"Peled","year":"2024","journal-title":"Nat Med"},{"key":"2026071814451519600_ref11","first-page":"819","article-title":"A multicenter study of a prediction model for early fecal microbiota transplantation failure in treating clostridium difficile infection","volume":"50","author":"Fischer","year":"2016","journal-title":"J Clin Gastroenterol"},{"key":"2026071814451519600_ref12","doi-asserted-by":"publisher","first-page":"921945","DOI":"10.3389\/fmolb.2022.921945","article-title":"Improve the colorectal cancer diagnosis using gut microbiome data","volume":"9","author":"Zhou","year":"2022","journal-title":"Front Mol Biosci"},{"key":"2026071814451519600_ref13","doi-asserted-by":"publisher","first-page":"610845","DOI":"10.3389\/fmolb.2020.610845","article-title":"Systematic comparisons for composition profiles, taxonomic levels, and machine learning methods for microbiome-based disease prediction","volume":"7","author":"Song","year":"2020","journal-title":"Front Mol Biosci"},{"key":"2026071814451519600_ref14","doi-asserted-by":"publisher","first-page":"10546","DOI":"10.1093\/nar\/gky889","article-title":"Multi-omics and multi-view clustering algorithms: review and cancer benchmark","volume":"46","author":"Rappoport","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2026071814451519600_ref15","doi-asserted-by":"publisher","first-page":"e8124","DOI":"10.15252\/msb.20178124","article-title":"Multi-omics factor analysis\u2014a framework for unsupervised integration of multi-omics data sets","volume":"14","author":"Argelaguet","year":"2018","journal-title":"Mol Syst Biol"},{"key":"2026071814451519600_ref16","doi-asserted-by":"publisher","first-page":"e1005752","DOI":"10.1371\/journal.pcbi.1005752","article-title":"mixOmics: An R package for \u2018omics feature selection and multiple data integration","volume":"13","author":"Rohart","year":"2017","journal-title":"PLoS Comput Biol"},{"key":"2026071814451519600_ref17","doi-asserted-by":"publisher","first-page":"104781","DOI":"10.1016\/j.jmva.2021.104781","article-title":"Eigenvector-based sparse canonical correlation analysis: fast computation for estimation of multiple canonical vectors","volume":"185","author":"Wang","year":"2021","journal-title":"J Multivar Anal"},{"key":"2026071814451519600_ref18","first-page":"1022","article-title":"Can you trust this prediction? Auditing pointwise reliability after learning","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Schulam","year":"2019"},{"key":"2026071814451519600_ref19","doi-asserted-by":"publisher","first-page":"948","DOI":"10.3390\/applmicrobiol4020064","article-title":"Predicting microbiome growth dynamics under environmental perturbations","volume":"4","author":"Sun","year":"2024","journal-title":"Appl Microbiol"},{"key":"2026071814451519600_ref20","first-page":"4765","article-title":"A unified approach to interpreting model predictions. In: Isabelle G, Von Luxburg U, Bengio et\u00a0al (eds). Advances in neural information processing systems","author":"Lundberg","year":"2017"},{"key":"2026071814451519600_ref21","first-page":"5998","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems Curran Associates, Inc.","author":"Vaswani","year":"2017"},{"key":"2026071814451519600_ref22","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2009","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2026071814451519600_ref23","doi-asserted-by":"publisher","first-page":"1539","DOI":"10.1056\/NEJMra1403772","article-title":"Clostridium difficile infection","volume":"372","author":"Leffler","year":"2015","journal-title":"N Engl J Med"},{"key":"2026071814451519600_ref24","doi-asserted-by":"publisher","first-page":"3985","DOI":"10.1021\/ac500405x","article-title":"Ion mobility derived collision cross sections to support metabolomics applications","volume":"86","author":"Paglia","year":"2014","journal-title":"Anal Chem"},{"key":"2026071814451519600_ref25","doi-asserted-by":"publisher","first-page":"14709","DOI":"10.1021\/acs.analchem.5c06667","article-title":"A unified Bayesian framework for cross-technology collision cross section postcalibration correction and multilaboratory harmonization","volume":"98","author":"Zhou","year":"2026","journal-title":"Anal Chem"},{"key":"2026071814451519600_ref26","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1101\/gr.216242.116","article-title":"Microbial strain-level population structure and genetic diversity from metagenomes","volume":"27","author":"Truong","year":"2017","journal-title":"Genome Res"},{"key":"2026071814451519600_ref27","doi-asserted-by":"publisher","first-page":"902","DOI":"10.1038\/nmeth.3589","article-title":"Metaphlan2 for enhanced metagenomic taxonomic profiling","volume":"12","author":"Truong","year":"2015","journal-title":"Nat Methods"},{"key":"2026071814451519600_ref28","doi-asserted-by":"publisher","first-page":"962","DOI":"10.1038\/s41592-018-0176-y","article-title":"Species-level functional profiling of metagenomes and metatranscriptomes","volume":"15","author":"Franzosa","year":"2018","journal-title":"Nat Methods"},{"key":"2026071814451519600_ref29","doi-asserted-by":"publisher","first-page":"e00706","DOI":"10.1128\/msphere.00706-24","article-title":"Metagenomic, metabolomic, and lipidomic shifts associated with fecal microbiota transplantation for recurrent Clostridioides difficile infection","volume":"9","author":"McMillan","year":"2024","journal-title":"mSphere"},{"key":"2026071814451519600_ref30","article-title":"Adam: a method for stochastic optimization","author":"Kingma","journal-title":"International Conference on Learning Representations"},{"key":"2026071814451519600_ref31","doi-asserted-by":"publisher","first-page":"231","DOI":"10.3390\/bioengineering10020231","article-title":"Leveraging scheme for cross-study microbiome machine learning prediction and feature evaluations","volume":"10","author":"Song","year":"2023","journal-title":"Bioengineering"},{"key":"2026071814451519600_ref32","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2026071814451519600_ref33","doi-asserted-by":"publisher","DOI":"10.1002\/9781118548387","volume-title":"Applied Logistic Regression","author":"Hosmer Jr","year":"2013"},{"key":"2026071814451519600_ref34","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the false discovery rate: a practical and powerful approach to multiple testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J R Stat Soc Ser B Methodol"},{"key":"2026071814451519600_ref35","first-page":"8026","article-title":"PyTorch: an imperative style, high-performance deep learning library","volume-title":"Advances in Neural Information Processing Systems,","author":"Paszke","year":"2019"},{"key":"2026071814451519600_ref36","first-page":"2825","article-title":"scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/4\/bbag389\/69325487\/bbag389.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/4\/bbag389\/69325487\/bbag389.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:45:24Z","timestamp":1784400324000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag389\/8737241"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":36,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag389","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,7]]},"published":{"date-parts":[[2026,7]]},"article-number":"bbag389"}}