Artificial intelligence-driven donor-recipient gut microbiome matching for optimized fecal microbiota transplantation
Clinical Snapshot
PICO Framework
| P — Population | 515 FMT procedures across 30 cohorts involving patients with 12 different gastrointestinal diseases |
| I — Intervention | MOZAIC framework for donor-recipient microbiome matching using multi-dimensional microbiota features |
| C — Comparator | Standard FMT donor selection without microbiome matching |
| O — Outcomes | Post-FMT microbiome convergence, clinical response rates, and prediction accuracy for FMT outcomes |
Bottom Line
This large multi-cohort study demonstrates that microbiome convergence between donor and recipient predicts FMT clinical success across multiple gastrointestinal diseases. The MOZAIC framework achieved high accuracy (AUC 0.88) in predicting microbiome convergence and 78.7% accuracy for clinical outcomes, with retrospective modeling suggesting a 1.44-fold improvement in response rates. While promising for precision FMT matching, the cross-sectional design limits causal inference, and real-world implementation requires significant sequencing infrastructure. The findings support microbiome-guided donor selection as a strategy to optimize FMT efficacy, though prospective validation studies are needed before clinical adoption. This research could inform Australian FMT guidelines and improve treatment outcomes for conditions like recurrent C. difficile infection and inflammatory bowel disease.
Key Findings
P Value: Not reported in abstract
Effect Size: 1.44-fold improvement in clinical response rates (49.4% to 71.0%)
Primary Outcome: Post-FMT microbiome convergence prediction and clinical response
Nnt Or Sensitivity: AUC 0.88 for microbiome convergence prediction, 78.7% accuracy for clinical outcomes
Confidence Interval: Not reported in abstract
Clinical Application
Requires metagenome sequencing infrastructure and bioinformatics expertise, potentially limiting immediate widespread adoption Relevant to Australian FMT programs; could inform TGA regulatory framework for FMT donor selection and improve PBS cost-effectiveness Patients requiring FMT for various gastrointestinal conditions including CDI, IBD, and other microbiome-related disorders
Abstract
Fecal microbiota transplantation (FMT) has emerged as a promising therapy for gastrointestinal diseases, yet its clinical efficacy remains individually variable. Here, we analyze multi-kingdom and functional profiles in pre- and post-FMT metagenomes from 515 FMTs across 30 cohorts and 12 diseases, in which 94 metagenomes from 44 FMTs are newly collected. We reveal a robust association between clinical efficacy and post-FMT microbiome convergence of recipients toward donors, across diseases. To predict post-FMT microbial convergence, we develop MOZAIC (Microbiome Matching Optimization via Artificial Intelligence), a framework that integrates multi-dimensional donor-recipient microbiota features. MOZAIC achieves an average area under the curve (AUC) of 0.88 and accuracy/recall >0.80 in forecasting microbiome convergence, with 78.7% accuracy in predicting clinical outcomes, and retrospectively simulates a 1.44-fold improvement (from 49.4% to 71.0%) in clinical response rates over baseline. This study establishes microbiome convergence as a key mediator of FMT and provides a scalable tool for precision matching in microbiota-based therapies.
References
- 1.Su, Q., Chen, S., Lau, L. H., Lui, R. N., Wang, Y., Xu, Z., Cheung, C. P., Ching, J. Y. L., Shen, X., Peng, Y., Tun, H. M., Ianiro, G., Rubin, D., Chang, E. B., Chan, F. K. L., & Ng, S. C. (2026). Artificial intelligence-driven donor-recipient gut microbiome matching for optimized fecal microbiota transplantation. Cell Reports, 45(6), 117301. https://doi.org/10.1016/j.celrep.2026.117301
Related Research
The American journal of pathology
An Integrated Machine Learning and Genomic Framework for Precise Detection of Gastric Cancer
3 Aug 2026
Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association
Artificial Intelligence Tools for Gastrointestinal Research: A Practical Guide
2 Aug 2026
Current opinion in critical care
Smart feeding: the role of artificial intelligence and integrated nutrition platforms in the ICU
2 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service