Durable Long-Term Bacterial Engraftment following Encapsulated Fecal Microbiota Transplantation To Treat Clostridium difficile Infection

Abstract

Fecal microbiota transplantation (FMT) has become a common rescue therapy for recurrent Clostridium difficile infection, and encapsulated delivery (cFMT) of healthy donor microbiota shows similar clinical efficacy as more traditional routes of administration. In this study, we characterized long-term patterns of bacterial engraftment in a cohort of 18 patients, who received capsules from one of three donors, up to 409 days post-FMT. Bacterial communities were characterized using Illumina sequencing of the V5-V6 hypervariable regions of the 16S rRNA gene, and engraftment was determined by using the Bayesian algorithm SourceTracker. All patients recovered clinically and were free of C. difficile infection following cFMT. The majority of patients (61%) showed high levels of engraftment after the first week following FMT, which were sustained throughout the year. A small subset, 22%, experienced a decline in donor engraftment after approximately 1 month, and a few patients (17%), two of whom were taking metformin, showed delayed and low levels of donor engraftment. Members of the genera Bacteroides, Parabacteroides, and Faecalibacterium were significantly and positively correlated with donor similarity (ρ = 0.237 to 0.373, P ≤ 0.017). Furthermore, throughout the year, patient fecal communities showed significant separation based on the donor fecal microbiota that they received (P < 0.001). Results of this study, which characterize long-term engraftment following cFMT, suggest that numerical donor similarity is not strictly related to clinical outcome and identify a persistent donor-specific effect on patient fecal microbial communities. Furthermore, results suggest that members of the Bacteroidetes may be important targets to improve engraftment via cFMT.IMPORTANCE Recurrent Clostridium difficile infection (rCDI) is the most common cause of hospital- and community-acquired diarrheal infection associated with antibiotic use. Fecal microbiota transplantation (FMT), a treatment that involves administration of fecal bacteria from a healthy donor to a recipient patient, is a highly effective rescue therapy for rCDI that is increasingly being incorporated into standard clinical practice. Encapsulated, freeze-dried preparations of fecal microbiota, administered orally, offer the simplest and most convenient route of FMT delivery for patients (cFMT). In this study, we evaluated the extent of bacterial engraftment following cFMT and the duration of donor bacterial persistence. All patients studied recovered clinically but showed differing patterns in long-term microbial community similarity to the donor that were associated with members of the bacterial group Bacteroidetes, previously shown to be prominent contributors to rCDI resistance. Results highlight long-lasting, donor-specific effects on recipient patient microbiota and reveal potential bacterial targets to improve cFMT engraftment.

Keywords: Bacteroides; capsule FMT; donor; engraftment; fecal transplant; stable.

FIG 1

Microbial community diversity and composition in patient and donor samples. (A) Shannon indices in samples grouped by time point. Error bars reflect standard error, letters denote statistical differences (Tukey’s post hoc P < 0.05), and bars that share the same letter did not differ significantly. (B) Distribution of abundant genera in samples grouped by time point (mean ± standard error). (C) Principal-coordinate analysis of Bray-Curtis distances among all patient and donor samples (r² = 0.40). Samples are grouped by days post-FMT, pre-FMT, or donor. Abundant genera that were significantly correlated with axis positions are shown.

FIG 2

Evaluation of donor engraftment in patient samples. (A) Mean similarity to all three donor lots (combined donor), the donor lot received (individual donor), or the patient’s pre-FMT sample, as determined by SourceTracker. (B) Patients showing sustained engraftment through the year-long follow-up. (C) Patients in whom a decline in donor similarity (approximately 20% or greater from maximum) was observed. (D) Patients in whom slow and/or poor engraftment was observed. For panels B to D, all data points were normalized to donor similarity in the patient’s pre-FMT sample and only the donor lot received was used as a source. Missing time points indicate that a sample was not collected during that period. Patients who were taking metformin are shown by triangles. Error bars reflect standard error.

FIG 3

Similarity to donor samples using shared OTUs. Solid lines reflect the relative abundances of empirically shared OTUs. Dashed lines reflect SourceTracker (ST) predictions of donor similarity. Error bars reflect SEM.

FIG 4

Principal-coordinate analysis of Bray-Curtis distances among patient samples collected: 28 to 45 days (r² = 0.38) (A), 86 to 134 (r² = 0.21) (B), and 346 to 409 days (r² = 0.35) (C) post-FMT. Samples are grouped by the donor lot received.

FIG 5

Bacterial community composition and diversity grouped by engraftment patterns. (A to C) Mean relative abundances of the five predominant genera are shown for samples from patients with sustained engraftment (A), declining engraftment (B), or slow/poor engraftment (C). (D) Mean Shannon indices for each engraftment pattern. Error bars reflect SEM.