An acutely dysbiotic gut microbial community is broadly dysfunctional and can no longer maintain the health of the host. For example, in the case of recurrent Clostridium difficile infection (rCDI), a disturbed microbial community is unable to prevent colonization by or overgrowth of the pathogen, leading to recurrent overgrowth of C. diff and clinical symptoms [24]. Acute dysbiosis has also been described with the “Anna Karenina principle”: all healthy microbiomes are alike but dysbiotic communities are all dysbiotic in their own ways [25] In this view of acute dysbiosis, microbial communities respond stochastically to stressors, resulting in dysbiotic communities which are characterized by increased variability rather than deterministic shifts to precise community type(s) [25].

In this model, the host simply needs to return to a “healthy” microbiome and thus choosing any healthy FMT donor should be sufficient to induce clinical improvements. Because there is no specific disease-associated microbial community and deviation from health is instead the more important factor, simply replenishing the microbiome with a healthy configuration should be sufficient. Indeed, FMT trials have demonstrated that rCDI can be effectively treated by almost any choice of healthy donor [26]. In this case, researchers should consider how they define a “healthy” microbiome and how they will ensure clinical efficacy, for example through engraftment of the transplanted healthy communities.

Absence of beneficial taxa

In other cases, perhaps a disease is being caused or exacerbated by the lack of certain specific microbes, and replenishing these few taxa would be sufficient to restore the host to health [14]. For example, Hsiao et al. showed that a single microbe, R. obeum, restricted infection by V. cholerae through quorum-sensing-mediated mechanisms [27]. Surprisingly, non-communicable diseases may also fall into this model: a single strain of Lactobacillus was sufficient to ameliorate salt-induced hypertension in mice, and follow-up studies indicate that similar mechanisms may be involved in salt-sensitive high blood pressure in humans as well [28].

In these cases, the donor selection strategy should focus on maximizing the probability of engraftment of the beneficial taxa. In cases where the unique taxa are not specifically known or are rare members of the human microbiota, many healthy donors could be pooled together or a donor with a high alpha diversity could be selected in order to maximize the probability that the transplanted sample contains the necessary taxa [14]. However, pooling donors may increase the risk of adverse events and should be pursued with caution. If the missing microbes are known and well-characterized, on the other hand, researchers can screen their pool of potential donors to find the sample with the highest abundance of these taxa.

Presence of harmful taxa

Rather than being characterized by the absence of individual bacteria, perhaps a disease is instead mediated by the presence or overabundance of specific microbes, and removing these bacteria in a targeted fashion could lead to improvements in disease progression. For example, Fusobacterium has been found to be more abundant in colorectal cancer patients, specifically enriched in the tumors themselves [29]. Multiple groups have identified mechanistic associations between Fusobacterium, inflammatory transcriptional signatures, and tumor growth in mouse and human models of colorectal cancer, pointing to a causal role for Fusobacterium in colorectal cancer progression [29, 30]. Recent work has found that treating tumors with antibiotics slows tumor progression, further confirming these causal associations and pointing toward potential microbiome-based therapeutic interventions [31].

Removing and replacing these bacteria should be the goal of FMT in cases where this disease model applies. This can be achieved by first removing the harmful bacteria (e.g. via antibiotic treatment) with follow-up FMT to re-establish a healthy community that prevents their re-colonization. In all cases, donors should be screened to exclude any samples which contain the harmful bacteria. Donor samples can then be selected based on the abundance of bacteria which are known to out-compete the harmful taxa. Competitors can be identified by searching the microbiology literature to identify bacteria which live in the same niche or which have been experimentally shown to directly out-compete the undesirable taxa, or they can perform these competition assays themselves. If resources to perform competition assays are not available and the literature is sparse, researchers can also mine existing microbiome data to find bacteria which consistently anti-correlate with the harmful taxa, and choose donor samples with a high abundance of these putative competitors [32].

Patient matching

Taxa-based donor selection strategies are particularly amenable to patient-matching, when both patient and donor microbiome data are available prior to the start of a trial [14]. For example, if one patient is completely missing some of the beneficial taxa but not others, then these taxa can be weighted more heavily in the donor selection process. The phylogenetic relationships between donor and recipient taxa could also be incorporated into donor selection: if a patient already has many bacteria which are closely phylogenetically related to known competitors of some of the harmful bacteria, then competitors of the other harmful bacteria can be upweighted in the donor selection process. Similarly, if patients already have taxa which are already filling certain niches important for health, the taxa which fill those same niches can be downweighted in donor selection.

Case study: Inflammatory bowel disease

An example where the “missing taxa” model may be applicable is in inflammatory bowel disease (IBD). Butyrate has long been associated with IBD [14, 33], and recent case-control and longitudinal studies point to a consistent lack of butyrate-producing bacteria in patients with IBD [34, 35]. Furthermore, preliminary FMT trials in IBD have been marked by variable efficacy, both between trials and between donors within individual trials, suggesting that donor microbiome characteristics may be associated with FMT response [36–38]. These results indicate that IBD may benefit from rational donor selection approach, and that donors with high abundances of butyrate-producing organisms may yield higher FMT response rates than randomly selected donors.

Given the availability of microbiome data from completed FMT studies, a clinician leading an IBD FMT trial may elect to perform rational donor selection based on the “absence of beneficial taxa” disease model. To illustrate this process, we re-analyzed microbiome data from three completed IBD FMT trials which provided publicly available sequencing data for patient and donor samples [36–38]. We selected butyrate-producers based on their genus-level taxonomy, using a simple heuristic from Vital et al. 2017 ([39], see Methods). Donors in the three studies exhibited a range of total abundances of butyrate-producing bacteria (Fig 2A; S1, S2, and S3 Figs). However, the abundance of butyrate producers in the donor stool was not associated with recipient patients’ clinical responses (Fig 2B) and we also found no association with response when matching donor abundances with their respective patient’s original abundance of butyrate producers (S4 Fig). This illustrative case study shows that selecting donors based on the abundance of butyrate producers may not yield improved clinical trial outcomes in IBD, and more broadly highlights some of the challenges involved in performing rational donor selection in a real-world context.

Despite their accessibility, taxonomy-based approaches are limited in their ability to identify functional or strain-level associations. For example, in this 16S-based analysis, we were unable to identify any of the Eubacteria taxa which are major contributors to SCFA production in the human gut [39, 40]. More complex methods to identify butyrate producers (e.g. using more finely resolved taxonomy, phylogenetic-aware methods and/or metagenomics data) could be used in the next iteration to develop a donor selection strategy, if these data are available to clinicians. Another approach, discussed below, is to select donors based on functional community assays and direct measurement of butyrate production rather than microbial taxonomies alone.

Some microbiome-associated diseases may not be addressable by replenishing the patient with a generically healthy community or by targeting individual taxa, and may instead be mediated by the microbiome through a community-level function. Here, there may not be a consistent disease-associated microbiome across patients in terms of taxonomic composition, but patients may be characterized by having microbiomes which are similarly missing or enriched in some core functionality. This model may also apply to conditions where there are consistent disease- or health-associated taxa, but in which their collective functioning is the more important mediator of disease. The IBD case study described above may reflect this situation: although depletion of butyrate producers is strongly associated with IBD throughout the literature, a successful donor selection strategy may need to consider butyrate production directly rather than through the proxy of taxonomy [14, 34, 35].

Missing community-level function

In the case where a community-level function is missing from patients’ microbiomes, the goal of FMT should be to replace the deficient community with a beneficially functional microbiome. Here, it is important that a single donor with an intact microbial community is used, rather than a mixture of donors which may not yield the desirable community composition at steady-state after FMT. To choose a donor, molecules which can serve as proxies for the metabolic output of the microbial community can be measured directly in donor stool, and donors can be selected based on the abundance of these molecules.

Like IBD, hepatic encephalopathy (HE) is an example where community functionality is likely more relevant to FMT outcome than specific taxa. A previous trial in HE [41] rationally selected their single donor by maximizing the abundance of Lachnospiraceae and Ruminococcaceae, taxa which were were previously found to be depleted in HE patients based on cross-sectional microbiome data. The clinical trial was a success, but it remains unclear from this trial whether the donor's strains engrafted in the patients post-FMT and whether this played any role in the successful FMT responses. The exact mechanisms of action of these strains remain unknown, though both bacterial families are known short chain fatty acid producers (in particular butyrate) [39]. Recent studies have more directly implicated deficiencies in the production of short-chain fatty acids (SCFAs) and secondary bile acids as being important in liver cirrhosis and subsequent complications such as HE, suggesting that community-level functioning may be a more important driver of FMT response. Thus, HE may be a case in which function-based donor selection can be employed. To illustrate this process, we analyzed stool metabolomics data from 83 OpenBiome donors and used this data to rank them based on their estimated production of SCFAs and secondary bile acids (Fig 3; [42]). As in the IBD case study (Fig 2A), we found that donors exhibited a range of values for our metabolites of interest (Fig 3A and 3C). We ranked donors based on their amounts of the three measured SCFAs (butyrate, isovalerate, and propionate) and on their bile acid conversion rates, approximated as the ratio between the total amounts of primary and secondary bile acids (Fig 3B and 3D, see Methods). With this process, we were able to identify four donors who were in the top 25% of all donors for both metrics (Fig 3E). In a real FMT trial, a clinician would then work with their stool bank to ensure that these donors were still active and/or had enough material to fulfill the full trial, or alternatively request that donors with a similar range of SCFAs and secondary bile acid conversion be provided.

While measuring metabolites in stool as a proxy for community production will likely be an improvement over taxonomy-based approaches in most cases, these measurements are also complicated by potential host effects. For example, different hosts may absorb these molecules at different rates, and so measuring them in stool may not be an accurate reflection of each donor community’s productive potential. Additionally, community function may depend on non-biologically relevant factors like the donor’s diet and time that they provided their sample. As an example, bile acid production spikes after meals [43], so the amount of bile acids measured in a given stool sample may reflect the amount of time since the donor last ate rather than their actual microbial community’s functional production of these molecules. If clinicians have access to sufficient resources, a better way to screen donors may be to perform ex vivo assays, in which each donor sample is homogenized and provided with the substrates (e.g. fiber) needed to produce the desirable output (e.g. short-chain fatty acids like butyrate). In this way, the donor community function can be measured directly [44, 45].

Overactive function

A disease may also be mediated by an overactive microbiome doing something harmful to the host. For example, TMAO produced by the microbiota contributes to atherosclerosis [46, 47]. Here, the goal of FMT should also be to replace the patient’s microbiome with a beneficially functional community, but the donor selection strategy may attempt to identify communities in which the harmful function is completely absent or which produces an inhibitor of the harmful microbe-derived molecule [47].

Diseases with more complex etiologies may not have a direct taxonomic or functional association with the microbiome but instead be related through some intermediate host phenotype which needs to be improved or corrected. For example, severe acute malnutrition has been associated with a gut microbiota which is not fully mature, with mouse experiments suggesting that this association may be causal [48, 49]. Other studies have shown a relationship between gut microbiome, immune development, and development of autoimmune conditions later in life [50–52]. These relationships may have mechanistic explanations which are not directly measurable from donor or patient stool (e.g. immunogenicity of bacteria, ability of bacteria to digest the host’s mucus) but which can nevertheless be inferred from existing data and used to select potential donors.

For these more complex cases, models can be trained from existing datasets to learn the community signatures linked to the disease-associated phenotype. In some cases, it may be possible to develop computational models which directly predict the phenotype of interest. For example, Stein et al. developed a model to predict the induction of regulatory T-cells by microbial communities [53]. In other cases with few known mechanistic models, machine learning algorithms can be trained on multiple cross-sectional datasets to identify complex signatures that reproducibly distinguish patients from healthy controls. These models can then be applied to score potential donors, and the donor with the “most healthy” score may be chosen for a trial.

In some conditions, there may not be enough understanding of the underlying microbiome-based etiology to inform donor selection in an FMT trial. It may also be the case that there are no existing datasets on which to train models, existing datasets are not sufficiently powered to distinguish the different potential underlying models, or logistical considerations constrain a clinician’s ability to select specific donors for their trial. In these cases, we recommend selecting different healthy donors, employing an adaptive clinical trial design in which donors are cycled after they have clinical failures (as described previously in [20]), and performing retrospective analyses to answer targeted hypotheses which were developed during the clinical trial design process.

Cycling healthy donors in adaptive trials

As donors change through the course of an adaptive trial, clinicians may elect to select their donors randomly or to more rationally cycle through donors [20]. “Differently healthy” donors may be selected through a combination of donor selection strategies to represent the different underlying disease-associated models described above. Clinicians may be able to test whether a biological mechanism is involved by strategically selecting donors and testing whether one type of donor led to better outcomes than the others. For example, if the hypothesized biological mechanism relates to butyrate production, healthy donors with high and low levels of butyrate production could be used in the FMT arm, and retrospective analyses may be able to determine whether there is an association between donor butyrate levels and FMT outcome. However, since clinical trials prioritize clinical efficacy over secondary outcomes like mechanistic insights, few exploratory FMT trials will likely have the sample size and power necessary to conclusively perform such analyses.

Donors may also be selected to span the range of “healthy” microbiomes in a given population. For example, clinicians may pick a "median" healthy donor who is similar to existing healthy reference microbiomes [54, 55], or simply based on the presence or abundance of certain consistently “core” health-associated bacteria [34, 56]. In a similar vein, “healthy” donors can also be chosen based on their distance from disease-associated microbiomes, as opposed or in addition to similarity to health. Published case-control datasets can be used to identify donors with communities which are farthest away from the median or average diseased patient. These datasets can also be mined to identify taxa which are consistently disease-associated, and which should be minimized or perhaps even absent in the potential donor. Pairing rational donor selection with adaptive trial designs may eventually yield insight into the underlying model mediating the disease of interest if certain types of “healthy” donors consistently perform better at treating patients than others.

Discovery-based retrospective analyses of completed FMT trials

In these exploratory FMT clinical trials, discovering microbiome characteristics which are differentially associated with FMT response may be a valuable secondary endpoint [16], identifying characteristics of good donors and informing donor selection strategy for future trials [36, 38, 57]. Furthermore, companies attempting to develop microbiome-based therapeutics may use FMT trials to discover the key bacteria which mediate FMT response in order to include these in their microbial cocktail product. However, exploratory FMT trials tend to enroll few patients, limiting the potential power of retrospective analyses of individual trials to find associations between the microbiome and FMT response.

We performed a simulation to determine the likelihood of a retrospective analysis to identify donor-derived bacteria associated with different patient responses to FMT. We performed this simulation for multiple FMT trial set-ups and outcomes (i.e. number of FMT responders and non-responders). We used existing microbiome datasets to model different effect sizes, where we use “effect size” to mean the number of bacteria which are differentially abundant in donor samples given to patients who did and did not respond to FMT. Case-control datasets were used to model the microbiome data and various effect sizes, with a large effect represented by an infectious diarrhea dataset [58], a medium effect represented by colorectal cancer [59], and a weak effect represented by obesity [60]. For each of these datasets, we identified the top ten most differentially abundant bacteria in the overall population as representative of “key mediating bacteria” (see Methods). Next, we simulated different trials, varying the numbers of patients in the FMT arm and the FMT response rates (i.e. proportion of patients which were FMT responders, represented by sampling from the “case” patients, vs. non-responders, represented by sampling from the “control” patients). We subsampled patients according to these parameter settings, identified differentially abundant genera, and compared these to the top ten genera identified from the entire datasets (Fig 4).

In cases where the microbial signature for FMT response is expected to be large (i.e. the difference in donor stools given to FMT responders vs. non-responders is as large as the effect of diarrhea effect on the microbiome), we found that small FMT trials would recover most of the top hits in the majority of cases. The power to detect associations decreased as FMT response rates became less balanced (i.e. response rates different from 50%), and in these cases trials would need to include up to 50 patients in the FMT arm to recover the key mediating taxa. For both medium and small effect sizes, however, prohibitively large FMT arms would be needed to recover most key mediating taxa regardless of FMT response rate. We found that when the microbial signature for FMT is equivalent to the effect of diseases like colorectal cancer on the microbiome, at least 100 patients are needed in the FMT arm to recover at least half of the most truly differentially abundant genera for most FMT trials. This simulation was performed at the genus-level, and underestimates the power needed to identify associations at finer taxonomic levels (e.g. OTU, ASV, or strain-level). In cases where strain-level biology is involved, FMT trials will need even more patients to be powered to find significant associations in retrospective analyses.

These results suggest that successful secondary analyses of microbiome data from FMT trials will require either very large FMT arms, investigating more targeted hypotheses, meta-analyses, or additional sample collections. For example, clinicians may consider pairing donor and patient samples or collecting longitudinal patient samples to increase power to make discoveries [57, 61]. They may also consider testing specific hypotheses developed before the trial, such as comparing the total abundance of butyrate producers between FMT responders and non-responders, or performing functional assays to measure specific metabolites thought to be associated with FMT response [57]. On the other hand, researchers wishing to identify the key taxa to include in an FMT drug may consider pursuing clinical trials in which identifying these taxa is the primary endpoint, and power them accordingly. In all cases, making microbiome sequencing data and associated patient-donor matching and clinical response metadata publicly available will allow for future meta-analyses that will have more power to make discoveries [34].