Ecological dynamics imposes fundamental challenges in community-based microbial source tracking

Abstract

Quantifying the contributions of possible environmental sources ("sources") to a specific microbial community ("sink") is a classical problem in microbiology known as microbial source tracking (MST). Solving the MST problem will not only help us understand how microbial communities were formed, but also have far-reaching applications in pollution control, public health, and forensics. MST methods generally fall into two categories: target-based methods (focusing on the detection of source-specific indicator species or chemicals); and community-based methods (using community structure to measure similarity between sink samples and potential source environments). As next-generation sequencing becomes a standard community-assessment method in microbiology, numerous community-based computational methods, referred to as MST solvers hereafter have been developed and applied to various real datasets to demonstrate their utility across different contexts. Yet, those MST solvers do not consider microbial interactions and priority effects in microbial communities. Here, we revisit the performance of several representative MST solvers. We show compelling evidence that solving the MST problem using existing MST solvers is impractical when ecological dynamics plays a role in community assembly. In particular, we clearly demonstrate that the presence of either microbial interactions or priority effects will render the MST problem mathematically unsolvable for MST solvers. We further analyze data from fecal microbiota transplantation studies, finding that the state-of-the-art MST solvers fail to identify donors for most of the recipients. Finally, we perform community coalescence experiments to demonstrate that the state-of-the-art MST solvers fail to identify the sources for most of the sinks. Our findings suggest that ecological dynamics imposes fundamental challenges in MST. Interpretation of results of existing MST solvers should be done cautiously.

Keywords: microbial interactions; microbial source tracking; priority effects.

Figure 1

Ecological dynamics imposes fundamental challenges in microbial source tracking. (Top) A sink is obtained by simultaneously mixing three sources (without any species overlap) with mixing proportions (1/3, 1/3, 1/3). Due to the presence of microbial interactions, the initial composition of the sink community (right after the mixing, which is typically not available for microbial source tracking [MST]) can be significantly different from the final composition (which is the input of MST solvers). Applying any MST solver to the final sink composition will yield different results from applying the MST solver to the initial sink composition. (Bottom) Due to the priority effects, three sources mixed with different orders can result in a total $3!=6$ different sinks with different compositions, even if the mixing proportions of the sources are exactly the same for the different mixing orders.

Figure 2

Impact of microbial interactions on microbial source tracking (MST). (A, B) Performance of SourceTracker (red), fast expectation‐maximization for microbial source tracking (FEAST) (blue), and random forest (green) in simulated sinks with different network connectivity $C$ (A) and characteristic interaction strengths $\sigma$ (B). Each simulation was performed using three synthetic sources and 100 synthetic sinks. Accuracy of each method is measured as the coefficients of determination ($R^2$) of the estimated proportions. Each point represents the mean $R^2$ for three independent source sets; error bars show s.e.m ($n=3$) of the mean of $R^2$. (C, D) Initial and final steady compositions (we only show the relative abundance of the first 10 species for visualization purposes) of a sink with different network connectivity (C) and characteristic interaction strengths (D). In (A, C), the diagonal elements of the interaction matrix $\mathbf{A}$ are set to be $a_{\mathit{ii}}=-5C$ to ensure the stability of the community, and the characteristic interaction strength $\sigma =0.1$. In (B, D), we set $a_{\mathit{ii}}=-5\sigma$ to ensure stability and network connectivity $C=0.5$. In all the simulations, we set the intrinsic growth rate $r=0.5$ for all the species. We added a pseudo number ${ϵ=10}^{-6}$ to the x‐axis for visualization purposes.

Figure 3

Impact of priority effects on microbial source tracking (MST). (A, B) We synthesized three sources, $S_1$, $S_2$, and $S_3$, whose species collections do not have any overlap (30 species for each source). We mixed these three sources using six different mixing orders but with the same mixing proportions $(\frac{1}{3},\frac{1}{3},\frac{1}{3})$, rendering six sinks. We set the network connectivity $C=0.5$, the characteristic interaction strength $\sigma =1$, and the intrinsic growth rate $r=0.5$ for each species. We set the diagonal elements of interaction matrix $\mathbf{A}$ to be $a_{\mathit{ii}}=-5$ to ensure stability. (A) Dimensionality reduction using t‐SNE shows the variations among the six sinks generated from the six different mixing orders. (B) Contribution of each source to the six simulated sinks estimated by fast expectation‐maximization for microbial source tracking (FEAST). (C) Between‐sink and between‐source Bray‐Curtis dissimilarity. We synthesized five sources. The species collection of each source includes $N_{\mathrm{u}}$ unique species and the remaining $(90-5N_{\mathrm{u}})$ species are shared by all the sources. We mixed these five sources with the same mixing proportions $(\frac{1}{5},\frac{1}{5},\frac{1}{5},\frac{1}{5},\frac{1}{5})$ in 100 different mixing orders randomly chosen from the total $5!=120$ mixing orders. We set the network connectivity $C=0.5$, the characteristic interaction strength $\sigma =1$, and the intrinsic growth rate $r=0.5$ for each species. We set the diagonal elements of interaction matrix $\mathbf{A}$ to be $a_{\mathit{ii}}=-10$ to ensure stability. p‐values were calculated using one‐sided Wilcoxon test.

Figure 4

Evaluation of fast expectation‐maximization for microbial source tracking (FEAST) using fecal microbiota transplantation (FMT) data from Staley et al. (A) Donor‐recipient relationship. Each trajectory represents a donor and its corresponding recipients at up to five time points. Trajectories of recipients who responded to FMT (i.e., responders) are colored in yellow. Trajectories of nonresponders are colored in blue. (B) Principal coordinates analysis (PCoA) plot based on the Bray‐Curtis dissimilarity. (C) True donor (red cycle) versus predicted donor (green square) of each recipient. For each post‐FMT community (sink), among all the seven donors, we referred to the one whose fecal sample has the highest contribution estimated by FEAST as the “predicted donor.” Here, we only showed the results for the first 65 sinks for visualization purposes (see Supporting Information: Figure S3 for results of the remaining 194 sinks). Sources: microbiome samples of donors and the pre‐FMT samples of recipients; Sinks: post‐FMT samples of recipients.

Figure 5

Evaluation of fast expectation‐maximization for microbial source tracking (FEAST) using data from pairwise community coalescence experiments. (A) Schematic diagram of the community coalescence experiments. There are 24 source communities (stool samples from 24 healthy individuals). Each sink community is obtained by mixing two different source communities ex vivo and the final composition of each sink was obtained from metagenomic sequencing of samples collected after 11 days of the ex vivo mixing. (B) True sources (red cycles) versus predicted sources (green squares) of each sink. For each sink, among the 24 known sources, the two sources with the top‐two largest contributions predicted by FEAST were referred to as the predicted sources. Here, we only showed the first 64 sinks for the visualization purpose (see Supporting Information: Figure S5 for results of the remaining 192 sinks).