Progressive Microbial Community Networks with Incremental Organic Loading Rates Underlie Higher Anaerobic Digestion Performance

Abstract

Although biotic interactions among members of microbial communities have been conceived to be crucial for community assembly, it remains unclear how changes in environmental conditions affect microbial interaction and consequently system performance. Here, we adopted a random matrix theory-based network analysis to explore microbial interactions in triplicate anaerobic digestion (AD) systems, which is widely applied for organic pollutant treatments. The digesters were operated with incremental organic loading rates (OLRs) from 1.0 g volatile solids (VS)/liter/day to 1.3 g VS/liter/day and then to 1.5 g VS/liter/day, which increased VS removal and methane production proportionally. Higher resource availability led to networks with higher connectivity and shorter harmonic geodesic distance, suggestive of more intense microbial interactions and quicker responses to environmental changes. Strikingly, a number of topological properties of microbial network showed significant (P < 0.05) correlation with AD performance (i.e., methane production, biogas production, and VS removal). When controlling for environmental parameters (e.g., total ammonia, pH, and the VS load), node connectivity, especially that of the methanogenic archaeal network, still correlated with AD performance. Last, we identified the Methanothermus, Methanobacterium, Chlorobium, and Haloarcula taxa and an unclassified Thaumarchaeota taxon as keystone nodes of the network.IMPORTANCE AD is a biological process widely used for effective waste treatment throughout the world. Biotic interactions among microbes are critical to the assembly and functioning of the microbial community, but the response of microbial interactions to environmental changes and their influence on AD performance are still poorly understood. Using well-replicated time series data of 16S rRNA gene amplicons and functional gene arrays, we constructed random matrix theory-based association networks to characterize potential microbial interactions with incremental OLRs. We demonstrated striking linkage between network topological features of methanogenic archaea and AD functioning independent of environmental parameters. As the intricate balance of multiple microbial functional groups is responsible for methane production, our results suggest that microbial interaction may be an important, previously unrecognized mechanism in determining AD performance.

Keywords: anaerobic digestion; microbial interaction; system performance.

FIG 1

Spearman correlation between network topological properties and AD parameters. The significance of correlations is determined as P < 0.05, and only significant correlations are visualized in the figure. avgK, the average degree of network; avgCC, average clustering coefficient; Centr.Clos, centralization of closeness; Gd, harmonic geodesic distance.

FIG 2

Interactions between microbial taxa revealed by the association network. (a) The two largest modules in the overall network constructed from all 66 samples. Nodes are colored according to OTU taxa. Labeled nodes are the hubs identified as module hubs. Node labels stand for the lowest taxonomic rank (A_ and B_ represent Archaea and Bacteria, respectively; p_, g_, and s_ represent phylum, genus, and species, respectively) of OTUs, and the node size is proportional to its degree. Blue edges represent positive associations, while red edges represent negative associations. (b) Interaction effect size between microbial taxa. The interaction effect size between any two groups was calculated as the difference of observed and random networks divided by the standard deviation. The heatmap shows only interactions with an effect size larger than 2.