1. Microbial communities are increasingly recognised as crucial for animal health. However, our understanding of how microbial communities are structured across wildlife populations is poor. Mechanisms such as interspecific associations are important in structuring free-living communities, but we still lack an understanding of how important interspecific associations are in structuring gut microbial communities in comparison to other factors such as host characteristics or spatial proximity of hosts.

2. Here we ask how gut microbial communities are structured in a population of North American moose (Alces alces). We identify key microbial interspecific associations within the moose gut and quantify how important they are relative to key host characteristics, such as body condition, for predicting microbial community composition.

3. We sampled gut microbial communities from 55 moose in a population experiencing decline due to a myriad of factors, including pathogens and malnutrition. We examined microbial community dynamics in this population utilizing novel graphical network models that can explicitly incorporate spatial information.

4. We found that interspecific associations were the most important mechanism structuring gut microbial communities in moose and detected both positive and negative associations. Models only accounting for associations between microbes had higher predictive value compared to models including moose sex, evidence of previous pathogen exposure, or body condition. Adding spatial information on moose location further strengthened our model and allowed us to predict microbe occurrences with ~90% accuracy.

5. Collectively, our results suggest that microbial interspecific associations coupled with host spatial proximity are vital in shaping gut microbial communities in a large herbivore. In this case, previous pathogen exposure and moose body condition were not as important in predicting gut microbial community composition. The approach applied here can be used to quantify interspecific associations and gain a more nuanced understanding of the spatial and host factors shaping microbial communities in non-model hosts.

The data was collected from fecal samples taken from live captured moose (55 individuals). Amplicons were sequenced sequenced on the Illumina MiSeq platform.

Raw sequencing reads were processed using the University of Minnesota’s metagenomics-pipeline (a complete description of the pipeline can be found at https://bitbucket.org/jgarbe/gopher-pipelines/wiki/metagenomics-pipeline.rst)

Representative OTU sequences were aligned against the Greengenes version 13_8 core set (DeSantis et al., 2006b) using UCLUST (Edgar, 2010) with QIIME default parameters.  

See Appendix 1 & 2 for details on the analyical pipeline used.

OTU_taxonomy_updated.csv - OTU data from the MiSeq runs. Singletons are removed and the table rarified to 100,859 reads.

envAll.csv - host and environmental data from the moose in this study

otu_jaccard.csv - functional information from a sepparate PiCRUST analysis.

Appendix1_GitHubCode.R  -  R Code used to conduct our analysis.

ggordiplot.R  - extra code used to overal a dendrogram onto a nMDS ordination.