Metagenome-Wide Association Study and Machine Learning Prediction of Bulk Soil Microbiome and Crop Productivity

Abstract

Areas within an agricultural field in the same season often differ in crop productivity despite having the same cropping history, crop genotype, and management practices. One hypothesis is that abiotic or biotic factors in the soils differ between areas resulting in these productivity differences. In this study, bulk soil samples collected from a high and a low productivity area from within six agronomic fields in Illinois were quantified for abiotic and biotic characteristics. Extracted DNA from these bulk soil samples were shotgun sequenced. While logistic regression analyses resulted in no significant association between crop productivity and the 26 soil characteristics, principal coordinate analysis and constrained correspondence analysis showed crop productivity explained a major proportion of the taxa variance in the bulk soil microbiome. Metagenome-wide association studies (MWAS) identified more Bradyrhizodium and Gammaproteobacteria in higher productivity areas and more Actinobacteria, Ascomycota, Planctomycetales, and Streptophyta in lower productivity areas. Machine learning using a random forest method successfully predicted productivity based on the microbiome composition with the best accuracy of 0.79 at the order level. Our study showed that crop productivity differences were associated with bulk soil microbiome composition and highlighted several nitrogen utility-related taxa. We demonstrated the merit of MWAS and machine learning for the first time in a plant-microbiome study.

Insights to plant–microbe interactions provide opportunities to improve resistance breeding against root diseases in grain legumes

“…Experimental fields should be characterized not only for soil type, soil structure, nutrient content, and pH, but also for the microbial bulk soil and rhizosphere community. Chang, Haudenshield, Bowen, and Hartman () were able to identify groups of microbes associated with productivity of soybean based on a metagenome‐wide association study assessing bulk soil from different field sites. Subsequently, they used a machine‐learning algorithm to successfully predict soybean productivity based on microbiome data.…”

“…However, direct selection of plants promoting a beneficial soil microbiome community is very challenging, because few studies are available where microbial diversity is linked with improved plant health and because fields are not yet characterized according to their microbiome profile. In the future, further research of the soil microbiome and employment of additional tools like metagenome‐wide association studies will allow to predict traits such as disease resistance based on the rhizosphere community composition (Chang et al, ; Nogales et al, ).…”

Predicting Growth and Carcass Traits in Swine Using Metagenomic Data and Machine Learning Algorithms

“…Finally, the interaction of metagenomic information with time points highlight how, in our data, metagenomic information collected at week 15 largely outperform (∼ 10 %) all other time point (as well as null models). To the best of our knowledge, this is the first attempt to formally assess metagenomic predictions in livestock Comparable models have been used within the context of prediction of disease occurrence in human data 42 , as well as in soil microbiome associated with crop yield 43 . In both cases, the use of microbiome data achieved good predictive power, but given the vast diversity of both scope and measures, it is difficult to draw a direct comparison.…”

Predicting microbiomes through a deep latent space

“…We distinguish two major types of study. First, work on single cases, where a unique dataset or problem is addressed, for example, microbial composition being used to predict productivity in soil (Chang et al, 2017), contaminants and geochemical features in wells (Smith et al, 2015), presence/absence of disease due to changes in abundances of microbes over time (Bogart et al, 2019), or biomarkers of cancer (and the type of cancer) from the human blood microbiome (Poore et al, 2020). Second, more general studies are emerging, where multiple datasets of different origin are addressed together, applying the same prediction procedure or tool.…”