Temporal Changes of Virus-Like Particle Abundance and Metagenomic Comparison of Viral Communities in Cropland and Prairie Soils

Abstract

During the last several decades, viruses have been increasingly recognized for their abundance, ubiquity, and important roles in different ecosystems. Despite known contributions to aquatic systems, few studies examine viral abundance and community structure over time in terrestrial ecosystems. The effects of land conversion and land management on soil microbes have been previously investigated, but their effects on virus population are not well studied. This study examined annual dynamics of viral abundance in soils from a native tallgrass prairie and two croplands, conventional till winter wheat and no-till canola, in Oklahoma. Virus-like particle (VLP) abundance varied across sites, and showed clear seasonal shifts. VLP abundance significantly correlated with environmental variables that were generally reflective of land use, including air temperature, soil nitrogen, and plant canopy coverage. Structural equation modeling supported the effects of land use on soil communities by emphasizing interactions between management, environmental factors, and viral and bacterial abundance. Between the viral metagenomes from the prairie and tilled wheat field, 1,231 unique viral operational taxonomic units (vOTUs) were identified, and only five were shared that were rare in the contrasting field. Only 13% of the vOTUs had similarity to previously identified viruses in the RefSeq database, with only 7% having known taxonomic classification. Together, our findings indicated land use and tillage practices influence virus abundance and community structure. Analyses of viromes over time and space are vital to viral ecology in providing insight on viral communities and key information on interactions between viruses, their microbial hosts, and the environment. IMPORTANCE Conversion of land alters the physiochemical and biological environments by not only changing the aboveground community, but also modifying the soil environment for viruses and microbes. Soil microbial communities are critical to nutrient cycling, carbon mineralization, and soil quality; and viruses are known for influencing microbial abundance, community structure, and evolution. Therefore, viruses are considered an important part of soil functions in terrestrial ecosystems. In aquatic environments, virus abundance generally exceeds bacterial counts by an order of magnitude, and they are thought to be one of the greatest genetic reservoirs on the planet. However, data are extremely limited on viruses in soils, and even less is known about their responses to the disturbances associated with land use and management. The study provides important insights into the temporal dynamics of viral abundance and the structure of viral communities in response to the common practice of turning native habitats into arable soils.

Keywords: agriculture; microbial ecology; soil virus; viral ecology; viral metagenomics.

FIG 1

Comparison of soil properties that significantly varied between land use and land management based on principal component analysis. Study sites include native tallgrass prairie, no-till canola, and conventional till wheat. Soil properties data were collected from August 2016 to July 2017.

FIG 2

VLP and bacterial abundance between different land usage and land management. (a) VLP abundance over a 1-year sampling period from October 2016 to September 2017. VLP abundance was calculated based on the dry weight of soil. (b) Bacterial cell abundance at corresponding sampling dates for VLP samples. Only time points of bacterial abundance that overlap with VLP abundance are shown in the figure.

FIG 3

Relationship between VLP abundance, bacterial abundance, land management, and soil and environmental factors based on structural equation modeling. Solid arrows indicate factors that had P values of <0.05. Dashed arrows indicate factors with marginal nonsignificant relationships (P < 0.1). Red arrows represent negative relationships, while blue arrows represent positive relationships. Native tallgrass prairie was used as the control, with the two management practices acting as treatments.

FIG 4

Overlap of viral community structure in soils from different intensities of land management. vOTUs were only considered to be present in an assembly if the vOTU had at least 75% sequence coverage. (a) Depiction of vOTUs in each virome and the number of shared vOTUs between the native and tillage viromes. (b) Bubble plot of the relative abundance of the shared vOTUs in the two viromes. vOTU abundance was normalized by the vOTU length and size of the individual assemblies then standardized by the minimal size of metagenomes (bp) across all samples. (c) Bar graph of portion of predicted genes identified in shared vOTUs. Unclassified genes had no high-quality matches in currently database. (d) Main groups of genes represented from shared vOTUs based on currently available virus protein sequences.

FIG 5

Gene sharing network of El Reno vOTUs clustered with RefSeq viral sequences. Solid colors indicate sequences from El Reno virus data set. Nodes are depicted as shapes of various colors that correspond to virus families within the RefSeq database. El Reno viruses in viral clusters that clearly grouped closely in the network on circled and labeled. Clusters in bolded circles represent those with El Reno viruses that could be taxonomically identified with the family-level taxonomy depicted. Viral clusters that contained only El Reno vOTUs and that did not interact with the main network are not pictured.