Changes of soil bacterial diversity as a consequence of agricultural land use in a semi-arid ecosystem

Abstract

Natural scrublands in semi-arid deserts are increasingly being converted into fields. This results in losses of characteristic flora and fauna, and may also affect microbial diversity. In the present study, the long-term effect (50 years) of such a transition on soil bacterial communities was explored at two sites typical of semi-arid deserts. Comparisons were made between soil samples from alfalfa fields and the adjacent scrublands by two complementary methods based on 16S rRNA gene fragments amplified from total community DNA. Denaturing gradient gel electrophoresis (DGGE) analyses revealed significant effects of the transition on community composition of Bacteria, Actinobacteria, Alpha- and Betaproteobacteria at both sites. PhyloChip hybridization analysis uncovered that the transition negatively affected taxa such as Acidobacteria, Chloroflexi, Acidimicrobiales, Rubrobacterales, Deltaproteobacteria and Clostridia, while Alpha-, Beta- and Gammaproteobacteria, Bacteroidetes and Actinobacteria increased in abundance. Redundancy analysis suggested that the community composition of phyla responding to agricultural use (except for Spirochaetes) correlated with soil parameters that were significantly different between the agricultural and scrubland soil. The arable soils were lower in organic matter and phosphate concentration, and higher in salinity. The variation in the bacterial community composition was higher in soils from scrubland than from agriculture, as revealed by DGGE and PhyloChip analyses, suggesting reduced beta diversity due to agricultural practices. The long-term use for agriculture resulted in profound changes in the bacterial community and physicochemical characteristics of former scrublands, which may irreversibly affect the natural soil ecosystem.

Figure 1. Boxplots of the variation of community structure under same sites and land use based on DGGE profiles for a: Bacteria; b: Actinobacteria; c: Alphaproteobacteria; d: Betaproteobacteria.

Figure 2. Redundancy analysis of the effect of discriminative soil parameters on bacterial communities using the PhyloChip data.

Numbers in brackets indicate the percent of the total variance explained by each axis. Only these soil parameters which significantly (p<0.05 by 1000 times permutation tests) explained the bacterial community variation was shown.