Function and Evolution of the Sox Multienzyme Complex in the Marine Gammaproteobacterium Congregibacter litoralis

Abstract

Core sets of sox genes were detected in several genome sequenced members of the environmental important OM60/NOR5 clade of marine gammaproteobacteria. However, emendation of media with thiosulfate did not result in stimulation of growth in two of these strains and cultures of Congregibacter litoralis DSM 17192(T) did not oxidize thiosulfate to sulfate in concentrations of one mmol L(-1) or above. On the other hand, a significant production of sulfate was detected upon growth with the organic sulfur compounds, cysteine and glutathione. It was found that degradation of glutathione resulted in the formation of submillimolar amounts of thiosulfate in the closely related sox-negative strain Chromatocurvus halotolerans DSM 23344(T). It is proposed that the Sox multienzyme complex in Congregibacter litoralis and related members of the OM60/NOR5 clade is adapted to the oxidation of submillimolar amounts of thiosulfate and nonfunctional at higher concentrations of reduced inorganic sulfur compounds. Pelagic bacteria thriving in the oxic zones of marine environments may rarely encounter amounts of thiosulfate, which would allow its utilization as electron donor for lithoautotrophic or mixotrophic growth. Consequently, in evolution the Sox multienzyme complex in some of these bacteria may have been optimized for the effective utilization of trace amounts of thiosulfate generated from the degradation of organic sulfur compounds.

Figure 1

Growth response of C. litoralis in LS medium containing 2.5 mM L-glutamate as carbon source and supplemented with various amounts of thiosulfate. Batch cultures were incubated in the dark under semiaerobic conditions. Growth over time determined as A ₆₆₀ values is indicated by open circles (no added thiosulfate), circles filled in grey (1 mM thiosulfate), and closed circles (10 mM thiosulfate). The concentrations of thiosulfate (triangles filled in grey) and sulfate (squares filled in grey) were monitored in cultures growing with 2.5 mM L-glutamate and 1 mM thiosulfate.

Figure 2

Growth response of C. litoralis and Chromatocurvus halotolerans in LS medium containing 2 mM L-glutathione as carbon source. Batch cultures of C. litoralis (a) and Chromatocurvus halotolerans (b) were incubated in the dark under semiaerobic conditions. Growth over time determined as A ₆₆₀ values is indicated by open circles. Concentrations of thiosulfate and sulfate are indicated by triangles and squares filled in grey, respectively.

Figure 3

Analyses of the transcription level of the soxB gene in C. litoralis under various incubation conditions. Cultures were grown in defined marine medium in the dark. The effect of thiosulfate was determined in media containing 2.5 mM L-glutamate as carbon source. The influence of reduced glutathione on soxB expression was determined by replacing this substrate with equimolar amounts of the amino acids L-glutamate, L-serine, and DL-glycine. The upper panel shows the results of a RT-PCR of the rpoZ gene, which was used to normalize mRNA levels in different samples of extracted RNA. The panel below shows results obtained with the same RNA samples after RT-PCR using specific soxB primers.

Figure 4

Growth response of C. litoralis in LS medium containing 2.0 mM L-glutamate as carbon source compared to medium supplemented with (a) 2.5 mM or (b) 0.5 mM thiosulfate. Batch cultures were incubated in the dark under semiaerobic conditions. Growth over time determined as A ₆₆₀ values is indicated by open circles (no added thiosulfate) or circles filled in grey (0.5 mM or 2.5 mM thiosulfate). Concentrations of thiosulfate and sulfate measured during growth are shown as triangles and squares filled in grey, respectively.

Figure 5

Phylogenetic dendrogram based on full-length protein sequences of SoxB illustrating the positions of members of the OM60/NOR5 clade (in bold). The SoxB sequence of Thermus thermophilus HB27 (Q72IT0) was used as outgroup (not shown). The displayed topology of the dendrogram is based on a reconstruction using the neighbor-joining algorithm. Bootstrap values (as percentages of 1000 resampling times) based on neighbor-joining and RAxML calculations are shown in the front of each node; provided that the branching was retrieved with both methods and at least with one reconstruction method, a value of 80% or above was obtained. Type strains are indicated by a superscript T. UniProt accession numbers of the used proteins are given in parentheses. Stable phylogenetic lineages of Sox proteins are indicated by dots or vertical line drawings followed by an arbitrary designation. The shown bar represents an estimated sequence divergence of 10%.

Figure 6

Phylogenetic dendrogram based on full-length protein sequences of SoxC illustrating the positions of members of the OM60/NOR5 clade (in bold). The SoxC sequence of Thermus thermophilus HB27 (Q72IT6) was used as an outgroup (not shown). For further details see legend of Figure 5.

Figure 7

Phylogenetic dendrogram based on full-length protein sequences of SoxA illustrating the positions of members of the OM60/NOR5 clade (in bold). The SoxA sequence of Thermus thermophilus HB27 (Q72IT2) was used as an outgroup (not shown). For further details see legend of Figure 5.