Novel metabolic features in Acinetobacter baylyi ADP1 revealed by a multiomics approach

Abstract

Expansive knowledge of bacterial metabolism has been gained from genome sequencing output, but the high proportion of genes lacking a proper functional annotation in a given genome still impedes the accurate prediction of the metabolism of a cell. To access to a more global view of the functioning of the soil bacterium Acinetobacter baylyi ADP1, we adopted a multi 'omics' approach. Application of RNA-seq transcriptomics and LC/MS-based metabolomics, along with the systematic phenotyping of the complete collection of single-gene deletion mutants of A. baylyi ADP1 made possible to interrogate on the metabolic perturbations encountered by the bacterium upon a biotic change. Shifting the sole carbon source from succinate to quinate elicited in the cell not only a specific transcriptional response, necessary to catabolize the new carbon source, but also a major reorganization of the transcription pattern. Here, the expression of more than 12 % of the total number of genes was affected, most of them being of unknown function. These perturbations were ultimately reflected in the metabolome, in which the concentration of about 50 % of the LC/MS-detected metabolites was impacted. And the differential regulation of many genes of unknown function is probably related to the synthesis of the numerous unidentified compounds that were present exclusively in quinate-grown cells. Together, these data suggest that A. baylyi ADP1 metabolism involves unsuspected enzymatic reactions that await discovery.

Keywords: Bacterial metabolism; Functional genomics; LC/MS-LTQ-Orbitrap; Metabolomics; Transcriptomics.

Fig. 1

The complete pathway for aromatic catabolism in A. baylyi ADP1. Enzymes are labeled within boxes by their genetic notation. Unnamed metabolites are labeled with circled numbers: 1 benzoate, 2 1,2-dihydro-1,2-dihydroxybenzoate (benzoate cis-glycol), 3 anthranilate, 4 salicylate, 5 alkyl salicylates, 6 benzylalkanoates, 7 benzyl alcohol, 8 benzaldehyde, 9 2-hydroxybenzylalkanoates (salicylalkanoates), 10 2-hydroxybenzyl alcohol, 11 2-hydroxybenzaldehyde, 12 4-hydroxybenzylalkanoates, 13 4-hydroxybenzyl alcohol, 14 4-hydroxybenzaldehyde, 15 4-hydroxybenzoate (p-hydroxybenzoate), 16 vanillate, 17 chlorogenate, 18 ferulate, 19 ferulyl-CoA, 20 vanillaldehyde, 21 p-coumarate, 22 p-coumaryl-CoA, 23 4-hydroxybenzaldehyde, 24 caffeate, 25 caffeyl-CoA, 26 protocatechualdehyde, 27 4-hydroxyphenylpropionate, 28 3,4-dehydroxyphenylpropionyl-CoA. Adapted from (Williams and Kay 2008)

Fig. 2

Number and functional classification of genes differentially expressed in A. baylyi ADP1 grown on quinate as compared with succinate. Each plot indicates the type of physiological role(s) and the total number of genes with increased or decreased expression within that category in cells grown on quinate (see also Online Resource 2, Table S-4)

Fig. 3

Visualization of the 451 LC/MS-detected metabolites of A. baylyi ADP1. The retention time on the ZIC-pHILIC column is represented by position on the x-axis. Mass-to-charge ratio is represented by position on the y-axis. Fold change is indicated by color and radius of each metabolite (log scale). Upper panels metabolites accumulating in quinate-grown cells. Lower panels metabolites accumulating in succinate-grown cells

Fig. 4

Differences for identified metabolites in ADP1 metabolomes. Alterations are expressed as log(fold). The confidence intervals of log(fold) at 95 % (red whiskers) were determined using Fieller’s formula (Fieller 1954) derived from the t test for the ratio of two means with unequal variances (Tamhane and Logan 2004). Data represent the average for 6 independent succinate metabolomes and 4 quinate metabolomes. Dotted blue lines correspond to a fold-change of 3. Asterisk indicates metabolites for which the fold-change is infinite (absence in quinate-grown cells) (Color figure online)