Insights into secondary metabolism from a global analysis of prokaryotic biosynthetic gene clusters

Abstract

Although biosynthetic gene clusters (BGCs) have been discovered for hundreds of bacterial metabolites, our knowledge of their diversity remains limited. Here, we used a novel algorithm to systematically identify BGCs in the extensive extant microbial sequencing data. Network analysis of the predicted BGCs revealed large gene cluster families, the vast majority uncharacterized. We experimentally characterized the most prominent family, consisting of two subfamilies of hundreds of BGCs distributed throughout the Proteobacteria; their products are aryl polyenes, lipids with an aryl head group conjugated to a polyene tail. We identified a distant relationship to a third subfamily of aryl polyene BGCs, and together the three subfamilies represent the largest known family of biosynthetic gene clusters, with more than 1,000 members. Although these clusters are widely divergent in sequence, their small molecule products are remarkably conserved, indicating for the first time the important roles these compounds play in Gram-negative cell biology.

Figure 1. ClusterFinder flowchart and distribution of BGC classes and counts

a, Flowchart of the four-step BGC prediction pipeline: (i) annotation of a genome sequence and compression to a string of Pfam domains, (ii) calculation of posterior probabilities of a BGC hidden state, (iii) clustering of genes that contain Pfam domain(s) with posterior probabilities of BGC hidden state above the threshold, and (iv) annotation of the predicted BGCs using an expanded version of the antiSMASH algorithm. b, Distribution of BGC classes for known (inset) and predicted BGCs. “Other” gene clusters include gene clusters from other known classes as well as a manually curated set of 1,024 putative gene clusters that fall outside known biosynthetic classes. Unexpectedly, 40% of all predicted BGCs encode saccharides, more than twice the size of the next largest class. c, Number of predicted BGCs by genome size. Most bacterial species follow a linear trend (the equation in the bottom-right corner); outliers (defined as having residuals >8) are colored red. d, The proportions of bacterial genomes devoted to secondary metabolite biosynthesis (left panel; 6.7% of species that devote >7.5% of their genome to biosynthesis are marked red), transcription (middle panel), and translation (right panel).

Figure 2. A systematic analysis of bacterial BGCs

Similarity network of known and putative BGCs, with the BGC similarity metric threshold at 0.5 (See also SI Figure 4). The topology of the network is robust to changes in the distance threshold, as described in the Extended Experimental Procedures. One connected component harbors most of the gene clusters (72%), and is largely composed of two linked subgraphs: one dominated by oligosaccharides and the other a mixture of nonribosomal peptides (NRPs) and polyketides/lipids, indicating that BGCs from these classes share a significant number of gene families with one another. Smaller BGC families with more unique compositions are represented at the bottom of the figure; only 812 BGCs (7.6%) do not have any connections with other BGCs at the chosen cutoff. A selection of node clusters within the network has been highlighted to show how gene cluster families form cliques within the network. The highlighted groups include widely distributed gene cluster families for O-antigens, capsular polysaccharides, carotenoids, and NRPS-independent siderophores, along with one of the lantibiotic BGC families and an unknown family of BGCs with type III polyketide synthases. The aryl polyene family that we characterized further in this study is shown in the middle of the network.

Figure 3. APE gene clusters comprise the largest known BGC family

a, Heat map and dendrogram of all 1,021 detected APE family gene clusters, based on Clusters of Orthologous Groups generated by OrthoMCL (Li et al., 2003) using our adapted version of the Lin distance metric (Lin et al., 2006) that includes sequence similarity. Light grey indicates the presence of one gene from a COG, whereas darker grey tones indicate the presence of two or three genes from a COG. The two BGC subfamilies that functioned as the starting point of our analysis (subfamilies 1 and 2) are shown in green and red, respectively, while the smaller BGC subfamily that includes the xanthomonadin and flexirubin gene clusters (subfamily 3) is shown in blue. The positions of the two experimentally targeted gene clusters (Ec for Escherichia coli CFT073 and Vf for Vibrio fischeri ES114) as well as the Xanthomonas campestris ATCC 33913 xanthomonadin (Xc) and Flavobacterium johnsonii ATCC 17061 flexirubin (Fj) gene clusters are indicated below the heat map. See SI Figure 5 for a version with more detailed annotations. b, Chemical structures obtained for the APE compounds from E. coli and V. fischeri, and the previously determined chemical structures of xanthomonadin and flexirubin. Note the difference in polyene acyl chain length as well as the distinct tailoring patterns on the aryl head groups. c, Bacterial pellets from strains harboring APE gene clusters showing the pigmentation conferred by aryl polyenes. d, Genetic architecture of the four characterized aryl polyene gene clusters. The inset in the Flavobacterium johnsonii flexirubin gene cluster is a sub-cluster putatively involved in the biosynthesis of dialkylresorcinol (Fuchs et al., 2013), which is acylated to an APE to form flexirubin. See SI Data File 1 for schematics of all 1,021 APE gene clusters from panel A.

Figure 4. APE gene clusters are widely but discontinuously distributed among Gram-negative bacteria

Presence/absence pattern of APE gene clusters across all complete genomes from selected bacterial genera, mapped onto the PhyloPhLan high-resolution phylogenetic tree (Segata et al., 2013). For each genus, the pie chart represents the percentage of sequenced genomes in which APE gene clusters are present (green) or absent (red). BGCs from the APE family occur throughout all subphyla of the Proteobacteria, as well as in a range of genera from the CFB group. The discontinuous presence/absence pattern suggests that gene cluster gain and/or loss has frequently occurred during evolution. A presence/absence mapping on all the genomes from our initial JGI dataset is provided in SI Data File 3.