An acquisition account of genomic islands based on genome signature comparisons

Abstract

Background: Recent analyses of prokaryotic genome sequences have demonstrated the important force horizontal gene transfer constitutes in genome evolution. Horizontally acquired sequences are detectable by, among others, their dinucleotide composition (genome signature) dissimilarity with the host genome. Genomic islands (GIs) comprise important and interesting horizontally transferred sequences, but information about acquisition events or relatedness between GIs is scarce. In Vibrio vulnificus CMCP6, 10 and 11 GIs have previously been identified in the sequenced chromosomes I and II, respectively. We assessed the compositional similarity and putative acquisition account of these GIs using the genome signature. For this analysis we developed a new algorithm, available as a web application.

Results: Of 21 GIs, VvI-1 and VvI-10 of chromosome I have similar genome signatures, and while artificially divided due to a linear annotation, they are adjacent on the circular chromosome and therefore comprise one GI. Similarly, GIs VvI-3 and VvI-4 of chromosome I together with the region between these two islands are compositionally similar, suggesting that they form one GI (making a total of 19 GIs in chromosome I + chromosome II). Cluster analysis assigned the 19 GIs to 11 different branches above our conservative threshold. This suggests a limited number of compositionally similar donors or intragenomic dispersion of ancestral acquisitions. Furthermore, 2 GIs of chromosome II cluster with chromosome I, while none of the 19 GIs group with chromosome II, suggesting an unidirectional dispersal of large anomalous gene clusters from chromosome I to chromosome II.

Conclusion: From the results, we infer 10 compositionally dissimilar donors for 19 GIs in the V. vulnificus CMCP6 genome, including chromosome I donating to chromosome II. This suggests multiple transfer events from individual donor types or from donors with similar genome signatures. Applied to other prokaryotes, this approach may elucidate the acquisition account in their genome sequences, and facilitate donor identification of GIs.

Figure 1

Overview of the two V. vulnificus chromosomes. Schematic representation of the δ* values and GC content of large putative horizontally transferred gene clusters in A) chromosome I and B) chromosome II of V. vulnificus CMCP6 using a window size of 5 kbp (x-axis represents chromosome position). Red depicts the low GC content GIs, while blue depicts the high GC content GIs. In green, a large ribosomal protein gene cluster is depicted (Rib). The horizontal dashed red line represents the average δ* value and GC percentage, respectively.

Figure 2

Hierarchic clustering with complete linkage of the V. vulnificus GIs (as described in table 1) based on the genome signature. Three non-anomalous genomic fragments (indicated with Vv5%, Vv10% and Vv25%) represent the conservative V. vulnificus (VvI) genomic variability, and this clade forms the cut-off value for the different clades (with the red dotted line; clades are indicated with black boxes). The Chlamydia clade consists of two genomic fragments (Ct1 and Ct2) and the genome sequence of C. trachomatis. VvII represents V. vulnificus chromosome II.

Figure 3

Hierarchic clustering with complete linkage of the V. vulnificus GIs from both chromosomes (as described in tables 1 and 2) based on the genome signature. For both chromosomes three non-anomalous genomic fragments are included, which represent the conservative V. vulnificus (VvI and VvII) genomic variability. VvI and VvII represent V. vulnificus chromosome I and II, respectively. VvI-3inter4 and VvI-101 represent the concatenated islands of VvI-3, VvI-inter and VvI-4 and of VvI10 and VvI-1 respectively.