Examining ancient inter-domain horizontal gene transfer

Abstract

Details of the genomic changes that occurred in the ancestors of Eukarya, Archaea and Bacteria are elusive. Ancient interdomain horizontal gene transfer (IDHGT) amongst the ancestors of these three domains has been difficult to detect and analyze because of the extreme degree of divergence of genes in these three domains and because most evidence for such events are poorly supported. In addition, many researchers have suggested that the prevalence of IDHGT events early in the evolution of life would most likely obscure the patterns of divergence of major groups of organisms let alone allow the tracking of horizontal transfer at this level. In order to approach this problem, we mined the E. coli genome for genes with distinct paralogs. Using the 1,268 E. coli K-12 genes with 40% or higher similarity level to a paralog elsewhere in the E. coli genome we detected 95 genes found exclusively in Bacteria and Archaea and 86 genes found in Bacteria and Eukarya. These genes form the basis for our analysis of IDHGT. We also applied a newly developed statistical test (the node height test), to examine the robustness of these inferences and to corroborate the phylogenetically identified cases of ancient IDHGT. Our results suggest that ancient inter domain HGT is restricted to special cases, mostly involving symbiosis in eukaryotes and specific adaptations in prokaryotes. Only three genes in the Bacteria + Eukarya class (Deoxyxylulose-5-phosphate synthase (DXPS), fructose 1,6-phosphate aldolase class II protein and glucosamine-6-phosphate deaminase) and three genes-in the Bacteria + Archaea class (ABC-type FE3+-siderophore transport system, ferrous iron transport protein B, and dipeptide transport protein) showed evidence of ancient IDHGT. However, we conclude that robust estimates of IDHGT will be very difficult to obtain due to the methodological limitations and the extreme sequence saturation of the genes suspected of being involved in IDHGT.

Keywords: blast; eschericia coli; horizontal gene transfer; node height test.

Figure 1

Distributional profile method. A first screening for genes involved in ancient IHGT was done using the distributional profile method. Based on the most accepted hypothesis of phylogenetic relationships between the three domains of life, genes that occur in Eukarya and Bacteria, but not in Archaea, or genes that occur in Archaea and Bacteria, but not in Eukarya were potential candidates to have been horizontally transferred between domains. Genes found in one of those two phyletic distributional categories were further tested for HGT (see text).

Figure 2

Maximum parsimony analysis of the gene Glucosamine-6-phosphate (nagB, COG0363). The tree depicts the strict consensus of 6 most parsimonious reconstructions. Bootstrap values above 75 are shown on nodes. Rooting was done with the paralog gene Phosphogluconate. E stands for Eukarya, B for Bacteria, and A for Archaea. The number 1 refers to sequences of the gene under analysis, and the number 2 to sequences of the paralog used for rooting.

Figure 3

The node height test. (a) If an Euk-Bac distribution was caused by gene loss, than the E1-B1 (Eukarya to Bacteria) average distance is expected to be higher than the average B1-B1 (Bacteria to Bacteria) distance. (b) However, if eukaryotic genes (E1) were gained by transfer from a particular group of bacteria (B1), than the average E1-B1 distance should not be higher than the average B1-B1 distance. These predictions were done based on the assumption that substitution rates are homogeneous across taxa.