A genomic survey of the fish parasite Spironucleus salmonicida indicates genomic plasticity among diplomonads and significant lateral gene transfer in eukaryote genome evolution

Abstract

Background: Comparative genomic studies of the mitochondrion-lacking protist group Diplomonadida (diplomonads) has been lacking, although Giardia lamblia has been intensively studied. We have performed a sequence survey project resulting in 2341 expressed sequence tags (EST) corresponding to 853 unique clones, 5275 genome survey sequences (GSS), and eleven finished contigs from the diplomonad fish parasite Spironucleus salmonicida (previously described as S. barkhanus).

Results: The analyses revealed a compact genome with few, if any, introns and very short 3' untranslated regions. Strikingly different patterns of codon usage were observed in genes corresponding to frequently sampled ESTs versus genes poorly sampled, indicating that translational selection is influencing the codon usage of highly expressed genes. Rigorous phylogenomic analyses identified 84 genes--mostly encoding metabolic proteins--that have been acquired by diplomonads or their relatively close ancestors via lateral gene transfer (LGT). Although most acquisitions were from prokaryotes, more than a dozen represent likely transfers of genes between eukaryotic lineages. Many genes that provide novel insights into the genetic basis of the biology and pathogenicity of this parasitic protist were identified including 149 that putatively encode variant-surface cysteine-rich proteins which are candidate virulence factors. A number of genomic properties that distinguish S. salmonicida from its human parasitic relative G. lamblia were identified such as nineteen putative lineage-specific gene acquisitions, distinct mutational biases and codon usage and distinct polyadenylation signals.

Conclusion: Our results highlight the power of comparative genomic studies to yield insights into the biology of parasitic protists and the evolution of their genomes, and suggest that genetic exchange between distantly-related protist lineages may be occurring at an appreciable rate in eukaryote genome evolution.

Figure 1

A plot of G+C content along the eleven finished contigs. G+C content calculated in 500-bp sliding windows in 50-bp steps along the finished contigs. The marks on the x axis indicate 1 kbp. Black lines, dark grey and light grey lines indicate annotated genes with sequence similarities in the public databases, hypothetical genes with matches in the EST data, and hypothetical genes without matches in the public databases or EST data, respectively. The position of the line on the y axis indicates the GC3_s value of the gene, an arrow indicates its direction (strand), and the annotated gene function is indicated. Average genomic G+C contents in the GSS clones are indicated by a dotted line. The order of the contigs is arbitrary.

Figure 2

5' and 3' untranslated regions in S. salmonicida. A: 5' regions of full-length genes from the completely sequenced contigs. The initiation codons of nine genes in the contigs (Figure 1) could be precisely identified based on sequence conservation compared to orthologs. The 5' sequences are aligned based on the initiation codons (indicated by a box). B: Sequence logo [107] around the termination codon of 134 Spironucleus cDNA sequences.

Figure 3

Structural organization of the two identified full-length candidate surface proteins with cysteine rich segments. A: Domain organization of the putative protein encoded by Sp10orf2 (573 residues) [GenBank:DQ812527]. The diagram shows the position of the seven furin-like domains (SM00261 – orange boxes) relative the transmembrane domain (blue box) as determined by SMART4.0 [125]. Several variations were inferred by SMART including some where furin-like domains corresponded to the related EGF-like domain (SM00181 – green boxes, see below). Due to the overlap between these inferences only the furin-like domains are shown for simplicity. The orientation of the protein in the membrane is N-terminus outside and C-terminus inside as inferred by TMHMM2.0 [126]. This is consistent with the hypothesis that cysteine-rich domains are facing the extracellular milieu where they could interact with other proteins. The alignment of the seven inferred furin-like domains as inferred by T-COFFEE [127] is shown below the diagram, with the positions of the first and last residue of each domain indicated on the left. Cysteines are highlighted in red and bold. No putative signal peptide was found with SignalP3.0 [128]. B: Domain organization of the putative protein encoded by Sp1orf4 (453 residues) [GenBank:DQ812518]. This protein has a similar structural organization as the one shown in A with three EGF-like domains inferred to face the external milieu. The three EGF-like domains were aligned manually. In addition, this sequence may have a signal peptide (indicated by a red box) since the S-score is positive in SignalP3.0 [128]. C: Domain organization of G. lamblia VSP417-6 protein (704 residues) [GenBank:AAF02907] [129] is shown for comparison. Four furin-like and two EGF-like domains identified by SMART4.0 [125] were aligned with T-COFFEE [127]. The G. lamblia sequence possesses a signal peptide according to SignalP3.0 [128]. All diagrams are drawn to scale.

Figure 4

Comparisons of codon usage in S. salmonicida and G. lamblia. A and B: The effective number of codons, N_c', plotted against the synonymous G+C content in the third codon position (GC3_s) of 1153 S. salmonicida genes (A) and 438 homologs in G. lamblia (B). Genes are represented by different colors and symbols according to the number of times they were sampled within the EST data. Genes identified to be involved in gene transfer and are shared with G. lamblia (LGT Diplo), or unique to S. salmonicida (LGT Spiro), are indicated by black and red squares, respectively (see Additional file 3). If the observed codon usage pattern is more uniform than expected by chance, the N_c' value is set to 61 [75, 117]. C and D: Correspondence analysis of the relative synonymous codon usage (RSCU) values for the same genes as in A and B for S. salmonicida (C) and G. lamblia (D). The candidate LGTs unique to S. salmonicida, and shared with G. lamblia, are indicated by red and black open squares, respectively.

Figure 5

Phylogenetic trees of five S. salmonicida genes from the phylogenomic analysis. ML tree of conceptually translated, aligned amino acid positions of (A) arginine deiminase, (B) conserved hypothetical protein, (C) conserved hypothetical protein, (D) carotenoid isomerase, and (E) rubrerythrin. Bootstrap support values > 50% are shown. Details about the phylogenetic analyses are found in the Methods section, and complete accession numbers and complete species names are found in Additional files 4 and 6. The unrooted trees are arbitrarily rooted for the presentation. The branches and species names are labeled according to their phylogenetic classification: Archaea (red), proteobacteria (grey), low G+C Gram positives (blue), cyanobacteria (green), and other eubacterial lineages (black). Eukaryotes are in boldface and labeled according to their classification into super-groups [18]: Opisthokonta (orange), Amoebozoa (purple), Chromalveolata (red), Archaeplastida (green), and Excavata (brown).