Evolution of a novel subfamily of nuclear receptors with members that each contain two DNA binding domains

Abstract

Background: Nuclear receptors (NRs) are important transcriptional modulators in metazoans which regulate transcription through binding to the promoter region of their target gene by the DNA binding domain (DBD) and activation or repression of mRNA synthesis through co-regulators bound to the ligand binding domain (LBD). NRs typically have a single DBD with a LBD.

Results: Three nuclear receptors named 2DBD-NRs, were identified from the flatworm Schistosoma mansoni that each possess a novel set of two DBDs in tandem with a LBD. They represent a novel NR modular structure: A/B-DBD-DBD-hinge-LBD. The 2DBD-NRs form a new subfamily of NRs, VII. By database mining, 2DBD-NR genes from other flatworm species (Schmidtea mediterranea and Dugesia japonica), from Mollusks (Lottia gigantean) and from arthropods (Daphnia pulex) were also identified. All 2DBD-NRs possess a P-box sequence of CEACKK in the first DBD, which is unique to 2DBD-NRs, and a P-box sequence of CEGCKG in the second DBD. Phylogenetic analyses of both DBD and ligand binding domain sequences showed that 2DBD-NR genes originate from a common two DBD-containing ancestor gene. A single 2DBD-NR orthologue was found in Arthropoda, Platyhelminths and Mollusca. Subsequent 2DBD-NR gene evolution in Mollusks and Platyhelminths involved gene duplication. Chromosome localization of S. mansoni 2DBD-NR genes by Fluorescent in situ hybridization (FISH) suggests that 2DBD-NR genes duplicated on different chromosomes in the Platyhelminths. Dimerization of Sm2DBDalpha indicates that 2DBD-NRs may act as homodimers, suggesting either that two repeats of a half-site are necessary for each DBD of 2DBD-NRs to bind to its target gene, or that each 2DBD-NR can recognize multiple sites.

Conclusion: 2DBD-NRs share a common ancestor gene which possessed an extra DBD that likely resulted from a recombination event. After the split of the Arthropods, Mollusks and Platyhelminths, 2DBD-NR underwent a recent duplication in a common ancestor of Mollusks, while two rounds of duplication occurred in a common ancestor of the Platyhelminths. This demonstrates that certain NR gene underwent recent duplication in Prostostome lineages after the split of the Prostostomia and Deuterostomia.

Figure 1

Functional domains of 2DBD-Nuclear receptors and sequence alignment of the LBD domain. A. Schematic representation of functional domains of 2DBD-NRs isolated from the fluke Schistosoma mansoni. hRORα (human RAR-related orphan receptor, NM_002943) as an example that shows the 'typical' modular structure of nuclear receptors, which contain an A/B domain, a C domain (DNA binding domain), a D domain (hinge region) and an E domain (ligand binding domain). Three Sm2DBD NRs (Sm2DBDα, Sm2DBDβ and Sm2DBDγ) exhibit a novel modular structure with an AB domain, two tandem DNA binding domains (C1 and C2), a D domain and an E domain. Sm2DBDα possesses an F domain at the C-terminal end of the E domain. The size of each domain in amino acids is indicated. B. Alignment of sequences from Helices 3–12 of the LBD domain of three S. mansoni 2DBD-NRs with that of members in NR subfamily I. Helices described in [64] are boxed, the signature sequence of the LBD (Tτ) is boxed with dash line. The autonomous activation domain (AF2-AD) is indicated and the conserved glutamic acids are shown in bold. Numbers at the end of each line indicate residue positions in the original sequence, amino acids of Sm2DBDα 1371–1527 and hRARα 453–462 are not shown in the alignment. Dark shaded areas show conserved residues in the signature sequence of the LBD. The accession numbers of the aligned human nuclear receptors can be found in additional file 2.

Figure 2

Alignment of the deduced peptide sequences of DNA binding domains of 2DBD-NRs. Each DBD is boxed with a solid line, P-box sequences (bold letters) are boxed with a dashed line. Stars identify the conserved cysteine residues that comprise the zinc finger of each DBD. Dashes indicate gaps in the sequence. The deduced amino acid sequence between DBDs for the NR from species other than S. mansoni is indicated with dots as we could not differentiate in the in silico analysis, exon sequence from intron sequence. All 2DBDs possess a P-box sequence of CEACKK in the first DBD and a P-box sequence of CEGCKG in the second DBD. Sm: flatworm Schistosoma mansoni, Se: flatworm Schmidtea mediterranea, Dj: flatworm Dugesia japonica, Lg: mollusk Lottia gigantea, Dp: arthropod Daphnia pulex.

Figure 3

Maximum Likelihood phylogenetic tree derived from sequences of DNA binding domains. Amino acid sequences were aligned with ClustalW. Phylogenetic relationships were examined by the Maximum Likelihood (ML) method under Jones-Taylor-Thornton (JTT) substitution model with a gamma distribution of rates between sites (eight categories, parameter alpha, estimated by the program) using PHYML (v2.4.4)). Support values for the tree were obtained by bootstrapping a 100 replicates and are indicated above each branch. Branches under the threshold value of 27 (this value was set to support subfamily II as a monophyletic group) were shown as polytomies. The same data set was also tested by Bayesian inference. The trees were started randomly with four simultaneous Markov chains running for 5 million generations. Bayesian posterior probabilities (PPs) were calculated using a Markov chain Monte Carlo (MCMC) sampling approach implemented in MrBAYES v3.1.1, the PPs values are shown below each branch or after the ML bootstrapping value separated by a slash. Star indicates the node obtained form by Bayesian inference which was different from that obtained by ML method. The accession number of each sequence used for the phylogenetic analysis can be found in additional file 2 and 3.

Figure 4

Maximum Likelihood phylogenetic tree produced using sequences of NR ligand binding domain. Phylogenetic relationship was examined by the Maximum Likelihood (ML) method as described for Fig. 3. Support values for the tree were obtained by bootstrapping a 100 replicates and are indicated above each branch. Branches under the threshold value of 46 (this value was set to support the subfamily IV as a monophyletic group) were shown as polytomies. Bayesian inference with the same methods as in Fig. 3, by running 3 million generations. The PPs are shown below each branch or after the ML bootstrapping value separated by a slash. Star indicates the node obtained form by Bayesian inference which was different from that obtained by the ML method. The accession number of each sequence used for phylogenetic analysis can be found in additiona1 file 2 and 3.

Figure 5

Protein-protein interaction of Sm2DBDα. A. Yeast two hybrid assays show that S. mansoni 2DBD-NR (Sm2DBDα) can act as a homodimer but not as a heterodimer with SmRXR1 and SmRXR2. Yeast AH109 was transformed with 1 μg of the following co-transformats: 1) pGBK-Sm2DBDα-C-F/pACT-SmRXR1, 2) pGAD-Sm2DBDα/pAs-SmRXR1-C-F, 3) pGBK-Sm2DBDα-C-F/pGAD-Sm2DBDα, 4) negative control plasmid pSV40/plamin C, 5) positive control plasmid pSV40/p53, 6) pGBK-Sm2DBDα-C-F/pACT-SmRXR2, 7) pGAD-Sm2DBDα/pAS-SmRXR2. Transformed yeast were plated on SD/-trp-leu and SD/-trp-his-leu-ade plus 3 mM 3-amino-1,2,4-triazole (3-AT). The results show that Sm2DBDα can form a homodimer but not a heterodimer with SmRXRs. B. GST pull down verified that the S. mansoni 2DBDα-E-F domain, in which the dimer interface is located, can form a homodimer in vitro.

Figure 6

Origin and duplication of 2DBD-NRs in metazoans. A. Deduction from traditional view of metazoan phylogeny. The common ancestor of 2DBD-NR originated from DBD duplication in a common bilaterian ancestor (red branch). The fact that 2DBD-NRs are present in both Acoelomates and Coelomates supports this view. Star indicates duplication event(s). B. Deduction from the molecular view of metazoan phylogeny. The common ancestor of 2DBD-NR might originate in a common Protostome ancestor (red branch). The fact that 2DBD-NRs are present in both Ecdysozoa and Lophotrochozoa supports this view. Another possibility is that 2DBD-NR might originate in a common ancestor of the Bilateria and was lost in the Deuterostome lineage after the split of Protostomes and Deuterostomes (blue branch). Ac: Acoelomates, Ar: Arthropoda, B: Bilateria, C: Chordates, Ce: Caenorhabditis elegans, Cn: Cnidarians, Co: Coelomates, De: Deuterostomes, Dp: Daphnia pulex, Dr: Drosophila, E: Ecdysozoans, Ec: Echinoderms, Lg: Lottia gigantean, Lo: Lophotrochozoans, M: metazoa, Pl: Platyhelminths, Po: Poriferans, Pr: Protostomes, Ps: Pseudocoelomates, Se: Schmidtea mediterranea, Sm: Schistosoma mansoni, Ec: Echinoidea. indicates 2DBD-NR, the number of indicates the number of 2DBD-NRs found in that taxon.

Figure 7

Duplication of 2DBD-NRs. A. Maximum Likelihood phylogenetic tree derived from sequences in the first and the second DBD of 2DBD-NRs. Phylogenetic relationship was examined by the Maximum Likelihood method as described for Fig. 3. Support values for the tree were obtained by bootstrapping a 100 replicates and are indicated above each branch. Branches under the threshold value of 45 were shown as polytomies. Bayesian inference with the same methods as in Fig. 3 running 5 million generations. The PPs are shown below each branch or after the ML bootstrapping value separated by a slash. B. Figure shows that the common ancestor gene of 2DBD-NRs underwent duplication after the split of the Arthropods, Molluscs and Platyhelminths. In Mollusks, the orthologue gene (γ) underwent a duplication giving rise to the α/β gene. In Platyhelminths, the orthologue gene (γ) underwent a duplication giving rise to a new gene, this new gene underwent a recent duplication to give birth to the two present genes (α and β genes). All three genes are present in the flatworm S. mansoni and the planarian S. mediterranea suggesting that the two rounds of 2DBD-NR duplication occurred in a common ancestor of the Platyhelminths.

Figure 8

Chromosome localization of S. mansoni 2DBD-NRs. S. mansoni 2DBD-NRs are located on different chromosomes as determined by FISH mapping using BAC DNA as a probe. a. Sm2DBDα (BAC: CHOR-18I10), b. Sm2DBDβ (BAC: SmBAC1 54O21), insert is the Z chromosome, c. Sm2DBDγ (BAC: SmBAC1 18F9). Chromosome numbers are indicated.

Figure 9

Quantitative real-time RT-PCR shows mRNA expression of S. mansoni 2DBD-NRs. Normalized gene expression (ΔΔCT) of Sm2DBDα, Sm2DBDβ and Sm2DBDγ were standardized to the relative quantities of S. mansoni tubulin. For graphical representation of expression, the normalized expression was recalculated by dividing the expression level for each gene in each stage by the expression level of Sm2DBDβ from sporocysts, the highest expression level. egg: eggs, sp: daughter sporocysts, cer: cercariae, 21d: 21-day worms, 28d: 28-day worms, f: adult female worms and m: adult male worms.