Histone H3K79 methyltransferase Dot1L is directly activated by thyroid hormone receptor during Xenopus metamorphosis

Abstract

Background: Thyroid hormone (T3) is important for adult organ function and vertebrate development. Amphibian metamorphosis is totally dependent on T3 and offers a unique opportunity to study how T3 controls postembryonic development in vertebrates. Earlier studies have demonstrated that TR mediates the metamorphic effects of T3 in Xenopus laevis. Liganded TR recruits histone modifying coactivator complexes to target genes during metamorphosis. This leads to nucleosomal removal and histone modifications, including methylation of histone H3 lysine (K) 79, in the promoter regions, and the activation of T3-inducible genes.

Results: We show that Dot1L, the only histone methyltransferase capable of methylating H3K79, is directly regulated by TR via binding to a T3 response element in the promoter region during metamorphosis in Xenopus tropicalis, a highly related species of Xenopus laevis. We further show that Dot1L expression in both the intestine and tail correlates with the transformation of the organs.

Conclusions: Our findings suggest that TR activates Dot1L, which in turn participates in metamorphosis through a positive feedback to enhance H3K79 methylation and gene activation by liganded TR.

Figure 1

Mouse and Xenopus tropicalis DOT1L proteins are highly conserved. (A) Schematic alignment of mouse and Xenopus tropicalis DOT1L. The gray boxes represent conserved domains for S-adenosylmethionine (AdoMet or SAM)-dependent methyltransferases (AdoMet-MTases). The black boxes indicate structural maintenance of chromosome (SMC) domains. GenBank accession numbers: Mouse (m; Mus musculus) Dot1a (AAP42293) [50], Xenopus tropicalis (Xt) Dot1L (XP_002937984). Note that the N-terminal region is highly conserved between mouse and Xenopus tropicalis Dot1L due to the presence of the AdoMet-MTase and SMC domains. (B) The amino acid sequences of the nearly perfectly conserved AdoMet-MTase domain of mouse and Xenopus DOT1L. The AdoMet-binding site, which is essential for the methyltransferase activity, is boxed.

Figure 2

Xenopus tropicalis Dot1L is induced in the intestine and tail upon treatment of premetamorphic tadpoles with T3. Stage 54 tadpoles were treated with 10 nM T3 for 2 days and total RNA was isolated from the intestine (A) and tail (B). qRT-PCR was conducted to examine the expression of Dot1L mRNA. Dot1L expression was normalized to the expression of the control gene EF1α (elongation factor 1α). Error bars indicate s.e.m.

Figure 3

Upregulation of Xenopus tropicalis Dot1L expression in the intestine and tail during natural metamorphosis. Total RNA was isolated from the intestine (A) and tail (B) at the indicated developmental stages from premetamorphosis to the end of metamorphosis (stage 66). The expression of Dot1L mRNA was determined by qRT-PCR as in Figure 2. Error bars indicate s.e.m. Note that there were no tail samples at stage 66 (B) as the tail is completely resorbed by stage 66.

Figure 4

TR binds to the putative TREs in Dot1L gene in vitro. (A) Schematics diagram of the putative TREs in Xenopus tropicalis Dot1L gene. The TREs are shown as white boxes with arrows indicating the orientation of TREs. The black box shows exon. (B) The sequences of wild type and mutant Dot1L TRE1 and TRE2 used in the gel shift assay in comparison to the consensus TRE and the TRE of Xenopus laevis TRβA gene. Bold letters show conserved nucleotides and the mutated nucleotides are underlined. (C) Both Dot1L TRE1 and TRE2 compete against the TRE of Xenopus laevis TRβA for binding to TR/RXR heterodimers. The labeled Xenopus laevis TRβA promoter TRE was mixed with in vitro translated TR/RXR heterodimers in the presence or absence of 4×, 20×, or 100× unlabeled wild type or mutant Dot1L TRE1 or TRE2 as indicated. The reaction mixture was analyzed by gel retardation assay. Arrowhead indicates the TR/RXR-TRE complex. Note that both wild-type Dot1L TREs competed while the mutations reduced or abolished their ability to compete for binding to TR/RXR. (D) Dot1L TRE2 has higher affinity than TRE1 for TR/RXR heterodimer in vitro. Gel mobility shift assay was done as in (C) except with 20× unlabeled Xenopus laevis TRβA TRE, Dot1L TRE1, and Dot1L TRE2. Note that Xenopus laevis TRβA TRE competed most effectively, followed by Dot1L TRE2, while Dot1L TRE1 was least effective.

Figure 5

The activation of Xenopus tropicalis Dot1L promoter by liganded TR in vivo is dependent on TRE2. On the top of each panel shows a schematic diagram of the promoter construct with or without mutations in TRE1 (mTRE1) and/or TRE2 (mTRE2). The lower portion shows the promoter activity in the frog oocytes. For the transcription assay, wild type or mutant promoter construct was co-injected with the control Renilla luciferase construct phRG-tk into the nuclei of the oocytes with or without prior cytoplasmic injection of mRNAs for Xenopus tropicalis TRα and RXRβ. The oocytes were incubated at 18°C overnight in the presence or absence of 100 nM T3 and then used for dual luciferase assays. The relative activities of the firefly luciferase to Renilla luciferase were plotted. Error bars indicate s.e.m. Note that mutation of TRE1 alone had no effect on the regulation of the promoter by TR/RXR both in the presence or absence of T3 while mutating of TRE2 alone or together with TRE1 abolished the regulation by TR/RXR, suggesting that TRE2 is the functional TRE

Figure 6

TR binds to the TRE2 in Dot1L promoter in the intestine and tail during T3-induced metamorphosis. Stage 54 tadpoles were treated with or without T3 for 2 days. The intestine (A) or tail (B) was isolated for ChIP assay with a polyclonal antibody against TR (top) or Id14 (bottom), a negative control for antibody specificity. The immunoprecipitated DNA was analyzed by qPCR for the presence of the TRE regions of Dot1L promoter. A region of exon 2 (ex2) of Dot1L gene was analyzed as a negative control for binding specificity. Note that strong binding of TR to TRE2 in Dot1L gene was observed in the absence of T3 in premetamorphic tadpoles and that this binding was increased slightly upon T3 treatment in both organs. TR signal at the TRE1 was very low in both organs with or without T3 treatment, consistent with the results from transcription and in vitro TR binding assays. Only background signals were observed with the anti-ID14 antibody. Error bars indicate s.e.m