Nanog safeguards early embryogenesis against global activation of maternal β-catenin activity by interfering with TCF factors

Abstract

Maternal β-catenin activity is essential and critical for dorsal induction and its dorsal activation has been thoroughly studied. However, how the maternal β-catenin activity is suppressed in the nondorsal cells remains poorly understood. Nanog is known to play a central role for maintenance of the pluripotency and maternal -zygotic transition (MZT). Here, we reveal a novel role of Nanog as a strong repressor of maternal β-catenin signaling to safeguard the embryo against hyperactivation of maternal β-catenin activity and hyperdorsalization. In zebrafish, knockdown of nanog at different levels led to either posteriorization or dorsalization, mimicking zygotic or maternal activation of Wnt/β-catenin activities, and the maternal zygotic mutant of nanog (MZnanog) showed strong activation of maternal β-catenin activity and hyperdorsalization. Although a constitutive activator-type Nanog (Vp16-Nanog, lacking the N terminal) perfectly rescued the MZT defects of MZnanog, it did not rescue the phenotypes resulting from β-catenin signaling activation. Mechanistically, the N terminal of Nanog directly interacts with T-cell factor (TCF) and interferes with the binding of β-catenin to TCF, thereby attenuating the transcriptional activity of β-catenin. Therefore, our study establishes a novel role for Nanog in repressing maternal β-catenin activity and demonstrates a transcriptional switch between β-catenin/TCF and Nanog/TCF complexes, which safeguards the embryo from global activation of maternal β-catenin activity.

Fig 1. Maternal TLEs do not likely contribute to the repression of maternal β-catenin activity.

(A) Detection of nuclear localization of maternal β-catenin in embryo at 512-cell stage by immunostainning against β-catenin. Signals were observed at animal view. Nuclei were co-stained with DAPI. Arrow heads indicate the nuclear accumulation of β-catenin. Scale bar, 50 μm. (B) In situ hybridization on cryosections of ovaries and WISH on unfertilized eggs (pink framed squares) showing wnt8a1, wnt8a2, ctnnb2, and nanog are maternally expressed during oogenesis and in unfertilized eggs. Scale bar, 100 μm. (C) In situ hybridization on cryosections of ovaries and WISH analysis of unfertilized eggs (pink framed squares) showing tle2a, tle3a, and tle3b are maternally expressed during oogenesis and in unfertilized eggs. Scale bar, 100 μm. (D) In comparison with tle2a, tle3a, and tle3b are significantly highly expressed in matured eggs as shown by RT-qPCR analysis. Error bars, mean ± SD, *P < 0.05, **P < 0.01. (E) The maternal -zygotic mutant of tle3a (MZtle3a) or tle3b (MZtle3b), or double mutant of tle3a and tle3b (MZtle3a, tle3b), showed no early developmental defect. Scale bar, 1 mm. (F) RT-qPCR analysis showing mRNA expression level of tle3a was significantly reduced in MZtle3a at 3 hpf. Error bars, mean ± SD, **P < 0.01. (G) RT-qPCR analysis showing mRNA expression level of tle3b was significantly reduced in MZtle3b at 3 hpf. Error bars, mean ± SD, **P < 0.01. The P values in this figure were calculated by Student t test. The underlying data in this figure can be found in S1 Data. hpf, hours post fertilization; MZtle3a, maternal -zygotic mutant of tle3a; MZtle3b, maternal -zygotic mutant of tle3b; RT-qPCR, reverse-transcription quantitative PCR; TLE, transducin-like enhancer of split; WISH, whole-mount in situ hybridization; WT, wild type.

Fig 2. Knockdown of nanog leads to dorsalization and posteriorization.

(A) WISH analysis showing nanog mRNA is maternally transcribed and vanishes at 75% epiboly stage. Scale bar, 100 μm. (B) Two different phenotypes are observed at 2 doses (0.5 ng/embryo, LD; 1.2 ng/embryo, MD) of nanog MO injected embryos, forebrain defect and dorsalization. Phenotype was observed at 36 hpf. N represents analyzed embryo number. Scale bar, 500 μm. (C) Western blot detection of Nanog in LD and MD nanog MO injected embryos. Nanog translation was blocked in all detected stages in the MD nanog MO injected embryos, and a low amount of Nanog protein can be detected at early stage in the LD nanog MO injected embryos. (D) Relative Nanog signal intensities in the western blot experiment (panel C). (E) WISH analysis showing expression of forebrain marker six3b and telencephalon marker emx1 were absent in LD MO injected embryos. krox20 was used as a stage-control marker. Red arrows indicate the expression region of six3b or emx1. Scale bar, 100 μm. (F) Statistical analysis of the embryos in panel E. N represents analyzed embryo number. (G) RT-qPCR analysis of six3b and emx1 in nanog morphants and WT embryos. Error bars, mean ± SD, ***P < 0.001. (H) WISH analysis showing 2 maternal β-catenin targets, boz and chd, were up-regulated in MD MO injected embryos. Scale bar, 100 μm. (I) Statistical analysis of the embryos in panel H. N represents analyzed embryo number. (J) RT-qPCR analysis of chd and boz in nanog morphants and WT embryos. Error bars, mean ± SD, ***P < 0.001. (K) WISH analysis showing expression of dorsal neuroectoderm marker otx2 was expanded in LD nanog MO injected embryos. Red arrow indicates the ventral expansion of otx2 signals. Scale bar, 100 μm. (L) Statistical analysis of the embryos in panel K. N represents analyzed embryo number. (M) WISH analysis showing the expression of ventral epidermal ectoderm marker foxi1 was eliminated in LD nanog MO injected embryos. Red arrow indicates the ventral absence of foxi1 signals. Scale bar, 100 μm. (N) Statistical analysis of the embryos in panel M. N represents analyzed embryo number. foxi1 and otx2 were detected at 90% epiboly stage, six3b and emx1 were detected at 2-somite stage, chd was detected at 5 hpf, and boz was detected at 4 hpf. The P values in this figure were calculated by Student t test. The underlying data in this figure can be found in S1 Data. hpf, hours post fertilization; LD, low dose; MD, moderate dose; MO, morpholino; RT-qPCR, reverse-transcription quantitative PCR; WISH, whole-mount in situ hybridization; WT, wild type.

Fig 3. Nanog negatively regulates Wnt/β-catenin signaling.

(A) The embryos injected with LD nanog MO (0.5 ng) exhibit the similar phenotypes—telencephalon defect—with wnt8a mRNA (1 pg per embryo) overexpressed embryos or tcf7l1a MO (1.6 ng per embryo) knocked down embryos. Phenotype was observed at 72 hpf. The numbers below the morphology pictures mean number of embryos showing representative phenotype/total number of embryos. Scale bar, 500 μm. (B) Embryos injected with titrated LDs of nanog MO (160 pg), wnt8a mRNA (0.1 pg), or tcf7l1a MO (800 pg) showed no obvious defect, respectively, and co-injection of nanog MO with wnt8a mRNA or tcf7l1a MO at the same doses resulted in forebrain truncation (headless). N represents analyzed embryo number. (C) WISH analysis showing the expression of zygotic Wnt target genes; sp5l was up-regulated in nanog morphant, whereas Wnt antagonist dkk1b and frzb were reduced, and this expression defect can be restored by knockdown of wnt8a. Scale bar, 100 μm. (D) Statistical analysis of the embryos in panel C. N represents analyzed embryo number. (E) Relative mRNA levels of sp5l, dkk1b, and frzb in nanog morphants and rescued embryos examined by RT-qPCR. Error bars, mean ± SD, **P < 0.01, ***P < 0.001. (F) WISH analysis showing the forebrain defect in nanog morphant could be rescued by knockdown of wnt8a1 and wnt8a2. Scale bar, 100 μm. (G) Statistical analysis of the embryos in panel F. N represents analyzed embryo number. (H) Relative mRNA level of six3b and emx1 in nanog morphants and rescued embryos examined by RT-qPCR. Error bars, mean ± SD, **P < 0.01, ***P < 0.001. sp5l was detected at 75% epiboly, frzb and dkk1b were detected at 6 hpf, six3b and emx1 were detected at 2-somite stage, krox20 was used as stage control. (I) TOPflash analysis showing β-catenin transcriptional activity was up-regulated in both of LD and MD of nanog MO injected embryos at 4 hpf. Error bars, mean ± SD, **P < 0.01. (J) TOPflash assay showing co-transfection of Nanog inhibited the up-regulated β-catenin transcriptional activity induced by β-catenin in a dose-dependent manner in HEK293T cells. Error bars, mean ± SD, *P < 0.05, **P < 0.01. (K) TOPflash analysis showing co-transfection of Nanog inhibited the up-regulated β-catenin transcriptional activity induced by ΔN-β-catenin (a constitutively activated type of β-catenin) in HEK293T cells. Error bars, mean ± SD, **P < 0.01. The P values in this figure were calculated by Student t test. The underlying data in this figure can be found in S1 Data. HEK293T cells, human embryonic kidney 293T cells; hpf, hours post fertilization; LD, low dose; MD, moderate dose; MO, morpholino; RT-qPCR, reverse-transcription quantitative PCR; WISH, whole-mount in situ hybridization; WT, wild type.

Fig 4. Maternal β-catenin activity is hyperactivated in nanog mutant.

(A) western blot showing translation of Nanog protein totally disappeared in MZnanog. Nanog protein can be detected as early as the 64-cell stage and vanished at 75% epiboly stage in WT embryos, whereas no Nanog protein was detected in MZnanog mutant embryos. (B) Immunolocalization of Nanog on cryosections of WT and MZnanog embryos at 4 hpf. Nanog is localized in the cell nuclei of WT embryos and disappeared in MZnanog embryos. Nuclei were co-stained with DAPI. Scale bar, 50 μm. (C) WISH analysis showing the injection of low dose of ctnnb2 mRNA (200 pg) induced slight up-regulation of boz and chd in WT embryos and induced massive expression of boz and chd in MZnanog embryos. boz was detected at 4 hpf, and chd was detected at 4.5 hpf. Scale bar, 100 μm. (D) Statistical analysis of the embryos in panel C. N represents analyzed embryo number. (E) Knockdown of ctnnb2 but not ctnnb1 rescued the developmental defects of MZnanog at gastrula stage. The numbers below the morphology pictures are the number of embryos showing representative phenotype/total number of embryos. Scale bar, 500 μm. (F) WISH analysis showing expression of chd and boz were expanded in MZnanog embryos, and knockdown of ctnnb2 (β2 MO) but not ctnnb1 (β1 MO) rescued these defects. boz was detected at 4 hpf, and chd was detected at 5 hpf. Scale bar, 100 μm. (G) Statistical analysis of the embryos in panel F. N represents analyzed embryo number. (H) Relative mRNA level of boz and chd in the embryos of WT, MZnanog, MZnanog co-injected with ctnnb1 MO (+ β1 MO) and MZnanog co-injected with ctnnb2 MO (+ β2 MO). Error bars, mean ± SD, **P < 0.01; NS means no significant difference. (I) TOPflash assay showing β-catenin transcriptional activity was significantly up-regulated in the embryos of MZnanog compared with WT, and co-injection of ctnnb2 MO (+ β2 MO) but not ctnnb1 MO (+ β1 MO) into MZnanog embryos significantly decreased the transcriptional activity. Error bars, mean ± SD, **P < 0.01, ***P < 0.001. The P values in this figure were calculated by Student t test. The underlying data in this figure can be found in S1 Data. hpf, hours post fertilization; MO, morpholino; MZnanog, maternal zygotic mutant of nanog; RT-qPCR, reverse-transcription quantitative PCR; WISH, whole-mount in situ hybridization; WT, wild type.

Fig 5. Transcriptional level of Wnt/β-catenin components and nuclear accumulation of β-catenin are not increased in MZnanog.

(A) WISH and (B, C) RT-qPCR showed the maternal transcription of wnt8a1, wnt8a2, and ctnnb2 were not affected in MZnanog eggs when compared with WT eggs. Scale bar, 100 μm. Error bars, mean ± SD, *P < 0.05; NS means no significant difference. (D) Western blot analysis of total β-catenin and nuclear β-catenin (active β-catenin) in WT, Mznanog, and wnt8a overexpressed embryos. Anti-total β-catenin was used as the β-catenin expression control and anti-β-actin was used as the internal control. A total of 2 pg of wnt8a mRNA was injected at the 1-cell stage in WT and used as a positive control. Embryos were collected at 4 hpf. Experiments were carried out for triplicates. (E) Statistical analysis of active β-catenin/total β-catenin level in panel D. Error bars, mean ± SD, ***P < 0.001. (F) Immunolocalization of β-catenin on whole-mount embryos at the 512-cell stage shows that nuclear β-catenin in both the WT and MZnanog was localized in dorsal margin cells and nondorsal cells, and nuclear β-catenin localization was not stimulated in MZnanog embryos. Signals were observed at animal view. Nuclei were co-stained with DAPI. Scale bar, 50 μm. The P values in this figure were calculated by Student t test. The underlying data in this figure can be found in S1 Data. hpf, hours post fertilization; MZnanog, maternal zygotic mutant of nanog; RT-qPCR, reverse-transcription quantitative PCR; WISH, whole-mount in situ hybridization; WT, wild type.

Fig 6. N-terminal of Nanog is required for its Wnt/β-catenin repressive activity.

(A) WISH analysis showing the expression of mesendoderm marker, mxtx2, strictly zygotic gene, blf, and microRNA-430 precursor (mir-430), and miR-430 target, sod1 in embryos of WT, MZnanog, MZnanog injected with nanog_FL, nanog_ΔC, or vp16-nanog mRNA. Expression of mxtx2, blf, and mir-430 was reduced, even absent, whereas expression of sod1 was significantly increased in MZnanog embryos; overexpression of nanog_FL, nanog_ΔC, or vp16-nanog restored the expression of mxtx2, blf, and mir-430 and cleaned the expression of sod1 in MZnanog embryos. mxtx2, blf, and sod1 were detected at 6 hpf, and mir-430 was detected at 4 hpf. Scale bar, 100 μm. (B) Statistical analysis of embryos in panel A. N represents analyzed embryo number. (C) Relative mRNA level of mxtx2, blf, and sod1 in WT, Mznanog, and the rescued embryos at 6 hpf examined by RT-qPCR analysis. Error bars, mean ± SD, **P < 0.01. (D) Overexpression of nanog_FL, nanog_ΔC, and vp16-nanog rescued the developmental defects of MZnanog. Both of nanog_FL and nanog_ΔC rescued embryos showed WT-like phenotype, whereas vp16-nanog rescued embryos still showed a forebrain defective phenotype. Phenotype was observed at 36 hpf. Scale bar, 100 μm. The numbers below the morphology pictures indicate number of embryos showing representative phenotype/total number of embryos. (E) WISH analysis showing the expression of neuroectoderm marker otx2 and forebrain marker six3b in embryos of WT, MZnanog, MZnanog injected with nanog_FL, nanog_ΔC, or vp16-nanog mRNA at 90% epiboly (for otx2) and 2-somite stage (for six3b). Expression of otx2 and six3b was absent in MZnanog embryos and restored by overexpression of nanog_FL or nanog_ΔC but not vp16-nanog. Red arrows indicate the absent expression of otx2 or six3b. Scale bar, 100 μm. (F) Statistical analysis of the embryos in panel E. N represents analyzed embryo number. (G) TOPflash assay showing co-transfection of nanog_FL (2 μg) or nanog_ΔC (2 μg) but not vp16-nanog (2 μg) significantly inhibited the up-regulated β-catenin transcriptional activity induced by β-catenin (0.5 μg) in HEK293T cells. Error bars, mean ± SD, **P < 0.01; NS means no significant difference. The P values in this figure were calculated by Student t test. The underlying data in this figure can be found in S1 Data. hpf, hours post fertilization; MZnanog, maternal zygotic mutant of nanog; nanog_FL, full length of Nanog; nanog_ΔC, C-terminal truncated Nanog; RT-qPCR, reverse-transcription quantitative PCR; vp16-nanog, Nanog homeodomain fusion with Vp16; WISH, whole-mount in situ hybridization; WT, wild type.

Fig 7. Nanog interferes with the binding of β-catenin to Tcf7 in vitro and in vivo.

(A) Nanog interacts with Tcf7 through its N terminal. Different Myc-tagged Nanog were constructed and co-transfection with HA-Tcf7 in HEK293T cells. Among all the mutated types of Nanog, only the N-terminal truncated Nanog (Nanog-ΔN) could not coprecipitate with Tcf7, indicating that Nanog physically interacts with Tcf7 through its N terminal. (B) Tcf7 interacts with Nanog through its GroBD. Different Myc-tagged Tcf7 were constructed and co-transfection with HA-Nanog in HEK293T cells. Among all the mutated types of Tcf7, only the GroBD deleted Tcf7 (Tcf7_ΔGroBD) could not coprecipitate with Nanog, indicating that Tcf7 binds with Nanog through GroBD. (C) Nanog and β-catenin competitively binds with Tcf7. Co-transfection of increasing amount of Nanog decreases the interaction between β-catenin and Tcf7 in a dose-dependent manner. When increased amount of Nanog was transfected into Tcf7 and β-catenin co-transfected cells, decreased amount of β-catenin could be coprecipitated. The molecular weight of HA-Nanog is around 55 Kda, and HA-β-catenin is around 100 KDa, so we could distinguish the 2 anti-HA bands by different protein sizes. (D) Co-transfection of Ctnnbip1 increased the binding affinity between Nanog and Tcf7. Two different amounts of HA-ctnnbip1 were co-transfected with Tcf7, Nanog and β-catenin in HEK293T cells; because Ctnnbip1 was overexpressed, an increased amount of Nanog was coprecipitated by myc-Tcf7. The molecular weight of HA-ctnnbip1 is around 10 KDa. Note that HA-β-catenin level was reduced when Ctnnbip1 was overexpressed. (E) Co-immunoprecipitation assay showed that increased amount of endogenous β-catenin could interact with Tcf7 in MZnanog mutants compared with WT embryos. Embryos were collected at 4 hpf. (F) The intensity ratio of β-catenin to Tcf7 in panel E. Error bars, mean ± SD, *P < 0.05. The P values in this figure were calculated by Student t test. The underlying data in this figure can be found in S1 Data. GroBD, Groucho binding domain; HEK293T cells, human embryonic kidney 293T cells; MZnanog, maternal -zygotic mutant of nanog; hpf, hours post fertilization; WT, wild type.

Fig 8. Confrontation of the β-catenin transcriptional activity in nucleus rescues the developmental defect of MZnanog.

(A) Injection of tcf7)_ΔβBD, tcf7_ΔHMG, or ctnnbip1 mRNA rescued the early developmental defects of MZnanog, whereas overexpression of tcf7_ΔGroBD did not. Phenotypes were observed at 8 hpf. At least 50 embryos were injected, and 3 independent experiments were performed. The numbers below the morphology pictures mean number of embryos showing representative phenotype/total number of embryos. Scale bar, 500 μm. (B) WISH analysis showing excessive and ectopic expression of chd in MZnanog was rescued by overexpression of tcf7)_ΔβBD, tcf7_ΔHMG, or ctnnbip1 at 4.5 hpf. Scale bar, 100 μm. (C) Statistical analysis of the embryos in panel B. N represents analyzed embryo number. (D) Relative mRNA level of chd in embryos of WT, MZnanog, and MZnanog injected with tcf7)_ΔβBD, tcf7_ΔHMG, or ctnnbip1 mRNA at 4.5 hpf examined by RT-qPCR. Error bars, mean ± SD, *P < 0.05, **P < 0.01, ***P < 0.001. (E) Relative β-catenin transcriptional activity in embryos of WT, MZnanog, and MZnanog injected with tcf7)_ΔβBD, tcf7_ΔHMG, or ctnnbip1 mRNA at 4 hpf examined by TOPflash assay. Error bars, mean ± SD, *P < 0.05, **P < 0.01, ***P < 0.001. (F) The model of Nanog repressing β-catenin transcriptional activity in nondorsal cell nuclei in WT embryo, and the ectopic activation of β-catenin transcriptional activity in the absence of Nanog in MZnanog embryo. In nondorsal cells of WT embryo, the amount of nucleus-deposited maternal Nanog (red cartoon object) is much higher than that of the nuclear β-catenin (green cartoon object); therefore Nanog binds to TCF (yellow cartoon object), and the β-catenin transcriptional activity is not activated. In nondorsal cells of MZnanog embryo, however, because of the absence of nanog in the nuclei, the small amount of nuclear β-catenin binds to TCF to activate the expression of dorsal genes (boz, chd, etc.), resulting in hyperdorsalization of the embryo. In dorsal cells of WT embryo, the amount of nuclear β-catenin is much higher than Nanog and facilitates the formation of β-catenin-TCF transcriptional complex to induce the expression of dorsal genes, boz, chd, etc. The P values in this figure were calculated by Student t test. The underlying data in this figure can be found in S1 Data. hpf, hours post fertilization; MZnanog, maternal zygotic mutant of nanog; RT-qPCR, reverse-transcription quantitative PCR; tcf7)_ΔβBD, β-catenin-binding domain deleted Tcf7, tcf7_ΔHMG, high mobility group (LEF1-binding domain) deleted Tcf7; tcf7_ΔGroBD, Groucho-binding domain deleted Tcf7; WISH, whole-mount in situ hybridization; WT, wild type.