CHD7 cooperates with PBAF to control multipotent neural crest formation

Abstract

Heterozygous mutations in the gene encoding the CHD (chromodomain helicase DNA-binding domain) member CHD7, an ATP-dependent chromatin remodeller homologous to the Drosophila trithorax-group protein Kismet, result in a complex constellation of congenital anomalies called CHARGE syndrome, which is a sporadic, autosomal dominant disorder characterized by malformations of the craniofacial structures, peripheral nervous system, ears, eyes and heart. Although it was postulated 25 years ago that CHARGE syndrome results from the abnormal development of the neural crest, this hypothesis remained untested. Here we show that, in both humans and Xenopus, CHD7 is essential for the formation of multipotent migratory neural crest (NC), a transient cell population that is ectodermal in origin but undergoes a major transcriptional reprogramming event to acquire a remarkably broad differentiation potential and ability to migrate throughout the body, giving rise to craniofacial bones and cartilages, the peripheral nervous system, pigmentation and cardiac structures. We demonstrate that CHD7 is essential for activation of the NC transcriptional circuitry, including Sox9, Twist and Slug. In Xenopus embryos, knockdown of Chd7 or overexpression of its catalytically inactive form recapitulates all major features of CHARGE syndrome. In human NC cells CHD7 associates with PBAF (polybromo- and BRG1-associated factor-containing complex) and both remodellers occupy a NC-specific distal SOX9 enhancer and a conserved genomic element located upstream of the TWIST1 gene. Consistently, during embryogenesis CHD7 and PBAF cooperate to promote NC gene expression and cell migration. Our work identifies an evolutionarily conserved role for CHD7 in orchestrating NC gene expression programs, provides insights into the synergistic control of distal elements by chromatin remodellers, illuminates the patho-embryology of CHARGE syndrome, and suggests a broader function for CHD7 in the regulation of cell motility.

Figure 1. CHD7 knockdown disrupts formation of the migratory, multipotent Neural Crest Like Cell (NCLC) population derived from human embryonic stem cells

(A) Schematic and morphological overview of the hNCLC derivation in vitro. H9 hESCs were collected by collagenase IV digestion and developed into compact spheres in neural induction medium (a and b). The neuroepithelial spheres spontaneously attached and formed rosette-like structures, with stellate morphology cells migrating away at 6 to 9 days of differentiation (c and d). Neural rosettes were manually removed and migratory cells formed a uniform population of stellate shaped cells on fibronectin-coated dishes (e). High magnification image showing representative morphology of the NCLCs (f). (B) hNCLCs express early neural crest markers. hNCLCs were immunostained with antibodies recognizing: p75ntr (a, green), AP2-α (b, red), NESTIN (b, green), SOX9 (c, green) and cell surface marker HNK1 (d, red); (lower panels show single channel images). Nuclei were stained with DAPI (a-d, blue in merged channel images). (C) Dox-inducible shRNA-mediated downregulation of CHD7 mRNA and protein levels.(a) CHD7 mRNA expression levels were analyzed by quantitative RT PCR of RNA samples prepared from hESCs infected with CHD7 shRNA or control shRNA lentiviruses and induced to differentiate as described in Figure 1A, either in the presence or in the absence of Dox. % of relative CHD7 expression at day 9 of differentiation is shown, with CHD7 expression in cells infected with a control shRNA lentivirus and cultured in the presence of Dox normalized to 100%. Error bars represent the standard deviation from two independent biological replicate experiments. (b) Extracts from shRNA lentivirus-infected cells differentiated in the presence of Dox, were normalized for protein concentration and analyzed by immunoblotting with α-CHD7 and α-RNA pol II antibodies. A two-fold dilution series is shown. (D) Formation of the migratory hNCLC population from CHD7 shRNA and control shRNA-expressing neural rosettes. hESC were infected with appropriate lentiviral shRNA vectors and induced to differentiate in the presence of Dox. At day 9 of differentiation, shRNA-expressing neural rosettes were identified by RFP expression at 5X magnification (a and c) and 10X magnification (b and d; images contain merged fluorescence and bright-field). Yellow arrows (c and d) highlight areas where RFP-expressing hNCLCs migrate out of the rosettes. The white arrow depicts RFP-negative cells migrating out of an RFP positive rosette (b). (E) Relative ratio of RFP expressing rosettes producing migratory cells. Migration defects as observed in C were quantified. The blue and red segments of the bar graph represent the percentage of rosettes from which hNCLCs did or did not, respectively, migrate out (N~200). Both red and non-red emigrating cells were included in the calculations. Error bars represent the standard deviations in two independent biological replicate experiments. (F) PAX3 and TWIST1 expression in CHD7 shRNA-infected cells. hESCs were infected in parallel with CHD7 or control shRNAs and induced to differentiate in the presence of Dox. (a) Neuroectodermal cells (attached and floating rosettes) were collected as a single cell suspension and stained with α-PAX3 antibody. The number of PAX3/RFP double-positive and PAX3 positive/RFP negative cells was determined by cell counting (N >500) (b) In the same experiment, the hNCLCs were isolated by discarding the floating spheres and dissecting out the attached rosettes (>95% of isolated cells showed nuclear TWIST1 expression). The number of TWIST1/RFP double-positive and TWIST1 positive/RFP negative cells was determined by cell counting (N >500).

Figure 2. CHD7 and its ATP-ase function are required for neural crest migration in vivo

(A) CHD7 mRNA expression during Xenopus embryogenesis. CHD7 expression was visualized by RNA in situ hybridization at indicated stages of development, showing diffuse pattern at the gastrula stage, but expression localized to the neural (arrow 1), neural crest (arrow 2) and preplacodal ectodermal (arrow 3) tissues at the late neurula stage. At the tailbud stages, CHD7 is expressed in the pharyngeal arches (arrow 4) and optic placode (arrow 5), as well as alongside the neural tube (arrow 6). (B) Morpholino mediated knockdown of CHD7 protein levels in Xenopus laevis embryos. Embryos were injected on both sides at the two-cell stage with morpholino oligonucleotide (MO) targeting either CHD7 or BRD7 at 3.3 uM concentration. Nuclei were extracted from these as well as uninjected control embryos at neurula stage. Whole nuclear lysates were normalized for protein concentrations and analyzed by immunoblotting with α-CHD7xl and α-RNA pol II antibodies. (C) Neural crest migration defect in CHD7 MO and hCHD7 ATP^K998R injected embryos. Two-cell stage embryos were injected with mRNA encoding a photo-activatable protein Kaede alone (a and b), Kaede and CHD7 MO (3.3 uM) (c), Kaede, CHD7 MO, and hCHD7 wt mRNA (1 ng) (d), or Kaede and hCHD7 ATP^K998R mRNA (9 ng) (e). At the neurula stage embryonic structures corresponding to a subset of the anterior neural and neural crest tissues were UV-irradiated to photo-convert Kaede protein from green to red fluorescence (schematics in Supplementary Figure 8A). Cell migration to the pharyngeal arches (PA) was assayed at the tailbud stage (orange arrows). (D) Effect of CHD7 knockdown on expression of transcription factors involved in neural crest formation. Two cell-stage embryos were injected with CHD7 MO at 3.3 uM asymmetrically into a single blastomere and analyzed by whole mount RNA in situ hybridization at neurula stage to visualize expression patterns transcription factors controlling: neural plate border territory specification (Msx1, Zic1, Pax3), maintenance of the competent border (MycII) and early neural crest formation (Sox9, Twist, Slug). Sox9 is detected in two major expression domains: the neural crest (blue arrow) and prospective otic placode (red arrow). (E) hCHD7 mRNA rescues defects in Sox9 and Twist expression. Two cell-stage embryos were co-injected with CHD7 MO (3.3 uM) and wild type full-length hCHD7 mRNA (1 ng) asymmetrically into a single blastomere. At late neurula stages the embryos were analyzed by whole mount RNA in situ hybridization. Representative examples of full and partial rescue are shown.

Figure 3. Overexpression of CHD7 ATPase mutant in Xenopus recapitulates CHARGE traits

(A) Craniofacial defects in Xenopus embryos expressing ATPase^K998R mRNA. Two-cell stage embryos were symmetrically injected with 9 ng of either ATPase^K998R or control mRNA (Kaede) on both sides and allowed to develop to the late tadpole stage (stage 45) for analysis of craniofacial cartilage by Alcian Blue staining and dissection. M: Meckel's cartilage, C: ceratohyle, B: basohyl, BA: branchial arch. (B) Coloboma of the eye with microphtalmia. Two-cell stage embryos were injected with ATPase^K998R mRNA asymmetrically into a single blastomere and allowed to develop to the late tadpole stage (stage 45). The eyes from uninjected and injected side were imaged under a stereomicroscope under the same magnification. Black arrows indicate the coloboma, a fissure that has not completely closed. (C) Defects in the formation of the otolith, a structure analogous to human ear. Four cell embryos were injected in one of the dorsal blastomeres with ATPase^K998R mRNA and raised to early tadpole stages (stage 40-44?). The left and right otolith was imaged at the same magnification. White arrows indicate three parts of the properly developed otolith. (D) The truncus arteriosus and cardiac outflow tract are abnormally positioned in ATPase^K998R expressing tadpoles. Transverse section through the stage 45 tadpoles expressing control mRNA (left panels) or ATPase^K998R mRNA (right panels). A: atrium, OFT: outflow tract, TA: truncus arteriosus, V: ventricle. Upper left section: The TA is located to the right and superior to the ventricle of the heart. Arrowheads indicate valves within the truncus arteriosus. Upper right section: Arrowhead indicating the TA in the ATPase^K998R mutant heart that is located to the right, but inferior to the ventricle of the heart. Lower left section: A relatively posterior transverse section of the control tadpole showing the normal connection of cardiac OFT to the ventricle of the heart. OFT is directly to the right and superiorly. Arrowheads indicate valves at the atrioventricular junction. Lower right section: Transverse section through a similar region of the ATPase^K998R expressing tadpole heart showing the aberrant orientation of cardiac OFT which is directed to the right and inferiorly.

Figure 4. CHD7 interacts with the PBAF complex in neural crest cells

(A) Identification of CHD7 protein partners in hNCLCs. A schematic representation of the purification process with polypeptides uniquely identified in CHD7 immunoaffinity purifications from NT2-derived or hESC-derived NCLCs shown on the left (see Methods for details). (B) Confirmation of association between CHD7 and PBAF. Nuclear extracts from hESC-derived hNCLCs were used as input for immunoprecipitation analyses with α-CHD7 or control antibodies. Bound polypeptides were analyzed by immunoblotting with antibodies recognizing common BAF/PBAF subunits as PBAF specific subunits, as indicated. (C) Schematic representation of the human PBAF complex. Arrows indicate unique PBAF subunits. (D) CHD7 co-immunoprecipitates with PBAFcomplex. Nuclear extracts from hESC-derived hNCLCs were used as input for immunoprecipitation analyses with α-BAF170, α-PB1 or control antibodies. Bound polypeptides were analyzed by immunoblotting with α-CHD7 antibody. (E) Effect of Brd7 and Brg1 MO injection on expression of transcription factors involved in neural crest formation. Eight cell-stage embryos were injected with either BRD7 MO (3.3 uM) or BRG1 MO (2.5uM) asymmetrically into a single dorsal anterior blastomere that gives rise to the dorsal-anterior part of the neurula embryo, as shown in the schematic. The late neurula stage embryos were analyzed by whole mount RNA in situ hybridization to visualize expression of Msx1, Zic1, Pax3, MycII, Twist and Slug.

Figure 5. Co-occupancy of CHD7 and BRG1 at distal elements

(A) Overlap between CHD7 and Brg1 occupancy in mouse ESCs. Brg1 bound regions occurring within mouse ENCODE regions (n=131) were identified in the genome-wide dataset reported by , and compared to 308 CHD7-bound regions within mouse ENCODE regions reported by . (B) Most CHD7-Brg1 sites are located more than 1 kb away from an annotated TSS. Distribution of CHD7-Brg1 co-occupied regions identified in A relative to annotated transcription start sites is shown. (C) CHD7 sites co-occupied by Brg1 display stronger and broader binding signals. Mouse ESC CHD7 binding signal (log2, y-axis) footprints were generated around CHD7 bound regions for: all mouse CHD7 bound regions (green), regions bound by both CHD7 and Brg1 (red) or by CHD7 alone (blue) as indicated above. Chd7 ChIP-chip signals used in footprint generation were obtained from Gene Expression Omnibus (GEO) data set GSE14460 . (D) CHD7 and BRG1 co-occupy neural crest specific distal enhancer controlling SOX9 expression.(a) Schematic representation of the SOX9 locus showing the relative position of the primer sets (P1-3) used for ChIP-qPCR analyses. NC^E: neural crest, and NGP^E: notochord, gut and pancreas SOX9 distal enhancer elements identified by . (b) ChIP-qPCR analysis of H3K4me1 levels at indicated genomic regions. Y axis shows percent of input recovery; (c) ChIP-qPCR analysis of CHD7 and Brg1 occupancy at indicated genomic regions. Y axis shows percent of input recovery. (E) CHD7 and BRG1 co-occupy a conserved distal element upstream from TWIST1 TSS.(a) Schematic representation of the TWIST1 locus showing the relative position of the primer sets (P1-2) used for ChIP-qPCR analyses. Conservation index for 31 eutherian mammals from ENSEMBL is shown at the bottom. (b) ChIP-qPCR analysis of H3K4me1 levels at indicated genomic regions. Y axis shows percent of input recovery; (c) ChIP-qPCR analysis of CHD7 and Brg1 occupancy at indicated genomic regions. Y axis shows percent of input recovery.

Figure 6. Cooperation between CHD7 and Brd7 in regulation of neural crest specific transcription and migration

(A) Synergistic effect of CHD7 and Brd7 MOs on Twist expression. Twist in situ hybridization analysis of embryos injected into a single dorsal-anterior blastomere at the 8-cell stage with indicated doses of CHD7 and/or Brd7 MOs. Representative images are shown and asymmetry in Twist expression is quantified at the bottom. P values were calculated by Fisher's exact test for count data. (B) Synergistic effect of CHD7 and Brd7 MOs on neural crest migration. Analysis of cell migration to PA in tadpoles derived from embryos co-injected into a single dorsal-anterior blastomere at the 8-cell stage with fluorescent lineage tracer (KikGR) and indicated doses of CHD7 and/or Brd7 MOs. Representative images are shown and migration to PA is quantified at the bottom. P values were calculated by Fisher's exact test for count data. (C) Model of CHD7 function in neural crest formation. We propose that CHD7 and PBAF cooperatively regulate activity of enhancer elements controlling expression of critical neural crest transcription factors. Activation of core components of neural crest transcriptional circuitry by coordinate action of CHD7 and PBAF in turn allows for transcriptional reprogramming of ectodermal border territory cells leading to epithelial to mesenchymal transition (EMT), acquisition of multipotency and migratory potential characteristic of the early neural crest cells.