Mutation of a gene essential for ribosome biogenesis, EMG1, causes Bowen-Conradi syndrome

Abstract

Bowen-Conradi syndrome (BCS) is an autosomal-recessive disorder characterized by severely impaired prenatal and postnatal growth, profound psychomotor retardation, and death in early childhood. Nearly all reported BCS cases have been among Hutterites, with an estimated birth prevalence of 1/355. We previously localized the BCS gene to a 1.9 Mbp interval on human chromosome 12p13.3. The 59 genes in this interval were ranked as candidates for BCS, and 35 of these, including all of the best candidates, were sequenced. We identified variant NM_006331.6:c.400A-->G, p.D86G in the 18S ribosome assembly protein EMG1 as the probable cause of BCS. This mutation segregated with disease, was not found in 414 non-Hutterite alleles, and altered a highly conserved aspartic acid (D) residue. A structural model of human EMG1 suggested that the D86 residue formed a salt bridge with arginine 84 that would be disrupted by the glycine (G) substitution. EMG1 mRNA was detected in all human adult and fetal tissues tested. In BCS patient fibroblasts, EMG1 mRNA levels did not differ from those of normal cells, but EMG1 protein was dramatically reduced in comparison to that of normal controls. In mammalian cells, overexpression of EMG1 harboring the D86G mutation decreased the level of soluble EMG1 protein, and in yeast two-hybrid analysis, the D86G substitution increased interaction between EMG1 subunits. These findings suggested that the D-to-G mutation caused aggregation of EMG1, thereby reducing the level of the protein and causing BCS.

Figure 1

Analysis of the EMG1 Mutation Causing BCS (A) Sequence chromatograms of a BCS-affected patient (top) and a normal control (bottom). The position of the A→G mutation is indicated by an arrow. (B) Detection of the c.400A→G mutation in a Hutterite family. The region of EMG1 containing the c.400A→G mutation was amplified by PCR from the DNA samples of a family with BCS-affected children with the use of a primer that created a KpnI site only in the presence of the mutation. The samples were analyzed by agarose gel electrophoresis. The affected children (black diamonds) have only the 82 bp fragment, whereas the parents and two of the siblings are heterozygous for c.400A→G, as indicated by the presence of both 104 bp and 82 bp fragments, and one child is homozygous for normal EMG1, as indicated by the presence of only the 104 bp fragment. (C) Protein sequence alignment via Clustal W of the region of the EMG1 protein containing the c.400A→G, p.D86G mutation. The residues that are completely conserved in all orthologs are indicated with an asterisk, and the Asp (D) that is mutated in BCS is shown in red.

Figure 2

Comparative Molecular Model of the Human EMG1 Homodimer (A) Ribbon diagram of the modeled homodimer, with the individual monomers colored green and blue. Methyl donors are drawn as sticks. (B) Close-up view, showing the hydrogen-bonding interactions of D86 with R84 occurring at the N terminus of α helix 2. The two parallel α helices from each monomer (α helices 2 and 7) that form the core of the dimer interface are labeled α2 and α7 for each monomer. (C) Electrostatic-potential map of the solvent-accessible surface of the human EMG1 homodimer model. The map shows that the model predicts a positively charged region (blue) that is homologous to the RNA-binding groove of Nep1, and R84 is located in the center of this groove. Red indicates a negative charge.

Figure 3

Expression of EMG1 in Adult and Fetal Tissues Five nanograms of cDNA from various tissues was amplified by PCR with the use of EMG1- (top panel) or GAPDH-specific primers (bottom panel). Samples were taken at different cycle numbers, separated on a 2% agarose gel, and stained with ethidium bromide. The results for the samples taken at 26 cycles are shown for both EMG1 and GAPDH. Control cDNA was provided with each panel, and the PCR reaction was performed in the absence of cDNA for the blank. Each panel was normalized to the expression levels of four housekeeping genes: GAPDH, beta-actin, alpha-tubulin, and phospholipase A2.

Figure 4

EMG1 mRNA Expression and Protein Levels in Unaffected Control and Patient Fibroblasts (A) RNA analysis. Seven micrograms of total RNA isolated from unaffected control (Ctrl) fibroblasts or BCS-affected patient fibroblasts were separated on 1.2% agarose gel and transferred to a nylon membrane. The membrane was UV cross-linked and probed with labeled EMG1 (top panel) and GAPDH (bottom panel) cDNA probes. Film was exposed to the membrane for 7 hr at −80°C (EMG1) or for 2 hr at room temperature (GAPDH). EMG1 is 1068 bp and GAPDH is 1310 bp; 18S rRNA position is marked. (B) Immunoblot analysis of EMG1 protein levels. Twenty-five micrograms of nuclear lysates from unaffected control fibroblasts and BCS-affected patient fibroblasts were separated on a 10% gel by SDS-PAGE, and protein was detected by immunoblot with an EMG1 antibody (top panel). The blot was then stripped and reprobed for fibrillarin (FBL), a nuclear protein, so that equal loading was ensured (bottom panel).

Figure 5

Transient Expression of D86G Mutant and Wild-Type EMG1 in BHK Cells The RIPA-soluble fraction from BHK cells transiently expressing HA-tagged EMG1 was separated from the insoluble fraction by centrifugation. The insoluble fraction was then resuspended in RIPA, sonicated before loading of approximately 20 μg of protein, and separated in a 10% gel by SDS-PAGE. Protein was then transferred to a nitrocellulose membrane and detected by immunoblot with an HA antibody. Cells were cotransfected with pRCMVβ-gal to serve as a transfection control; loading was therefore corrected for both protein concentration and β-galactosidase activity. Abbreviations are as follows: V, vector control; WT, wild-type protein; M, mutant D86G protein.

Figure 6

Yeast Two-Hybrid Analysis of Dimerization of EMG1-D86G Interactions between wild-type EMG1 and the D86G mutant monomers, as well as each monomer with itself, were analyzed in the yeast two-hybrid system. Wild-type and mutant EMG1 were fused to the Gal4-activation or DNA-binding domain and tested against each other by coexpression in the two-hybrid yeast strain PJ69-4A. For quantification of binding affinity, β-galactosidase activity was measured. Data are from two independent yeast clones and the error bars represent standard deviation. A two-tailed, independent t test between Ad-EMG1+BdEMG1 and Ad-EMG1-D86G+Bd-EMG1-D86G showed that β-gal transcriptional activity in the mutant dimer was significantly higher with p = 0.0012.