The quakingviable mutation affects qkI mRNA expression specifically in myelin-producing cells of the nervous system

Abstract

The genetic lesion in the quakingviable (qk(v)) mutant mice is a deletion 5' to the qkI gene, resulting in severe hypomyelination. qkI produces several QKI protein isoforms via alternative splicing of the C-terminal coding exons. In the qk(v)/qk(v) brain, immunostaining of QKI proteins is diminished in an isoform-differential manner with undefined mechanisms. We examined the expression of QKI protein isoforms and qkI mRNA isoforms in the qk(v)/qk(v) mutants and the non-phenotypic wt/qk(v) littermates. Our results indicated significant reduction of all qkI mRNA isoforms in the central and peripheral nervous system during active myelination without detectable post-transcriptional abnormalities. In the early stage of myelin development, qkI mRNAs are differentially reduced, which appeared to be responsible for the reduction of the corresponding QKI protein isoforms. The reduced qkI expression was a specific consequence of the qk(v) lesion, not observed in other hypomyelination mutants. Further more, no abnormal qkI expression was found in testis, heart and astroglia of the qk(v)/qk(v) mice, suggesting that the reduction of qkI mRNAs occurred specifically in myelin-producing cells of the nervous system. These observations suggest that diminished qkI expression results from deletion of an enhancer that promotes qkI transcription specifically in myelinating glia during active myelinogenesis.

Figure 1

Expression of QKI protein isoforms in the qk^v/qk^v and the wt/qk^v littermates. (A) Schematic representation of QKI protein isoforms derived from alternative usage of the C-terminal exons. The QKA1 and QKA2 together with the single KH domain form the RNA-binding domain of QKI. (B) SDS–PAGE analysis of immunoprecipitated ³⁵S-QKI isoforms derived from in vitro translation. The input and immunoprecipitates for corresponding proteins are labeled on the left. (C) Immunoblot analysis of nuclear and cytoplasmic QKI isoforms in the C6 glioma cell line. The signals for the corresponding QKI isoforms are marked on the left. N, nuclear lysate; C, cytoplasmic lysate. (D) Reduction of QKI isoforms in the qk^v/qk^v brain stem. Whole cell lysates were prepared from the brain stem of a P10 qk^v/qk^v mouse and wt/qk^v littermate, followed by SDS–PAGE immunoblot analysis. The blot was re-probed by the antibody against the house-keeping protein eIF5α as a loading control. The detected proteins are marked on the left. The level of each QKI isoform was determined by densitometry analysis using the NIH image software and was normalized to that of the loading control. The relative quantity of QKI in the wt/qk^v mice was normalized to the non-phenotypic littermate control (%) and is indicated on the right.

Figure 2

QKI isoforms bind the 3′UTR of the mRNA encoding the 14 kDa MBP (M14). ³⁵S-QKI isoforms derived from in vitro translation were incubated with biotin-labeled full-length M14, or M14 lacking the 3′UTR (M14Δ3′UTR), before being captured by streptavidin-conjugated magnetic beads. The RNA-bound QKIs were quantitatively analyzed by scintillation counting, in which the RNA-binding activity by full-length M14 was set at 100% for normalization of binding by M14Δ3′UTR in parallel experiments. RNA binding for each QKI isoform was repeated four times (n = 4). Within each experiment, the binding activity of each QKI isoform is comparable. *P < 0.05, ***P < 0.001 (paired t-test).

Figure 3

RPA for detecting qkI mRNA isoforms. (A) Schematic representation of qkI mRNA isoforms illustrating the common 5′ domain and the alternative 3′ exons. The primers used in RT–PCR cloning of the 3′ coding region of each isoform are marked by arrowheads. The synthesis of full-length RPA probe is shown on the right. (B) RPA of total RNA isolated from wild-type mouse brain using the isoform-specific riboprobes. Each RPA is expected to generate an isoform-specific band and a common band for the rest of the isoforms. The size of predicted PRA products for each qkI isoform is illustrated on top of the corresponding panels, and marked by arrowheads in the corresponding RPA. Additional minor RPA products for qkI-5 and qkI-7 are marked by arrows, most likely representing undefined splicing junctions. MWM, molecular weight marker.

Figure 4

Reduction of qkI mRNAs in the CNS and PNS during myelin development of the qk^v/qk^v mutant. (A) Representative RPA gel of reduced qkI mRNA isoform expression in brain stem during active myelin development. The genotype and age of the animals are labeled at the top of each lane. The RPA products for each isoform are marked on the left. The RPA for the house-keeping mRNA GAPDH was used as a loading control. Phosphorimager reading of qkI isoforms in each lane was normalized to that of GAPDH and is shown in the bottom panel. (B) Quantification and statistical analysis of qkI mRNA levels in the brain stem of qk^v/qk^v mutant and wt/qk^v littermates. The level of qkI mRNA in the non-phenotypic wt/qk^v littermate control is set as 100% for normalization of reduced qkI mRNA in the qk^v/qk^v mutant in paired experiments. The number of experiments is indicated at the bottom for each qkI mRNA. **P < 0.01, ***P < 0.001 (paired t-test). (C) Reduced qkI mRNAs in the nuclei isolated from the P20 brain stem of qk^v/qk^v mutant. Nuclei were isolated from wt/qk^v and qk^v/qk^v littermates in parallel experiments, and the level of qkI mRNA was compared. The reduction level is comparable with that in the total RNA (Fig. 4A). (D) Reduction of qkI mRNAs occurred in both the CNS and PNS of the qk^v/qk^v mutant. (Top) Reduced qkI expression in qk^v/qk^v sciatic nerve at P16 and P20 detected by the qkI-5 probe. (Bottom) Statistical analysis of phosphorimager quantification of qkI mRNA in brain stem (BS), optic nerve (OPN) and sciatic nerve (SN) derived from the qk^v/qk^v and the wt/qk^v littermate control at P20. **P < 0.01, ***P < 0.001 (paired t-test, n = 3).

Figure 5

Reduced qkI expression specifically occurs in myelin-producing cells of the qk^v/qk^v brain. (A) qkI mRNAs are not reduced in the testis and heart of the qk^v/qk^v mutant. The genotypes and tissue types are labeled on top of the corresponding lanes. The RPA products are marked on the left. The house-keeping β-actin mRNA is used as a loading control. The ratio of phosphorimager reading of qkI-5 to actin is indicated at the bottom of each lane. (B) qkI mRNAs are reduced in the brain stem but not in the non- myelinating astrocytes. RNA was isolated from P18 brain stem, or from primary cultures of astrocytes derived from individual brain stems of the qk^v/qk^v mutant and the wt/qk^v littermate, as described in Materials and Methods, before being subjected to a parallel RPA. (Left) A representative RPA gel and (right) the statistical analysis of results derived from repeated experiments. ***P < 0.001 (standard t-test, n = 3).

Figure 6

Normal qkI expression in the jp^msd hypomyelination mutant at P18. (A) Reduction of QKI proteins in the qk^v/qk^v but not in the jp^msd hypomyelination mutant by immunoblot analysis. The genotype of each mutant and the littermate control is indicated at the top of the corresponding lanes and the proteins detected are marked on the left. Note the more severe reduction of MBP in the jp^msd hypomyelination mutant than in the qk^v/qk^v mutant. (B) Representative RPA indicating significant reduction of qkI mRNA in the qk^v/qk^v mutant but not in the jp^msd mutant. (C) Phosphorimager quantification of qkI mRNA levels in the qk^v/qk^v and the jp^msd mutant normalized to their non-phenotypic littermate controls. ***P < 0.001 (paired t-test, n = 3).

Figure 7

qkI mRNAs are engaged in normal translation in the qk^v/qk^v mutant brain. Cytoplasmic extracts were prepared from the brain stem of P19 qk^v/qk^v and their wt/qk^v littermates before being fractionated on a 15–45% (w/v) linear sucrose gradient. The separation of ribosomal components was monitored at OD254 and is shown on top of each panel. The distribution of qkI mRNAs and that of the house-keeping GAPDH mRNA in each gradient was analyzed by RPA and superimposed with the OD254 absorption profile. The fraction numbers are indicated at the bottom. EDTA treatment dissociates polyribosomes into subunits, resulting in a shift of mRNA into the top fractions.