Mouse nuclear myosin I knock-out shows interchangeability and redundancy of myosin isoforms in the cell nucleus

Abstract

Background: Nuclear myosin I (NM1) is a nuclear isoform of the well-known "cytoplasmic" Myosin 1c protein (Myo1c). Located on the 11(th) chromosome in mice, NM1 results from an alternative start of transcription of the Myo1c gene adding an extra 16 amino acids at the N-terminus. Previous studies revealed its roles in RNA Polymerase I and RNA Polymerase II transcription, chromatin remodeling, and chromosomal movements. Its nuclear localization signal is localized in the middle of the molecule and therefore directs both Myosin 1c isoforms to the nucleus.

Methodology/principal findings: In order to trace specific functions of the NM1 isoform, we generated mice lacking the NM1 start codon without affecting the cytoplasmic Myo1c protein. Mutant mice were analyzed in a comprehensive phenotypic screen in cooperation with the German Mouse Clinic. Strikingly, no obvious phenotype related to previously described functions has been observed. However, we found minor changes in bone mineral density and the number and size of red blood cells in knock-out mice, which are most probably not related to previously described functions of NM1 in the nucleus. In Myo1c/NM1 depleted U2OS cells, the level of Pol I transcription was restored by overexpression of shRNA-resistant mouse Myo1c. Moreover, we found Myo1c interacting with Pol II. The ratio between Myo1c and NM1 proteins were similar in the nucleus and deletion of NM1 did not cause any compensatory overexpression of Myo1c protein.

Conclusion/significance: We observed that Myo1c can replace NM1 in its nuclear functions. Amount of both proteins is nearly equal and NM1 knock-out does not cause any compensatory overexpression of Myo1c. We therefore suggest that both isoforms can substitute each other in nuclear processes.

Figure 1. Preparation of NM1 knock-out cassette.

(A) WT genomic locus of Myo1c gene. Short homology arm (SA), floxed part (FP), and long homology arm (LA) of appropriate length (0.9; 0.3; 1.7 kb respectively), were cloned to pEasyFlox vector carrying neomycin (NeoR) and thymidine kinase (ThK) selection genes (B). Black lines represent genomic sequences; red line represents sequences derived from pEasyFlox vector. (B). (C) Genomic loci of Myo1c gene with excision of exon -1; P1 – P6 represent different primers needed for genotyping of ES cells and knock-out mice, yellow triangles represent loxP recombination sites. (D) Genotyping of NM1 knock-out mice by PCR. P5 and P6 primers were used to distinguish between wild type (+/+), heterozygous (+/−) and knock-out (−/−) animals. (E) Western blot analysis of NM1 levels in NM1 wild type (+/+) and knock-out (−/−) mice. Fifteen micrograms of protein per lane was loaded, and probed for NM1. Equal loading was monitored by Coomassie Brilliant Blue staining of the band corresponding to actin.

Figure 2. Red blood cells related phenotype in NM1 knock-out mice.

Figure 3. NM1 knock-out has no effect on cell proliferation and Pol I transcription.

(A) Proliferation of NM1 KO cells (NM1 −/−) is not altered in comparison to WT cells (NM1 +/+). 1×10⁵ cells were seeded on plates (20% confluence; day 0) and let to grow for six days when number of cells was counted again (day 6). (B) Pol I transcription rate in NM1 KO (NM1 −/−) and WT (NM1 +/+) cells is equal. RNA from exponentially growing cells was isolated and expression of 45S pre-rRNA was measured by RT-qPCR. Expression of 45S pre-rRNA is compared relatively to GAPDH expression. Data are presented as mean +/− SD.

Figure 4. Ratio between NM1 and Myo1c is nearby equal.

(A) HeLa cells were fractionated into cytosolic and nuclear fractions. NM1 and Myo1c amounts were quantified using double fluorescent labeling of western blot membranes after normalization to NM1-GFP band. (B) Total amounts of NM1+Myo1c were compared in mouse skin fibroblasts derived from NM1 knock-out and NM1 wild type mouse. Beta actin signal was used as loading normalizer. (C) Total amounts of NM1+Myo1c were compared in lungs and stomach from NM1 knock out and NM1 wild type mouse. GAPDH signal was used as loading normalizer. (D) The graph shows the amount of NM1 and Myo1c after densitometric quantification of bands from figures 4B and 4C showing the ratio between NM1 and Myo1c as compared to actin/GAPDH expression.

Figure 5. Myo1C is able to function in Pol I and Pol II transcription without changes in its expression level.

(A) The level of nascent rRNA was decreased to 80% of WT levels in NM1/Myo1c knock-down cells (U2OS+C8). An overexpression of mouse NM1 (U2OS+C8+NM1) or Myo1c (U2OS+C8+M1c) resistant to shRNA causes restoration of Pol I transcription to almost endogenous levels. As a negative control were used U2OS cells with transduced empty pLKO1.1 vector (U2OS+NC). (B) Both NM1-Flag and Myo1c-Flag interact with Pol II. Extracts from cells overexpressing NM1-Flag and Myo1c-Flag were co-immunoprecipitated with Flag antibody and control IgG. Immunoprecipitates were analyzed by western blotting with antibodies against Flag, Pol II CTD subunit and Myo1c (tail domain recognizing both NM1 and Myo1c). (C) NM1 knock-out does not cause compensatory changes in expression of Myo1c. Expression of Myo1c was measured by RT-qPCR and compared relative to GAPDH expression. Data are presented as mean +/− SD. *** p<0.001.