DNA breaks and chromosome pulverization from errors in mitosis

Abstract

The involvement of whole-chromosome aneuploidy in tumorigenesis is the subject of debate, in large part because of the lack of insight into underlying mechanisms. Here we identify a mechanism by which errors in mitotic chromosome segregation generate DNA breaks via the formation of structures called micronuclei. Whole-chromosome-containing micronuclei form when mitotic errors produce lagging chromosomes. We tracked the fate of newly generated micronuclei and found that they undergo defective and asynchronous DNA replication, resulting in DNA damage and often extensive fragmentation of the chromosome in the micronucleus. Micronuclei can persist in cells over several generations but the chromosome in the micronucleus can also be distributed to daughter nuclei. Thus, chromosome segregation errors potentially lead to mutations and chromosome rearrangements that can integrate into the genome. Pulverization of chromosomes in micronuclei may also be one explanation for 'chromothripsis' in cancer and developmental disorders, where isolated chromosomes or chromosome arms undergo massive local DNA breakage and rearrangement.

Figure 1. Micronuclei from lagging chromosome develop DNA breaks

a, Schematic of the experiment. b, Representative images of micronucleated G₁ (6h), S (16h), G₂ (22h) and irradiated RPE-1 cells (IR) labelled for DNA (blue), centromeres (ACA, red), and γ-H2AX (green). Insets show enlarged images of micronuclei (MN). Scale bars, 10 μM. c-d, Percentage of primary nuclei (PN, blue bars) and centric MN (red bars) with (c) γ-H2AX foci and (d) TUNEL labelling (3 experiments, n=100). Errors bars, s.e.m.

Figure 2. DNA breaks in a human artificial chromosome targeted to a micronucleus

a, (Right) Schematic. (Left) Fluorescence in situ hybridisation images of HAC (red) in a primary nucleus (+Dox) or MN (-Dox). b, Images of micronucleated cells as in Fig. 1b (enlarged and brightened in insets). Scale bars, 10 μM c-d, Percentage of primary nuclei (blue bars) and centric MN (red bars) with (c) γ-H2AX foci and (d) TUNEL labelling. (3 experiments, n=100). Errors bars, s.e.m.

Figure 3. DNA damage in micronuclei results from aberrant DNA replication

a-c, DNA replication requirement for acquisition of DNA damage in MN. a, RPE-1 cells were synchronized as in Fig. 1a and released into media with (+TH) or without (-TH) 2 mM thymidine. Cells were co-labelled for TUNEL (green) and cyclin B1 (red). Shown are images from 22 h sample. Scale bar, 10 μM. b,c, Percentage of TUNEL-positive primary nuclei (blue bars) and MN (red bars) (b) with or (c) without thymidine treatment. (3 experiments, n=100). Errors bars, s.e.m. d, Inefficient and asynchronous DNA replication in MN. RPE-1 cells as in Fig. 1a were pulse-labelled with BrdU and labelled: DNA (white) and BrdU (red). e, The ratio of BrdU incorporation in MN relative to primary nuclei after a 30 min pulse label. Normalized fluorescence intensity (F.I.) measurements are as shown in the box and whisker plots (2 experiments, n=50).

Figure 4. Defective MCM2-7 complex recruitment, DNA damage response and nucleocytoplasmic transport in MN

a, Impaired Mcm2 recruitment into MN. G1 RPE-1 cells were synchronized as in Fig. 1a and stained for chromatin-bound Mcm2 and DNA. Scale bar, 10 μM. b, Relative Mcm2 fluorescence intensity (F.I.) as in Fig. 3e. Approximate cell cycle stage of timepoints: 6h, G₁; 10h, early S-phase; 16h, mid-S phase and 20h, late S-phase. (2 experiments, n=50). c,d, Micronuclei are partially defective for nuclear import of NFATc1-EGFP. c, Representative images of micronucleated U2OS cells stably expressing NFATc1-EGFP in G₁ and G₂ with or without treatment with 0.2 μM thapsigargin for 10 min. d, Ratio of NFATc1-EGFP fluorescence intensity between MN and primary nuclei. (3 experiments, n=30).

Figure 5. The fate of chromosomes in micronuclei

MN were induced in RPE-1 cells as described in Fig. 1a (after p53 knockdown) and chromosome spreads were prepared 24 h after nocodazole release. a-c, Pulverization of chromosome 1 demonstrated by (a) DAPI staining (chromosome fragments, brightened in inset, yellow arrrows), (b) SKY probes (pseudo-colored), and (c) aligned SKY karyotype. d-f, Pulverization of chromosome 16, viewed as in (a-c). g, A BrdU positive MN-containing G₂ RPE-1 cell. 2 h BrdU pulse label, DNA: white, BrdU: red. h, Selective BrdU labelling of a pulverized chromosome. i, The percentage of cells with intact MN (blue bars) or pulverized chromosomes, PC (red bars) from control or nocodazole-released (NOC) RPE-1 cells. Interphase is 18 h sample and metaphase is 24 h. j, Images from live-cell experiment showing a pre-converted green-fluorescent MN (white arrows) photo-converted to a red-fluorescent MN (yellow arrows) imaged through mitosis. Following anaphase, MN either reincorporated with the primary nucleus or failed to reincorporate and reformed as MN top row: reincorporation of MN into primary nucleus; bottom row: no reincorporation. Time shown is hr:min.