miR-22 suppresses DNA ligase III addiction in multiple myeloma

Abstract

Multiple myeloma (MM) is a hematologic malignancy characterized by high genomic instability. Here we provide evidence that hyper-activation of DNA ligase III (LIG3) is crucial for genomic instability and survival of MM cells. LIG3 mRNA expression in MM patients correlates with shorter survival and even increases with more advanced stage of disease. Knockdown of LIG3 impairs MM cells viability in vitro and in vivo, suggesting that neoplastic plasmacells are dependent on LIG3-driven repair. To investigate the mechanisms involved in LIG3 expression, we investigated the post-transcriptional regulation. We identified miR-22-3p as effective negative regulator of LIG3 in MM. Enforced expression of miR-22 in MM cells downregulated LIG3 protein, which in turn increased DNA damage inhibiting in vitro and in vivo cell growth. Taken together, our findings demonstrate that myeloma cells are addicted to LIG3, which can be effectively inhibited by miR-22, promoting a novel axis of genome stability regulation.

Fig. 1

High LIG3 levels are associated with poor prognosis in multiple myeloma patients. a Data obtained from GSE24080 dataset showing prognostic relevance of LIG3 mRNA (NM_013975 transcript variant alpha) on OS and EFS of MM patients. b Analysis of GSE39683 dataset. Left panel: LIG3 mRNA levels in healthy donors and patients’ multiple myeloma and plasmacell leukemia. Right panel: DNA ligases mRNA levels in MM patients. *, p < 0.001; **, p < 0.0001. c Analysis of GSE9782 dataset. Left panel: LIG3 mRNA levels in MM patients with clinical response (R) or progressive disease (PD) after bortezomib treatment. Right panel: prognostic relevance of LIG3 mRNA levels on OS of MM patients enrolled to bortezomib-based therapy. *p < 0.05

Fig. 2

Addiction of MM cells to DNA ligase III. a Left panel: immunoblot of LIG3 performed on plasmacells from MM cell lines and patients (Pts) compared to peripheral blood mononuclear cells (PBMCs) collected from healthy donors. GAPDH was used as a loading control. Right panel: immunofluorescence analysis showing subcellular distribution of LIG3 in AMO1 and patient (Pt#2) MM cells. b Left panel: indicated MM cell lines were transfected with either scramble control or LIG3-siRNA clone #2. CTG assay was performed 96 h from transfection. Results are expressed as percentage of siR-NC-transfected cells. Right panel: LIG3 knockdown was confirmed by western blot analysis 48 h after transfection. c Left panel: AMO1 cells were transduced with IPTG inducible CTRL-shRNA or LIG3-shRNA lentiviral particles as described above. CTG assay was peformed 6 days from IPTG induction (Top). LIG3 knockdown was confirmed by Western blotting 4 days from IPTG induction (Bottom). Rigth panel: inducible IPTG CTRL-shRNA or LIG3-shRNA AMO1 cells were injected s.c. into SCID/NOD mice. Averaged tumor volume of each group ± SD and LIG3 protein knockdown from a representative AMO1 xenograft per group, are shown. *p < 0.05; **p < 0.01

Fig. 3

miR-22 as negative regulator of LIG3 expression in multiple myeloma patients. a Graphs of correlations between endogenous mRNA expression levels of LIG3 (NM_013975, transcript variant alpha) and MIR22HG in patient’s multiple myeloma cells from published datasets GSE39683 and GSE47552. b Left panel: graphs of correlations between endogenous mRNA expression levels of LIG3 and miR-22 in patient’s PCL cases from proprietary dataset. Right panel: miR-22-3p basal expression as evaluated by miRNA profiling on proprietary datasets. *p < 0.05, **p < 0.01. c Left panel: dual-luciferase assay performed on AMO1 cells co-transfected with firefly luciferase constructs containing the 3′ UTR of LIG3 or a deletion mutant (3′ UTR del) and miR-22 mimics or miR-NC as indicated. The data are shown as relative luciferase activity of miR-22–transfected cells compared with the control (miR-NC). Values represent mean ± SD of three different experiments. *p < 0.05. Right panel: ectopic expression of miR-22 mimics or inhibitor in AMO1 and R8226 cells modulates protein levels of LIG3 as evaluated by immunoblot using GAPDH as loading control

Fig. 4

In vitro tumor suppressor activity of miR-22 in MM cells. a Left panel: CTG assay was performed 96 h after transfection of indicated MM cell lines with miR-22 mimics or scrambled controls (miR-NC). *p < 0.01. Right panel: cell viability of CD138+ cells from three different MM patients co-cultured with HS-5 stromal cells and transfected with miR-22 mimics or miR-NC. The assay was performed 48 h after cell transfection. *p < 0.05, **p < 0.01. b CTG assay performed in ABZB cells (left panel) and in primary PCs from n = 5 relapsed MM patients (right panel) 48 h after co-treatment with miR-22 and bortezomib. *p < 0.05; °synergistic index > 1.0. c AMO1 cells were co-transfected with LIG3 ORF or control ORF and miR-22 mimics or miR-NC: left panel: CTG survival assay were performed 96 h after transfection. *p < 0.01. Right panel: immunoblot shows the levels of LIG3 and GAPDH 48 h after cell transfection

Fig. 5

miR-22 overexpression counteracts LIG3 activity and induces DNA damage in MM cells. a Alt-NHEJ repair was evaluated by EJ2-GFP assay on AMO1 cells 48 h after transfection with miR-22 mimics or miR-NC. b Mitochondrial DNA copy number in AMO1 48 h after transfection. c AMO1 and R8226 cells were transfected with miR-22 mimics or miR-NC. Left panel: immunoblot analysis was performed 48 h after cell transfection. Right panel: γ-H2AX foci evaluation by immunofluorescence 48 h after cell transfection. Representative images of unrepaired DSBs are shown. DAPI (blue) was used for nuclear staining. d AMO1 cells were co-transfected with LIG3 ORF or control ORF and miR-22 mimics or miR-NC: immunoblot analysis was performed 48 h after cell transfection. *p < 0.05, **p < 0.01

Fig. 6

In vivo activity of miR-22 overexpression in MM xenograft models. a Inducible-CTRL or inducible-miR-22 cells were injected s.c. into SCID/NOD mice. When palpable tumors became detectable, animals were randomized to receive either vehicle (5% sucrose) or doxycycline (2 mg/mL in 5% sucrose) via drinking water for duration of study. Left panel: averaged tumor volume of each group ± SD is shown; *p < 0.01. Right panel: LIG3 knockdown and miR-22 overexpression were confirmed respectively by western blot analysis and qRT-PCR from a representative AMO1 xenograft per group. *p < 0.01. b In vivo growth of luciferase gene-marked AMO1 xenografts intra-tumorally treated with miR-22 mimic or scramble controls. Palpable subcutaneous tumor xenografts were treated with 20 mg of NLE-formulated oligos. Intra-tumor injections were administered every other day, for a total of three injections (indicated by arrows). Left panel: averaged tumor volume of each group ± SD is shown. *p < 0.01. Right panel: survival curves (Kaplan–Meier) of each group (log-rank test, p < 0.05). Survival was evaluated from the first day of treatment until death or sacrifice. Percentage of mice alive is shown. c Left panel: immunoblot of p-ATM, p-ATR, p-CHECK1, p-CHECK2, cleaved-caspase-3, and PARP in lysates from a representative AMO1 xenograft per group. GAPDH was used as a loading control. Right panel: IHC analysis (20×, 40x insets) from a representative AMO1 xenograft per group for LIG3 and p-H2AX expression

Fig. 7

Esplicative cartoon of miR-22-mediated modulation of LIG3-driven DNA repair