Restoration of TET2 Function Blocks Aberrant Self-Renewal and Leukemia Progression

Abstract

Loss-of-function mutations in TET2 occur frequently in patients with clonal hematopoiesis, myelodysplastic syndrome (MDS), and acute myeloid leukemia (AML) and are associated with a DNA hypermethylation phenotype. To determine the role of TET2 deficiency in leukemia stem cell maintenance, we generated a reversible transgenic RNAi mouse to model restoration of endogenous Tet2 expression. Tet2 restoration reverses aberrant hematopoietic stem and progenitor cell (HSPC) self-renewal in vitro and in vivo. Treatment with vitamin C, a co-factor of Fe2⁺ and α-KG-dependent dioxygenases, mimics TET2 restoration by enhancing 5-hydroxymethylcytosine formation in Tet2-deficient mouse HSPCs and suppresses human leukemic colony formation and leukemia progression of primary human leukemia PDXs. Vitamin C also drives DNA hypomethylation and expression of a TET2-dependent gene signature in human leukemia cell lines. Furthermore, TET-mediated DNA oxidation induced by vitamin C treatment in leukemia cells enhances their sensitivity to PARP inhibition and could provide a safe and effective combination strategy to selectively target TET deficiency in cancer. PAPERCLIP.

Keywords: DNA demethylation; DNA oxidation; HSCs; PARP inhibitor; TET2; hydroxymethylcytosine; leukemia; reversible RNAi; self-renewal; vitamin C.

Figure 1. Generation of Inducible and Reversible Tet2 Knockdown Mice

(A) Schematic representation of Vav-tTA-driven (VTA) reversible Tet2 knockdown mice. (B) Schematic representation of Rosa-rtTA-driven (RTA) inducible Tet2 knockdown mice. (C) Tet2 mRNA levels (normalized to Hprt) in bone marrow, thymus, and spleen cells from VTA shTet2 mice, compared with cognate cells from VTA shRen control mice. (D) Schematic representation of Tet2 restoration (RS) versus knockdown (KD) in mice treated with doxycycline (Dox) food for 28 days (D0–D28). (E and F) Representative flow cytometric analysis of GFP in peripheral blood cells of Dox-regulated RTA shTet2 inducible knockdown (E) mice and following Tet2 restoration in VTA shTet2 mice (F). (G and H) Tet2 mRNA expression (normalized to Hprt, relative to RTA shTet2 at day 0) in cells isolated from RTA shTet2 and VTA shTet2 mice treated with Dox food to compare knockdown (KD) or restoration (RS), respectively, in cKit⁺ bone marrow cells (G) and CD11b⁺ immature myeloid cells (H) (n = 4–5 mice per group). See also Figure S1.

Figure 2. Tet2 Restoration Blocks Aberrant Hematopoietic Stem Cell Self-Renewal In Vitro and In Vivo

(A) Schematic of colony-forming assays performed with Tet2 knockdown cells. After re-plating for four successive passages (P1–P4), VTA shTet2-expressing cells are treated with Dox to determine the effects of Tet2 restoration on re-plating. (B) Total number of colony-forming units (CFU) generated by VTA shRen control or VTA shTet2 knockdown cells. Data are representative of three experiments (mean + SD), **p < 0.005. (C) Representative appearance of colonies generated after 4 passages (P4) with Tet2 knockdown re-plated ± Dox from P4–P5. (D) Number of CFUs from passage 5 (P5) Tet2 knockdown (KD) and Tet2-restored (RS) cells. (E) Tet2 mRNA levels normalized to Hprt in RS cells relative to KD from (D). Mean + SEM from 3 experiments is shown, **p < 0.005 and ***p < 0.005. (F and G) Donor peripheral blood cell (PBC) percentage in mice subjected to competitive bone marrow reconstitution and given Dox food from 6 weeks post-transplant of VTA shRen control (F) or VTA shTet2 donor bone marrow cells (G). (H) Representative flow cytometric analysis of donor chimerism and GFP expression in VTA shTet2-transplanted mice ± Dox treatment at 28 weeks post-transplant. (I and J) Representation of donor PBCs in the indicated hematopoietic lineages 28 weeks post-transplant in mice with VTA shRen (I) or VTA shTet2 (J) bone marrow cells ± Dox treatment. (K) Tet2 mRNA levels, normalized to Hprt expression, in Tet2 KD or Tet2 RS cells isolated from VTA shTet2-reconstituted mice at 28 weeks post-transplant. Mean + SEM is shown (n = 4–5 mice per group). *p < 0.05, **p < 0.005. See also Figure S2.

Figure 3. Tet2 Restoration Promotes DNA Demethylation, Differentiation, and Cell Death

(A–E) Effects of Tet2 restoration on Tet2 mRNA levels, proliferation, survival, and differentiation of cKit⁺ cells. Tet2 mRNA levels (normalized to Hprt) in cKit⁺ cells grown in liquid culture for 28 days with sustained Tet2 knockdown (KD) or inducible restoration (RS) upon Dox administration (A). Proliferation (B) and apoptosis, as assessed by Annexin V staining (C), of Tet2 RS versus sustained Tet2 KD cells. Representative flow cytometry histograms of stem and progenitor (cKit and CD34) or differentiation (CD11b) marker expression upon Tet2 KD or Tet2 RS after 21 days in culture (D). Quantification of GFP by relative mean fluorescence intensity (MFI) is shown (E). (F and G) Global changes in methylation were measured in genomic DNA isolated from cKit⁺ cells during inducible Tet2 RS, and compared to cells with sustained Tet2 KD. Quantification was performed using ELISAs for 5mC (F) and 5hmC (G). Mean ± SEM is shown for 2 biological replicates, performed in triplicate. *p < 0.05, **p < 0.005, and ***p < 0.005. See also Figure S3.

Figure 4. Differential Methylation and Global Transcriptional Changes upon Tet2 Restoration

(A and B) Reduced representation bisulfite sequencing (RRBS) of DNA from cKit⁺ cells in vitro, showing the number of differentially methylated cytosines (DMCs) (q < 0.05, DiffMeth >10%) (A) and the distribution of differentially methylated regions (DMRs) according to CpG context and genomic location (B) at 10 days of Tet2 restoration (q < 0.05, DiffMeth >10%, 500 bp window). (C–F) Distribution of differentially expressed genes (DEGS, p < 0.05) in cKit⁺ cells subjected to Tet2 restoration for the indicated times. The average log2 fold-changes in all upregulated genes (C) with >2-fold change in expression (D) and in all downregulated genes (E) with >2-fold change in expression (F) are shown. (G–I) Gene-expression analysis and gene set enrichment analysis (GSEA). Heatmap shows a subset of differentially expressed genes in cKit⁺ cells subjected to Tet2 restoration for the indicated times (G). GSEA plots of genes hypermethylated in AML patients that are upregulated in Tet2 restored cells (H) or hypo-methylated genes in AML patients that are downregulated upon Tet2 restoration (I) (related to Table S1). Decreased gene expression is indicated by shades of blue; increased expression is indicated by shades of red. RRBS and RNA-seq were performed on 2 replicates per time point. *p < 0.05, **p < 0.005, and ***p < 0.005. See also Figure S4.

Figure 5. Vitamin C Treatment Mimics Tet2 Restoration in Hematopoietic Stem Cells and Blocks Myeloid Disease Progression

(A) DNA dot blots for 5hmC and 5mC in genomic DNA from primary mouse cKit⁺ cells treated with 250 μM vitamin C (L-ascorbic acid, L-AA) for 6 days. Data are representative of 2 experiments. (B–D) Colony-formation assays with Tet2^+/+, Tet2^+/−, and Tet2^−/− bone marrow cells treated with L-AA. Cells were re-plated for four passages (P1–P4) (B), Tet2^−/− CFUs re-plated from passage 4 to 5 (P4–P5) ± catalase (C), and Tet2^+/−, Tet2^−/−, and Tet2/3 double-deficient colonies re-plated from P4 to P5. Data shown are the means + SEM of 4 experiments for each genotype, assayed in triplicate. (E and F) DNA dot-blot for 5hmC in primary mouse cKit⁺ cells cultured for 6 days ± L-ascorbic acid (L-AA) (E), and relative Tet1, Tet2, and Tet3 mRNA levels in cKit⁺ cells, quantified by RT-PCR and normalized to Hprt (F). Data are representative of 2 experiments. (G) Time course showing increase in 5hmC levels (quantified by flow cytometry) in peripheral blood cells of mice treated with a single i.p. injection of sodium ascorbate. (H–J) Vitamin C treatment of mice reconstituted with Tet2^+/+ and Tet2^−/− bone marrow. Mice were injected i.p. with PBS (control) or ascorbate (ASC, 4 g/kg), and white blood cell (WBC) counts were monitored for 24 weeks post-transplant (PT) (H). Frequency (I) and number (J) of donor B and T lymphocytes and myeloid cells (M) in peripheral blood of recipients at 24 weeks PT treated with ASC or control (PBS). *p < 0.05, **p < 0.005, and ***p < 0.005 in all experiments. See also Figure S5.

Figure 6. Vitamin C Treatment Increases TET Activity in Human AML and Drives DNA Hypomethylation

(A) DNA dot blots for 5hmC in MOLM13 and HL60 cells treated for 72 hr with 250 μM L-ascorbic acid (L-AA). Data are representative of 2 experiments. (B and C) Differentially hydroxymethylated peaks (Diff Peaks) with gain or loss of 5hmC (Diff Peaks, q < 0.05), assayed by 5hmeDIP-seq, in HL60 cells treated with 250 μM L-AA for 72 hr. Frequency and total number of significant Diff Peaks (B) and gene body distribution of the top 10,000 significant peaks following L-AA treatment (C), displayed as peak density ± 3 kb from the transcription start site (TSS) to the transcription termination site (TTS). (D) Number of differentially methylated cytosines (DMCs), either hypermethylated (gain of 5mC) or hypomethylated (loss of 5mC), in HL60 and MOLM13 cells treated for 72 hr with 250 μM L-AA, assayed by bisulfite sequencing (q < 0.05, DiffMeth >25%). (E–G) Differentially methylated regions (DMRs) in 72 hr L-AA-treated HL60 and MOLM13 cells (q < 0.05, DiffMeth >10%, 500 bp). Total DMR frequencies, according to CpG context and genomic location (E), are shown as the frequency of hypermethylated (gain of 5mC) or hypomethylated (loss of 5mC) DMRs across all chromosomes (F) and by the total number of DMRs with gain or loss of 5mC according to CpG context and genomic location (G). (H) Gene-set enrichment analysis for up- and downregulated genes associated with 10 days of Tet2 restoration in cKit⁺ cells (497 upregulated and 136 downregulated, Log2FC, p < 0.05) in HL60 and MOLM13 cells treated with L-AA (250 μM) for 12 hr. Lowest gene expression (dark blue) to highest expression (red) is displayed for each plot. (I) Heatmap showing expression of genes upregulated by Tet2 restoration in cKit⁺ cells in HL60 and MOLM13 cells treated with L-AA (250 μM) for 0, 12, or 72 hr. Scale represents log-transformed counts, normalized by library size, from lowest (dark blue) to highest expression (red). For all sequencing experiments, 3 replicates were analyzed per time point. See also Figure S6.

Figure 7. TET-Mediated Oxidation of DNA in Vitamin C-Treated Leukemia Cells Increases Killing in Combination with PARP Inhibition

(A) Relative viability of human leukemia lines grown for 3 days in increasing concentrations of L-ascorbic acid (L-AA). Shown are means ± SD. Data for 4 experiments. (B and C) Dot blots of genomic DNA from human leukemia lines subjected to 0, 24, and 72 hr of L-AA treatment, probed for 5hmC (B), and from HL60 and MOLM13 probed for 5hmC, 5fC, 5caC, and 5mC (C). Data are representative of 3 experiments. (D–F) Fold-changes in mRNA levels of genes associated with BER and active DNA demethylation in Tet2-restored mouse HSPCs and vitamin C-treated human leukemia cells. Fold-changes were calculated from normalized counts from RNA-sequencing in day 10-restored cKit⁺ cells, relative to knockdown (D), and in 12 hr L-AA-treated, relative to untreated, HL60 (E) and MOLM13 cells (F). *p < 0.05, **p < 0.00, and ***p < 0.005. (G) Relative viability of AML lines treated with L-AA in combination with PARP inhibitor (Olaparib) at the indicated concentrations. Cells were assayed in triplicate at each concentration. Mean ± SEM are shown for 3 independent experiments. See also Figure S7.