ATR inhibition facilitates targeting of leukemia dependence on convergent nucleotide biosynthetic pathways

Abstract

Leukemia cells rely on two nucleotide biosynthetic pathways, de novo and salvage, to produce dNTPs for DNA replication. Here, using metabolomic, proteomic, and phosphoproteomic approaches, we show that inhibition of the replication stress sensing kinase ataxia telangiectasia and Rad3-related protein (ATR) reduces the output of both de novo and salvage pathways by regulating the activity of their respective rate-limiting enzymes, ribonucleotide reductase (RNR) and deoxycytidine kinase (dCK), via distinct molecular mechanisms. Quantification of nucleotide biosynthesis in ATR-inhibited acute lymphoblastic leukemia (ALL) cells reveals substantial remaining de novo and salvage activities, and could not eliminate the disease in vivo. However, targeting these remaining activities with RNR and dCK inhibitors triggers lethal replication stress in vitro and long-term disease-free survival in mice with B-ALL, without detectable toxicity. Thus the functional interplay between alternative nucleotide biosynthetic routes and ATR provides therapeutic opportunities in leukemia and potentially other cancers.Leukemic cells depend on the nucleotide synthesis pathway to proliferate. Here the authors use metabolomics and proteomics to show that inhibition of ATR reduced the activity of these pathways thus providing a valuable therapeutic target in leukemia.

Fig. 1

Effects of ATR and dCK inhibition on G1-S transition and substrate utilization for dCTP biosynthesis. a, b Flow cytometry analysis of EdU incorporation in CEM T-ALL cells treated with VE-822 (1 µM) and/or dCKi (DI-82,1 µM) for 6 a and 12 h b following release from G1 arrest, respectively. Bar graphs summarize the percentage of cell populations in S1 (early S-phase) and S2 (mid to late S-phase) at 6 and 12 h (mean ± s.d., n = 2, one-way ANOVA, Bonferroni corrected). Plots are representative of two independent experiments. c Comparison of metabolite labeling by [¹³C₆]glucose in CEM T-ALL cells treated with VE-822 and/or dCKi for 12 h following release from G1 arrest. Number of metabolites exhibiting alterations in [¹³C₆]glucose labeling greater than 15% with significance at a false discovery rate ≤ 20% are indicated. d Percent glucose labeling of ribonucleotides intermediates in the de novo dCTP biosynthesis (mean ± s.d., n = 6, one-way ANOVA, Bonferroni corrected). e Workflow for targeted LC-MS/MS-MRM analysis of dCTP incorporated into newly replicated DNA using a triple quadrupole mass spectrometer. See text for details and Supplementary Fig. 4 for the LC-MS/MS-MRM analysis of dCTP pools. f, g Contributions of the de novo and salvage pathways to dCTP pools f and dCTP incorporated into newly synthesized DNA g in CEM cells treated with VE-822 and/or dCKi after release from G1 arrest (mean ± s.d., n = 3). Results are representative of two independent experiments. NT = Not treated, V = VE-822, D = dCKi, V + D = VE-822 + dCKi. *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001. ATR ataxia telangiectasia and Rad3-related protein, EDU 5’-ethynyl-2’-deoxyuridine, FDR false discovery rate, RNR ribonucleotide reductase, CTPS1/2 CTP synthase 1/2, R5P ribose 5-phosphate, OMP orotidine monophosphate, rCDP cytidine diphosphate, CTP cytidine triphosphate, UTP uridine triphosphate, dCTP deoxycytidine triphosphate, LC-MS/MS-MRM liquid chromatography tandem mass spectrometry operating in multiple reaction monitoring

Fig. 2

Alterations in total protein and phosphoprotein levels following ATR and dCK inhibition. a Workflow for quantitative global proteomics using nLC-MS/MS. See text for details. b Comparison of protein levels in CEM cells treated with VE-822 and/or dCKi for 12 h following release from G1 arrest. Number of proteins exhibiting fold changes greater than 15% changes with significance at a false discovery rate ≤ 20% are indicated. c Protein levels of nucleotide biosynthetic enzymes (mean ± s.d., n = 3, one-way analysis of variance (ANOVA, Bonferroni corrected). d Protein levels in asynchronous CEM cells treated with VE-822 (1 µM) for 12 h (mean ± s.d., n = 3, one sample t-test to assess if the mean of the protein level normalized to untreated control is equal to one). e Relative level of RRM2 pT33 normalized to RRM2 protein level from d, in asynchronous CEM cells treated with VE-822 (1 µM) for 12 h (mean ± s.d., n = 3, unpaired two-tailed Student’s t-test). (f, left panel) Salvage produced [¹³C₉,¹⁵N₃]dCMP in asynchronous CEM cells treated with VE-822 or dCKi for 12 h (mean ± s.d., n = 3, one-way ANOVA, Bonferroni corrected). (f, right panel) Relative levels of dCK pS74, after normalized to dCK protein level from d, in asynchronous CEM cells treated with VE-822 (1 µM) for 12 h (mean ± s.d., n = 3, unpaired two-tailed Student’s t-test). g Summary of the observed effects of ATR and dCK inhibition in CEM cells. ↓ partial decrease/inhibition, ↓↓↓ nearly complete inhibition, ↑ increase, ⟷ no change, nd not determined. NT = Not treated, V = VE-822, D = dCKi, V + D = VE-822 + dCKi. *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001. nLC-MS/MS nano liquid chromatography tandem mass spectrometry, RRM1 ribonucleotide reductase subunit 1, RRM2 ribonucleotide reductase subunit 2, TYMS thymidylate synthase, dCK deoxycytidine kinase, dCMP deoxycytidine monophosphate

Fig. 3

3-AP potently inhibits RNR and enhances salvage nucleotide biosynthesis. a Mechanisms of action of four RNR inhibitors. The two RNR subunits, RRM1 (α) and RRM2 (β) form a catalytically active α₂β₂ complex. Each RRM1 subunit contains two allosteric regulatory sites (the specificity and activity sites), as well as the active site, where nucleotide reduction occurs. The active form of the RRM2 dimer (holo-β₂) houses the di-iron cofactor and the tyrosyl radical (Y-O•). 3-AP forms a complex with Fe²⁺ which interferes with the regeneration of the tyrosyl radical in RRM2 therefore promoting the formation of an inactive met-β small subunit which retains its di-iron center. Hydroxyurea (HU) scavenges the RRM2 tyrosyl radical and depletes the di-iron center to form an inactive apo-β form. Gallium maltolate (GaM) releases Ga³⁺ which mimics Fe³⁺ and disrupts the RRM2 di-iron center. Thymidine (dT) is converted via the salvage pathway to thymidine triphosphate (dTTP) which binds to the allosteric specificity site on RRM1 to favor GDP reduction over pyrimidine (CDP and UDP) reduction, thereby resulting in dCTP insufficiency. b Effects of RNR inhibitors on cell cycle progression. CEM cells were incubated for 24 h with indicated concentrations of RNR inhibitors followed by cell cycle analyses using flow cytometry. Shown in bold red are the concentrations of each RNR inhibitor required to induce a greater than 45% increase in the S-phase population, indicative of S-phase arrest due to nucleotide insufficiency. Cell cycle plots are representative of two independent experiments. See Supplementary Fig. 8 for quantification. c LC-MS/MS-MRM analysis of dCTP biosynthesis in CEM cells treated with 500 nM 3-AP for 12 h (mean ± s.d., n = 3). NT not treated. CMPK1 uridine-cytidine monophosphate kinase 1, NME1/2 nucleoside diphosphate kinase 1/2, dC 2’-deoxycytidine, dCMP deoxycytidine monophosphate, dCDP deoxycytidine diphosphate

Fig. 4

Synthetic lethality induced by combined inhibition of ATR, dCK and RNR. a LC-MS/MS-MRM analysis of dCTP biosynthesis in CEM cells treated as indicated in the text for 12 h (mean ± s.d., n = 3). Results are representative of two independent experiments. b, left Flow cytometry analyses of ssDNA (F7-26) and pH2A.X levels in CEM cells treated as indicated for 0.5 and 4 h. b, right Bar graphs summarizing the percentage of ssDNA⁺ and ssDNA⁺;pH2A.X⁺ cells at 0.5 and 4 h, respectively (mean ± s.d., n = 2, one-way ANOVA, Bonferroni corrected). ssDNA-pH2A.X plots are representative two independent experiments. c Representative immunoblots of CEM cells treated as indicated in the text for 0.5 and 4 h. *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001. ssDNA single-stranded DNA, DSB double-stranded breaks, PARP Poly (ADP-ribose) polymerase

Fig. 5

ATR inhibition alone is effective but not sufficient to achieve disease-free survival in a systemic primary B-ALL model. a IC₅₀ values of VE-822 in a panel of cancer cell lines and patient-derived samples (CellTiter-Glo assay at 72 h, mean ± s.d., n = 3). b, c Bioluminescence images b and quantification of whole-body radiance c of leukemia bearing mice treated with 40 mg kg^–1 VE-822 (n = 6) or vehicle (control, n = 6). VE-822 was administered once daily. d Kaplan-Meier survival analysis of C57BL/6 mice bearing p185^BCR-ABL Arf ^–/– systemic pre-B-ALL treated with 40 mg kg^–1 day^–1 VE-822 (n = 6) or vehicle (control, n = 6). Median survival for the control group was 15 days after treatment initiation and 32.5 days for the VE-822 group (Mantel–Cox test). e Apoptosis induction in p185^BCR-ABL Arf ^–/– pre-B-ALL cells treated as indicated (350 nM 3-AP, 100 nM VE-822, and 1 µM dCKi) for 72 h using flow cytometry for Annexin V and PI staining (mean ± s.d., n = 2, one-way analysis of variance, Bonferroni corrected). *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001. HCC hepatocellular carcinoma, PDAC pancreatic ductal adenocarcinoma

Fig. 6

The triple combination therapy is effective and well-tolerated in a systemic primary B-ALL model. a Plasma pharmacokinetic parameters for 3-AP (15 mg kg⁻¹), VE-822 (40 mg kg⁻¹) and dCKi (50 mg kg⁻¹) in C57BL/6 mice (n ≥ 3) after single dose oral co-administration (mean ± s.d., n ≥ 3). b Doses and schedules for the triple combination therapy of leukemia bearing mice. c, d Bioluminescence images c and quantification of whole body radiance d of leukemia bearing mice treated with the combination therapy (treated, n = 5) or vehicle (control, n = 5) at indicated days after tumor inoculation. See also Supplementary Figs 11–13. e, f Kaplan–Meier survival analysis e and body weight measurements f of leukemia bearing mice treated with the combination therapy (treated, n = 5) or vehicle (control, n = 5). Median survival for the control group was 14 days after treatment initiation, whereas median survival for the treated group remains undefined (Mantel–Cox test). *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001. q.d. once/day; b.i.d. twice/day