Imidazole Ketone Erastin Induces Ferroptosis and Slows Tumor Growth in a Mouse Lymphoma Model

Abstract

Ferroptosis is a form of regulated cell death that can be induced by inhibition of the cystine-glutamate antiporter, system x_c^-. Among the existing system x_c^- inhibitors, imidazole ketone erastin (IKE) is a potent, metabolically stable inhibitor of system x_c^- and inducer of ferroptosis potentially suitable for in vivo applications. We investigated the pharmacokinetic and pharmacodynamic features of IKE in a diffuse large B cell lymphoma (DLBCL) xenograft model and demonstrated that IKE exerted an antitumor effect by inhibiting system x_c^-, leading to glutathione depletion, lipid peroxidation, and the induction of ferroptosis biomarkers both in vitro and in vivo. Using untargeted lipidomics and qPCR, we identified distinct features of lipid metabolism in IKE-induced ferroptosis. In addition, biodegradable polyethylene glycol-poly(lactic-co-glycolic acid) nanoparticles were employed to aid in IKE delivery and exhibited reduced toxicity compared with free IKE in a DLBCL xenograft model.

Keywords: DLBCL; ROS; cancer; cell death; cysteine; cystine; erastin; ferroptosis; glutathione; lipidomics; lymphoma; nanoparticle; peroxidation; system x(c)(–).

Figure 1.

IKE is a potent ferroptosis inducer. (A) The small molecule IKE with isopropoxy, ketone, and imidazole substitutions is more potent than erastin. (B) DLBCL cell line sensitivity was measured by incubating cells with a two-fold series dilution of IKE (starting from 100 μM) for 24 hours followed by a Cell Titor-Glo luminescent cell viability test. LY8, DOHH2, SUDHL5, SUDHL2, SUDHL6, SUDHL10, and SUDHL16 were classified as sensitive cell lines (red). HBL1, SUDHL9, WSU-NHL, SUDHL8, RIVA, and KARPAS422 were classified as moderately resistant cell lines (black). SUDHL7, U937, A3/KAW, LY7, and U2932 were classified as resistant cell lines (blue). (C) GSH level was measured with a fluorometric-green probe in SUDHL6 cells treated with different concentration of IKE with or without 10 μM β-ME for 24 hours. (D) Lipid ROS detected with C11-BODIPY fluorescence was measured in SUDHL6 cells treated with different concentration of IKE with or without 10 μM fer-1 co-treatment. (E) RT-qPCR performed in SUDHL6 cells treated with 500 nM IKE for different lengths of time detected SLC7A11, CHAC1, and PTGS2 mRNA induction compared with DMSO-treated samples. (F) Co-treatment of 10 μM fer-1 with 500 nM IKE for 6 hours prevented PTGS2 upregulation, but not SLC7A11 and CHAC1 upregulation, while 10 μM β-ME co-treatment prevented the upregulation of all three mRNAs. Data are plotted as the mean ± s.d., n=2 (B) and (C), or n=3 (E) and (F) biological replicates. Three independent experiments were performed with similar results (B) to (F). See also Figure S1.

Figure 2.

Heat map of significantly changed (one-way ANOVA, p < 0.05) lipid species in SUDHL6 cells treated with DMSO, 500 nM IKE, 1 μM IKE, 500 nM IKE with 10 μM fer-1 co-treatment, 500 nM IKE with10 μM β-ME co-treatment, 500 nM IKE with10 μM DFO co-treatment, measured by LC-MS. Each row represents z-score-normalized intensities of the detected lipid species in (A) negative electrospray ionization mode and (B) positive electrospray ionization mode. Each column represents an independent biological replicate. The lipid abundance is color-coded, with red indicating high signal intensity, and dark blue indicating low signal intensity.</P/>Abbreviations: PC, phosphatidylcholine; PE, phosphatidylethanolamine; PS, phosphatidylserine, LPC, lysoPC; PE P-, plasmalogen PE; TAG, triacylglycerol; DAG, diacylglycerol, MAG, monoacylglycerol. (C) Fold change in expression of ACC1, ELOVL7, ATGL, sPLA2F, LPCAT4, LPEAT1, ALOX12, and ALOX15 with 500 nM IKE treatment, 500 nM IKE with 10 μM fer-1 co-treatment, and 500 nM with 10 μM β-ME co-treatment compared with DMSO control in SUDHL6 cells. Data are plotted as the mean ± s.d., n=3 biologically independent samples. (D) Schematic view of fatty acid biosynthesis, lipid remodeling, and arachidonic acid oxidation. The genes upregulated upon IKE treatment were labeled with red. See also Figure S2.

Figure 3.

IKE-induced ferroptosis biomarker changes in a lymphoma xenograft model. (A) A pharmacokinetic study performed in SUDHL6 subcutaneously xenografted NCG mice measured IKE accumulation over time in plasma and tumor using LC-MS. (B) Analysis of GSH extracted from tumor tissue by fluorometric-green showed over 50% GSH depletion with IKE treatment starting at 4 hours. *** P<0.001, **** P<0.0001 by one-way ANOVA. Data are plotted as the mean ± s.d., n=3 individual mice (A) to (B). (C) RT-qPCR performed using RNA extracted from tumor tissue showed PTGS2, SLC7A11, and CHAC1 mRNA increase starting from 3 hours, colored as blue in the heatmap. Data are plotted as the mean, n=3 individual mice. (D) and (E) Immunofluorescence of dihydropyridine-MDA-lysine adduct in paraffin-embedded tumor samples from mice four hours after treatment with one dose of vehicle or IKE. Quantification of fluorescence intensity showed 1.6-fold increase of dihydropyridine-MDA-lysine adducts and 1.5-fold increase of 8-OH-dG in IKE-treated mouse tumor tissue relative to the vehicle-treated mouse tumor tissue (sections were cut from 3 mice in each group, five images from each section were captured on Zeiss LSM 800 63x/1.40 Oil DIC objective). *** P<0.001, **** P<0.0001 by t test. Heatmaps of dysregulated lipids in SUDHL6 subcutaneously xenografted NCG mice treated with one dosage IKE for at 0, 1, 2, 3, 4, 6, and 24 hours or with vehicle, detected by untargeted UPLC-MS analysis. Data shown in heatmaps are lipid species that were identified as being statistically significant (p < 0.05) among the groups in (F) negative electrospray ionization mode and (G) positive electrospray ionization mode. Each column represents an independent biological replicate. Each row represents z- score normalized intensity of a lipid feature. The relative abundance of each identified lipid is color coded in blue, indicating low signal intensity, and red indicating high signal intensity. Abbreviations: PC, phosphatidylcholine; PE, phosphatidylethanolamine; PI, Phosphatidylinositol; PS, phosphatidylserine, LPC, lysoPC; LPE, lysoPE; FA, free fatty acid; TAG, triacylglycerol; DAG, diacylglycerol, MAG, monoacylglycerol. See also Figure S3 and Table S2.

Figure 4.

IKE PEG-PLGA NPs < 100 nm in diameter were formulated and showed reduced toxicity in SUDHL6-subcutaneous-xenografted mice. (A) A NanoAssemblr equipped with a microfluidic mixer was used to formulate PEG-PLGA NPs (polymer structure shown). The nanoparticles were characterized with a Zetasizer Nano ZS to have a mean diameter of 80 nm, polydispersity index of 0.17, and surface charge of −17 mV. (B) IKE PEG-PLGA NP cellular activity was measured by Cell Titer-Glo luminescence cell viability assay in SUDHL6 cells with 24-hour incubation. The encapsulated IKE in PEG-PLGA NPs was measured by LC-MS. The x-axis shows IKE concentration. Data are plotted as the mean ± s.d., n=2 biologically replicates. Three independent experiments were performed with similar results. (C) Tumor volume fold change compared with day 0, measured by electronic caliper daily and calculated using the formula volume = 0.5 × length × width², revealed a reduction of tumor growth by IKE 40 mg/kg (n=9), IKE 23 mg/kg (n=11), and IKE NP 23 mg/kg (n=13) treatment for 14 days comparing with vehicle (n=13) and NP vehicle (n=13) controls (data analyzed by two-way ANOVA). (D) Mouse weight was measured daily and indicated no weight loss upon NP and IKE NP treatments, but weight loss upon IKE 40 mg/kg and IKE 23 mg/kg treatment starting from day 9. Data are plotted as the mean ± s.d. See also Figure S4.

Figure 5.

IKE treatment induced lipid peroxidation in tumor tissue during the efficacy study. (A, D) Immunofluorescence of COX-2 on frozen tumor sections showed 2.0 and 2.8-fold increase on COX-2 intensity upon IKE 23 mg/kg and IKE 40 mg/kg treatment daily for 14 days. (B, E) Immunofluorescence of MDA on frozen tumor sections measured by confocal microscopy showed 1.4, 1.8, 1.8, and 2.0-fold increase in MDA intensity upon NP vehicle, IKE NP 23 mg/kg, IKE 23 mg/kg, and IKE 40 mg/kg treatment daily for 14 days. (C, F) Immunofluorescence of 8-OH-dG on frozen tumor sections measured by confocal microscopy showed 2.3, 1.8, and 2.2-fold increase in 8-OH-dG intensity upon IKE NP 23 mg/kg, IKE 23 mg/kg, and IKE 40 mg/kg treatment daily for 14 days. (Sections were cut from 5 randomly chosen mice in each group, three images from each section were captured on Zeiss LSM 800 63x/1.40 Oil DIC objective) (G) TBARS assay measuring MDA-TBA adduct fluorescence showed 1.6, 1.4, and 1.8-fold MDA increase upon IKE NP 23 mg/kg, IKE 23 mg/kg and IKE 40 mg/kg treatment. ns P>0.5, * P<0.05, ** P<0.01, *** P<0.001, **** P<0.0001 by one-way ANOVA. Data are plotted as the mean ± s.d.