Development of an orally bioavailable mSWI/SNF ATPase degrader and acquired mechanisms of resistance in prostate cancer

Abstract

Mammalian switch/sucrose nonfermentable (mSWI/SNF) ATPase degraders have been shown to be effective in enhancer-driven cancers by functioning to impede oncogenic transcription factor chromatin accessibility. Here, we developed AU-24118, an orally bioavailable proteolysis-targeting chimera (PROTAC) degrader of mSWI/SNF ATPases (SMARCA2 and SMARCA4) and PBRM1. AU-24118 demonstrated tumor regression in a model of castration-resistant prostate cancer (CRPC) which was further enhanced with combination enzalutamide treatment, a standard of care androgen receptor (AR) antagonist used in CRPC patients. Importantly, AU-24118 exhibited favorable pharmacokinetic profiles in preclinical analyses in mice and rats, and further toxicity testing in mice showed a favorable safety profile. As acquired resistance is common with targeted cancer therapeutics, experiments were designed to explore potential mechanisms of resistance that may arise with long-term mSWI/SNF ATPase PROTAC treatment. Prostate cancer cell lines exposed to long-term treatment with high doses of a mSWI/SNF ATPase degrader developed SMARCA4 bromodomain mutations and ABCB1 (ATP binding cassette subfamily B member 1) overexpression as acquired mechanisms of resistance. Intriguingly, while SMARCA4 mutations provided specific resistance to mSWI/SNF degraders, ABCB1 overexpression provided broader resistance to other potent PROTAC degraders targeting bromodomain-containing protein 4 and AR. The ABCB1 inhibitor, zosuquidar, reversed resistance to all three PROTAC degraders tested. Combined, these findings position mSWI/SNF degraders for clinical translation for patients with enhancer-driven cancers and define strategies to overcome resistance mechanisms that may arise.

Keywords: ABCB1; SMARCA2; SMARCA4; mSWI/SNF; proteolysis-targeting chimera (PROTAC).

Fig. 1.

AU-24118 is an orally bioavailable degrader of the mSWI/SNF ATPases SMARCA2/4 and PBRM1. (A) Chemical structures of first (AU-15330) and second (AU-24118) generation mSWI/SNF ATPase degraders. The ligand to the protein target is highlighted in red, and the linker is highlighted in black. The E3 ligase binder is highlighted in blue. (B) Immunoblot analysis of VCaP cells assessing protein levels of SMARCA4 (BRG1) and PBRM1 upon treatment with indicated doses of AU-15330 or AU-24118 for 4 h. Vinculin was used as a loading control for all immunoblots unless otherwise indicated. (C) Effects of AU-15330 and AU-24118 (2-h treatment) on the proteome of VCaP cells. Data plotted are Log2 of the fold change (FC) versus dimethyl sulfoxide (DMSO) control against −Log10 of the P-value from three biological replicates. t tests were performed as two-tailed t tests assuming equal variances. (D) IC₅₀ values of AU-15330 and AU-24118 in a panel of human cancer or normal cell lines after 5 d of treatment determined by Cell-TiterGlo viability assays. Cell lines are color-coded based on the treatment. (E) Plasma concentrations over time of AU-24118 in mice or rats upon one-time oral (p.o.) or intravenous (i.v.) dose of AU-24118. (F) Plasma concentrations over time of AU-24118 in mice upon oral dosing of indicated concentrations of AU-24118. (G) Pharmacokinetics metrics for AU-24118 in mice as determined by dose-escalation analyses conducted according to panel F. Cmax = Peak Concentration, C0 = Initial Concentration, AUC_0-last = Area Under the Curve from Time 0 to Last Measurable Concentration, Tmax = Time to Peak Concentration. (H) Oral bioavailability (%F) of AU-15330 and AU-24118 in mice and rats.

Fig. 2.

AU-24118 induces tumor regression as a single agent, as well as in combination with enzalutamide, in a VCaP CRPC model. (A) Schematic of in vivo efficacy study of AU-24118 with or without enzalutamide in a VCaP CRPC model. VCaP-bearing mice were castrated and, upon tumor regrowth, randomized into treatment arms of vehicle, AU-24118, enzalutamide, or both AU-24118 and enzalutamide at indicated doses. (B) Tumor measurements showing efficacy of AU-24118, enzalutamide, and AU-24118 + enzalutamide measured biweekly (analyzed with a two-way ANOVA with Dunnett’s multiple comparisons tests). Data shown are average tumor volumes +SEM. (C) Waterfall plots showing change in tumor volume compared to baseline (day 0) at endpoint (day 25) of individual tumors of each treatment arm. (D) Weights of individual tumors in each treatment arm at endpoint (day 25). Statistics were performed with a two-tailed unpaired t test. (E) Immunoblot of direct AU-24118 targets (SMARCA4, PBRM1, SMARCA2), validated downstream targets (AR, ERG, c-MYC, PSA/KLK3), and cleaved PARP (cPARP) in four tumors taken down at day 5 of treatment for pharmacodynamics assessment in the VCaP cell line-derived xenograft (CDX) model. (F) Representative DAPI and TUNEL staining from VCaP xenograft of each treatment arm after 5 d treatment (scale, 100 µm). (G) Representative H&E staining with corresponding IHC analysis of direct AU-24118 target SMARCA4 and downstream targets (AR, ERG, c-MYC), and proliferation marker Ki-67 after 5 d of treatment (scale, 50 µm). (The Inset scale = 20 µm.)

Fig. 3.

Mutations in the SMARCA4 bromodomain as a mechanism of resistance to mSWI/SNF ATPase degraders. (A) Schematic of process used to generate and characterize four independent AU-15330-resistant (AUR) 22Rv1 cell lines. (B) Table of 22Rv1 cell lines, highlighting SMARCA4 mutation profile, ABCB1 expression status, and classification of resistance mechanism. (C) Lollipop plot of SMARCA4 mutations detected through whole-exome sequencing of AUR-1 and AUR-2 cell lines. Amino acid residues are plotted on the X axis with protein domains highlighted and labeled. Mutation frequencies are plotted on the Y axis. (D) Immunoblot analysis of the indicated target proteins in 22Rv1 parental WT cells treated with vehicle DMSO (−) or 1 µM AU-15330 (+) for 4 h compared with 22Rv1 AUR-2 cells continuously cultured with 1 µM AU-15330. (E) Immunoblot of HEK293 cells transfected with labeled overexpression vectors or untransfected (parental) for 48 h prior to treatment with AU-15330 (1 µM, +) or DMSO (−) for 24 h showing changes in SMARCA4 or FLAG (FLAG-SMARCA4).

Fig. 4.

ABCB1/MDR1 overexpression as a mechanism of resistance to PROTAC degraders which can be overcome with ABCB1 inhibition. (A) Volcano plot visualizing the overall transcriptomic alterations as assessed by RNA-seq in 22Rv1-AUR-3 versus 22Rv1-WT cells. (B) Immunoblot analysis of 22Rv1-wild type (WT) or 22Rv1 AUR-3 cells treated with DMSO, 0.1 µM AU-15330, or 1 µM AU-15330 for 4 h. Histone H3 was used as a loading control. (C) qPCR analysis of C4-2B CDX tumors upon 24 d of dosing with either vehicle or AU-15330 showing changes in mRNA level of ABCB1. t tests were performed as two-tailed t tests assuming equal variances. (D) Immunoblot illustrating changes in protein level of ABCB1 and SMARCA4 in C4-2B CDX tumors after long-term AU-15330 treatment. Vinculin is utilized as the loading control across immunoblots. (E) Immunoblot analysis of 22Rv1-wild type (WT) or 22Rv1 AUR-3 cells treated with DMSO, si-ABCB1 (pooled), or si-control (siCtrl, pooled) and 1 µM AU-15330 for the indicated durations. Vinculin is utilized as the loading control across immunoblots. (F) Immunoblot analysis of 22Rv1-wild type (WT) or 22Rv1 AUR-3 cells treated with DMSO, 1 µM zosuquidar, and 1 µM AU-15330 for the indicated timepoints. Vinculin is utilized as the loading control across immunoblots. (G) Dose–response curves of 22Rv1-wild type (WT) or 22Rv1 AUR-3 cells treated with AU-15330 with or without zosuquidar (1 µM). Data are presented as mean ± SD (n = 6) from one of three independent experiments. IC₅₀ values calculated from dose–response curve experiment. (H, Left) Dose–response curves of 22Rv1-wild type (WT) or 22Rv1 AUR-3 cells treated with ZBC-260 with or without zosuquidar (1 µM). Data are presented as mean ± SD (n = 6) from one of three independent experiments. IC₅₀ values calculated from dose–response curve experiment. (Right) Dose–response curves of 22Rv1-wild type (WT) or 22Rv1 AUR-3 cells treated with ARD-61 with or without zosuquidar (1 µM). Data are presented as mean ± SD (n = 6) from one of three independent experiments. IC₅₀ values calculated from dose–response curve experiment. (I) Schematic of in vivo pharmacodynamics study of AU-15330 with indicated doses of zosuquidar and AU-15330 in a 22Rv1-AUR-3 xenograft model. (J) Immunoblot illustrating levels of the indicated proteins in 22Rv1-AUR-3 xenografts after 5-d treatment with the indicated dosing regimens. Vinculin is utilized as the loading control across immunoblots.