ARID1A determines luminal identity and therapeutic response in estrogen-receptor-positive breast cancer

Abstract

Mutations in ARID1A, a subunit of the SWI/SNF chromatin remodeling complex, are the most common alterations of the SWI/SNF complex in estrogen-receptor-positive (ER⁺) breast cancer. We identify that ARID1A inactivating mutations are present at a high frequency in advanced endocrine-resistant ER⁺ breast cancer. An epigenome CRISPR-CAS9 knockout (KO) screen identifies ARID1A as the top candidate whose loss determines resistance to the ER degrader fulvestrant. ARID1A inactivation in cells and in patients leads to resistance to ER degraders by facilitating a switch from ER-dependent luminal cells to ER-independent basal-like cells. Cellular plasticity is mediated by loss of ARID1A-dependent SWI/SNF complex targeting to genomic sites of the luminal lineage-determining transcription factors including ER, forkhead box protein A1 (FOXA1) and GATA-binding factor 3 (GATA3). ARID1A also regulates genome-wide ER-FOXA1 chromatin interactions and ER-dependent transcription. Altogether, we uncover a critical role for ARID1A in maintaining luminal cell identity and endocrine therapeutic response in ER⁺ breast cancer.

Extended Data Fig. 1 |. Enrichment of mutations of core subunits of the SWI/SNF complex in HR+ HER2- breast cancer.

(a) Mutation enrichment based on IMPACT study. (b) Mutation enrichment based on TCGA and METABRIC studies.

Extended Data Fig. 2 |. Loss of SWI/SNF complex subunits mediate resistance to endocrine therapy.

(a) In vitro proliferation of ARID1A knockout (KO) MCF7 cells as measured by cell quantification. (b) Cell cycle distributions as measured by FACS analyses of control and ARID1A KO MCF7 cells. Error bars=mean ±SEM, n=2 biologically independent samples, center values are means. P values were calculated using two-way ANOVA test; all P values > 0.2. N.S=non-significant. (c) Cell quantification of ARID1A KO vs. control cells upon fulvestrant treatment (100nM). (d) In vitro proliferation assay in ARID1A KO vs. control cells upon a dose response of the ER degrader GDC0927. The experiments were repeated thrice with similar results. (e) Cell quantification of ARID1A KO vs. control cells under estrogen (E₂) depleted media vs. full media. (f) In vitro proliferation assay of ARID1A KO vs. control cells in estrogen depleted media and full media. The experiments were repeated thrice with similar results. (g) Cropped western blot of SMARCB1 or SMARCE1 KO (sg1-sg5) vs. control MCF7 cells. (h) In vitro proliferation assay in SMARCB1 or SMARCE1 KO vs. control MCF7 cells upon treatment with fulvestrant (100nM). The experiments were repeated three times with similar results. (i) The ratio of RFP+ SMARCB1 or SMARCE1 (sg1-sg5) knockout cells to GFP+ control cells (sgNT-GFP) upon DMSO or fulvestrant treatment (100nM) for 8 days as measured by flow cytometry. For (a), (c), (e), (i), error bars=mean ±SEM, n=3 biologically independent samples, center values are means. P values, Student’s two-sided t test.

Extended Data Fig. 3 |. ARID1A knockout leads to equal chromatin accessibility changes in DMSO or fulvestrant setting.

(a) Cropped western blot with indicated antibodies in MCF7 cells. (b) Pie chart of peak distributions to various genic parts. (c) ATAC-seq analysis revealed 59,000 peaks in total; 33% in intergenic regions, ~30% in promoter regions, and 35% in intron regions. Violin plot shows probability density of peaks across the samples. (d) Heatmap of differential peaks in control vs. ARID1A KO (knockout) upon DMSO or fulvestrant (fulv) treatment (absolute log2 fold change > 0.5, Benjamini-Hochberg adjusted P < 0.05). (e) ChIP-qPCR analyses of TEAD4 binding in control and ARID1A KO MCF7. Error bars=mean ±SEM, n=2 biologically independent samples, center values are means. P values, Student’s two-sided t test. (f) Cropped western blot of TEAD4 in control and ARID1A KO MCF7. (g) Crystal violet assay of TEAD4 knockdown cells in control and ARID1A KO upon DMSO or fulvestrant (100nM). (h) Cropped western blot of GATA3 overexpression in MCF7 (n=3). (i) In vitro proliferation of GATA3 overexpressed cells in control and ARID1A KO setting upon DMSO or fulvestrant treatment (100nM). The experiments were repeated thrice with similar results. (j) Cell quantification of GATA3 overexpressed cells in control and ARID1A KO setting upon DMSO or fulvestrant treatment (100nM). Error bars=mean ±SEM, n=3 biologically independent samples, center values are means. P values, Student’s two-sided t test. (k) Learned coefficients of transcription factors motifs that gain or lose enrichment in control vs. ARID1A KO in DMSO or fulvestrant (n=15 samples).

Extended Data Fig. 4 |. ARID1A loss mediates a basal-like gene expression.

(a) Volcano plot; x-axis is log2 fold change and y-axis represents -log10(P); n=18 samples, statistical by DESeq2. (b) mRNA levels of luminal and basal-like/stemness markers in control and ARID1A KO cells. Error bars=mean ±SEM, n=2 biologically independent samples, center values are means. *P value<0.05, ** P value<0.01, Student’s two-sided t test. (c) Cropped western blot of indicated antibodies. (d) mRNA levels of aforementioned markers in MCF7 upon addition of doxycycline (DOX) knockdown of ARID1A. Error bars=mean ±SEM, n=2 biologically independent samples, center values are means. *P value<0.05, ** P value<0.01, Student’s two-sided t test. Also shown are ARID1A and vinculin levels. (e and f) Cropped western blot with indicated antibodies in BT474 or MDA-MB-361 cells expressing sgNT and two sgRNAs against ARID1A. (g and h) Enrichment of basal-like signatures in BT474 (Charafe breast cancer luminal vs. basal down) or MDA-MB-361 (Huper breast basal vs. luminal up) upon ARID1A KO. (n=6 per cell type, nominal P values and FDR adjusted P values were calculated using GSEA package.) (i and j) Enrichment of basal-like and estrogen response signatures in MCF7 after SMARCB1 or SMARCE1 knockout; n=8 per gene knockout, nominal P values and FDR adjusted P values were calculated using GSEA package. (k) Enrichment of basal-like signatures in ARIDlA wild type vs. biallelic loss of ARIDlA of patient sample pairs (*, FDR < 0.25;). n=2 for each patient pair, nominal P values and FDR adjusted P values were calculated using GSEA package).

Extended Data Fig. 5 |. SWI/SNF binding to chromatin but not complex assembly is lost upon ARID1A loss.

(a) BAF155–2 and BRG1–2 at BAF155/BRG1 binding sites in control and ARID1A KO MCF7 cells (n=1). (b) Box plot representing mean signal across differential BAF155–2 or BRG1–2 after ARID1A KO at BAF155/BRG1 sites. (c) Cropped western blots of co-immunoprecipitation of BRG1 with subunits of the SWI/SNF complex in control and ARID1A KO MCF7. (d) Plot of the fold change between control and ARID1A KO of ATAC-seq sites vs. similar fold change of BAF155/BRG1 sites; n=14838 peaks, R and P values calculated using spearman correlation from ggpubr package in R. (e) BAF155–2 and BRG1–2 at differential accessible sites in control and ARID1A KO MCF7. (f) Box plot representing mean signal across differential BAF155–2 or BRG1–2 after ARID1A KO at lost accessible sites. (g) ChIP-qPCR analysis of ER, FOXA1, and GATA3 in shared loci in control and ARID1A KO cells. (h) ChIP-qPCR analysis of FOS, JUN, and IgG control. (i) ChIP-seq tracks of BRG1 and BAF155 in control and ARID1A KO cells (n=1). For (g) and (h), error bars=mean ±SEM, n=3 biologically independent samples, center values are means. P values, Student’s two-sided t test. For the box plots P-values, Mann-Whitney U test (Wilcoxon rank-sum test, two-sided) and effect size (rosenthal’s coefficient) are shown. The log2FC which is calculated as log2 (mean KO / mean Control) is also indicated (n=6). Box shows 25^th, median and 75^th percentiles with whiskers extending to ± 1.5 * IQR.

Extended Data Fig. 6 |. ARID1A regulates the expression of nuclear hormone receptors in breast cancer.

(a) ECDF plot of log2 fold changes in gene expression between ARID1A knockout and control for genes nearest to the TSS-distal SWI/SNF binding sites at GRHL1, FOXA1, FOS, JUN, GATA3, and ER motifs loci. P values were measured by the Mann-Whitney U test (Wilcoxon rank-sum test, two-sided) and effect size (rosenthal’s coefficients. The log2FC (fold change) values which are calculated as log2 (mean KO / mean Control) are also indicated (n=9). (b) Expression of ER canonical targets in control and ARID1A knockout MCF7 cells. Error bars=mean ±SEM, n=3 biologically independent samples, center values are means. P values, Student’s two-sided t test. (c) Cropped western blot of AR+ TNBC breast cancer cells BT549 and HCC70 with the indicated antibodies. (d) and (e) Cropped western blot with the indicated antibodies of control and ARID1A knockout BT549 or HCC70. (f) and (g) GSEA of androgen response in BT549 and HCC70 after ARID1A knockout; n=8 for each cell line, nominal P values and FDR adjusted P values were calculated using GSEA package.

Fig. 1 |. ARID1A loss mediates endocrine therapy resistance.

a, Gene-level enrichment analysis of mutations in genes that are significantly more common in metastases compared to primary tumors (q<0.05) in ER⁺/HER2⁻ breast cancer (MSK primary = 739; TCGA primary = 579; MSK metastatic = 762). b, Workflow of the epigenome-wide CRISPR-CAS9 screen on treatment with fulvestrant. MOI, multiplicity of infection. NGS, next-generation sequencing. c, Sequencing data analysis demonstrating ARID1A sgRNAs (10 out of 12 sgRNAs targeting ARID1A) to mediate fulvestrant resistance. d, Cropped western blot with the indicated antibodies in MCF7 cells expressing sgNT as controls and distinct sgRNAs targeting ARID1A. e, In vitro proliferation assay of MCF7 cells expressing sgNT-1 and sgNT-2 as controls and four sgRNAs against ARID1A on DMSO or fulvestrant treatment (n = 3 independent experiments). f, In vivo xenografts of MCF7 ARID1A KO and control cells treated with vehicle or fulvestrant (3 mg per mouse per week) for 13 weeks. Error bars, s.e.m., n = 5 per group, center values represent the means. P values were calculated using a two-sided Mann-Whitney U-test. g, Cropped western blot with the indicated antibodies of MDA-MB-415 cells expressing sgNT-GFP, sgCOPGFP-GFP, sgARID1A-1-RFP and sgARID1A-2-RFP. h, Ratio of RFP⁺ ARID1A KO cells (sgARID1A-1 or sgARID1A-2) to GFP⁺ control cells (sgNT-GFP or sgCOPGFP-GFP) on DMSO or fulvestrant administration (100 nM) for 14d as measured by flow cytometry. P values are shown. A two-sided Student’st-test was used. The error bars indicate the mean±s.e.m.; n = 3 biologically independent samples; the center values are the means. i, Kaplan-Meier curves displaying the progression-free survival of patients receiving SERD therapy based on ARID1A alterations from the MSK-IMPACT cohort. Pvalue as indicated. A log-rank test was used.

Fig. 2 |. ARID1A impacts the accessibility of several transcription factor motifs involved in luminal differentiation.

a, Volcano plot of ATAC-seq assays in control and ARID1A KO cells. The x axis shows the log₂ fold change and the y axis shows the −log₁₀(P). The red dots represent a significant increase in chromatin accessibility (1,701 sites) whereas the green dots represent a significant decrease in chromatin accessibility (3,537 sites) (absolute log₂ fold change >0.5 and Benjamini-Hochberg-adjusted P<0.05). b, Heatmap of significantly differentially accessible sites in MCF7 cells expressing three distinct sgRNAs against ARID1A and two control sgRNAs (4,608 differential peaks; log₂ fold change > 0.5 and Benjamini-Hochberg-adjusted P< 0.05). c, Pie chart showing the distributions of differential peaks to various genic parts. d, Heatmap of H3K27ac ChlP-seq in the differentially accessible sites obtained by ATAC-seq on ARID1A loss (±2-kb regions centered at the peak summit). PSS, peak start site; PES, peak end site. e, Box plot showing the mean signal across peaks that lost chromatin accessibility on ARID1A KO. Also shown is the H3K27ac ChlP-seq differential binding in control and ARID1A KO cells. P values are as shown. A two-sided Mann-Whitney U-test and effect size (Rosenthal’s coefficient) are also shown. The log₂ fold change calculated as log₂ (mean KO/mean control) is also shown (n = 15). The box shows the 25th, median and 75th percentiles with the whiskers extending to ±1.5× interquartile range (IQR). f, Top significant transcription factor motifs enriched in the lost or gained accessible sites on ARID1A KO as analyzed by a ridge regression model (FDR< 0.01). The x axis represents the ridge regression coefficients.

Fig. 3 |. ARID1A loss results in enrichment of a basal-like signature in cells and patient samples.

a, Heatmap displaying significantly differential gene expression as obtained by RNA-seq performed in two control (sgNT, sgCOPGFP) and three sgRNAs against ARID1A (sgARID1A-1, sgARID1A-2, sgARID1A-3) MCF7 cells (1,230 downregulated, 2,585 upregulated genes; absolute log₂ fold change>0.5, Benjamini-Hochberg-adjusted P<0.01). b, ECDF plot of the log₂ fold change of nearest gene expression (ARID1A KO versus control cells) in sites that have increased or decreased chromatin accessibility. P values are as shown. A two-sided Mann-Whitney U-test and effect size (Rosenthal’s coefficient) are also shown. Also shown is the difference in mean log₂ fold change between two distributions (n = 9). c, GSEA in MCF7 after ARID1A KO (log₂ fold change calculated using n = 9; nominal P values and FDR-adjusted P values were calculated using the GSEA package). NES, normalized enrichment score. d, Fold change (ARID1A KO versus control) of luminal and basal-like/stemness markers in MCF7 as obtained by RNA-seq (absolute log₂ fold change> 0.5, Benjamini-Hochberg-adjusted P< 0.01). e, Cropped western blot with indicated antibodies of MDA-MB-415 cells expressing sgNT and two distinct sgRNAs against ARID1A. f, Enrichment of basal-like signatures in MDA-MB-415 on ARID1A KO; log₂ fold change calculated using n = 6, nominal P values and FDR-adjusted P values were calculated using the GSEA package. g, Enrichment of basal signatures in patient samples with biallelic ARID1A loss versus patient samples WT for ARID1A; log₂ fold change calculated using n = 12, nominal P values and FDR-adjusted P values were calculated using the GSEA package v.2.2.1.

Fig. 4 |. ARID1A loss causes defects in SWI/SNF targeting to chromatin at luminal lineage-determining transcription factor loci.

a, Heatmap of the ChIP-seq profiles of the SWI/SNF binding sites, as probed by the overlap of BAF155/BRG1 peaks (14,007 common peaks) for the core subunits in control and ARIDlA mutant MCF7 cells shown in a horizontal window of ±2 kb from the peak center. The experiment was conducted once. b, Enrichment of BAF155 and BRG1 occupancy in the differentially accessible sites observed by ATAC-seq. The experiment was conducted once. PC, peak center. c, Box plot representing the mean signal across peaks that lose chromatin accessibility on ARIDlA KO cells. Also shown are the BAF155 and BRG1 ChIP-seq differential binding in control and ARIDlA KO cells. P values were calculated using a two-sided Mann-Whitney U-test; the effect size (Rosenthal’s coefficients) was calculated as described in the Methods. The log₂ fold change, which was calculated as log₂ (mean KO/mean control) is also shown (n = 13). The box shows the 25th, median and 75th percentiles with the whiskers extending to ±1.5× IQR. d, Motif enrichment of transcription factors found in lost BAF155/BRG1 sites on ARIDlA silencing; n = 9,555peaks, P values were calculated using CentriMo v.4.11.4. e, ChIP-seq tracks of BRG1 and BAF155 in control and ARIDlA KO cells. The experiment was conducted once. f, ChIP-seq profiles for GRHL1 (generated in this study), FOXA1 (ENCODE ENCSR126YEB), GATA3 (ENCODE ENCSR000BST), FOS/JUN (ENCODE ENCSR176EXN) and JUND (ENCODE ENCSR000BSU) at the predicted motif sites obtained from lost SWI/SNF binding sites after ARIDlA loss (n = 1).

Fig. 5 |. ARID1A regulates ER and FOXA1 chromatin occupancy and ER-dependent transcription.

a, ChIP-seq of ER (n = 2 independent experiments) in control and ARIDlA KO cells at ER peaks that overlap with BAF155/BRG1 peaks (n = 344) Also shown are the BAF155 and BRG1 ChIP-seq levels. b, Box plot representing the mean signal of ER sites shown in a in control cells and after ARIDlA KO. Also shown are the mean signals for BAF155 and BRG1 ChIP-seq. The log₂ fold change is shown (n = 8). c, Heatmap displaying the differential gene expression changes obtained by RNA-seq in ARIDlA KO versus control MCF7 cells. Cells were estrogen-depleted for 3d, and this was followed by estrogen treatment for 12h. d, Examples of expression of estrogen-dependent genes in control and ARIDlA KO cells on vehicle or estrogen treatment by RNA-seq. The bar plot shows the mean expression and s.e.m. bars (n = 12). e, ChIP-seq levels of FOXA1 at the BAF155/BRG1 shared sites in control and ARIDlA KO MCF7 cells. Also shown is the box plot representing the mean signal across differential FOXA1 sites at the BAF155/BRG1 sites after ARIDlA KO. f, ChIP-seq of FOXA1 at differential ATAC-seq sites on ARIDlA loss. Also shown is the box plot demonstrating the mean signal across differential FOXA1 sites at the ATAC-seq sites after ARIDlA KO. P values, two-sided Mann-Whitney U-test and effect size (Rosenthal’s coefficient) are shown. The log₂ fold change, which was calculated as log₂ (mean KO/mean control) is also shown (n = 4). The box shows the 25th, median and 75th percentiles with the whiskers extending to ±1.5× IQR.

Fig. 6 |. Proposed model.

Model depicting lineage plasticity and endocrine therapy resistance in ER+ breast cancer due to loss of ARID1A compared to ER⁺ breast cancer with WT ARID1A.