Aberrant FGFR signaling mediates resistance to CDK4/6 inhibitors in ER+ breast cancer

Abstract

Using an ORF kinome screen in MCF-7 cells treated with the CDK4/6 inhibitor ribociclib plus fulvestrant, we identified FGFR1 as a mechanism of drug resistance. FGFR1-amplified/ER+ breast cancer cells and MCF-7 cells transduced with FGFR1 were resistant to fulvestrant ± ribociclib or palbociclib. This resistance was abrogated by treatment with the FGFR tyrosine kinase inhibitor (TKI) lucitanib. Addition of the FGFR TKI erdafitinib to palbociclib/fulvestrant induced complete responses of FGFR1-amplified/ER+ patient-derived-xenografts. Next generation sequencing of circulating tumor DNA (ctDNA) in 34 patients after progression on CDK4/6 inhibitors identified FGFR1/2 amplification or activating mutations in 14/34 (41%) post-progression specimens. Finally, ctDNA from patients enrolled in MONALEESA-2, the registration trial of ribociclib, showed that patients with FGFR1 amplification exhibited a shorter progression-free survival compared to patients with wild type FGFR1. Thus, we propose breast cancers with FGFR pathway alterations should be considered for trials using combinations of ER, CDK4/6 and FGFR antagonists.

Fig. 1

ORF kinome screen identifies drivers of resistance to fulvestrant ± CDK4/6 inhibitors. a, b ORF kinome screen in MCF-7 cells treated with fulvestrant (a) or fulvestrant plus ribociclib (b). ORFs are visualized by plotting the function y = z-score, x = gene name. Data points represent the average of two replicate plates. c Modified Venn diagram of screening results showing the number of fulvestrant hits (left) or fulvestrant plus ribociclib hits (right). d Heat map displaying validation results of the hits selected in the fulvestrant plus ribociclib screen. Top and bottom row show the normalized area under the curve (AUC) for each candidate genes with 5-point drug concentration, fulvestrant plus palbociclib (top row) and fulvestrant plus ribociclib (bottom row). GFP and mutant MEK^S218/222D (MEK-DD) were used as internal controls

Fig. 2

FGFR1 overexpression confers resistance to fulvestrant and palbociclib. a Tile plot of ER+ breast cancers in TCGA (Cell 2015) with amplification and/or mRNA upregulation of FGFR1, CRKL, HCK, FRK, and FGR. b–d MCF-7^eGFP and MCF-7^FGFR1 cells were seeded in 6-well plates in full media supplemented with 2 ng/mL FGF2 and treated with vehicle (DMSO), 1 μM fulvestrant, or 1 μM fulvestrant plus 1 μM palbociclib ± 1 μM lucitanib. Drugs and media were replenished every 3 days. After 14 days, monolayers were stained with crystal violet and analyzed as described in Methods. Quantification of the integrated intensity values as fold change relative to vehicle-treated controls are shown (c) (**p < 0.01 vs. controls, Student’s t-test). Cell lysates were subjected to immunoblot analyses with the indicated antibodies (d). e T47D^eGFP and T47D^FGFR1 cells were seeded in 6-well plates in full media supplemented with 2 ng/mL FGF2 and treated with vehicle (DMSO), 0.5 μM fulvestrant, or 0.5 μM fulvestrant plus 0.5 μM palbociclib ± 1 μM lucitanib. Drugs and media were replenished every 3 days. After 14 days, plates were washed and stained with crystal violet; imaging intensity was quantified by spectrophotometric detection. Quantification of the integrated intensity values as fold change relative to vehicle-treated controls are shown (**p < 0.01 vs. controls, Student’s t-test). Lysates from T47D cells stably transduced with an FGFR1 expression vector were subjected to immunoblot analysis with FGFR1 and actin antibodies (on top-right of the panel)

Fig. 3

FGFR inhibitor lucitanib enhances the action of fulvestrant plus palbociclib against MCF-7^FGFR1 xenografts. a MCF-7^eGFP (left) and MCF-7^FGFR1 (right) xenografts were established in ovariectomized athymic mice implanted with a s.c. 14-day release, 0.17-mg 17β-estradiol pellet. Once tumors reached ≥200 mm³, mice were randomized to treatment with vehicle, fulvestrant (5 mg/week), fulvestrant plus palbociclib (30 mg/kg/day p.o.), or fulvestrant plus palbociclib plus lucitanib (10 mg/kg/day p.o.). Each data point represents the mean tumor volume in mm³ ± SEM (n = 8 per arm, ****p < 0.0001 vs. single drug arms; Student’s t-test). b, c MCF-7^eGFP and MCF-7^FGFR1 tumors were harvested at the end of the treatment. Formalin-fixed, paraffin-embedded (FFPE) tumor sections were subjected to IHC with p-RB S807/811 (b) and p-FGFR1 Y653/4 (c) antibodies as described in Methods. The percent of p-RB+ and p-FGFR1+ tumor cells and their staining intensity were assessed by an expert breast pathologist (P.G.E.) blinded to treatment to generate an H-score. Total p-RB and p-FGFR1 H-scores are shown (*p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001; Student’s t-test)

Fig. 4

FGFR1 signaling sustains cell proliferation in FGFR1-amplified ER+ breast cancer cells treated with fulvestrant plus palbociclib. a, b CAMA1 cells were treated with vehicle (DMSO) or the indicated inhibitors (each at 1 µM) in FGF2-containing media. Cell media and inhibitors were replenished every 3 days. After 14 days, plates were washed and stained with crystal violet; imaging intensity was quantified by spectrophotometric detection. Representative images (a) and quantification of the integrated intensity values as fold change relative to vehicle-treated controls (b) are shown (****p < 0.0001 vs. controls, Student’s t-test). c CAMA1 cells were treated as in a for 24 h. Cell lysates were prepared and subjected to immunoblot analysis with the indicated antibodies. d CAMA1 cells were serum-starved for 24 h and then treated with vehicle (DMSO) or each of the indicated inhibitors (all at 1 µM) in FGF2-containing media for 24 h. Following treatment, cells were stained with propidium iodide and analyzed by FACS. e, f CAMA1 cells were treated as above for 6 days. Representative images (e) and the percent of senescence-associated (SA)-β-galactosidase-positive cells per 5 high-power fields (f) are shown (**p < 0.01,***p < 0.001 vs. controls, Student’s t-test). g CAMA1 cells were treated as in e for 6 days. Cell lysates were prepared and subjected to immunoblot analysis with the indicated antibodies. h Modified Venn diagram showing the number of downregulated genes (q < 0.01, log2 fold change >−0.5) in FGF2-stimulated CAMA1 cells treated with fulvestrant plus palbociclib (blue) or fulvestrant plus palbociclib plus lucitanib (FPL, red). i Heat map representing the modulation (FDR <0.05) of 30 gene expression signatures in FGF2-stimulated CAMA1 cells treated with fulvestrant plus palbociclib ± lucitanib for 6 h. j Enrichment plot for CCND1, Estrogen Response Early, and E2F1 signatures in CAMA1 cells

Fig. 5

Cyclin D1 mediates FGFR1-driven resistance to fulvestrant plus palbociclib. a FGF2-stimulated CAMA1 cells were treated with the indicated inhibitors for 6 h. cDNA was analyzed using the RT² Cell Cycle PCR Array (Qiagen). b, c FGF2-stimulated CAMA1 cells were treated with the indicated inhibitors for 6 h. CCND1 mRNA levels were analyzed by qRT-PCR (b) and cyclin D1 protein levels were analyzed by immunoblot (c). In b, each bar represents the mean CCND1 transcript levels ± SD (****p < 0.001, Student’s t-test). d MCF-7^FGFR1 cells in full media containing FGF2 were transfected with CCND1 or control siRNAs as described in Methods. Four days later, monolayers were harvested and cell counts determined using a Coulter Counter. Each bar represents the fold change relative to vehicle-treated controls (*p < 0.05, ***p < 0.001 vs. control siRNA, Student’s t-test). e Cyclin D1 knockdown was confirmed by immunoblot analysis of cell lysates from plates treated as in d. f CAMA1 cells were transfected with CCND1 or control siRNAs as described in Methods. Full media containing FGF2 ± the indicated inhibitors was replenished every 3 days. Three and 6 days later, monolayers were harvested and cell counts determined using a Coulter Counter. Each data point represents the mean cell number ± SD of triplicate wells (***p < 0.001 vs. fulvestrant plus palbociclib, Student’s t-test). Cyclin D1 knockdown was confirmed by immunoblot analysis of cell lysates from plates treated for 3 days (inset). g Lysates from MCF-7 cells stably transduced with a cyclin D1 expression vector were subjected to immunoblot analysis with cyclin D1 and actin antibodies. h MCF-7^eGFP and MCF-7^CCND1 cells were plated in full media and treated with fulvestrant ± palbociclib over a dose range (0–1 μM) for 7 days. Cells were stained with crystal violet and monolayers quantified as described in Methods. Representative images at the concentration of 0.125 μM and quantification of the integrated intensity values as % of vehicle-treated controls are shown

Fig. 6

Combined inhibition of ER, CDK4/6, and FGFR1 inhibits the growth of ERα/FGFR1-amplified breast cancer PDXs. a ER+/HER2−/FGFR1-amplified TM00386 PDX fragments were established in ovariectomized SCID/beige mice supplemented with a 21-day release, 0.25-mg 17β-estradiol pellet. Once tumors reached ≥200 mm³, mice were randomized to the indicated treatment arms. Each data point represents the fold change in volume ± SEM (n = 8 per arm; ANOVA test). b Bar graph showing the % change in volume in individual xenografts after 3 weeks of treatment relative to individual tumor volumes on day 0. c Xenografts were harvested after 1 week of treatment and FFPE tumor sections were subjected to Ki67 IHC as described in Methods. The percent of Ki67+ tumor cells (inset) was assessed by an expert breast pathologist (P.G.E.) blinded to the treatment arm. d TM00386 PDXs in mice treated with vehicle or fulvestrant plus palbociclib were harvested and snap frozen at the end of treatment. RNA was extracted and subjected to nanoString analysis as described in Methods. Heat map represents different gene expression levels between controls (n = 4) and tumors treated with fulvestrant plus palbociclib (n = 4). e, f TM00386 PDXs were harvested at the end of treatment. FFPE sections from the PDXs were subjected to IHC with p-RB (e) and CCND1 (f) antibodies as described in Methods. The percent of p-RB and CCND1-positive tumor cells and their staining intensity were assessed by an expert breast pathologist (P.G.E.) blinded to the treatment arm to generate an H-score (shown in Supplementary figures). g TM00386 tumors were harvested at the end of treatment, 4 h after the last dose of palbociclib and erdafitinib and 24 h after the last dose of fulvestrant. Tumor lysates were prepared and subjected to immunoblot analyses with the indicated antibodies

Fig. 7

FGFR alterations correlate with poor outcome in ER+ breast cancers treated with CDK4/6 inhibitors and endocrine therapy. a Landscape of alterations in plasma tumor ctDNA from 34 patients progressing on palbociclib. b PFS in patients in the MONALEESA-2 trial of letrozole (Let) plus ribociclib (Rib) vs. letrozole plus placebo (PBO). Among patients treated in the investigational arm with letrozole plus ribociclib, those with detectable FGFR1/ZNF703 amplification (ALT) in ctDNA had a PFS of 10.61 months vs. 24.84 months in patients without FGFR1/ZNF703 amplification. c PFS in patients in MONALEESA-2 as a function of FGFR1 mRNA in archival tumor biopsies. Patients with cancers with high FGFR1 mRNA treated with letrozole/ribociclib exhibited a shorter PFS compared to patients with tumors with low FGFR1 mRNA