Genome-wide functional genetic screen with the anticancer agent AMPI-109 identifies PRL-3 as an oncogenic driver in triple-negative breast cancers

Abstract

Triple-negative breast cancers (TNBC) are among the most aggressive and heterogeneous cancers with a high propensity to invade, metastasize and relapse. Here, we demonstrate that the anticancer compound, AMPI-109, is selectively efficacious in inhibiting proliferation and inducing apoptosis of multiple TNBC subtype cell lines as assessed by activation of pro-apoptotic caspases-3 and 7, PARP cleavage and nucleosomal DNA fragmentation. AMPI-109 had little to no effect on growth in the majority of non-TNBC cell lines examined. We therefore utilized AMPI-109 in a genome-wide shRNA screen in the TNBC cell line, BT-20, to investigate the utility of AMPI-109 as a tool in helping to identify molecular alterations unique to TNBC. Our screen identified the oncogenic phosphatase, PRL-3, as a potentially important driver of TNBC growth, migration and invasion. Through stable lentiviral knock downs and transfection with catalytically impaired PRL-3 in TNBC cells, loss of PRL-3 expression, or functionality, led to substantial growth inhibition. Moreover, AMPI-109 treatment, downregulation of PRL-3 expression or impairment of PRL-3 activity reduced TNBC cell migration and invasion. Histological evaluation of human breast cancers revealed PRL-3 was significantly, though not exclusively, associated with the TNBC subtype and correlated positively with regional and distant metastases, as well as 1 and 3 year relapse free survival. Collectively, our study is proof-of-concept that AMPI-109, a selectively active agent against TNBC cell lines, can be used as a molecular tool to uncover unique drivers of disease progression, such as PRL-3, which we show promotes oncogenic phenotypes in TNBC cells.

Keywords: AMPI-109; PRL-3; functional genomics; phosphatase; triple-negative breast cancer.

Figure 1. Structure of AMPI-109

Figure 2. AMPI-109 mediated growth inhibition and induction of apoptosis is specific for TNBC cell lines

A. The response of the indicated TNBC (BT-20, MDA-MB-231 and MDA-MB-468) and non-TNBC (MCF7, MCF10A and T47D) cell lines to ethanol vehicle control (Ctl; blue) or 100 nM AMPI-109 (AMPI-109; red) was determined by real time kinetic monitoring of cellular proliferation. B. The same cell lines were analyzed for induction of apoptosis by real time kinetic monitoring of caspase 3/7 activity after treatment with ethanol vehicle control (Ctl; blue) or 100 nM AMPI-109 (AMPI-109; red). For (A and B) * = p-value < 0.05 as determined by Student t test on last time-point. C. the indicated cell lines were treated with ethanol control (C; purple), paclitaxel (10⁻⁷ M, (T; green)), 1,25D (10⁻⁷ M, (D; red)), or AMPI-109 (10⁻⁷ M, (A; blue)) for 24 hrs. Cytoplasmic nucleosomal DNA was measured by ELISA to assess apoptosis. D. The same cells as in C. were treated for 24 hrs and PARP cleavage determined by immunoblot.

Figure 3. AMPI-109 action is independent of VDR

(Top) Immunoblot analysis of VDR levels in two pools of BT-20, MDA-MB-231 and MDA-MB-468 cells with VDR shRNAs (VDR3 and VDR8). pLKO is non-silencing control. (Bottom) Corresponding graphs depict response of the indicated pools of VDR pLKO and shRNA cells to ethanol vehicle control (Ctl; blue) or 100 nM AMPI-109 (AMPI-109; red) as determined by real time kinetic monitoring of cellular proliferation. * = p-value < 0.05 as determined by Student t test on last time-point.

Figure 4. Functional genetic screen with AMPI-109 identifies PRL-3 amplification in invasive basal breast cancers

A. Schematic representation of the experimental work flow of the functional genomic screen. BT-20 cells were transduced with a genome-wide shRNA library and treated with AMPI-109 (750 nM) or left untreated. After 5 passages the shRNA tag sequences were recovered and quantified by deep sequencing. Data were analyzed by complementary computational analyses generating lists of mediators of chemoresistance and chemosensitivity to AMPI-109. B. Heatmap of shRNA tag representation in AMPI-109-treated and untreated samples. Right panel: Two analysis strategies (NB, negative binomial and RFC, relative fold change) implicated 2,084 genes that modulate the effects of AMPI-109. 201 genes were identified by combined analysis strategies. C. Table highlighting highest ranking gene hits enriched by AMPI-109 treatment by normalized fold change (nFC). D. Bar graph depicting level of PRL-3 amplification in TCGA Nature, 2012 cohort (red) and TCGA Cell, 2015 dataset (blue) for patients with invasive breast cancer (all tumors) and those with invasive basal breast cancer as determined by the PAM50 signature (PAM50 Basal).

Figure 5. PRL-3 knock down and expression of catalytically impaired PRL-3 results in reduced growth of TNBC cells

A. Immunoblot analysis of PRL-3 levels following transduction of BT-20 (left) and MDA-MB-468 (right) cells with lentiviral vectors expressing PRL-3 shRNAs (sh1 and sh2). pLKO is non-silencing control shRNA. B. Real time kinetic monitoring of cellular proliferation of BT-20 (left) and MDA-MB-468 (right) TNBC cells with non-silencing control shRNA (pLKO; blue) and PRL-3 shRNAs (sh1; red, sh2: green). C. SDS-PAGE analysis of FLAG-tagged recombinant wild type PRL-3 (FLAG-WT) and PRL-3 C104A (FLAG-C104A). Numbers indicate molecular weights (MW) in kilodaltons. D. The enzymatic activity of FLAG-tagged recombinant proteins was determined by in vitro phosphatase assay. E. BT-20 (top) and MDA-MB-468 (bottom) cells were transiently transfected with pC104A mammalian expression vector (pC104A; purple) or empty vector (Ctl; blue) 24 hrs prior to plating in IncuCyte. Cells were treated with ethanol vehicle control (EtOH; green) or 100 nM AMPI-109 (AMPI-109; black). Transfection control cells treated with ethanol vehicle (Ctl + EtOH; red) and pC104A cells treated with AMPI-109 (pC104A + AMPI-109; orange) are also depicted. Cellular proliferation measured by real time kinetic monitoring of plate confluence. * = p-value < 0.05 as determined by Student t test on last time-point.

Figure 6. Knock down of PRL-3, AMPI-109 treatment and forced expression of catalytically impaired PRL-3 inhibit TNBC cell migration and invasion

A. Quantification of wound closure in non-silencing control (pLKO; blue) and PRL-3 knock down (sh2; red) BT-20 and MDA-MB-468 cells as assessed by real time kinetic monitoring of relative wound density. B. BT-20 and MDA-MB-468 cells were treated with 100 nM AMPI-109 (AMPI-109; green) or ethanol vehicle control (Ctl; red) and cellular migration measured by scratch wound assay. C. BT-20 and MDA-MB-468 cells were transiently transfected overnight with mammalian expression vectors for wild type PRL-3 (pWT; blue), catalytically impaired PRL-3 (pC104A; purple) or empty vector (Ctl; red) and cellular migration measured by scratch wound assay. D. Immunoblot comparing PRL-3 protein levels across several TNBC cell lines. E. Real-time kinetic monitoring of cellular invasion through Matrigel Matrix in SUM159 and BT-20 cells treated with 100 nM AMPI-109 (top panel; red), stably expressing two different shRNA clones to knock down PRL-3 (middle panel; red and purple) or BT-20 cells transiently transfected to overexpress wild type PRL-3 (bottom panel; red). Invasive score was determined by the ability of cells to invade through a Matrigel wound (Relative Wound Density). Inset panels show PRL-3 levels by immunoblot analysis. * = p-value < 0.05 as determined by Student t test on last time-point.

Figure 7. PRL-3 expression is increased in TNBC

A. Examples of PRL-3 staining scored as low or high, 20 μm scale bars. B. Whisker plot and table of PRL-3 expression across different breast cancer subtypes. * = p-value (< 0.008) based on post hoc Dunn's test from Kruskal-Wallis non-parametric ANOVA. (C and D) Differential PRL-3 mRNA expression in two human breast cancer datasets examining correlation to regional disease and visceral metastases.